Study of the characteristics of brain activity that allow the prediction of working memory performance and its implementation in body sensor networks (Phase 2)

This technological development project focuses on addressing the difficulty in managing inter- and intra-subject variability in brain activity related to Working Memory (WM) in real-time, real-world environments. WM is fundamental for information processing, and its performance varies significantly between individuals and over time due to internal and external factors. The proposed solution involves studying and characterizing physiological signals, specifically EEG, alongside other signals such as ECG and inertial sensors, to improve cognitive performance prediction. The methodological approach is quantitative, featuring an experimental design distributed across three main studies: the first focuses on analyzing existing EEG datasets and applying feature engineering and artificial intelligence for pattern recognition; the second incorporates physical activity and inertial sensors to correlate brain activity with movement; and the third evaluates the impact of additional physiological signals (ECG, heart rate) on predictive accuracy. The ultimate goal is to implement the optimized algorithms within Body Sensor Networks (BSN) to enable robust, low-cost monitoring. Expected outcomes include publications indexed in Scopus and Web of Science, and the development of open-source hardware and software technologies benefiting fields such as healthcare (monitoring conditions like ADHD or Parkinson's), education, and neuroergonomics.<br/><br/><b>Goal</b>: <br/>To study the characteristics of physiological signals from EEG, ECG, or inertial sensors that allow for improved prediction of working memory (WM) performance and its subsequent implementation in Body Sensor Networks (BSN). The project aims to develop and implement efficient methodologies to manage inter- and intra-subject variability in brain activity during cognitive tasks in real-world environments.<br/><br/><b>Research lines</b>: <br/>Telematics applied to medicine