Study of the characteristics of brain activity that allow the prediction of working memory performance applied to decision-making (Phase 3)

This research project, in its third phase, focuses on analyzing brain dynamics and physiological signals to predict working memory (WM) performance during decision-making processes. Given the difficulty of managing inter- and intra-subject variability in real-world environments, the team proposes a transdisciplinary approach that integrates artificial intelligence, neuroergonomics, and body sensor networks (BSN). The study utilizes EEG, ECG, and inertial sensor data to characterize neuronal and physiological activity, aiming to optimize the usability and accuracy of predictive models. The research addresses the need for continuous monitoring in daily activities, overcoming technical challenges such as signal noise and the non-stationary nature of brain activity. Through an experimental design, the project evaluates machine learning algorithms to identify relevant patterns in successful decision-making versus failures. Expected outcomes include the publication of scientific articles, the development of data analysis methodologies, and the creation of a specialized laboratory for the acquisition and processing of physiological signals, benefiting fields such as health, education, and security.<br/><br/><b>Goal</b>: <br/>To study the characteristics of physiological signals (EEG, ECG, inertial sensors) to improve the prediction of working memory performance in decision-making. The project aims to develop efficient algorithms that handle inter- and intra-subject variability in real-world environments.<br/><br/><b>Research lines</b>: <br/>Telecommunications and information technologies<br/>Telematics applied to medicine