Copyright Notice
The following material is presented here to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
2017 
Vázquez, Manuel; Míguez, Joaquín A Robust Scheme for Distributed Particle Filtering in Wireless Sensors Networks (Journal Article) Signal Processing, 131 , pp. 190–201, 2017, ISSN: 01651684. @article{Vazquez2017, title = {A Robust Scheme for Distributed Particle Filtering in Wireless Sensors Networks}, author = {Vázquez, Manuel A. and Míguez, Joaquín}, url = {http://www.sciencedirect.com/science/article/pii/S016516841630189X}, doi = {10.1016/j.sigpro.2016.08.003}, issn = {01651684}, year = {2017}, date = {20170201}, journal = {Signal Processing}, volume = {131}, pages = {190201}, abstract = {Wireless sensor networks (WSNs) have become a popular technology for a broad range of applications where the goal is to track and forecast the evolution of timevarying physical magnitudes. Several authors have investigated the use of particle filters (PFs) in this scenario. PFs are very flexible, Monte Carlo based algorithms for tracking and prediction in statespace dynamical models. However, to implement a PF in a WSN, the algorithm should run over different nodes in the network to produce estimators based on locally collected data. These local estimators then need to be combined so as to produce a global estimator. Existing approaches to the problem are either heuristic or wellprincipled but impractical (as they impose stringent conditions on the WSN communication capacity). Here, we introduce a novel distributed PF that relies on the computation of median posterior probability distributions in order to combine local Bayesian estimators (obtained at different nodes) in a way that is efficient, both computation and communicationwise. An extensive simulation study for a target tracking problem shows that the proposed scheme is competitive with existing consensusbased distributed PFs in terms of estimation accuracy, while it clearly outperforms these methods in terms of robustness and communication requirements.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Wireless sensor networks (WSNs) have become a popular technology for a broad range of applications where the goal is to track and forecast the evolution of timevarying physical magnitudes. Several authors have investigated the use of particle filters (PFs) in this scenario. PFs are very flexible, Monte Carlo based algorithms for tracking and prediction in statespace dynamical models. However, to implement a PF in a WSN, the algorithm should run over different nodes in the network to produce estimators based on locally collected data. These local estimators then need to be combined so as to produce a global estimator. Existing approaches to the problem are either heuristic or wellprincipled but impractical (as they impose stringent conditions on the WSN communication capacity). Here, we introduce a novel distributed PF that relies on the computation of median posterior probability distributions in order to combine local Bayesian estimators (obtained at different nodes) in a way that is efficient, both computation and communicationwise. An extensive simulation study for a target tracking problem shows that the proposed scheme is competitive with existing consensusbased distributed PFs in terms of estimation accuracy, while it clearly outperforms these methods in terms of robustness and communication requirements. 
2016 
Vázquez, Manuel; Míguez, Joaquín On the Use of the Channel SecondOrder Statistics in MMSE Receivers for Time and FrequencySelective MIMO Transmission Systems (Journal Article) EURASIP Journal on Wireless Communications and Networking, 2016 (1), 2016. @article{Vazquez2016, title = {On the Use of the Channel SecondOrder Statistics in MMSE Receivers for Time and FrequencySelective MIMO Transmission Systems}, author = {Vázquez, Manuel A. and Míguez, Joaquín}, url = {http://jwcn.eurasipjournals.springeropen.com/articles/10.1186/s1363801607680}, doi = {10.1186/s1363801607680}, year = {2016}, date = {20161201}, journal = {EURASIP Journal on Wireless Communications and Networking}, volume = {2016}, number = {1}, publisher = {Springer International Publishing}, abstract = {Equalization of unknown frequency and timeselective multiple input multiple output (MIMO) channels is often carried out by means of decision feedback receivers. These consist of a channel estimator and a linear filter (for the estimation of the transmitted symbols), interconnected by a feedback loop through a symbolwise threshold detector. The linear filter is often a minimum mean square error (MMSE) filter, and its mathematical expression involves secondorder statistics (SOS) of the channel, which are usually ignored by simply assuming that the channel is a known (deterministic) parameter given by an estimate thereof. This appears to be suboptimal and in this work we investigate the kind of performance gains that can be expected when the MMSE equalizer is obtained using SOS of the channel process. As a result, we demonstrate that improvements of several dBs in the signaltonoise ratio needed to achieve a prescribed symbol error rate are possible.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Equalization of unknown frequency and timeselective multiple input multiple output (MIMO) channels is often carried out by means of decision feedback receivers. These consist of a channel estimator and a linear filter (for the estimation of the transmitted symbols), interconnected by a feedback loop through a symbolwise threshold detector. The linear filter is often a minimum mean square error (MMSE) filter, and its mathematical expression involves secondorder statistics (SOS) of the channel, which are usually ignored by simply assuming that the channel is a known (deterministic) parameter given by an estimate thereof. This appears to be suboptimal and in this work we investigate the kind of performance gains that can be expected when the MMSE equalizer is obtained using SOS of the channel process. As a result, we demonstrate that improvements of several dBs in the signaltonoise ratio needed to achieve a prescribed symbol error rate are possible. 
Míguez, Joaquín; Vázquez, Manuel A Proof of Uniform Convergence Over Time for a Distributed Particle Filter (Journal Article) Signal Processing, 122 , pp. 152–163, 2016, ISSN: 01651684. @article{Miguez2016, title = {A Proof of Uniform Convergence Over Time for a Distributed Particle Filter}, author = {Míguez, Joaquín and Vázquez, Manuel A.}, url = {http://www.sciencedirect.com/science/article/pii/S0165168415004077}, doi = {10.1016/j.sigpro.2015.11.015}, issn = {01651684}, year = {2016}, date = {20160501}, journal = {Signal Processing}, volume = {122}, pages = {152163}, abstract = {Distributed signal processing algorithms have become a hot topic during the past years. One class of algorithms that have received special attention are particles filters (PFs). However, most distributed PFs involve various heuristic or simplifying approximations and, as a consequence, classical convergence theorems for standard PFs do not hold for their distributed counterparts. In this paper, we analyze a distributed PF based on the nonproportional weightallocation scheme of Bolic et al (2005) and prove rigorously that, under certain stability assumptions, its asymptotic convergence is guaranteed uniformly over time, in such a way that approximation errors can be kept bounded with a fixed computational budget. To illustrate the theoretical findings, we carry out computer simulations for a target tracking problem. The numerical results show that the distributed PF has a negligible performance loss (compared to a centralized filter) for this problem and enable us to empirically validate the key assumptions of the analysis.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Distributed signal processing algorithms have become a hot topic during the past years. One class of algorithms that have received special attention are particles filters (PFs). However, most distributed PFs involve various heuristic or simplifying approximations and, as a consequence, classical convergence theorems for standard PFs do not hold for their distributed counterparts. In this paper, we analyze a distributed PF based on the nonproportional weightallocation scheme of Bolic et al (2005) and prove rigorously that, under certain stability assumptions, its asymptotic convergence is guaranteed uniformly over time, in such a way that approximation errors can be kept bounded with a fixed computational budget. To illustrate the theoretical findings, we carry out computer simulations for a target tracking problem. The numerical results show that the distributed PF has a negligible performance loss (compared to a centralized filter) for this problem and enable us to empirically validate the key assumptions of the analysis. 
Koblents, Eugenia; Míguez, Joaquín; Rodríguez, Marco; Schmidt, Alexandra A Nonlinear Population Monte Carlo Scheme for the Bayesian Estimation of Parameters of $alpha$stable Distributions (Journal Article) Computational Statistics & Data Analysis, 95 , pp. 57–74, 2016, ISSN: 01679473. @article{Koblents2016, title = {A Nonlinear Population Monte Carlo Scheme for the Bayesian Estimation of Parameters of $alpha$stable Distributions}, author = {Koblents, Eugenia and Míguez, Joaquín and Rodríguez, Marco A. and Schmidt, Alexandra M.}, url = {http://www.sciencedirect.com/science/article/pii/S0167947315002340}, doi = {10.1016/j.csda.2015.09.007}, issn = {01679473}, year = {2016}, date = {20160301}, journal = {Computational Statistics & Data Analysis}, volume = {95}, pages = {5774}, abstract = {The class of $alpha$stable distributions enjoys multiple practical applications in signal processing, finance, biology and other areas because it allows to describe interesting and complex data patterns, such as asymmetry or heavy tails, in contrast with the simpler and widely used Gaussian distribution. The density associated with a general $alpha$stable distribution cannot be obtained in closed form, which hinders the process of estimating its parameters. A nonlinear population Monte Carlo (NPMC) scheme is applied in order to approximate the posterior probability distribution of the parameters of an $alpha$stable random variable given a set of random realizations of the latter. The approximate posterior distribution is computed by way of an iterative algorithm and it consists of a collection of samples in the parameter space with associated nonlinearlytransformed importance weights. A numerical comparison of the main existing methods to estimate the $alpha$stable parameters is provided, including the traditional frequentist techniques as well as a Markov chain Monte Carlo (MCMC) and a likelihoodfree Bayesian approach. It is shown by means of computer simulations that the NPMC method outperforms the existing techniques in terms of parameter estimation error and failure rate for the whole range of values of $alpha$, including the smaller values for which most existing methods fail to work properly. Furthermore, it is shown that accurate parameter estimates can often be computed based on a low number of observations. Additionally, numerical results based on a set of real fish displacement data are provided.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The class of $alpha$stable distributions enjoys multiple practical applications in signal processing, finance, biology and other areas because it allows to describe interesting and complex data patterns, such as asymmetry or heavy tails, in contrast with the simpler and widely used Gaussian distribution. The density associated with a general $alpha$stable distribution cannot be obtained in closed form, which hinders the process of estimating its parameters. A nonlinear population Monte Carlo (NPMC) scheme is applied in order to approximate the posterior probability distribution of the parameters of an $alpha$stable random variable given a set of random realizations of the latter. The approximate posterior distribution is computed by way of an iterative algorithm and it consists of a collection of samples in the parameter space with associated nonlinearlytransformed importance weights. A numerical comparison of the main existing methods to estimate the $alpha$stable parameters is provided, including the traditional frequentist techniques as well as a Markov chain Monte Carlo (MCMC) and a likelihoodfree Bayesian approach. It is shown by means of computer simulations that the NPMC method outperforms the existing techniques in terms of parameter estimation error and failure rate for the whole range of values of $alpha$, including the smaller values for which most existing methods fail to work properly. Furthermore, it is shown that accurate parameter estimates can often be computed based on a low number of observations. Additionally, numerical results based on a set of real fish displacement data are provided. 
MartínFernández,; Ruiz,; Torija,; Miguez, Joaquin A Bayesian Method for Model Selection in Environmental Noise Prediction (Journal Article) Journal of Environmental Informatics, 27 (1), pp. 31–42, 2016, ISSN: 17262135. @article{MartinFernandez2015b, title = {A Bayesian Method for Model Selection in Environmental Noise Prediction}, author = {MartínFernández, L. and Ruiz, D. P. and Torija, A. J. and Miguez, Joaquin}, url = {http://www.researchgate.net/publication/268213140_A_Bayesian_method_for_model_selection_in_environmental_noise_prediction}, issn = {17262135}, year = {2016}, date = {20160301}, journal = {Journal of Environmental Informatics}, volume = {27}, number = {1}, pages = {3142}, abstract = {Environmental noise prediction and modeling are key factors for addressing a proper planning and management of urban sound environments. In this paper we propose a maximum a posteriori (MAP) method to compare nonlinear statespace models that describe the problem of predicting environmental sound levels. The numerical implementation of this method is based on particle filtering and we use a Markov chain Monte Carlo technique to improve the resampling step. In order to demonstrate the validity of the proposed approach for this particular problem, we have conducted a set of experiments where two prediction models are quantitatively compared using real noise measurement data collected in different urban areas.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Environmental noise prediction and modeling are key factors for addressing a proper planning and management of urban sound environments. In this paper we propose a maximum a posteriori (MAP) method to compare nonlinear statespace models that describe the problem of predicting environmental sound levels. The numerical implementation of this method is based on particle filtering and we use a Markov chain Monte Carlo technique to improve the resampling step. In order to demonstrate the validity of the proposed approach for this particular problem, we have conducted a set of experiments where two prediction models are quantitatively compared using real noise measurement data collected in different urban areas. 
Asheghan, Mohammad Mostafa; Míguez, Joaquín Stability Analysis and Robust Control of Heart Beat Rate During Treadmill Exercise (Journal Article) Automatica, 63 , pp. 311–320, 2016, ISSN: 00051098. @article{Asheghan2016, title = {Stability Analysis and Robust Control of Heart Beat Rate During Treadmill Exercise}, author = {Asheghan, Mohammad Mostafa and Míguez, Joaquín}, doi = {10.1016/j.automatica.2015.10.027}, issn = {00051098}, year = {2016}, date = {20160101}, journal = {Automatica}, volume = {63}, pages = {311320}, abstract = {We investigate a nonlinear dynamical model of a human's heart beat rate (HBR) during a treadmill exercise. We begin with a rigorous analysis of the stability of the model that extends significantly the results available in the literature. In particular, we first identify a simple set of necessary and sufficient conditions for both inputstate stability and Lyapunov stability of the system, and then prove that the same conditions also hold when the model parameters are subject to unknown but bounded perturbations. The second part of the paper is devoted to the design and analysis of a control structure for this model, where the treadmill speed plays the role of the control input and the output is the subject's HBR, which is intended to follow a prescribed pattern. We propose a simple control scheme, suitable for a practical implementation, and then analyze its performance. Specifically, we prove (i) that the same conditions that guarantee the stability of the system also ensure that the controller attains a desired level of performance (quantified in terms of the admissible deviation of the HBR from the prescribed profile) and (ii) that the controller is robust to bounded perturbations both in the system parameters and the control input. Numerical simulations are also presented in order to illustrate some of the theoretical results.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We investigate a nonlinear dynamical model of a human's heart beat rate (HBR) during a treadmill exercise. We begin with a rigorous analysis of the stability of the model that extends significantly the results available in the literature. In particular, we first identify a simple set of necessary and sufficient conditions for both inputstate stability and Lyapunov stability of the system, and then prove that the same conditions also hold when the model parameters are subject to unknown but bounded perturbations. The second part of the paper is devoted to the design and analysis of a control structure for this model, where the treadmill speed plays the role of the control input and the output is the subject's HBR, which is intended to follow a prescribed pattern. We propose a simple control scheme, suitable for a practical implementation, and then analyze its performance. Specifically, we prove (i) that the same conditions that guarantee the stability of the system also ensure that the controller attains a desired level of performance (quantified in terms of the admissible deviation of the HBR from the prescribed profile) and (ii) that the controller is robust to bounded perturbations both in the system parameters and the control input. Numerical simulations are also presented in order to illustrate some of the theoretical results. 
