Ahmed Fakhfakh
Biography
Prof. Ahmed Fakhfakh received the B.Eng. degree in Electrical Engineering from the National School of Engineering of Sfax (ENIS), Tunisia, in 1997, the Ph.D. degree in Electrical Engineering from the University of Bordeaux, France, in 2002, and the Habilitation à Diriger des Recherches (HDR) degree from the University of Sfax, Tunisia, in 2009.
He has been a Full Professor with the National School of Electronics and Telecommunications of Sfax (ENET'Com), University of Sfax, Tunisia, since 2015. Since 2023, he has also served as the General Director of the Digital Research Center of Sfax (CRNS), Tunisia. He leads the Intelligent Systems: Design and Implementation research group within the Signals, Systems, Artificial Intelligence, and Networks (SM@RTS) Laboratory at the CRNS.
His research interests include intelligent energy management for smart grids, Internet of Things (IoT), wireless sensor networks, wake-up radio technologies, energy harvesting systems, embedded intelligent systems, and artificial intelligence for cyber-physical systems. His current research also focuses on the development of AI-driven digital solutions for smart energy, e-health, smart agriculture, and Industry 4.0/5.0 applications. Prof. Fakhfakh has authored and co-authored numerous scientific publications in international journals and conferences and has participated in several national and international research projects.
Title
From Bio-Signals to Embedded Intelligence: Wearable Sensing and AI for Human Movement, Neurological and Health Monitoring
Abstract
The rapid convergence of wearable sensing technologies, embedded systems, and artificial intelligence is transforming the way we monitor human movement, neurological function, and overall health. This keynote explores the journey from raw bio-signals — captured through wearable sensors such as inertial measurement units (IMUs), electromyography (EMG), electroencephalography (EEG), and electrocardiography (ECG) — to actionable clinical insights generated by embedded AI models running directly on low-power devices.
We will discuss the challenges and opportunities in acquiring high-quality bio-signals in real-world conditions, including motion artifacts, energy constraints, and data privacy. The presentation will highlight recent advances in lightweight deep learning architectures and edge computing techniques that enable real-time, on-device analysis for applications such as gait analysis, fall detection, seizure prediction, and cardiovascular monitoring. Case studies from ongoing research projects will illustrate how these technologies can support clinicians, empower patients, and enable continuous, personalized health monitoring in everyday environments.
Finally, the talk will outline open research directions, including the integration of explainable AI, the development of energy-autonomous wearable platforms, and the ethical and regulatory considerations for deploying AI-driven health monitoring systems at scale.