Principal investigator in the following projectsProject FLUID Project CoRP PETRAProject CoRP: Human Behavior Characterization with deep generativ models. Caracterización de Comportamiento con Redes Profundas (CoRP).
The ultimate objective of the proposed research project is the study of statistical signal processing techniques for the automatic characterization of human behavior at a personalized level, using latent (hidden) generative projection models capable of capturing correlations between heterogeneous data collected from mobile devices, such as smartphones or smartwatches. The characterization of the patient's behavior will be translated into the analysis of the time evolution of its latent projection. Sudden changes of the same can be associated to variations of behavior. In a psychiatric patient monitoring (one of the pilot tests contemplated in this project), this may be linked, for example, to a manic crisis in patients with schizophrenia. Given the enormous amount of gathered information for each patient, solutions based on generative models constructed from deep neural networks are proposed. Incorporating the heterogeneity of the behavioral data in this type of models constitutes the first objective of the project. Then, the specific design for the characterization of human behavior with data collected by eB2 in real patients is the next objective. In this regard, a close collaboration is proposed with the psychiatric service of the Fundación Jiménez Díaz University Hospital (HU-FJD), for the acquisition of experimental data included in a protocol already approved for the demonstration of the clinical usefulness of monitoring. Interpretability in generative models will be emphasized using hierarchical structures and models based-on nonparametric mixtures. On the other hand, the calibration of the developed methods and how they can give a representation of the functional behavior of each patient will be carried out jointly with experts of the FJD. |