2015 
Koblents, Eugenia; Miguez, Joaquin A Population Monte Carlo Scheme with Transformed Weights and Its Application to Stochastic Kinetic Models (Journal Article) Statistics and Computing, 25 (2), pp. 407–425, 2015, ISSN: 09603174. @article{Koblents2014b, title = {A Population Monte Carlo Scheme with Transformed Weights and Its Application to Stochastic Kinetic Models}, author = {Koblents, Eugenia and Miguez, Joaquin}, url = {http://link.springer.com/10.1007/s1122201394402 http://gts.tsc.uc3m.es/wpcontent/uploads/2014/01/NPMC_ApopulationMonteCarloschemewithtransformed_jma.pdf}, doi = {10.1007/s1122201394402}, issn = {09603174}, year = {2015}, date = {20150301}, journal = {Statistics and Computing}, volume = {25}, number = {2}, pages = {407425}, abstract = {This paper addresses the Monte Carlo approximation of posterior probability distributions. In particular, we consider the population Monte Carlo (PMC) technique, which is based on an iterative importance sampling (IS) approach. An important drawback of this methodology is the degeneracy of the importance weights (IWs) when the dimension of either the observations or the variables of interest is high. To alleviate this difficulty, we propose a new method that performs a nonlinear transformation of the IWs. This operation reduces the weight variation, hence it avoids degeneracy and increases the efficiency of the IS scheme, specially when drawing from proposal functions which are poorly adapted to the true posterior. For the sake of illustration, we have applied the proposed algorithm to the estimation of the parameters of a Gaussian mixture model. This is a simple problem that enables us to discuss the main features of the proposed technique. As a practical application, we have also considered the challenging problem of estimating the rate parameters of a stochastic kinetic model (SKM). SKMs are multivariate systems that model molecular interactions in biological and chemical problems. We introduce a particularization of the proposed algorithm to SKMs and present numerical results.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper addresses the Monte Carlo approximation of posterior probability distributions. In particular, we consider the population Monte Carlo (PMC) technique, which is based on an iterative importance sampling (IS) approach. An important drawback of this methodology is the degeneracy of the importance weights (IWs) when the dimension of either the observations or the variables of interest is high. To alleviate this difficulty, we propose a new method that performs a nonlinear transformation of the IWs. This operation reduces the weight variation, hence it avoids degeneracy and increases the efficiency of the IS scheme, specially when drawing from proposal functions which are poorly adapted to the true posterior. For the sake of illustration, we have applied the proposed algorithm to the estimation of the parameters of a Gaussian mixture model. This is a simple problem that enables us to discuss the main features of the proposed technique. As a practical application, we have also considered the challenging problem of estimating the rate parameters of a stochastic kinetic model (SKM). SKMs are multivariate systems that model molecular interactions in biological and chemical problems. We introduce a particularization of the proposed algorithm to SKMs and present numerical results. 
MartínFernández, Laura; Ruiz, Diego; Torija, Antonio; Miguez, Joaquin A Bayesian Method for Model Selection in Environmental Noise Prediction. (Journal Article) Journal of Environmental Informatics, January 20 , 2015, ISSN: 17262135. @article{MartinFernandez2015, title = {A Bayesian Method for Model Selection in Environmental Noise Prediction.}, author = {MartínFernández, Laura and Ruiz, Diego P. and Torija, Antonio J. and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P44_Bayesian method for model selection in environmental noise prediction.pdf http://www.researchgate.net/publication/268213140_A_Bayesian_method_for_model_selection_in_environmental_noise_prediction}, issn = {17262135}, year = {2015}, date = {20150101}, journal = {Journal of Environmental Informatics}, volume = {January 20}, abstract = {Environmental noise prediction and modeling are key factors for addressing a proper planning and management of urban sound environments. In this paper we propose a maximum a posteriori (MAP) method to compare nonlinear statespace models that describe the problem of predicting environmental sound levels. The numerical implementation of this method is based on particle filtering and we use a Markov chain Monte Carlo technique to improve the resampling step. In order to demonstrate the validity of the proposed approach for this particular problem, we have conducted a set of experiments where two prediction models are quantitatively compared using real noise measurement data collected in different urban areas.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Environmental noise prediction and modeling are key factors for addressing a proper planning and management of urban sound environments. In this paper we propose a maximum a posteriori (MAP) method to compare nonlinear statespace models that describe the problem of predicting environmental sound levels. The numerical implementation of this method is based on particle filtering and we use a Markov chain Monte Carlo technique to improve the resampling step. In order to demonstrate the validity of the proposed approach for this particular problem, we have conducted a set of experiments where two prediction models are quantitatively compared using real noise measurement data collected in different urban areas. 
2014 
Koblents, Eugenia; Miguez, Joaquin A Population Monte Carlo Scheme with Transformed Weights and Its Application to Stochastic Kinetic Models (Journal Article) Statistics and Computing, (to appear) , 2014, ISSN: 09603174. @article{Koblents2014, title = {A Population Monte Carlo Scheme with Transformed Weights and Its Application to Stochastic Kinetic Models}, author = {Koblents, Eugenia and Miguez, Joaquin}, url = {http://link.springer.com/10.1007/s1122201394402 http://gts.tsc.uc3m.es/wpcontent/uploads/2014/01/NPMC_ApopulationMonteCarloschemewithtransformed_jma.pdf}, issn = {09603174}, year = {2014}, date = {20140101}, journal = {Statistics and Computing}, volume = {(to appear)}, abstract = {This paper addresses the Monte Carlo approximation of posterior probability distributions. In particular, we consider the population Monte Carlo (PMC) technique, which is based on an iterative importance sampling (IS) approach. An important drawback of this methodology is the degeneracy of the importance weights (IWs) when the dimension of either the observations or the variables of interest is high. To alleviate this difficulty, we propose a new method that performs a nonlinear transformation of the IWs. This operation reduces the weight variation, hence it avoids degeneracy and increases the efficiency of the IS scheme, specially when drawing from proposal functions which are poorly adapted to the true posterior. For the sake of illustration, we have applied the proposed algorithm to the estimation of the parameters of a Gaussian mixture model. This is a simple problem that enables us to discuss the main features of the proposed technique. As a practical application, we have also considered the challenging problem of estimating the rate parameters of a stochastic kinetic model (SKM). SKMs are multivariate systems that model molecular interactions in biological and chemical problems. We introduce a particularization of the proposed algorithm to SKMs and present numerical results.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper addresses the Monte Carlo approximation of posterior probability distributions. In particular, we consider the population Monte Carlo (PMC) technique, which is based on an iterative importance sampling (IS) approach. An important drawback of this methodology is the degeneracy of the importance weights (IWs) when the dimension of either the observations or the variables of interest is high. To alleviate this difficulty, we propose a new method that performs a nonlinear transformation of the IWs. This operation reduces the weight variation, hence it avoids degeneracy and increases the efficiency of the IS scheme, specially when drawing from proposal functions which are poorly adapted to the true posterior. For the sake of illustration, we have applied the proposed algorithm to the estimation of the parameters of a Gaussian mixture model. This is a simple problem that enables us to discuss the main features of the proposed technique. As a practical application, we have also considered the challenging problem of estimating the rate parameters of a stochastic kinetic model (SKM). SKMs are multivariate systems that model molecular interactions in biological and chemical problems. We introduce a particularization of the proposed algorithm to SKMs and present numerical results. 
MartinFernandez, Laura; Gilioli, Gianni; Lanzarone, Ettore; Miguez, Joaquin; Pasquali, Sara; Ruggeri, Fabrizio; Ruiz, Diego A RaoBlackwellized Particle Filter for Joint Parameter Estimation and Biomass Tracking in a Stochastic PredatorPrey System (Journal Article) Mathematical Biosciences and Engineering, 11 (3), pp. 573–597, 2014. @article{MartinFernandez2014, title = {A RaoBlackwellized Particle Filter for Joint Parameter Estimation and Biomass Tracking in a Stochastic PredatorPrey System}, author = {MartinFernandez, Laura and Gilioli, Gianni and Lanzarone, Ettore and Miguez, Joaquin and Pasquali, Sara and Ruggeri, Fabrizio and Ruiz, Diego P.}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P42_2014_A RaoBlackwellized Particle Filter for Joint Parameter Estimation and Biomass Tracking in a Stochastic PredatorPrey System.pdf https://www.aimsciences.org/journals/pdfs.jsp?paperID=9557&mode=full http://gts.tsc.uc3m.es/wpcontent/uploads/2014/01/LMF_et_al_MBE13_ARAOBLACKWELLIZEDPARTICLEFILTER_jma.pdf https://www.aimsciences.org/journals/displayArticlesnew.jsp?paperID=9557}, year = {2014}, date = {20140101}, journal = {Mathematical Biosciences and Engineering}, volume = {11}, number = {3}, pages = {573597}, abstract = {Functional response estimation and population tracking in predator prey systems are critical problems in ecology. In this paper we consider a stochastic predatorprey system with a LotkaVolterra functional response and propose a particle ltering method for: (a) estimating the behavioral parameter representing the rate of e ective search per predator in the functional response and (b) forecasting the population biomass using eld data. In particular, the proposed technique combines a sequential Monte Carlo sampling scheme for tracking the timevarying biomass with the analytical integration of the unknown behavioral parameter. In order to assess the performance of the method, we show results for both synthetic and observed data collected in an acarine predatorprey system, namely the pest mite Tetranychus urticae and the predatory mite Phytoseiulus persimilis.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Functional response estimation and population tracking in predator prey systems are critical problems in ecology. In this paper we consider a stochastic predatorprey system with a LotkaVolterra functional response and propose a particle ltering method for: (a) estimating the behavioral parameter representing the rate of e ective search per predator in the functional response and (b) forecasting the population biomass using eld data. In particular, the proposed technique combines a sequential Monte Carlo sampling scheme for tracking the timevarying biomass with the analytical integration of the unknown behavioral parameter. In order to assess the performance of the method, we show results for both synthetic and observed data collected in an acarine predatorprey system, namely the pest mite Tetranychus urticae and the predatory mite Phytoseiulus persimilis.

Crisan, Dan; Miguez, Joaquin ParticleKernel Estimation of the Filter Density in StateSpace Models (Journal Article) Bernoulli, (to appear) , 2014. @article{Crisan2014, title = {ParticleKernel Estimation of the Filter Density in StateSpace Models}, author = {Crisan, Dan and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P43_2014_ParticleKernel Estimation of the Filter Density in StateSpace Models.pdf http://www.bernoullisociety.org/index.php/publications/bernoullijournal/bernoullijournalpapers}, year = {2014}, date = {20140101}, journal = {Bernoulli}, volume = {(to appear)}, abstract = {Sequential Monte Carlo (SMC) methods, also known as particle filters, are simulationbased recursive algorithms for the approximation of the a posteriori probability measures generated by statespace dynamical models. At any given time t, a SMC method produces a set of samples over the state space of the system of interest (often termed “particles”) that is used to build a discrete and random approximation of the posterior probability distribution of the state variables, conditional on a sequence of available observations. One potential application of the methodology is the estimation of the densities associated to the sequence of a posteriori distributions. While practitioners have rather freely applied such density approximations in the past, the issue has received less attention from a theoretical perspective. In this paper, we address the problem of constructing kernelbased estimates of the posterior probability density function and its derivatives, and obtain asymptotic convergence results for the estimation errors. In particular, we find convergence rates for the approximation errors that hold uniformly on the state space and guarantee that the error vanishes almost surely as the number of particles in the filter grows. Based on this uniform convergence result, we first show how to build continuous measures that converge almost surely (with known rate) toward the posterior measure and then address a few applications. The latter include maximum a posteriori estimation of the system state using the approximate derivatives of the posterior density and the approximation of functionals of it, e.g., Shannon’s entropy.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Sequential Monte Carlo (SMC) methods, also known as particle filters, are simulationbased recursive algorithms for the approximation of the a posteriori probability measures generated by statespace dynamical models. At any given time t, a SMC method produces a set of samples over the state space of the system of interest (often termed “particles”) that is used to build a discrete and random approximation of the posterior probability distribution of the state variables, conditional on a sequence of available observations. One potential application of the methodology is the estimation of the densities associated to the sequence of a posteriori distributions. While practitioners have rather freely applied such density approximations in the past, the issue has received less attention from a theoretical perspective. In this paper, we address the problem of constructing kernelbased estimates of the posterior probability density function and its derivatives, and obtain asymptotic convergence results for the estimation errors. In particular, we find convergence rates for the approximation errors that hold uniformly on the state space and guarantee that the error vanishes almost surely as the number of particles in the filter grows. Based on this uniform convergence result, we first show how to build continuous measures that converge almost surely (with known rate) toward the posterior measure and then address a few applications. The latter include maximum a posteriori estimation of the system state using the approximate derivatives of the posterior density and the approximation of functionals of it, e.g., Shannon’s entropy. 
Read, Jesse; Achutegui, Katrin; Miguez, Joaquin A Distributed Particle Filter for Nonlinear Tracking in Wireless Sensor Networks (Journal Article) Signal Processing, 98 , pp. 121–134, 2014. @article{Read2014, title = {A Distributed Particle Filter for Nonlinear Tracking in Wireless Sensor Networks}, author = {Read, Jesse and Achutegui, Katrin and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P40_2014_A Distributed Particle Filter for Nonlinear Tracking in Wireless Sensor Networks.pdf http://www.sciencedirect.com/science/article/pii/S0165168413004568 http://users.ics.aalto.fi/jesse/papers/A distributed particle filter for nonlinear tracking in wireless sensor networks.pdf}, year = {2014}, date = {20140101}, journal = {Signal Processing}, volume = {98}, pages = {121134}, abstract = {The use of distributed particle filters for tracking in sensor networks has become popular in recent years. The distributed particle filters proposed in the literature up to now are only approximations of the centralized particle filter or, if they are a proper distributed version of the particle filter, their implementation in a wireless sensor network demands a prohibitive communication capability. In this work, we propose a mathematically sound distributed particle filter for tracking in a realworld indoor wireless sensor network composed of lowpower nodes. We provide formal and general descriptions of our methodology and then present the results of both realworld experiments and/or computer simulations that use models fitted with real data. With the same number of particles as a centralized filter, the distributed algorithm is over four times faster, yet our simulations show that, even assuming the same processing speed, the accuracy of the centralized and distributed algorithms is practically identical. The main limitation of the proposed scheme is the need to make all the sensor observations available to every processing node. Therefore, it is better suited to broadcast networks or multihop networks where the volume of generated data is kept low, e.g., by an adequate local preprocessing of the observations.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The use of distributed particle filters for tracking in sensor networks has become popular in recent years. The distributed particle filters proposed in the literature up to now are only approximations of the centralized particle filter or, if they are a proper distributed version of the particle filter, their implementation in a wireless sensor network demands a prohibitive communication capability. In this work, we propose a mathematically sound distributed particle filter for tracking in a realworld indoor wireless sensor network composed of lowpower nodes. We provide formal and general descriptions of our methodology and then present the results of both realworld experiments and/or computer simulations that use models fitted with real data. With the same number of particles as a centralized filter, the distributed algorithm is over four times faster, yet our simulations show that, even assuming the same processing speed, the accuracy of the centralized and distributed algorithms is practically identical. The main limitation of the proposed scheme is the need to make all the sensor observations available to every processing node. Therefore, it is better suited to broadcast networks or multihop networks where the volume of generated data is kept low, e.g., by an adequate local preprocessing of the observations. 
2013 
Asheghan, Mohammad Mostafa; Miguez, Joaquin Robust Global Synchronization of two Complex Dynamical Networks (Journal Article) Chaos (Woodbury, N.Y.), 23 (2), pp. 023108, 2013, ISSN: 10897682. @article{Asheghan2013, title = {Robust Global Synchronization of two Complex Dynamical Networks}, author = {Asheghan, Mohammad Mostafa and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P38_2013_Robust Global Synchronization of two Complex Dynamical Networks.pdf http://www.researchgate.net/publication/245026922_Robust_global_synchronization_of_two_complex_dynamical_networks}, issn = {10897682}, year = {2013}, date = {20130101}, journal = {Chaos (Woodbury, N.Y.)}, volume = {23}, number = {2}, pages = {023108}, abstract = {We investigate the synchronization of two coupled complex dynamical networks, a problem that has been termed outer synchronization in the literature. Our approach relies on (a) a basic lemma on the eigendecomposition of matrices resulting from Kronecker products and (b) a suitable choice of Lyapunov function related to the synchronization error dynamics. Starting from these two ingredients, a theorem that provides a sufficient condition for outer synchronization of the networks is proved. The condition in the theorem is expressed as a linear matrix inequality. When satisfied, synchronization is guaranteed to occur globally, i.e., independently of the initial conditions of the networks. The argument of the proof includes the design of the gain of the synchronizer, which is a constant square matrix with dimension dependent on the number of dynamic variables in a single network node, but independent of the size of the overall network, which can be much larger. This basic result is subsequently elaborated to simplify the design of the synchronizer, to avoid unnecessarily restrictive assumptions (e.g., diffusivity) on the coupling matrix that defines the topology of the networks and, finally, to obtain synchronizers that are robust to model errors in the parameters of the coupled networks. An illustrative numerical example for the outer synchronization of two networks of classical Lorenz nodes with perturbed parameters is presented.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We investigate the synchronization of two coupled complex dynamical networks, a problem that has been termed outer synchronization in the literature. Our approach relies on (a) a basic lemma on the eigendecomposition of matrices resulting from Kronecker products and (b) a suitable choice of Lyapunov function related to the synchronization error dynamics. Starting from these two ingredients, a theorem that provides a sufficient condition for outer synchronization of the networks is proved. The condition in the theorem is expressed as a linear matrix inequality. When satisfied, synchronization is guaranteed to occur globally, i.e., independently of the initial conditions of the networks. The argument of the proof includes the design of the gain of the synchronizer, which is a constant square matrix with dimension dependent on the number of dynamic variables in a single network node, but independent of the size of the overall network, which can be much larger. This basic result is subsequently elaborated to simplify the design of the synchronizer, to avoid unnecessarily restrictive assumptions (e.g., diffusivity) on the coupling matrix that defines the topology of the networks and, finally, to obtain synchronizers that are robust to model errors in the parameters of the coupled networks. An illustrative numerical example for the outer synchronization of two networks of classical Lorenz nodes with perturbed parameters is presented. 
