About
Dr. Fouad Sakr is a Visiting Professor at Queen Mary University of London's School of Electronic Engineering and Computer Science. His research focuses on advancing machine learning techniques for embedded systems, particularly in edge computing and resource-constrained environments. He specializes in neural networks, microcontroller-based implementations, and energy-efficient algorithms. His work includes developing inference engines for binarized neural networks and optimizing CNNs for electronic skin systems.
Key research interests include real-time structural health monitoring, memory optimization in embedded AI, and unsupervised learning on low-power devices. Sakr has contributed to frameworks like CMSIS-NN and explored IoT applications in air quality monitoring.
His publications span topics such as self-learning pipelines for low-energy devices and efficient machine learning on mainstream microcontrollers. While no awards or grants are explicitly listed, his work emphasizes practical deployments on STM32 and similar platforms.
No academic advising details or lab affiliations are provided in the available text.
