Workshops
Detailed information about the workshops will be announced soon. Please check back for updates.
Workshops
Computational Methods for Biomedical Signal Analysis: Theory and Applications
Dr. Ezgi ÖZER
Assistant Professor, Piri Reis University, Department of Computer Engineering, Türkiye
Short Bio:
Dr. Özer is an Assistant Professor and researcher specializing in artificial intelligence, optimization, and data-driven decision-making. She teaches undergraduate and graduate courses in optimization, artificial intelligence, and robotics. She received her Ph.D. in Statistics with a dissertation on the early detection of epileptic seizures from electroencephalography (EEG) signals using deep learning. Since 2018, she has been a member of the Advanced Signal Processing Initiative (ASPI) at NOVA University Lisbon. As part of her doctoral research, she spent two years as a visiting researcher in the Department of Electrical and Computer Engineering at NOVA University Lisbon. Her research interests include biomedical signal and image analysis, feature engineering, forecasting, and explainable artificial intelligence, with applications in computer-aided medical diagnosis and intelligent decision support.
Abstract:
The growing availability of biomedical data and advances in artificial intelligence have transformed the analysis of physiological signals, enabling more accurate diagnosis, patient monitoring, and clinical decision support. Biomedical signals such as electroencephalography (EEG), electrocardiography (ECG), electromyography (EMG), and heart rate variability (HRV) contain informative physiological patterns but require robust analytical approaches to extract meaningful patterns. Hybrid deep learning models, which combine advanced feature engineering, have emerged as powerful tools for analyzing these complex and high-dimensional data.
This workshop presents a framework for biomedical signal analysis, covering the fundamental concepts and implementation of deep learning methods for computer-aided medical diagnosis. Participants will gain insights into signal preprocessing, feature engineering, hybrid deep learning architectures, optimization methods, and explainable artificial intelligence (XAI). Through real-world case studies, the workshop will illustrate how these methods can be applied to biomedical signal analysis while addressing key challenges related to model generalizability, data quality, privacy, ethics, and clinical translation.