Miguez, Joaquin; Crisan, Dan; Djuric, Petar On the Convergence of Two Sequential Monte Carlo Methods for Maximum a Posteriori Sequence Estimation and Stochastic Global Optimization (Journal Article) Statistics and Computing, 23 (1), pp. 91–107, 2013, ISSN: 09603174. @article{Miguez2011, title = {On the Convergence of Two Sequential Monte Carlo Methods for Maximum a Posteriori Sequence Estimation and Stochastic Global Optimization}, author = {Miguez, Joaquin and Crisan, Dan and Djuric, Petar M.}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P36_2013_On the Convergence of Two Sequential Monte Carlo Methods for Maximum a Posteriori Sequence Estimation and Stochastic Global Optimization.pdf http://www.researchgate.net/publication/225447686_On_the_convergence_of_two_sequential_Monte_Carlo_methods_for_maximum_a_posteriori_sequence_estimation_and_stochastic_global_optimization http://www.tsc.uc3m.es/~jmiguez/papers/miguez11.pdf}, issn = {09603174}, year = {2013}, date = {20130101}, journal = {Statistics and Computing}, volume = {23}, number = {1}, pages = {91107}, abstract = {This paper addresses the problem of maximum a posteriori (MAP) sequence estimation in general statespace models. We consider two algorithms based on the sequential Monte Carlo (SMC) methodology (also known as particle filtering). We prove that they produce approximations of the MAP estimator and that they converge almost surely. We also derive a lower bound for the number of particles that are needed to achieve a given approximation accuracy. In the last part of the paper, we investigate the application of particle filtering and MAP estimation to the global optimization of a class of (possibly nonconvex and possibly nondifferentiable) cost functions. In particular, we show how to convert the costminimization problem into one of MAP sequence estimation for a statespace model that is “matched” to the cost of interest. We provide examples that illustrate the application of the methodology as well as numerical results.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper addresses the problem of maximum a posteriori (MAP) sequence estimation in general statespace models. We consider two algorithms based on the sequential Monte Carlo (SMC) methodology (also known as particle filtering). We prove that they produce approximations of the MAP estimator and that they converge almost surely. We also derive a lower bound for the number of particles that are needed to achieve a given approximation accuracy. In the last part of the paper, we investigate the application of particle filtering and MAP estimation to the global optimization of a class of (possibly nonconvex and possibly nondifferentiable) cost functions. In particular, we show how to convert the costminimization problem into one of MAP sequence estimation for a statespace model that is “matched” to the cost of interest. We provide examples that illustrate the application of the methodology as well as numerical results. 
Valera, Isabel; Sieskul, Bamrung; Miguez, Joaquin On the Maximum Likelihood Estimation of the ToA Under an Imperfect Path Loss Exponent (Journal Article) EURASIP Journal on Wireless Communications and Networking, 2013 (1), pp. 158, 2013, ISSN: 16871499. @article{Valera2013, title = {On the Maximum Likelihood Estimation of the ToA Under an Imperfect Path Loss Exponent}, author = {Valera, Isabel and Sieskul, Bamrung and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P37_2013_On the Maximum Likelihood Estimation of the ToA Under an Imperfect Path Loss Exponent.pdf http://jwcn.eurasipjournals.com/content/2013/1/158}, issn = {16871499}, year = {2013}, date = {20130101}, journal = {EURASIP Journal on Wireless Communications and Networking}, volume = {2013}, number = {1}, pages = {158}, publisher = {Springer}, abstract = {We investigate the estimation of the time of arrival (ToA) of a radio signal transmitted over a flatfading channel. The path attenuation is assumed to depend only on the transmitterreceiver distance and the path loss exponent (PLE) which, in turn, depends on the physical environment. All previous approaches to the problem either assume that the PLE is perfectly known or rely on estimators of the ToA which do not depend on the PLE. In this paper, we introduce a novel analysis of the performance of the maximum likelihood (ML) estimator of the ToA under an imperfect knowledge of the PLE. Specifically, we carry out a Taylor series expansion that approximates the bias and the root mean square error of the ML estimator in closed form as a function of the PLE error. The analysis is first carried out for a path loss model in which the received signal gain depends only on the PLE and the transmitterreceiver distance. Then, we extend the obtained results to account also for shadow fading scenarios. Our computer simulations show that this approximate analysis is accurate when the signaltonoise ratio (SNR) of the received signal is medium to high. A simple Monte Carlo method based on the analysis is also proposed. This technique is computationally efficient and yields a better approximation of the ML estimator in the low SNR region. The obtained analytical (and Monte Carlo) approximations can be useful at the design stage of wireless communication and localization systems.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We investigate the estimation of the time of arrival (ToA) of a radio signal transmitted over a flatfading channel. The path attenuation is assumed to depend only on the transmitterreceiver distance and the path loss exponent (PLE) which, in turn, depends on the physical environment. All previous approaches to the problem either assume that the PLE is perfectly known or rely on estimators of the ToA which do not depend on the PLE. In this paper, we introduce a novel analysis of the performance of the maximum likelihood (ML) estimator of the ToA under an imperfect knowledge of the PLE. Specifically, we carry out a Taylor series expansion that approximates the bias and the root mean square error of the ML estimator in closed form as a function of the PLE error. The analysis is first carried out for a path loss model in which the received signal gain depends only on the PLE and the transmitterreceiver distance. Then, we extend the obtained results to account also for shadow fading scenarios. Our computer simulations show that this approximate analysis is accurate when the signaltonoise ratio (SNR) of the received signal is medium to high. A simple Monte Carlo method based on the analysis is also proposed. This technique is computationally efficient and yields a better approximation of the ML estimator in the low SNR region. The obtained analytical (and Monte Carlo) approximations can be useful at the design stage of wireless communication and localization systems. 
Vazquez, Manuel; Miguez, Joaquin User Activity Tracking in DSCDMA Systems (Journal Article) IEEE Transactions on Vehicular Technology, 62 (7), pp. 3188–3203, 2013, ISSN: 00189545. @article{Vazquez2013a, title = {User Activity Tracking in DSCDMA Systems}, author = {Vazquez, Manuel A. and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P39_2013_User Activity Tracking in DSCDMA Systems.pdf http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6473922}, issn = {00189545}, year = {2013}, date = {20130101}, journal = {IEEE Transactions on Vehicular Technology}, volume = {62}, number = {7}, pages = {31883203}, abstract = {In modern multiuser communication systems, users are allowed to enter or leave the system at any given time. Thus, the number of active users is an unknown and timevarying parameter, and the performance of the system depends on how accurately this parameter is estimated over time. The socalled problem of user identification, which consists of determining the number and identities of users transmitting in a communication system, is usually solved prior to, and hence independently of, that posed by the detection of the transmitted data. Since both problems are tightly connected, a joint solution is desirable. In this paper, we focus on directsequence (DS) codedivision multipleaccess (CDMA) systems and derive, within a Bayesian framework, different receivers that cope with an unknown and timevarying number of users while performing joint channel estimation and data detection. The main feature of these receivers, compared with other recently proposed schemes for user activity detection, is that they are natural extensions of existing maximum a posteriori (MAP) equalizers for multipleinputmultipleoutput communication channels. We assess the validity of the proposed receivers, including their reliability in detecting the number and identities of active users, by way of computer simulations.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In modern multiuser communication systems, users are allowed to enter or leave the system at any given time. Thus, the number of active users is an unknown and timevarying parameter, and the performance of the system depends on how accurately this parameter is estimated over time. The socalled problem of user identification, which consists of determining the number and identities of users transmitting in a communication system, is usually solved prior to, and hence independently of, that posed by the detection of the transmitted data. Since both problems are tightly connected, a joint solution is desirable. In this paper, we focus on directsequence (DS) codedivision multipleaccess (CDMA) systems and derive, within a Bayesian framework, different receivers that cope with an unknown and timevarying number of users while performing joint channel estimation and data detection. The main feature of these receivers, compared with other recently proposed schemes for user activity detection, is that they are natural extensions of existing maximum a posteriori (MAP) equalizers for multipleinputmultipleoutput communication channels. We assess the validity of the proposed receivers, including their reliability in detecting the number and identities of active users, by way of computer simulations. 
2012 
Achutegui, Katrin; Miguez, Joaquin; Rodas, Javier; Escudero, Carlos A MultiModel Sequential Monte Carlo Methodology for Indoor Tracking: Algorithms and Experimental Results (Journal Article) Signal Processing, 92 (11), pp. 2594–2613, 2012. @article{Achutegui2012, title = {A MultiModel Sequential Monte Carlo Methodology for Indoor Tracking: Algorithms and Experimental Results}, author = {Achutegui, Katrin and Miguez, Joaquin and Rodas, Javier and Escudero, Carlos J.}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P32_2012_ MultiModel Sequential Monte Carlo Methodology for Indoor Tracking Algorithms and Experimental Results.pdf http://www.sciencedirect.com/science/article/pii/S0165168412001077}, year = {2012}, date = {20120101}, journal = {Signal Processing}, volume = {92}, number = {11}, pages = {25942613}, abstract = {In this paper we address the problem of indoor tracking using received signal strength (RSS) as a positiondependent data measurement. Since RSS is highly influenced by multipath propagation, it turns out very hard to adequately model the correspondence between the received power and the transmittertoreceiver distance. Although various models have been proposed in the literature, they often require the use of very large collections of data in order to fit them and display great sensitivity to changes in the radio propagation environment. In this work we advocate the use of switching multiple models that account for different classes of target dynamics and propagation environments and propose a flexible probabilistic switching scheme. The resulting statespace structure is termed a generalized switching multiple model (GSMM) system. Within this framework, we investigate two types of models for the RSS data: polynomial models and classical logarithmic pathloss representation. The first model is more accurate however it demands an offline model fitting step. The second one is less precise but it can be fitted in an online procedure. We have designed two tracking algorithms built around a RaoBlackwellized particle filter, tailored to the GSMM structure and assessed its performances both with synthetic and experimental measurements.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In this paper we address the problem of indoor tracking using received signal strength (RSS) as a positiondependent data measurement. Since RSS is highly influenced by multipath propagation, it turns out very hard to adequately model the correspondence between the received power and the transmittertoreceiver distance. Although various models have been proposed in the literature, they often require the use of very large collections of data in order to fit them and display great sensitivity to changes in the radio propagation environment. In this work we advocate the use of switching multiple models that account for different classes of target dynamics and propagation environments and propose a flexible probabilistic switching scheme. The resulting statespace structure is termed a generalized switching multiple model (GSMM) system. Within this framework, we investigate two types of models for the RSS data: polynomial models and classical logarithmic pathloss representation. The first model is more accurate however it demands an offline model fitting step. The second one is less precise but it can be fitted in an online procedure. We have designed two tracking algorithms built around a RaoBlackwellized particle filter, tailored to the GSMM structure and assessed its performances both with synthetic and experimental measurements. 
Luengo, David; Miguez, Joaquin; Martino, Luca Efficient Sampling from Truncated Bivariate Gaussians via BoxMuller Transformation (Journal Article) Electronics Letters, 48 (24), pp. 1533–1534, 2012, ISSN: 00135194. @article{Luengo2012a, title = {Efficient Sampling from Truncated Bivariate Gaussians via BoxMuller Transformation}, author = {Luengo, David and Miguez, Joaquin and Martino, Luca}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P35_2012_Efficient Sampling from Truncated Bivariate Gaussians via BoxMuller Transformation.pdf http://www.researchgate.net/publication/235004345_Efficient_Sampling_from_Truncated_Bivariate_Gaussians_via_the_BoxMuller_Transformation}, issn = {00135194}, year = {2012}, date = {20120101}, journal = {Electronics Letters}, volume = {48}, number = {24}, pages = {15331534}, abstract = {Many practical simulation tasks demand procedures to draw samples efficiently from multivariate truncated Gaussian distributions. In this work, we introduce a novel rejection approach, based on the BoxMuller transformation, to generate samples from a truncated bivariate Gaussian density with an arbitrary support. Furthermore, for an important class of support regions the new method allows us to achieve exact sampling, thus becoming the most efficient approach possible. Introduction: The numerical simulation of many systems of practical interest demands the ability to produce Monte Carlo samples from truncated Gaussian distributions [5, 3, 7]. The simplest way to address this problem is to perform rejection sampling using the corresponding (nontruncated) Gaussian distribution as a proposal. This trivial method produces independent and identically distributed (i.i.d.) samples, but it is time consuming and computationally inefficient. For these two reasons, different methods have been introduced in the literature, e.g., using MCMC techniques [5, 7] or rejection sampling [1]. Unfortunately, MCMC schemes produce correlated samples, which can lead to a very slow convergence of the chain, whereas rejection methods can be computationally inefficient. In this paper, we introduce a novel approach, based on the BoxMuller transformation (BMT) [2], to generate i.i.d. samples from truncated bivariate Gaussian distributions. The main advantages of the proposed approach are the following: (1) it allows sampling within a generic domain D ⊆ R 2 without any restriction and (2) the inverse transformation of the BMT maps any region D ⊆ R 2 (either bounded or unbounded) into a bounded region, A ⊆ R = [0, 1] × [0, 1]. Hence, all the procedures developed for drawing efficiently uniform random variables within bounded regions, e.g., adaptive rejection sampling or strip methods [2, 4], can always be used. Furthermore, for an important class of support regions the BMT allows us to perform exact sampling (i.e., draw i.i.d. samples from the target distribution without any rejection), which is the most efficient situation possible. Problem Formulation: The problem considered here is related to drawing samples from a truncated multivariate Gaussian distribution. In particular, in this letter we focus on drawing samples from a bivariate truncated standard Gaussian PDF, denoted as Z ∼ T N (0, I, D), where the support domain D ⊆ R 2 is a nonnull Borel set. Note that drawing samples from a nontruncated standard Gaussian distribution, Z ∼ N (0, I), enables us to draw samples from an arbitrary Gaussian distribution, X ∼ N (µ, $Sigma$), whenever $Sigma$ is positive definite. More precisely, since $Sigma$ is positive definite, it can be expressed as $Sigma$ = SS , using for instance the Cholesky decomposition, and the random vector X = SZ + µ has the desired distribution, X ∼ N (µ, $Sigma$). Similarly, sampling from a truncated bivariate standard Gaussian distribution allows us to generate samples from an arbitrary truncated bivariate Gaussian. In this case, if Z ∼ T N (0, I, D), then we can obtain X ∼ T N (µ, $Sigma$, D *) simply through the transformation X = SZ + µ, with $Sigma$ = SS and}, keywords = {}, pubstate = {published}, tppubtype = {article} } Many practical simulation tasks demand procedures to draw samples efficiently from multivariate truncated Gaussian distributions. In this work, we introduce a novel rejection approach, based on the BoxMuller transformation, to generate samples from a truncated bivariate Gaussian density with an arbitrary support. Furthermore, for an important class of support regions the new method allows us to achieve exact sampling, thus becoming the most efficient approach possible. Introduction: The numerical simulation of many systems of practical interest demands the ability to produce Monte Carlo samples from truncated Gaussian distributions [5, 3, 7]. The simplest way to address this problem is to perform rejection sampling using the corresponding (nontruncated) Gaussian distribution as a proposal. This trivial method produces independent and identically distributed (i.i.d.) samples, but it is time consuming and computationally inefficient. For these two reasons, different methods have been introduced in the literature, e.g., using MCMC techniques [5, 7] or rejection sampling [1]. Unfortunately, MCMC schemes produce correlated samples, which can lead to a very slow convergence of the chain, whereas rejection methods can be computationally inefficient. In this paper, we introduce a novel approach, based on the BoxMuller transformation (BMT) [2], to generate i.i.d. samples from truncated bivariate Gaussian distributions. The main advantages of the proposed approach are the following: (1) it allows sampling within a generic domain D ⊆ R 2 without any restriction and (2) the inverse transformation of the BMT maps any region D ⊆ R 2 (either bounded or unbounded) into a bounded region, A ⊆ R = [0, 1] × [0, 1]. Hence, all the procedures developed for drawing efficiently uniform random variables within bounded regions, e.g., adaptive rejection sampling or strip methods [2, 4], can always be used. Furthermore, for an important class of support regions the BMT allows us to perform exact sampling (i.e., draw i.i.d. samples from the target distribution without any rejection), which is the most efficient situation possible. Problem Formulation: The problem considered here is related to drawing samples from a truncated multivariate Gaussian distribution. In particular, in this letter we focus on drawing samples from a bivariate truncated standard Gaussian PDF, denoted as Z ∼ T N (0, I, D), where the support domain D ⊆ R 2 is a nonnull Borel set. Note that drawing samples from a nontruncated standard Gaussian distribution, Z ∼ N (0, I), enables us to draw samples from an arbitrary Gaussian distribution, X ∼ N (µ, $Sigma$), whenever $Sigma$ is positive definite. More precisely, since $Sigma$ is positive definite, it can be expressed as $Sigma$ = SS , using for instance the Cholesky decomposition, and the random vector X = SZ + µ has the desired distribution, X ∼ N (µ, $Sigma$). Similarly, sampling from a truncated bivariate standard Gaussian distribution allows us to generate samples from an arbitrary truncated bivariate Gaussian. In this case, if Z ∼ T N (0, I, D), then we can obtain X ∼ T N (µ, $Sigma$, D *) simply through the transformation X = SZ + µ, with $Sigma$ = SS and 
Maiz, Cristina; MolanesLopez, Elisa; Miguez, Joaquin; Djuric, Petar A Particle Filtering Scheme for Processing Time Series Corrupted by Outliers (Journal Article) IEEE Transactions on Signal Processing, 60 (9), pp. 46114627, 2012, ISSN: 1053587X. @article{Maiz2012, title = {A Particle Filtering Scheme for Processing Time Series Corrupted by Outliers}, author = {Maiz, Cristina S. and MolanesLopez, Elisa M. and Miguez, Joaquin and Djuric, Petar M.}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P34_2012_A Particle Filtering Scheme for Processing Time Series Corrupted by Outliers.pdf http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6203606}, issn = {1053587X}, year = {2012}, date = {20120101}, journal = {IEEE Transactions on Signal Processing}, volume = {60}, number = {9}, pages = {46114627}, abstract = {The literature in engineering and statistics is abounding in techniques for detecting and properly processing anomalous observations in the data. Most of these techniques have been developed in the framework of static models and it is only in recent years that we have seen attempts that address the presence of outliers in nonlinear time series. For a target tracking problem described by a nonlinear statespace model, we propose the online detection of outliers by including an outlier detection step within the standard particle filtering algorithm. The outlier detection step is implemented by a test involving a statistic of the predictive distribution of the observations, such as a concentration measure or an extreme upper quantile. We also provide asymptotic results about the convergence of the particle approximations of the predictive distribution (and its statistics) and assess the performance of the resulting algorithms by computer simulations of target tracking problems with signal power observations.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The literature in engineering and statistics is abounding in techniques for detecting and properly processing anomalous observations in the data. Most of these techniques have been developed in the framework of static models and it is only in recent years that we have seen attempts that address the presence of outliers in nonlinear time series. For a target tracking problem described by a nonlinear statespace model, we propose the online detection of outliers by including an outlier detection step within the standard particle filtering algorithm. The outlier detection step is implemented by a test involving a statistic of the predictive distribution of the observations, such as a concentration measure or an extreme upper quantile. We also provide asymptotic results about the convergence of the particle approximations of the predictive distribution (and its statistics) and assess the performance of the resulting algorithms by computer simulations of target tracking problems with signal power observations. 
