AI-driven monitoring: from wearable sensors to personalized health insights’
9:00 AM PDT / 12:00 PM EDT / 5:00 PM BST / 6:00 PM CEST
This talk will explore how artificial intelligence combined with wearable biomedical sensors is revolutionizing personalized health monitoring. Drawing on research from the Posada Q Lab at UConn, Dr. Posada-Quintero will present methods for analyzing physiological signals, such as electrodermal activity, electroretinography, electrocardiography, and electromyography, to objectively detect and predict conditions like pain, stress, sleep deprivation, and neurological disorders.
We will also examine how time-frequency analysis, graph signal processing, and deep learning models can extract meaningful health insights from noisy, real-world data. These methods enable continuous, non-invasive assessment of human well-being. These methods have applications in the early detection of central nervous system toxicity, heart failure decompensation, and neurological disorders such as ADHD and ASD.
The talk will also highlight the development of smartphone-based diagnostic tools and wearable systems for real-time monitoring. Emphasis will be placed on how these technologies can enhance emotional awareness, pain management, and support for individuals with neurological disorders and improve performance and safety in high-risk environments. By combining engineering innovation with clinical and behavioral science, our goal is to pave the way for personalized, accessible, and ethically sound digital health solutions.
Speaker
Hugo F. Posada-Quintero is an Assistant Professor in the Department of Biomedical Engineering at the University of Connecticut. He received his Bachelor of Science in Electronic Engineering from Universidad Distrital in Colombia in 2005, his Master of Science in Electronics and Computer Engineering from Universidad de los Andes in Colombia in 2008, and his Ph.D. in Biomedical Engineering from the University of Connecticut in 2016.
His research focuses on biomedical signal processing, wearable instrumentation, and sensor development for health-related applications. He aims to detect and predict physiological and cognitive states, such as stress, fatigue, pain, emotional state, and cognitive performance, by analyzing bioelectrical signals. He develops sensitive biomarkers and multimodal algorithms that combine multiple signals using advanced mathematical methods and data-driven models powered by machine learning and deep learning. He also designs novel sensors and portable, wearable electronic devices to improve the capture of electrophysiological signals in real-world settings.