2011 
Asheghan, Mohammad Mostafa; Miguez, Joaquin; HamidiBeheshti, Mohammad; Tavazoei, Mohammad Saleh Robust Outer Synchronization between two Complex Networks with Fractional Order Dynamics (Journal Article) Chaos (Woodbury, N.Y.), 21 (3), pp. 033121, 2011, ISSN: 10897682. @article{Asheghan2011, title = {Robust Outer Synchronization between two Complex Networks with Fractional Order Dynamics}, author = {Asheghan, Mohammad Mostafa and Miguez, Joaquin and HamidiBeheshti, Mohammad T and Tavazoei, Mohammad Saleh}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P32_2011_Robust Outer Synchronization between two Complex Networks with Fractional Order Dynamics.pdf http://scitation.aip.org/content/aip/journal/chaos/21/3/10.1063/1.3629986 http://www.tsc.uc3m.es/~jmiguez/papers/Asheghan11.pdf}, issn = {10897682}, year = {2011}, date = {20110101}, journal = {Chaos (Woodbury, N.Y.)}, volume = {21}, number = {3}, pages = {033121}, publisher = {AIP Publishing}, abstract = {Synchronization between two coupled complex networks with fractionalorder dynamics, hereafter referred to as outer synchronization, is investigated in this work. In particular, we consider two systems consisting of interconnected nodes. The state variables of each node evolve with time according to a set of (possibly nonlinear and chaotic) fractionalorder differential equations. One of the networks plays the role of a master system and drives the second network by way of an openplusclosedloop (OPCL) scheme. Starting from a simple analysis of the synchronization error and a basic lemma on the eigenvalues of matrices resulting from Kronecker products, we establish various sets of conditions for outer synchronization, i.e., for ensuring that the errors between the state variables of the master and response systems can asymptotically vanish with time. Then, we address the problem of robust outer synchronization, i.e., how to guarantee that the states of the nodes converge to common values when the parameters of the master and response networks are not identical, but present some perturbations. Assuming that these perturbations are bounded, we also find conditions for outer synchronization, this time given in terms of sets of linear matrix inequalities (LMIs). Most of the analytical results in this paper are valid both for fractionalorder and integerorder dynamics. The assumptions on the inner (coupling) structure of the networks are mild, involving, at most, symmetry and diffusivity. The analytical results are complemented with numerical examples. In particular, we show examples of generalized and robust outer synchronization for networks whose nodes are governed by fractionalorder Lorenz dynamics.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Synchronization between two coupled complex networks with fractionalorder dynamics, hereafter referred to as outer synchronization, is investigated in this work. In particular, we consider two systems consisting of interconnected nodes. The state variables of each node evolve with time according to a set of (possibly nonlinear and chaotic) fractionalorder differential equations. One of the networks plays the role of a master system and drives the second network by way of an openplusclosedloop (OPCL) scheme. Starting from a simple analysis of the synchronization error and a basic lemma on the eigenvalues of matrices resulting from Kronecker products, we establish various sets of conditions for outer synchronization, i.e., for ensuring that the errors between the state variables of the master and response systems can asymptotically vanish with time. Then, we address the problem of robust outer synchronization, i.e., how to guarantee that the states of the nodes converge to common values when the parameters of the master and response networks are not identical, but present some perturbations. Assuming that these perturbations are bounded, we also find conditions for outer synchronization, this time given in terms of sets of linear matrix inequalities (LMIs). Most of the analytical results in this paper are valid both for fractionalorder and integerorder dynamics. The assumptions on the inner (coupling) structure of the networks are mild, involving, at most, symmetry and diffusivity. The analytical results are complemented with numerical examples. In particular, we show examples of generalized and robust outer synchronization for networks whose nodes are governed by fractionalorder Lorenz dynamics. 
Vazquez, Manuel; Miguez, Joaquin A PerSurvivor Processing Receiver for MIMO Transmission Systems With One Unknown Channel Order Per Output (Journal Article) IEEE Transactions on Vehicular Technology, 60 (9), pp. 4415–4426, 2011, ISSN: 00189545. @article{Vazquez2011, title = {A PerSurvivor Processing Receiver for MIMO Transmission Systems With One Unknown Channel Order Per Output}, author = {Vazquez, Manuel A. and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P31_2011_A PerSurvivor Processing Receiver for MIMO Transmission Systems With One Unknown Channel Order Per Output.pdf http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6032763 http://www.tsc.uc3m.es/~jmiguez/papers/vazquez11.pdf}, issn = {00189545}, year = {2011}, date = {20110101}, journal = {IEEE Transactions on Vehicular Technology}, volume = {60}, number = {9}, pages = {44154426}, abstract = {The order of a communications channel is the length of its impulse response. Recently, several works have tackled the problem of estimating the order of a frequencyselective multipleinputmultipleoutput (MIMO) channel. However, all of them consider a single order, despite the fact that a MIMO channel comprises several subchannels (specifically, as many as the number of inputs times the number of outputs), each one possibly with its own order. In this paper, we introduce an algorithm for maximumlikelihood sequence detection (MLSD) in frequency and timeselective MIMO channels that incorporates full estimation of the MIMO channel impulse response (CIR) coefficients, including one channel order per output. Simulation results following the analytical derivation of the algorithm suggest that the proposed receiver can achieve significant improvements in performance when transmitting through a MIMO channel that effectively comprises subchannels of different lengths.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The order of a communications channel is the length of its impulse response. Recently, several works have tackled the problem of estimating the order of a frequencyselective multipleinputmultipleoutput (MIMO) channel. However, all of them consider a single order, despite the fact that a MIMO channel comprises several subchannels (specifically, as many as the number of inputs times the number of outputs), each one possibly with its own order. In this paper, we introduce an algorithm for maximumlikelihood sequence detection (MLSD) in frequency and timeselective MIMO channels that incorporates full estimation of the MIMO channel impulse response (CIR) coefficients, including one channel order per output. Simulation results following the analytical derivation of the algorithm suggest that the proposed receiver can achieve significant improvements in performance when transmitting through a MIMO channel that effectively comprises subchannels of different lengths. 
2010 
Djuric, Petar; Miguez, Joaquin Assessment of Nonlinear Dynamic Models by Kolmogorov–Smirnov Statistics (Journal Article) IEEE Transactions on Signal Processing, 58 (10), pp. 5069–5079, 2010, ISSN: 1053587X. @article{Djuric2010a, title = {Assessment of Nonlinear Dynamic Models by Kolmogorov–Smirnov Statistics}, author = {Djuric, Petar M. and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P28_2010_Assessment of Nonlinear Dynamic Models by Kolmogorov–Smirnov Statistics.pdf http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5491124}, issn = {1053587X}, year = {2010}, date = {20100101}, journal = {IEEE Transactions on Signal Processing}, volume = {58}, number = {10}, pages = {50695079}, abstract = {Model assessment is a fundamental problem in science and engineering and it addresses the question of the validity of a model in the light of empirical evidence. In this paper, we propose a method for the assessment of dynamic nonlinear models based on empirical and predictive cumulative distributions of data and the KolmogorovSmirnov statistics. The technique is based on the generation of discrete random variables that come from a known discrete distribution if the entertained model is correct. We provide simulation examples that demonstrate the performance of the proposed method.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Model assessment is a fundamental problem in science and engineering and it addresses the question of the validity of a model in the light of empirical evidence. In this paper, we propose a method for the assessment of dynamic nonlinear models based on empirical and predictive cumulative distributions of data and the KolmogorovSmirnov statistics. The technique is based on the generation of discrete random variables that come from a known discrete distribution if the entertained model is correct. We provide simulation examples that demonstrate the performance of the proposed method. 
Martino, Luca; Miguez, Joaquin Generalized Rejection Sampling Schemes and Applications in Signal Processing (Journal Article) Signal Processing, 90 (11), pp. 2981–2995, 2010. @article{Martino2010a, title = {Generalized Rejection Sampling Schemes and Applications in Signal Processing}, author = {Martino, Luca and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P29_2010_Generalized Rejection Sampling Schemes and Applications in Signal Processing.pdf http://www.sciencedirect.com/science/article/pii/S0165168410001866}, year = {2010}, date = {20100101}, journal = {Signal Processing}, volume = {90}, number = {11}, pages = {29812995}, abstract = {Bayesian methods and their implementations by means of sophisticated Monte Carlo techniques, such as Markov chain Monte Carlo (MCMC) and particle filters, have become very popular in signal processing over the last years. However, in many problems of practical interest these techniques demand procedures for sampling from probability distributions with nonstandard forms, hence we are often brought back to the consideration of fundamental simulation algorithms, such as rejection sampling (RS). Unfortunately, the use of RS techniques demands the calculation of tight upper bounds for the ratio of the target probability density function (pdf) over the proposal density from which candidate samples are drawn. Except for the class of logconcave target pdf\'s, for which an efficient algorithm exists, there are no general methods to analytically determine this bound, which has to be derived from scratch for each specific case. In this paper, we introduce new schemes for (a) obtaining upper bounds for likelihood functions and (b) adaptively computing proposal densities that approximate the target pdf closely. The former class of methods provides the tools to easily sample from a posteriori probability distributions (that appear very often in signal processing problems) by drawing candidates from the prior distribution. However, they are even more useful when they are exploited to derive the generalized adaptive RS (GARS) algorithm introduced in the second part of the paper. The proposed GARS method yields a sequence of proposal densities that converge towards the target pdf and enable a very efficient sampling of a broad class of probability distributions, possibly with multiple modes and nonstandard forms. We provide some simple numerical examples to illustrate the use of the proposed techniques, including an example of target localization using range measurements, often encountered in sensor network applications.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Bayesian methods and their implementations by means of sophisticated Monte Carlo techniques, such as Markov chain Monte Carlo (MCMC) and particle filters, have become very popular in signal processing over the last years. However, in many problems of practical interest these techniques demand procedures for sampling from probability distributions with nonstandard forms, hence we are often brought back to the consideration of fundamental simulation algorithms, such as rejection sampling (RS). Unfortunately, the use of RS techniques demands the calculation of tight upper bounds for the ratio of the target probability density function (pdf) over the proposal density from which candidate samples are drawn. Except for the class of logconcave target pdf's, for which an efficient algorithm exists, there are no general methods to analytically determine this bound, which has to be derived from scratch for each specific case. In this paper, we introduce new schemes for (a) obtaining upper bounds for likelihood functions and (b) adaptively computing proposal densities that approximate the target pdf closely. The former class of methods provides the tools to easily sample from a posteriori probability distributions (that appear very often in signal processing problems) by drawing candidates from the prior distribution. However, they are even more useful when they are exploited to derive the generalized adaptive RS (GARS) algorithm introduced in the second part of the paper. The proposed GARS method yields a sequence of proposal densities that converge towards the target pdf and enable a very efficient sampling of a broad class of probability distributions, possibly with multiple modes and nonstandard forms. We provide some simple numerical examples to illustrate the use of the proposed techniques, including an example of target localization using range measurements, often encountered in sensor network applications. 
Martino, Luca; Miguez, Joaquin A Generalization of the Adaptive Rejection Sampling Algorithm (Journal Article) Statistics and Computing, 21 (4), pp. 633–647, 2010, ISSN: 09603174. @article{Martino2010b, title = {A Generalization of the Adaptive Rejection Sampling Algorithm}, author = {Martino, Luca and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P30_2011_A Generalization of the Adaptive Rejection Sampling Algorithm.pdf http://link.springer.com/10.1007/s1122201091979}, issn = {09603174}, year = {2010}, date = {20100101}, journal = {Statistics and Computing}, volume = {21}, number = {4}, pages = {633647}, abstract = {Rejection sampling is a wellknown method to generate random samples from arbitrary target probability distributions. It demands the design of a suitable proposal probability density function (pdf) from which candidate samples can be drawn. These samples are either accepted or rejected depending on a test involving the ratio of the target and proposal densities. The adaptive rejection sampling method is an efficient algorithm to sample from a logconcave target density, that attains high acceptance rates by improving the proposal density whenever a sample is rejected. In this paper we introduce a generalized adaptive rejection sampling procedure that can be applied with a broad class of target probability distributions, possibly nonlogconcave and exhibiting multiple modes. The proposed technique yields a sequence of proposal densities that converge toward the target pdf, thus achieving very high acceptance rates. We provide a simple numerical example to illustrate the basic use of the proposed technique, together with a more elaborate positioning application using real data.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Rejection sampling is a wellknown method to generate random samples from arbitrary target probability distributions. It demands the design of a suitable proposal probability density function (pdf) from which candidate samples can be drawn. These samples are either accepted or rejected depending on a test involving the ratio of the target and proposal densities. The adaptive rejection sampling method is an efficient algorithm to sample from a logconcave target density, that attains high acceptance rates by improving the proposal density whenever a sample is rejected. In this paper we introduce a generalized adaptive rejection sampling procedure that can be applied with a broad class of target probability distributions, possibly nonlogconcave and exhibiting multiple modes. The proposed technique yields a sequence of proposal densities that converge toward the target pdf, thus achieving very high acceptance rates. We provide a simple numerical example to illustrate the basic use of the proposed technique, together with a more elaborate positioning application using real data. 
Miguez, Joaquin Analysis of a Sequential Monte Carlo Method for Optimization in Dynamical Systems (Journal Article) Signal Processing, 90 (5), pp. 1609–1622, 2010. @article{Zoubir2010, title = {Analysis of a Sequential Monte Carlo Method for Optimization in Dynamical Systems}, author = {Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P27_2010_Analysis of a Sequential Monte Carlo Method for Optimization in Dynamical Systems.pdf http://www.sciencedirect.com/science/article/pii/S0165168409004708 http://www.tsc.uc3m.es/~jmiguez/papers/miguez10a.pdf}, year = {2010}, date = {20100101}, journal = {Signal Processing}, volume = {90}, number = {5}, pages = {16091622}, abstract = {We investigate a recently proposed sequential Monte Carlo methodology for recursively tracking the minima of a cost function that evolves with time. These methods, subsequently referred to as sequential Monte Carlo minimization (SMCM) procedures, have an algorithmic structure similar to particle filters: they involve the generation of random paths in the space of the signal of interest (SoI), the stochastic selection of the fittest paths and the ranking of the survivors according to their cost. In this paper, we propose an extension of the original SMCM methodology (that makes it applicable to a broader class of cost functions) and introduce an asymptoticconvergence analysis. Our analytical results are based on simple induction arguments and show how the SoIestimates computed by a SMCM algorithm converge, in probability, to a sequence of minimizers of the cost function. We illustrate these results by means of two computer simulation examples.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We investigate a recently proposed sequential Monte Carlo methodology for recursively tracking the minima of a cost function that evolves with time. These methods, subsequently referred to as sequential Monte Carlo minimization (SMCM) procedures, have an algorithmic structure similar to particle filters: they involve the generation of random paths in the space of the signal of interest (SoI), the stochastic selection of the fittest paths and the ranking of the survivors according to their cost. In this paper, we propose an extension of the original SMCM methodology (that makes it applicable to a broader class of cost functions) and introduce an asymptoticconvergence analysis. Our analytical results are based on simple induction arguments and show how the SoIestimates computed by a SMCM algorithm converge, in probability, to a sequence of minimizers of the cost function. We illustrate these results by means of two computer simulation examples. 
2009 
Mariño, Inés; Miguez, Joaquin; Meucci, Riccardo Monte Carlo Method for Adaptively Estimating the Unknown Parameters and the Dynamic State of Chaotic Systems (Journal Article) Physical Review E, 79 (5), pp. 056218, 2009, ISSN: 15393755. @article{Marino2009, title = {Monte Carlo Method for Adaptively Estimating the Unknown Parameters and the Dynamic State of Chaotic Systems}, author = {Mariño, Inés and Miguez, Joaquin and Meucci, Riccardo}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P26_2009_Monte Carlo Method for Adaptively Estimating the Unknown Parameters and the Dynamic State of Chaotic Systems.pdf http://link.aps.org/doi/10.1103/PhysRevE.79.056218}, issn = {15393755}, year = {2009}, date = {20090101}, journal = {Physical Review E}, volume = {79}, number = {5}, pages = {056218}, publisher = {American Physical Society}, abstract = {We propose a Monte Carlo methodology for the joint estimation of unobserved dynamic variables and unknown static parameters in chaotic systems. The technique is sequential, i.e., it updates the variable and parameter estimates recursively as new observations become available, and, hence, suitable for online implementation. We demonstrate the validity of the method by way of two examples. In the first one, we tackle the estimation of all the dynamic variables and one unknown parameter of a fivedimensional nonlinear model using a time series of scalar observations experimentally collected from a chaotic CO2 laser. In the second example, we address the estimation of the two dynamic variables and the phase parameter of a numerical model commonly employed to represent the dynamics of optoelectronic feedback loops designed for chaotic communications over fiberoptic links.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We propose a Monte Carlo methodology for the joint estimation of unobserved dynamic variables and unknown static parameters in chaotic systems. The technique is sequential, i.e., it updates the variable and parameter estimates recursively as new observations become available, and, hence, suitable for online implementation. We demonstrate the validity of the method by way of two examples. In the first one, we tackle the estimation of all the dynamic variables and one unknown parameter of a fivedimensional nonlinear model using a time series of scalar observations experimentally collected from a chaotic CO2 laser. In the second example, we address the estimation of the two dynamic variables and the phase parameter of a numerical model commonly employed to represent the dynamics of optoelectronic feedback loops designed for chaotic communications over fiberoptic links. 
Vazquez, Manuel; Miguez, Joaquin MaximumLikelihood Sequence Detection in Time and FrequencySelective MIMO Channels With Unknown Order (Journal Article) IEEE Transactions on Vehicular Technology, 58 (1), pp. 499–504, 2009, ISSN: 00189545. @article{Vazquez2009, title = {MaximumLikelihood Sequence Detection in Time and FrequencySelective MIMO Channels With Unknown Order}, author = {Vazquez, Manuel A. and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P25_2009_MaximumLikelihood Sequence Detection in Time and FrequencySelective MIMO Channels With Unknown Order.pdf http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4510724 http://www.tsc.uc3m.es/~jmiguez/papers/vazquez08b.ps}, issn = {00189545}, year = {2009}, date = {20090101}, journal = {IEEE Transactions on Vehicular Technology}, volume = {58}, number = {1}, pages = {499504}, abstract = {In the equalization of frequencyselective multipleinputmultipleoutput (MIMO) channels, it is usually assumed that the length of the channel impulse response (CIR), which is also referred to as the channel order, is known. However, this is not true in most practical situations, and it is a common approach to overestimate the channel order to avoid the serious performance degradation that occurs when the CIR length is underestimated. Unfortunately, the computational complexity of maximumlikelihood sequence detection (MLSD) in frequencyselective channels exponentially grows with the channel order; hence, overestimation can actually be undesirable because it leads to more expensive and inefficient receivers. In this paper, we introduce an algorithm for MLSD that incorporates the full estimation of the MIMO CIR parameters, including its order. The proposed technique is based on the persurvivor processing (PSP) methodology; it admits both blind and semiblind implementations, depending on the availability of pilot data, and is designed to work with timeselective channels. In addition to the analytical derivation of the algorithm, we provide computer simulation results that illustrate the effectiveness of the resulting receiver.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In the equalization of frequencyselective multipleinputmultipleoutput (MIMO) channels, it is usually assumed that the length of the channel impulse response (CIR), which is also referred to as the channel order, is known. However, this is not true in most practical situations, and it is a common approach to overestimate the channel order to avoid the serious performance degradation that occurs when the CIR length is underestimated. Unfortunately, the computational complexity of maximumlikelihood sequence detection (MLSD) in frequencyselective channels exponentially grows with the channel order; hence, overestimation can actually be undesirable because it leads to more expensive and inefficient receivers. In this paper, we introduce an algorithm for MLSD that incorporates the full estimation of the MIMO CIR parameters, including its order. The proposed technique is based on the persurvivor processing (PSP) methodology; it admits both blind and semiblind implementations, depending on the availability of pilot data, and is designed to work with timeselective channels. In addition to the analytical derivation of the algorithm, we provide computer simulation results that illustrate the effectiveness of the resulting receiver. 
2008 
Vazquez, Manuel; Bugallo, Monica; Miguez, Joaquin Sequential Monte Carlo Methods for ComplexityConstrained MAP Equalization of Dispersive MIMO Channels (Journal Article) Signal Processing, 88 (4), pp. 1017–1034, 2008. @article{Vazquez2008b, title = {Sequential Monte Carlo Methods for ComplexityConstrained MAP Equalization of Dispersive MIMO Channels}, author = {Vazquez, Manuel A. and Bugallo, Monica F. and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P24_2008_Sequential Monte Carlo Methods for ComplexityConstrained MAP Equalization of Dispersive MIMO Channels.pdf http://www.sciencedirect.com/science/article/pii/S0165168407003763 http://www.tsc.uc3m.es/~jmiguez/papers/vazquez08.ps}, year = {2008}, date = {20080101}, journal = {Signal Processing}, volume = {88}, number = {4}, pages = {10171034}, abstract = {The ability to perform nearly optimal equalization of multiple input multiple output (MIMO) wireless channels using sequential Monte Carlo (SMC) techniques has recently been demonstrated. SMC methods allow to recursively approximate the a posteriori probabilities of the transmitted symbols, as observations are sequentially collected, using samples from adequate probability distributions. Hence, they are a class of online (adaptive) algorithms, suitable to handle the timevarying channels typical of high speed mobile communication applications. The main drawback of the SMCbased MIMOchannel equalizers so far proposed is that their computational complexity grows exponentially with the number of input data streams and the length of the channel impulse response, rendering these methods impractical. In this paper, we introduce novel SMC schemes that overcome this limitation by the adequate design of proposal probability distribution functions that can be sampled with a lesser computational burden, yet provide a closetooptimal performance in terms of the resulting equalizer bit error rate and channel estimation error. We show that the complexity of the resulting receivers grows polynomially with the number of input data streams and the length of the channel response, and present computer simulation results that illustrate their performance in some typical scenarios.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The ability to perform nearly optimal equalization of multiple input multiple output (MIMO) wireless channels using sequential Monte Carlo (SMC) techniques has recently been demonstrated. SMC methods allow to recursively approximate the a posteriori probabilities of the transmitted symbols, as observations are sequentially collected, using samples from adequate probability distributions. Hence, they are a class of online (adaptive) algorithms, suitable to handle the timevarying channels typical of high speed mobile communication applications. The main drawback of the SMCbased MIMOchannel equalizers so far proposed is that their computational complexity grows exponentially with the number of input data streams and the length of the channel impulse response, rendering these methods impractical. In this paper, we introduce novel SMC schemes that overcome this limitation by the adequate design of proposal probability distribution functions that can be sampled with a lesser computational burden, yet provide a closetooptimal performance in terms of the resulting equalizer bit error rate and channel estimation error. We show that the complexity of the resulting receivers grows polynomially with the number of input data streams and the length of the channel response, and present computer simulation results that illustrate their performance in some typical scenarios. 
2007 
Mariño, Inés; Miguez, Joaquin Monte Carlo Method for Multiparameter Estimation in Coupled Chaotic Systems. (Journal Article) Physical review. E, Statistical, nonlinear, and soft matter physics, 76 (5 Pt 2), pp. 057203, 2007, ISSN: 15393755. @article{Marino2007, title = {Monte Carlo Method for Multiparameter Estimation in Coupled Chaotic Systems.}, author = {Mariño, Inés and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P23_2007_Monte Carlo Method for Multiparameter Estimation in Coupled Chaotic Systems.pdf http://www.ncbi.nlm.nih.gov/pubmed/18233798 http://www.tsc.uc3m.es/~jmiguez/papers/marino07.ps}, issn = {15393755}, year = {2007}, date = {20070101}, journal = {Physical review. E, Statistical, nonlinear, and soft matter physics}, volume = {76}, number = {5 Pt 2}, pages = {057203}, abstract = {We address the problem of estimating multiple parameters of a chaotic dynamical model from the observation of a scalar time series. We assume that the series is produced by a chaotic system with the same functional form as the model, so that synchronization between the two systems can be achieved by an adequate coupling. In this scenario, we propose an efficient Monte Carlo optimization algorithm that iteratively updates the model parameters in order to minimize the synchronization error. As an example, we apply it to jointly estimate the three static parameters of a chaotic Lorenz system.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We address the problem of estimating multiple parameters of a chaotic dynamical model from the observation of a scalar time series. We assume that the series is produced by a chaotic system with the same functional form as the model, so that synchronization between the two systems can be achieved by an adequate coupling. In this scenario, we propose an efficient Monte Carlo optimization algorithm that iteratively updates the model parameters in order to minimize the synchronization error. As an example, we apply it to jointly estimate the three static parameters of a chaotic Lorenz system. 
Miguez, Joaquin Analysis of Parallelizable Resampling Algorithms for Particle Filtering (Journal Article) Signal Processing, 87 (12), pp. 3155–3174, 2007. @article{Miguez2007, title = {Analysis of Parallelizable Resampling Algorithms for Particle Filtering}, author = {Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P21_2007_Analysis of Parallelizable Resampling Algorithms for Particle Filtering.pdf http://www.sciencedirect.com/science/article/pii/S0165168407002290 http://www.tsc.uc3m.es/~jmiguez/papers/Miguez07b.ps}, year = {2007}, date = {20070101}, journal = {Signal Processing}, volume = {87}, number = {12}, pages = {31553174}, abstract = {Particle filtering methods are powerful tools for online estimation and tracking in nonlinear and nonGaussian dynamical systems. They commonly consist of three steps: (1) drawing samples in the statespace of the system, (2) computing proper importance weights of each sample and (3) resampling. Steps 1 and 2 can be carried out concurrently for each sample, but standard resampling techniques require strong interaction. This is an important limitation, because one of the potential advantages of particle filtering is the possibility to perform very fast online signal processing using parallel computing devices. It is only very recently that resampling techniques specifically designed for parallel computation have been proposed, but little is known about the properties of such algorithms and how they compare to standard methods. In this paper, we investigate two classes of such techniques, distributed resampling with nonproportional allocation (DRNA) and local selection (LS). Namely, we analyze the effect of DRNA and LS on the sample variance of the importance weights; the distortion, due to the resampling step, of the discrete probability measure given by the particle filter; and the variance of estimators after resampling. Finally, we carry out computer simulations to support the analytical results and to illustrate the actual performance of DRNA and LS. Two typical problems are considered: vehicle navigation and tracking the dynamic variables of the chaotic Lorenz system driven by white noise.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Particle filtering methods are powerful tools for online estimation and tracking in nonlinear and nonGaussian dynamical systems. They commonly consist of three steps: (1) drawing samples in the statespace of the system, (2) computing proper importance weights of each sample and (3) resampling. Steps 1 and 2 can be carried out concurrently for each sample, but standard resampling techniques require strong interaction. This is an important limitation, because one of the potential advantages of particle filtering is the possibility to perform very fast online signal processing using parallel computing devices. It is only very recently that resampling techniques specifically designed for parallel computation have been proposed, but little is known about the properties of such algorithms and how they compare to standard methods. In this paper, we investigate two classes of such techniques, distributed resampling with nonproportional allocation (DRNA) and local selection (LS). Namely, we analyze the effect of DRNA and LS on the sample variance of the importance weights; the distortion, due to the resampling step, of the discrete probability measure given by the particle filter; and the variance of estimators after resampling. Finally, we carry out computer simulations to support the analytical results and to illustrate the actual performance of DRNA and LS. Two typical problems are considered: vehicle navigation and tracking the dynamic variables of the chaotic Lorenz system driven by white noise. 
Miguez, Joaquin Analysis of Selection Methods for CostReference Particle Filtering with Applications to Maneuvering Target Tracking and Dynamic Optimization (Journal Article) Digital Signal Processing, 17 (4), pp. 787–807, 2007. @article{Miguez2007a, title = {Analysis of Selection Methods for CostReference Particle Filtering with Applications to Maneuvering Target Tracking and Dynamic Optimization}, author = {Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P22_2007_Analysis of Selection Methods for CostReference Particle Filtering with Applications to Maneuvering Target Tracking and Dynamic Optimization.pdf http://www.sciencedirect.com/science/article/pii/S1051200406001357 http://promultidis.tsc.uc3m.es/files/promultidisfiles/papers/Miguez06d.pdf http://www.tsc.uc3m.es/~jmiguez/papers/miguez06c.ps}, year = {2007}, date = {20070101}, journal = {Digital Signal Processing}, volume = {17}, number = {4}, pages = {787807}, abstract = {Costreference particle filtering (CRPF) is a recently proposed sequential Monte Carlo (SMC) methodology aimed at estimating the state of a discretetime dynamic random system. The estimation task is carried out through the dynamic optimization of a userdefined cost function which is not necessarily tied to the statistics of the signals in the system. In this paper, we first revisit the basics of the CRPF methodology, introducing a generalization of the original algorithm that enables the derivation of some common particle filters within the novel framework, as well as a new and simple convergence analysis. Then, we propose and analyze a particle selection algorithm for CRPF that is suitable for implementation with parallel computing devices and, therefore, circumvents the main drawback of the conventional resampling techniques for particle filters. We illustrate the application of the methodology with two examples. The first one is an instance of one class of problems typically addressed using SMC algorithms, namely the tracking of a maneuvering target using a sensor network. The second example is the application of CRPF to solve a dynamic optimization problem.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Costreference particle filtering (CRPF) is a recently proposed sequential Monte Carlo (SMC) methodology aimed at estimating the state of a discretetime dynamic random system. The estimation task is carried out through the dynamic optimization of a userdefined cost function which is not necessarily tied to the statistics of the signals in the system. In this paper, we first revisit the basics of the CRPF methodology, introducing a generalization of the original algorithm that enables the derivation of some common particle filters within the novel framework, as well as a new and simple convergence analysis. Then, we propose and analyze a particle selection algorithm for CRPF that is suitable for implementation with parallel computing devices and, therefore, circumvents the main drawback of the conventional resampling techniques for particle filters. We illustrate the application of the methodology with two examples. The first one is an instance of one class of problems typically addressed using SMC algorithms, namely the tracking of a maneuvering target using a sensor network. The second example is the application of CRPF to solve a dynamic optimization problem. 
2006 
Mariño, Inés; Miguez, Joaquin An Approximate GradientDescent Method for Joint Parameter Estimation and Synchronization of Coupled Chaotic Systems (Journal Article) Physics Letters A, 351 (4), pp. 262–267, 2006. @article{Marino2006a, title = {An Approximate GradientDescent Method for Joint Parameter Estimation and Synchronization of Coupled Chaotic Systems}, author = {Mariño, Inés and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P18_2006_An Approximate GradientDescent Method for Joint Parameter Estimation and Synchronization of Coupled Chaotic Systems.pdf http://www.sciencedirect.com/science/article/pii/S0375960105017032 http://www.tsc.uc3m.es/~jmiguez/papers/marino06.ps}, year = {2006}, date = {20060101}, journal = {Physics Letters A}, volume = {351}, number = {4}, pages = {262267}, abstract = {We address the problem of estimating the unknown parameters of a primary chaotic system that produces an observed time series. These observations are used to drive a secondary system in a way that ensures synchronization when the two systems have identical parameters. We propose a new method to adaptively adjust the parameters in the secondary system until synchronization is achieved. It is based on the gradientdescent optimization of a suitably defined cost function and can be systematically applied to arbitrary systems. We illustrate its application by estimating the complete parameter vector of a Lorenz system.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We address the problem of estimating the unknown parameters of a primary chaotic system that produces an observed time series. These observations are used to drive a secondary system in a way that ensures synchronization when the two systems have identical parameters. We propose a new method to adaptively adjust the parameters in the secondary system until synchronization is achieved. It is based on the gradientdescent optimization of a suitably defined cost function and can be systematically applied to arbitrary systems. We illustrate its application by estimating the complete parameter vector of a Lorenz system. 
Mariño, Inés; Miguez, Joaquin On a Recursive Method for the Estimation of Unknown Parameters of Partially Observed Chaotic Systems (Journal Article) Physica D: Nonlinear Phenomena, 220 (2), pp. 175–182, 2006. @article{Marino2006, title = {On a Recursive Method for the Estimation of Unknown Parameters of Partially Observed Chaotic Systems}, author = {Mariño, Inés and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P19_2006_On a Recursive Method for the Estimation of Unknown Parameters of Partially Observed Chaotic Systems.pdf http://www.sciencedirect.com/science/article/pii/S0167278906002399 http://www.tsc.uc3m.es/~jmiguez/papers/marino06b.ps}, year = {2006}, date = {20060101}, journal = {Physica D: Nonlinear Phenomena}, volume = {220}, number = {2}, pages = {175182}, abstract = {We investigate a recently proposed method for online parameter estimation and synchronization in chaotic systems. This novel technique has been shown effective to estimate a single unknown parameter of a primary chaotic system with known functional form that is only partially observed through a scalar time series. It works by periodically updating the parameter of interest in a secondary system, with the same functional form as the primary one but no explicit coupling between their dynamic variables, in order to minimize a suitably defined cost function. In this paper, we review the basics of the method, and investigate its robustness and new extensions. In particular, we study the performance of the novel technique in the presence of noise (either observational, i.e., an additive contamination of the observed time series, or dynamical, i.e., a random perturbation of the system dynamics) and when there is a mismatch between the primary and secondary systems. Numerical results, including comparisons with other techniques, are presented. Finally, we investigate the extension of the original method to perform the estimation of two unknown parameters and illustrate its effectiveness by means of computer simulations.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We investigate a recently proposed method for online parameter estimation and synchronization in chaotic systems. This novel technique has been shown effective to estimate a single unknown parameter of a primary chaotic system with known functional form that is only partially observed through a scalar time series. It works by periodically updating the parameter of interest in a secondary system, with the same functional form as the primary one but no explicit coupling between their dynamic variables, in order to minimize a suitably defined cost function. In this paper, we review the basics of the method, and investigate its robustness and new extensions. In particular, we study the performance of the novel technique in the presence of noise (either observational, i.e., an additive contamination of the observed time series, or dynamical, i.e., a random perturbation of the system dynamics) and when there is a mismatch between the primary and secondary systems. Numerical results, including comparisons with other techniques, are presented. Finally, we investigate the extension of the original method to perform the estimation of two unknown parameters and illustrate its effectiveness by means of computer simulations. 
Miguez, Joaquin; ArtésRodríguez, Antonio Particle Filtering Algorithms for Tracking a Maneuvering Target Using a Network of Wireless Dynamic Sensors (Journal Article) EURASIP Journal on Advances in Signal Processing, 2006 (1), pp. 1–17, 2006, ISSN: 16876172. @article{Miguez2006, title = {Particle Filtering Algorithms for Tracking a Maneuvering Target Using a Network of Wireless Dynamic Sensors}, author = {Miguez, Joaquin and ArtésRodríguez, Antonio}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P20_2006_Particle Filtering Algorithms for Tracking a Maneuvering Target Using a Network of Wireless Dynamic Sensors.pdf http://asp.eurasipjournals.com/content/2006/1/083042 http://www.tsc.uc3m.es/~jmiguez/papers/miguez06b.ps}, issn = {16876172}, year = {2006}, date = {20060101}, journal = {EURASIP Journal on Advances in Signal Processing}, volume = {2006}, number = {1}, pages = {117}, publisher = {Springer}, abstract = {We investigate the problem of tracking a maneuvering target using a wireless sensor network. We assume that the sensors are binary (they transmit \'1\' for target detection and \'0\' for target absence) and capable of motion, in order to enable the tracking of targets that move over large regions. The sensor velocity is governed by the tracker, but subject to random perturbations that make the actual sensor locations uncertain. The binary local decisions are transmitted over the network to a fusion center that recursively integrates them in order to sequentially produce estimates of the target position, its velocity, and the sensor locations. We investigate the application of particle filtering techniques (namely, sequential importance sampling, auxiliary particle filtering and costreference particle filtering) in order to efficiently perform data fusion, and propose new sampling schemes tailored to the problem under study. The validity of the resulting algorithms is illustrated by means of computer simulations.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We investigate the problem of tracking a maneuvering target using a wireless sensor network. We assume that the sensors are binary (they transmit '1' for target detection and '0' for target absence) and capable of motion, in order to enable the tracking of targets that move over large regions. The sensor velocity is governed by the tracker, but subject to random perturbations that make the actual sensor locations uncertain. The binary local decisions are transmitted over the network to a fusion center that recursively integrates them in order to sequentially produce estimates of the target position, its velocity, and the sensor locations. We investigate the application of particle filtering techniques (namely, sequential importance sampling, auxiliary particle filtering and costreference particle filtering) in order to efficiently perform data fusion, and propose new sampling schemes tailored to the problem under study. The validity of the resulting algorithms is illustrated by means of computer simulations. 
2005 
Ghirmai,; Bugallo, Monica; Miguez, Joaquin; Djuric, Petar A Sequential Monte Carlo Method for Adaptive Blind Timing Estimation and Data Detection (Journal Article) IEEE Transactions on Signal Processing, 53 (8), pp. 2855–2865, 2005, ISSN: 1053587X. @article{Ghirmai2005, title = {A Sequential Monte Carlo Method for Adaptive Blind Timing Estimation and Data Detection}, author = {Ghirmai, T. and Bugallo, Monica F. and Miguez, Joaquin and Djuric, Petar M.}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P15_2005_A Sequential Monte Carlo Method for Adaptive Blind Timing Estimation and Data Detection.pdf http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1468478 http://www.tsc.uc3m.es/~jmiguez/papers/ghirmai05.ps}, issn = {1053587X}, year = {2005}, date = {20050101}, journal = {IEEE Transactions on Signal Processing}, volume = {53}, number = {8}, pages = {28552865}, abstract = {Accurate estimation of synchronization parameters is critical for reliable data detection in digital transmission. Although several techniques have been proposed in the literature for estimation of the reference parameters, i.e., timing, carrier phase, and carrier frequency offsets, they are based on either heuristic arguments or approximations, since optimal estimation is analytically intractable in most practical setups. In this paper, we introduce a new alternative approach for blind synchronization and data detection derived within the Bayesian framework and implemented via the sequential Monte Carlo (SMC) methodology. By considering an extended dynamic system where the reference parameters and the transmitted symbols are systemstate variables, the proposed SMC technique guarantees asymptotically minimal symbol error rate when it is combined with adequate receiver architectures, both in openloop and closedloop configurations. The performance of the proposed technique is studied analytically, by deriving the posterior Cra´merRao bound for timing estimation and through computer simulations that illustrate the overall performance of the resulting receivers.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Accurate estimation of synchronization parameters is critical for reliable data detection in digital transmission. Although several techniques have been proposed in the literature for estimation of the reference parameters, i.e., timing, carrier phase, and carrier frequency offsets, they are based on either heuristic arguments or approximations, since optimal estimation is analytically intractable in most practical setups. In this paper, we introduce a new alternative approach for blind synchronization and data detection derived within the Bayesian framework and implemented via the sequential Monte Carlo (SMC) methodology. By considering an extended dynamic system where the reference parameters and the transmitted symbols are systemstate variables, the proposed SMC technique guarantees asymptotically minimal symbol error rate when it is combined with adequate receiver architectures, both in openloop and closedloop configurations. The performance of the proposed technique is studied analytically, by deriving the posterior Cra´merRao bound for timing estimation and through computer simulations that illustrate the overall performance of the resulting receivers. 
Mariño, Inés; Miguez, Joaquin Adaptive Approximation Method for Joint Parameter Estimation and Identical Synchronization of Chaotic Systems (Journal Article) Physical Review E, 72 (5), pp. 057202 (4 pages), 2005, ISSN: 15393755. @article{Marino2005, title = {Adaptive Approximation Method for Joint Parameter Estimation and Identical Synchronization of Chaotic Systems}, author = {Mariño, Inés and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P16_2005_Adaptive Approximation Method for Joint Parameter Estimation and Identical Synchronization of Chaotic Systems.pdf http://link.aps.org/doi/10.1103/PhysRevE.72.057202 http://www.tsc.uc3m.es/~jmiguez/papers/marino05.ps}, issn = {15393755}, year = {2005}, date = {20050101}, journal = {Physical Review E}, volume = {72}, number = {5}, pages = {057202 (4 pages)}, publisher = {American Physical Society}, abstract = {We introduce a numerical approximation method for estimating an unknown parameter of a (primary) chaotic system which is partially observed through a scalar time series. Specifically, we show that the recursive minimization of a suitably designed cost function that involves the dynamic state of a fully observed (secondary) system and the observed time series can lead to the identical synchronization of the two systems and the accurate estimation of the unknown parameter. The salient feature of the proposed technique is that the only external input to the secondary system is the unknown parameter which needs to be adjusted. We present numerical examples for the Lorenz system which show how our algorithm can be considerably faster than some previously proposed methods.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We introduce a numerical approximation method for estimating an unknown parameter of a (primary) chaotic system which is partially observed through a scalar time series. Specifically, we show that the recursive minimization of a suitably designed cost function that involves the dynamic state of a fully observed (secondary) system and the observed time series can lead to the identical synchronization of the two systems and the accurate estimation of the unknown parameter. The salient feature of the proposed technique is that the only external input to the secondary system is the unknown parameter which needs to be adjusted. We present numerical examples for the Lorenz system which show how our algorithm can be considerably faster than some previously proposed methods. 
Miguez, Joaquin; Bugallo, Monica On the Estimation of Random Unobserved Signals by Maximization of Target Likelihoods and Its Application to Blind Timing and Phase recovery (Journal Article) Digital Signal Processing, 15 (2), pp. 171–190, 2005. @article{Miguez2005, title = {On the Estimation of Random Unobserved Signals by Maximization of Target Likelihoods and Its Application to Blind Timing and Phase recovery}, author = {Miguez, Joaquin and Bugallo, Monica F.}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P17_2005_On the Estimation of Random Unobserved Signals by Maximization of Target Likelihoods and Its Application to Blind Timing and Phase recovery.pdf http://www.sciencedirect.com/science/article/pii/S105120040400048X http://www.ece.sunysb.edu/~monica/Publications_files/journal05c.pdf http://www.tsc.uc3m.es/~jmiguez/papers/miguez05a.ps}, year = {2005}, date = {20050101}, journal = {Digital Signal Processing}, volume = {15}, number = {2}, pages = {171190}, abstract = {Many important problems in signal processing can be reduced to the adequate selection of the parameters of a (possibly nonlinear) filter in order to obtain an output signal that complies with some desired properties. In this work, we analyze a novel criterion for selecting filter parameters that relies on the ability to characterize the desired filter output in terms of a target probability density function (pdf). This target pdf can be handled as a likelihood function to be maximized, thus we refer to the new criterion as maximum targetlikelihood (MTL). We present a very general signal model where the MTL criterion can be applied and derive necessary and sufficient conditions for asymptotic convergence of the method. The relationship and differences between MTL and standard maximum likelihood (ML), minimum Kullback–Leibler divergence (MKLD), and minimum entropy (ME) methods are explored. Finally, as an example, we apply the novel criterion to the problem of blind timing and phase recovery in a digital transmission system and show that the resulting algorithm is competitive with existing nondataaided MLbased algorithms.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Many important problems in signal processing can be reduced to the adequate selection of the parameters of a (possibly nonlinear) filter in order to obtain an output signal that complies with some desired properties. In this work, we analyze a novel criterion for selecting filter parameters that relies on the ability to characterize the desired filter output in terms of a target probability density function (pdf). This target pdf can be handled as a likelihood function to be maximized, thus we refer to the new criterion as maximum targetlikelihood (MTL). We present a very general signal model where the MTL criterion can be applied and derive necessary and sufficient conditions for asymptotic convergence of the method. The relationship and differences between MTL and standard maximum likelihood (ML), minimum Kullback–Leibler divergence (MKLD), and minimum entropy (ME) methods are explored. Finally, as an example, we apply the novel criterion to the problem of blind timing and phase recovery in a digital transmission system and show that the resulting algorithm is competitive with existing nondataaided MLbased algorithms. 
2004 
GonzálezLópez, Miguel; Miguez, Joaquin; Castedo, Luis Maximum Likelihood Turbo Iterative Channel Estimation for SpaceTime Coded Systems and Its Application to Radio Transmission in Subway Tunnels (Journal Article) EURASIP Journal on Advances in Signal Processing, 2004 (5), pp. 727–739, 2004, ISSN: 16876172. @article{GonzalezLopez2004, title = {Maximum Likelihood Turbo Iterative Channel Estimation for SpaceTime Coded Systems and Its Application to Radio Transmission in Subway Tunnels}, author = {GonzálezLópez, Miguel and Miguez, Joaquin and Castedo, Luis}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P14_2004_“Maximum Likelihood Turbo Iterative Channel Estimation for SpaceTime Coded Systems and Its Application to Radio Transmission in Subway Tunnels.pdf http://asp.eurasipjournals.com/content/2004/5/843618 http://gtec.des.udc.es/web/images/pdfsJournals/2004/eurasip_jasp_gonzalez_lopez_2004.pdf}, issn = {16876172}, year = {2004}, date = {20040101}, journal = {EURASIP Journal on Advances in Signal Processing}, volume = {2004}, number = {5}, pages = {727739}, publisher = {Springer}, abstract = {This paper presents a novel channel estimation technique for spacetime coded (STC) systems. It is based on applying the maximum likelihood (ML) principle not only over a known pilot sequence but also over the unknown symbols in a data frame. The resulting channel estimator gathers both the deterministic information corresponding to the pilot sequence and the statistical information, in terms of a posteriori probabilities, about the unknown symbols. The method is suitable for Turbo equalization schemes where those probabilities are computed with more and more precision at each iteration. Since the ML channel estimation problem does not have a closedform solution, we employ the expectationmaximization (EM) algorithm in order to iteratively compute the ML estimate. The proposed channel estimator is first derived for a general timedispersive MIMO channel and then is particularized to a realistic scenario consisting of a transmission system based on the global system mobile (GSM) standard performing in a subway tunnel. In this latter case, the channel is nondispersive but there exists controlled ISI introduced by the Gaussian minimum shift keying (GMSK) modulation format used in GSM. We demonstrate, using experimentally measured channels, that the training sequence length can be reduced from 26 bits as in the GSM standard to only 5 bits, thus achieving a 14% improvement in system throughput}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper presents a novel channel estimation technique for spacetime coded (STC) systems. It is based on applying the maximum likelihood (ML) principle not only over a known pilot sequence but also over the unknown symbols in a data frame. The resulting channel estimator gathers both the deterministic information corresponding to the pilot sequence and the statistical information, in terms of a posteriori probabilities, about the unknown symbols. The method is suitable for Turbo equalization schemes where those probabilities are computed with more and more precision at each iteration. Since the ML channel estimation problem does not have a closedform solution, we employ the expectationmaximization (EM) algorithm in order to iteratively compute the ML estimate. The proposed channel estimator is first derived for a general timedispersive MIMO channel and then is particularized to a realistic scenario consisting of a transmission system based on the global system mobile (GSM) standard performing in a subway tunnel. In this latter case, the channel is nondispersive but there exists controlled ISI introduced by the Gaussian minimum shift keying (GMSK) modulation format used in GSM. We demonstrate, using experimentally measured channels, that the training sequence length can be reduced from 26 bits as in the GSM standard to only 5 bits, thus achieving a 14% improvement in system throughput 
Miguez, Joaquin; Bugallo, Monica; Djuric, Petar A New Class of Particle Filters for Random Dynamic Systems with Unknown Statistics (Journal Article) EURASIP Journal on Advances in Signal Processing, 2004 (15), pp. 2278–2294, 2004, ISSN: 16876172. @article{Miguez2004, title = {A New Class of Particle Filters for Random Dynamic Systems with Unknown Statistics}, author = {Miguez, Joaquin and Bugallo, Monica F. and Djuric, Petar M.}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P11_2004_A New Class of Particle Filters for Random Dynamic Systems with Unknown Statistics.pdf http://dl.acm.org/citation.cfm?id=1289340.1289531 http://asp.eurasipjournals.com/content/pdf/168761802004303619.pdf http://www.tsc.uc3m.es/~jmiguez/papers/miguez04c.ps}, issn = {16876172}, year = {2004}, date = {20040101}, journal = {EURASIP Journal on Advances in Signal Processing}, volume = {2004}, number = {15}, pages = {22782294}, publisher = {Hindawi Publishing Corp.}, abstract = {In recent years, particle filtering has become a powerful tool for tracking signals and timevarying parameters of random dynamic systems. These methods require a mathematical representation of the dynamics of the system evolution, together with assumptions of probabilistic models. In this paper, we present a new class of particle filtering methods that do not assume explicit mathematical forms of the probability distributions of the noise in the system. As a consequence, the proposed techniques are simpler, more robust, and more flexible than standard particle filters. Apart from the theoretical development of specific methods in the new class, we provide computer simulation results that demonstrate the performance of the algorithms in the problem of autonomous positioning of a vehicle in a 2dimensional space}, keywords = {}, pubstate = {published}, tppubtype = {article} } In recent years, particle filtering has become a powerful tool for tracking signals and timevarying parameters of random dynamic systems. These methods require a mathematical representation of the dynamics of the system evolution, together with assumptions of probabilistic models. In this paper, we present a new class of particle filtering methods that do not assume explicit mathematical forms of the probability distributions of the noise in the system. As a consequence, the proposed techniques are simpler, more robust, and more flexible than standard particle filters. Apart from the theoretical development of specific methods in the new class, we provide computer simulation results that demonstrate the performance of the algorithms in the problem of autonomous positioning of a vehicle in a 2dimensional space 
Miguez, Joaquin; Djuric, Petar Blind Equalization of FrequencySelective Channels by Sequential Importance Sampling (Journal Article) IEEE Transactions on Signal Processing, 52 (10), pp. 2738–2748, 2004, ISSN: 1053587X. @article{Miguez2004a, title = {Blind Equalization of FrequencySelective Channels by Sequential Importance Sampling}, author = {Miguez, Joaquin and Djuric, Petar M}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P13_2004_Blind Equalization of FrequencySelective Channels by Sequential Importance Sampling.pdf http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=1337243 http://www.tsc.uc3m.es/~jmiguez/papers/miguez04a.ps}, issn = {1053587X}, year = {2004}, date = {20040101}, journal = {IEEE Transactions on Signal Processing}, volume = {52}, number = {10}, pages = {27382748}, publisher = {IEEE}, abstract = {This paper introduces a novel blind equalization algorithm for frequencyselective channels based on a Bayesian formulation of the problem and the sequential importance sampling (SIS) technique. SIS methods rely on building a Monte Carlo (MC) representation of the probability distribution of interest that consists of a set of samples (usually called particles) and associated weights computed recursively in time. We elaborate on this principle to derive blind sequential algorithms that perform maximum a posteriori (MAP) symbol detection without explicit estimation of the channel parameters. In particular, we start with a basic algorithm that only requires the a priori knowledge of the model order of the channel, but we subsequently relax this assumption and investigate novel procedures to handle model order uncertainty as well. The bit error rate (BER) performance of the proposed Bayesian equalizers is evaluated and compared with that of other equalizers through computer simulations}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper introduces a novel blind equalization algorithm for frequencyselective channels based on a Bayesian formulation of the problem and the sequential importance sampling (SIS) technique. SIS methods rely on building a Monte Carlo (MC) representation of the probability distribution of interest that consists of a set of samples (usually called particles) and associated weights computed recursively in time. We elaborate on this principle to derive blind sequential algorithms that perform maximum a posteriori (MAP) symbol detection without explicit estimation of the channel parameters. In particular, we start with a basic algorithm that only requires the a priori knowledge of the model order of the channel, but we subsequently relax this assumption and investigate novel procedures to handle model order uncertainty as well. The bit error rate (BER) performance of the proposed Bayesian equalizers is evaluated and compared with that of other equalizers through computer simulations 
Miguez, Joaquin; Ghirmai, Tadesse; Bugallo, Monica; Djuric, Petar A Sequential Monte Carlo Technique for Blind Synchronization and Detection in FrequencyFlat Rayleigh Fading Wireless Channels (Journal Article) Signal Processing, 84 (11), pp. 2081–2096, 2004. @article{Miguez2004b, title = {A Sequential Monte Carlo Technique for Blind Synchronization and Detection in FrequencyFlat Rayleigh Fading Wireless Channels}, author = {Miguez, Joaquin and Ghirmai, Tadesse and Bugallo, Monica F. and Djuric, Petar M.}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P12_2004_A Sequential Monte Carlo Technique for Blind Synchronization and Detection in FrequencyFlat Rayleigh Fading Wireless Channels.pdf http://www.sciencedirect.com/science/article/pii/S0165168404001781 http://www.tsc.uc3m.es/~jmiguez/papers/miguez04b.ps}, year = {2004}, date = {20040101}, journal = {Signal Processing}, volume = {84}, number = {11}, pages = {20812096}, abstract = {This paper is aimed at the derivation of adaptive signal processing algorithms that jointly perform the tasks of blind data detection and generalized synchronization in a digital receiver. Optimal recovery of the synchronization parameters (timing, phase and frequency offsets) is analytically intractable and, as a consequence, most existing synchronization methods are either heuristic or based on approximate maximum likelihood (ML) arguments. We herein introduce an alternative approach derived within a Bayesian estimation framework and implemented via the sequential Monte Carlo (SMC) methodology. The algorithm is derived by considering an extended dynamic system where the reference parameters and the transmitted symbols are systemstate random processes. The proposed model is well suited to represent frequencyflat fastfading wireless channels. We also suggest two possible configurations for the receiver architecture that, combined with the proposed SMC technique, guarantee the achievement of asymptotically minimal symbol error rate (SER). The performance of the proposed technique is studied both analytically, by deriving the posterior Cramér–Rao bound (PCRB) for timing estimation, and through computer simulations that illustrate the accuracy of synchronization and the overall performance of the resulting blind receiver in terms of its SER.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper is aimed at the derivation of adaptive signal processing algorithms that jointly perform the tasks of blind data detection and generalized synchronization in a digital receiver. Optimal recovery of the synchronization parameters (timing, phase and frequency offsets) is analytically intractable and, as a consequence, most existing synchronization methods are either heuristic or based on approximate maximum likelihood (ML) arguments. We herein introduce an alternative approach derived within a Bayesian estimation framework and implemented via the sequential Monte Carlo (SMC) methodology. The algorithm is derived by considering an extended dynamic system where the reference parameters and the transmitted symbols are systemstate random processes. The proposed model is well suited to represent frequencyflat fastfading wireless channels. We also suggest two possible configurations for the receiver architecture that, combined with the proposed SMC technique, guarantee the achievement of asymptotically minimal symbol error rate (SER). The performance of the proposed technique is studied both analytically, by deriving the posterior Cramér–Rao bound (PCRB) for timing estimation, and through computer simulations that illustrate the accuracy of synchronization and the overall performance of the resulting blind receiver in terms of its SER. 
2003 
Djuric,; Kotecha,; Zhang,; Huang,; Ghirmai,; Bugallo,; Miguez, Joaquin Particle Filtering [IEEE Signal Processing Magazine Award 2007] (Journal Article) IEEE Signal Processing Magazine, 20 (5), pp. 19–38, 2003, ISSN: 10535888. @article{Djuric2003, title = {Particle Filtering [IEEE Signal Processing Magazine Award 2007]}, author = {Djuric, P.M. and Kotecha, J.H. and Zhang, J. and Huang, Y. and Ghirmai, T. and Bugallo, M.F. and Miguez, Joaquin}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P9_2003_Particle Filtering.pdf http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=1236770}, issn = {10535888}, year = {2003}, date = {20030101}, journal = {IEEE Signal Processing Magazine}, volume = {20}, number = {5}, pages = {1938}, publisher = {IEEE}, abstract = {Recent developments have demonstrated that particle filtering is an emerging and powerful methodology, using Monte Carlo methods, for sequential signal processing with a wide range of applications in science and engineering. It has captured the attention of many researchers in various communities, including those of signal processing, statistics and econometrics. Based on the concept of sequential importance sampling and the use of Bayesian theory, particle filtering is particularly useful in dealing with difficult nonlinear and nonGaussian problems. The underlying principle of the methodology is the approximation of relevant distributions with random measures composed of particles (samples from the space of the unknowns) and their associated weights. First, we present a brief review of particle filtering theory; and then we show how it can be used for resolving many problems in wireless communications. We demonstrate its application to blind equalization, blind detection over flat fading channels, multiuser detection, and estimation and detection of spacetime codes in fading channels.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Recent developments have demonstrated that particle filtering is an emerging and powerful methodology, using Monte Carlo methods, for sequential signal processing with a wide range of applications in science and engineering. It has captured the attention of many researchers in various communities, including those of signal processing, statistics and econometrics. Based on the concept of sequential importance sampling and the use of Bayesian theory, particle filtering is particularly useful in dealing with difficult nonlinear and nonGaussian problems. The underlying principle of the methodology is the approximation of relevant distributions with random measures composed of particles (samples from the space of the unknowns) and their associated weights. First, we present a brief review of particle filtering theory; and then we show how it can be used for resolving many problems in wireless communications. We demonstrate its application to blind equalization, blind detection over flat fading channels, multiuser detection, and estimation and detection of spacetime codes in fading channels. 
Bugallo, Monica; Miguez, Joaquin; Castedo, Luis DecisionFeedback Interference Suppression in CDMA Systems: a MLBased Semiblind Approach (Journal Article) Signal Processing, 83 (10), pp. 2179–2193, 2003, ISSN: 01651684. @article{Bugallo2003, title = {DecisionFeedback Interference Suppression in CDMA Systems: a MLBased Semiblind Approach}, author = {Bugallo, Monica F. and Miguez, Joaquin and Castedo, Luis}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P8_2003_DecisionFeedback Interference Suppression in CDMA Systems a MLBased Semiblind Approach.pdf http://www.sciencedirect.com/science/article/pii/S0165168403001610 http://www.tsc.uc3m.es/~jmiguez/papers/bugallo03.ps}, issn = {01651684}, year = {2003}, date = {20030101}, journal = {Signal Processing}, volume = {83}, number = {10}, pages = {21792193}, abstract = {This paper addresses the problem of interference suppression in direct sequence code division multiple access systems. We propose a novel semiblind decision feedback (DF) receiver based on the maximum likelihood principle that simultaneously exploits the transmission of training sequences and the statistical information of the unknown transmitted symbols. Both iterative and adaptive implementations of the proposed receiver, derived within the framework of the expectation maximization algorithm, are presented. Computer simulations show that the resulting multiuser detectors attain practically the same performance as the theoretical DF minimum mean square error receiver.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper addresses the problem of interference suppression in direct sequence code division multiple access systems. We propose a novel semiblind decision feedback (DF) receiver based on the maximum likelihood principle that simultaneously exploits the transmission of training sequences and the statistical information of the unknown transmitted symbols. Both iterative and adaptive implementations of the proposed receiver, derived within the framework of the expectation maximization algorithm, are presented. Computer simulations show that the resulting multiuser detectors attain practically the same performance as the theoretical DF minimum mean square error receiver. 
Miguez, Joaquin; Castedo, Luis Space–Time Channel Estimation and Soft Detection in TimeVarying Multiaccess Channels (Journal Article) Signal Processing, 83 (2), pp. 389–411, 2003, ISSN: 01651684. @article{Miguez2003, title = {Space–Time Channel Estimation and Soft Detection in TimeVarying Multiaccess Channels}, author = {Miguez, Joaquin and Castedo, Luis}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P10_2003_Space–Time Channel Estimation and Soft Detection in TimeVarying Multiaccess Channels.pdf http://www.sciencedirect.com/science/article/pii/S0165168402004267 http://www.tsc.uc3m.es/~jmiguez/papers/miguez03a.ps}, issn = {01651684}, year = {2003}, date = {20030101}, journal = {Signal Processing}, volume = {83}, number = {2}, pages = {389411}, abstract = {This paper introduces an iterative space–time soft estimator (ISSE) that performs joint channel estimation and soft data detection in timevarying multipleinput multipleoutput channels. The ISSE alternates channel estimation, taking explicitly into account the channel variability, and soft data detection. We suggest to implement the latter stage as a decision feedback (DF) structure consisting of two linear minimum mean square error (MMSE) matrix filters with an intercalated threshold detector. DF schemes are known to provide an appealing tradeoff between performance and computational complexity. The main contribution of the paper is the channel estimation scheme. We derive a timevarying sequence of linear filters for channel estimation according to the MMSE principle. These filters depend both on the data and the second order statistics of the channel. Hence, we introduce a scalar approximation of the channel autocovariance function that relies on the statistical homogeneity of the multipath scattering. Under this assumption, we also design a globally convergent blockadaptive algorithm to estimate and track the second order statistics of a stationary channel. The robustness of the proposed approach when either the homogeneity or the stationarity hypotheses do not hold is shown through computer simulations.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper introduces an iterative space–time soft estimator (ISSE) that performs joint channel estimation and soft data detection in timevarying multipleinput multipleoutput channels. The ISSE alternates channel estimation, taking explicitly into account the channel variability, and soft data detection. We suggest to implement the latter stage as a decision feedback (DF) structure consisting of two linear minimum mean square error (MMSE) matrix filters with an intercalated threshold detector. DF schemes are known to provide an appealing tradeoff between performance and computational complexity. The main contribution of the paper is the channel estimation scheme. We derive a timevarying sequence of linear filters for channel estimation according to the MMSE principle. These filters depend both on the data and the second order statistics of the channel. Hence, we introduce a scalar approximation of the channel autocovariance function that relies on the statistical homogeneity of the multipath scattering. Under this assumption, we also design a globally convergent blockadaptive algorithm to estimate and track the second order statistics of a stationary channel. The robustness of the proposed approach when either the homogeneity or the stationarity hypotheses do not hold is shown through computer simulations. 
2002 
Miguez, Joaquin; Castedo, Semiblind MaximumLikelihood Demodulation for CDMA Systems (Journal Article) IEEE Transactions on Vehicular Technology, 51 (4), pp. 775–781, 2002, ISSN: 00189545. @article{Miguez2002, title = {Semiblind MaximumLikelihood Demodulation for CDMA Systems}, author = {Miguez, Joaquin and Castedo, L.}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P6_2002_Semiblind MaximumLikelihood Demodulation for CDMA Systems.pdf http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=1015357 http://www.tsc.uc3m.es/~jmiguez/papers/miguez02c.ps}, issn = {00189545}, year = {2002}, date = {20020101}, journal = {IEEE Transactions on Vehicular Technology}, volume = {51}, number = {4}, pages = {775781}, publisher = {IEEE}, abstract = {This correspondence addresses the problem of channel estimation and symbol detection in wireless directsequence codedivision multipleaccess (DSCDMA) communication systems. We introduce a novel multiuser demodulation scheme that proceeds in two steps. First, the multiaccess channel parameters are estimated according to a suitable modification of the maximumlikelihood (ML) criterion using the expectation maximization (EM) algorithm. Subsequently, this estimate and other useful side information are employed to perform ML detection of the transmitted symbols with the Viterbi algorithm. Our main contribution is the development of a novel stochastic ML method for channel estimation that takes advantage of all the available statistical information referred to the transmitted signals and channel noise. Additionally, it can incorporate the knowledge of a fraction of the transmitted symbols; hence, the term semiblind. Computer simulation results are presented that show how closetooptimum performance is achieved in timedispersive fading channels using remarkably short training sequences}, keywords = {}, pubstate = {published}, tppubtype = {article} } This correspondence addresses the problem of channel estimation and symbol detection in wireless directsequence codedivision multipleaccess (DSCDMA) communication systems. We introduce a novel multiuser demodulation scheme that proceeds in two steps. First, the multiaccess channel parameters are estimated according to a suitable modification of the maximumlikelihood (ML) criterion using the expectation maximization (EM) algorithm. Subsequently, this estimate and other useful side information are employed to perform ML detection of the transmitted symbols with the Viterbi algorithm. Our main contribution is the development of a novel stochastic ML method for channel estimation that takes advantage of all the available statistical information referred to the transmitted signals and channel noise. Additionally, it can incorporate the knowledge of a fraction of the transmitted symbols; hence, the term semiblind. Computer simulation results are presented that show how closetooptimum performance is achieved in timedispersive fading channels using remarkably short training sequences 
Miguez, Joaquin; Castedo, Luis Maximum Likelihood Unsupervised Source Separation in Gaussian Noise (Journal Article) Journal of VLSI signal processing systems for signal, image and video technology, 31 (1), pp. 7–18, 2002, ISSN: 1573109X. @article{Miguez2002a, title = {Maximum Likelihood Unsupervised Source Separation in Gaussian Noise}, author = {Miguez, Joaquin and Castedo, Luis}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P5_2002_Maximum Likelihood Unsupervised Source Separation in Gaussian Noise.pdf http://link.springer.com/article/10.1023/A:1014437019997 http://www.tsc.uc3m.es/~jmiguez/papers/miguez02b.ps}, issn = {1573109X}, year = {2002}, date = {20020101}, journal = {Journal of VLSI signal processing systems for signal, image and video technology}, volume = {31}, number = {1}, pages = {718}, publisher = {Kluwer Academic Publishers}, abstract = {This paper presents a new Maximum Likelihood (ML) based approach to the separation of convolutive mixtures of unobserved sources in the presence of Additive Gaussian Noise (AGN). The proposed method proceeds in two steps. First, the mixing system coefficients are estimated in the ML sense and, afterwards, this information is employed to attain source separation according to either the ML or the linear Minimum Mean Square Error (MMSE) criteria. System coefficient estimation is carried out in a blockiterative way using an extension of the Expectation Maximization (EM) method. Both deterministic and stochastic (Monte Carlo) implementations of the resulting estimation algorithm are considered. The proposed algorithms rely on the knowledge of the sources joint probability density function (p.d.f.). This is a fairly realistic assumption in applications such as digital communications but computer simulations reveal that it is not an stringent requirement. The proposed estimation algorithm can be successfully used with a tentative p.d.f. when this is not known a priori.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper presents a new Maximum Likelihood (ML) based approach to the separation of convolutive mixtures of unobserved sources in the presence of Additive Gaussian Noise (AGN). The proposed method proceeds in two steps. First, the mixing system coefficients are estimated in the ML sense and, afterwards, this information is employed to attain source separation according to either the ML or the linear Minimum Mean Square Error (MMSE) criteria. System coefficient estimation is carried out in a blockiterative way using an extension of the Expectation Maximization (EM) method. Both deterministic and stochastic (Monte Carlo) implementations of the resulting estimation algorithm are considered. The proposed algorithms rely on the knowledge of the sources joint probability density function (p.d.f.). This is a fairly realistic assumption in applications such as digital communications but computer simulations reveal that it is not an stringent requirement. The proposed estimation algorithm can be successfully used with a tentative p.d.f. when this is not known a priori. 
Miguez, Joaquin; Castedo, Luis Semiblind Space–Time Decoding in Wireless Communications: a Maximum Likelihood Approach (Journal Article) Signal Processing, 82 (1), pp. 1–18, 2002, ISSN: 01651684. @article{Miguez2002b, title = {Semiblind Space–Time Decoding in Wireless Communications: a Maximum Likelihood Approach}, author = {Miguez, Joaquin and Castedo, Luis}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P7_2002_Semiblind Space–Time Decoding in Wireless Communications a Maximum Likelihood Approach.pdf http://www.sciencedirect.com/science/article/pii/S0165168401001475 http://www.tsc.uc3m.es/~jmiguez/papers/miguez02a.ps.zip}, issn = {01651684}, year = {2002}, date = {20020101}, journal = {Signal Processing}, volume = {82}, number = {1}, pages = {118}, abstract = {It has been recently shown that deploying multiple transmitting and receiving antennae can substantially improve the capacity of multipath wireless channels if the rich timescattering is properly exploited. Space–time coding (STC) is a novel proposal that combines channel coding techniques suitable for multiple transmitting elements with signal processing algorithms that exploit the spatial and temporal diversity at the receiver. In this paper, we focus on the signal processing perspective and propose a novel space–time semiblind decoding scheme that performs maximum likelihood (ML) based channel estimation and data detection. The multiple input multiple output (MIMO) timescattering channel is estimated using a block iterative expectationmaximization (EM) algorithm that fully exploits the statistical features of the transmitted signal together with the knowledge of a small number of transmitted symbols, hence the term semiblind. Data detection is efficiently carried out using the Viterbi algorithm. In order to reduce the computational load of the receiver, a modification of the EM algorithm with a potentially lower complexity is also suggested. Computer simulations show that the proposed semiblind decoder clearly outperforms conventional receivers that estimate the channel parameters exclusively from the a priori known transmitted symbols.}, keywords = {}, pubstate = {published}, tppubtype = {article} } It has been recently shown that deploying multiple transmitting and receiving antennae can substantially improve the capacity of multipath wireless channels if the rich timescattering is properly exploited. Space–time coding (STC) is a novel proposal that combines channel coding techniques suitable for multiple transmitting elements with signal processing algorithms that exploit the spatial and temporal diversity at the receiver. In this paper, we focus on the signal processing perspective and propose a novel space–time semiblind decoding scheme that performs maximum likelihood (ML) based channel estimation and data detection. The multiple input multiple output (MIMO) timescattering channel is estimated using a block iterative expectationmaximization (EM) algorithm that fully exploits the statistical features of the transmitted signal together with the knowledge of a small number of transmitted symbols, hence the term semiblind. Data detection is efficiently carried out using the Viterbi algorithm. In order to reduce the computational load of the receiver, a modification of the EM algorithm with a potentially lower complexity is also suggested. Computer simulations show that the proposed semiblind decoder clearly outperforms conventional receivers that estimate the channel parameters exclusively from the a priori known transmitted symbols. 
2001 
Bugallo, Monica; Miguez, Joaquin; Castedo, Luis A Maximum Likelihood Approach to Blind Multiuser Interference Cancellation (Journal Article) IEEE Transactions on Signal Processing, 49 (6), pp. 1228–1239, 2001, ISSN: 1053587X. @article{Bugallo2001, title = {A Maximum Likelihood Approach to Blind Multiuser Interference Cancellation}, author = {Bugallo, Monica F and Miguez, Joaquin and Castedo, Luis}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P3_2001_A Maximum Likelihood Approach to Blind Multiuser Interference Cancellation.pdf http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=923305 http://www.tsc.uc3m.es/~jmiguez/papers/bugallo01a.ps}, issn = {1053587X}, year = {2001}, date = {20010101}, journal = {IEEE Transactions on Signal Processing}, volume = {49}, number = {6}, pages = {12281239}, publisher = {IEEE}, abstract = {This paper addresses the problem of blind multiple access interference (MAI) and intersymbol interference (ISI) suppression in direct sequence code division multiple access (DS CDMA) systems. A novel approach to obtain the coefficients of a linear receiver using the maximum likelihood (ML) principle is proposed. The method is blind because it only exploits the statistical features of the transmitted symbols and Gaussian noise in the channel. We demonstrate that an adequate linear constraint on these coefficients ensures that the desired user is extracted and the resulting linearly constrained maximum likelihood linear (LCMLL) receiver can be efficiently implemented using the iterative space alternating generalized expectationmaximization (SAGE) algorithm. In order to take advantage of the diversity inherent to multipath channels, we also introduce a blind RAKE multiuser receiver that proceeds in two steps. First, soft estimates of the desired user transmitted symbols are obtained from each propagation path using a bank of appropriate LCMLL receivers. Afterwards, these estimates are adequately combined to enhance the signaltointerferenceandnoise ratio (SINR). Computer simulations show that the proposed blind algorithms for multiuser detection are nearfar resistant and attain convergence using small blocks of data, thus outperforming existing linearly constrained minimum variance (LCMV) blind receivers}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper addresses the problem of blind multiple access interference (MAI) and intersymbol interference (ISI) suppression in direct sequence code division multiple access (DS CDMA) systems. A novel approach to obtain the coefficients of a linear receiver using the maximum likelihood (ML) principle is proposed. The method is blind because it only exploits the statistical features of the transmitted symbols and Gaussian noise in the channel. We demonstrate that an adequate linear constraint on these coefficients ensures that the desired user is extracted and the resulting linearly constrained maximum likelihood linear (LCMLL) receiver can be efficiently implemented using the iterative space alternating generalized expectationmaximization (SAGE) algorithm. In order to take advantage of the diversity inherent to multipath channels, we also introduce a blind RAKE multiuser receiver that proceeds in two steps. First, soft estimates of the desired user transmitted symbols are obtained from each propagation path using a bank of appropriate LCMLL receivers. Afterwards, these estimates are adequately combined to enhance the signaltointerferenceandnoise ratio (SINR). Computer simulations show that the proposed blind algorithms for multiuser detection are nearfar resistant and attain convergence using small blocks of data, thus outperforming existing linearly constrained minimum variance (LCMV) blind receivers 
Bugallo, Monica; Miguez, Joaquin; Castedo, Luis Semiblind Linear Multiuser Interference Cancellation: a Maximum Likelihood Approach (Journal Article) Signal Processing, 81 (10), pp. 2041–2057, 2001, ISSN: 01651684. @article{Bugallo2001a, title = {Semiblind Linear Multiuser Interference Cancellation: a Maximum Likelihood Approach}, author = {Bugallo, Monica F. and Miguez, Joaquin and Castedo, Luis}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P4_2001_Semiblind Linear Multiuser Interference Cancellation a Maximum Likelihood Approach.pdf http://www.sciencedirect.com/science/article/pii/S0165168401000858 http://www.tsc.uc3m.es/~jmiguez/papers/bugallo01b.ps}, issn = {01651684}, year = {2001}, date = {20010101}, journal = {Signal Processing}, volume = {81}, number = {10}, pages = {20412057}, abstract = {This paper introduces a linear interference suppression algorithm based on the maximum likelihood principle. The method is termed semiblind because it simultaneously exploits the transmission of training sequences and the statistics of the unknown transmitted symbols. We propose both iterative and adaptive implementations of the receiver using the expectation maximization algorithm and the matrix inversion lemma, respectively. Computer simulations show that the resulting multiuser receivers attain practically the same performance as the linear minimum mean square error multiuser detector.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper introduces a linear interference suppression algorithm based on the maximum likelihood principle. The method is termed semiblind because it simultaneously exploits the transmission of training sequences and the statistics of the unknown transmitted symbols. We propose both iterative and adaptive implementations of the receiver using the expectation maximization algorithm and the matrix inversion lemma, respectively. Computer simulations show that the resulting multiuser receivers attain practically the same performance as the linear minimum mean square error multiuser detector. 
1998 
Miguez, Joaquin; Castedo, Luis A Linearly Constrained Constant Modulus Approach to Blind Adaptive Multiuser Interference Suppression (Journal Article) IEEE Communications Letters, 2 (8), pp. 217–219, 1998, ISSN: 10897798. @article{Miguez1998, title = {A Linearly Constrained Constant Modulus Approach to Blind Adaptive Multiuser Interference Suppression}, author = {Miguez, Joaquin and Castedo, Luis}, url = {http://www.tsc.uc3m.es/~jmiguez/papers/P2_1998_A Linearly Constrained Constant Modulus Approach to Blind Adaptive Multiuser Interference Suppression.pdf http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=709436 http://www.tsc.uc3m.es/~jmiguez/papers/miguez98a.ps}, issn = {10897798}, year = {1998}, date = {19980101}, journal = {IEEE Communications Letters}, volume = {2}, number = {8}, pages = {217219}, publisher = {IEEE}, abstract = {This article presents a linearly constrained constant modulus approach for the blind suppression of multiuser interferences in directsequence code division multiple access systems. The method performs the same as minimum mean square error receivers and outperforms existing blind approaches because it only requires a rough estimate of the desired user code and timing.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This article presents a linearly constrained constant modulus approach for the blind suppression of multiuser interferences in directsequence code division multiple access systems. The method performs the same as minimum mean square error receivers and outperforms existing blind approaches because it only requires a rough estimate of the desired user code and timing. 