Integrated Systems Laboratory

Open Opportunities

Continual Learning for Adaptive Hand Gesture Recognition with A-mode Ultrasound ETH Zurich Digital Circuits and Systems (Benini) Hand Gesture Recognition has gained significant attention in recent years due to its potential applications in various fields, including interaction with virtual environments (like the Metaverse), teleoperation, and prosthetic device control. Multiple sensing techniques can be employed for hand movement recognition, including vision-based sensors (cameras), mechanical sensors (e.g., IMUs), sEMG, and the more recent and increasingly popular Ultrasound (US). US enables high-spatial (submillimeter) and temporal (fraction of a millisecond) resolution imaging of deep musculoskeletal structures. While several studies [1], [2], [3] have used US for hand gesture recognition, challenges remain in ensuring robustness against factors like sensor shift, donning and doffing, varying muscle force, and interday use [4]. Biomedical Engineering, Electrical and Electronic Engineering, Information, Computing and Communication Sciences Bachelor Thesis, Master Thesis, Semester Project

Flexible Wireless Sensing Node for Continuous Body Monitoring ETH Zurich Digital Circuits and Systems (Benini) Advancements in sensor technology, low-power mixed-signal/RF circuits, and Wireless Sensor Networks (WSNs) have enabled the creation of compact, cost-effective solutions for healthcare applications. A notable development in this field is the Body Sensor Network, which is designed to monitor the human body for healthcare purposes. Biomedical Engineering, Electrical and Electronic Engineering Bachelor Thesis, Internship, Semester Project

Quantizing Vision and Language Foundation Models for Efficient Inference ETH Zurich Digital Circuits and Systems (Benini) Foundation models are a breakthrough in the field of artificial intelligence. These models are characterized by massive size, reaching billions (even trillions) of parameters, and by the ability to be adapted to a wide variety of tasks without needing to be trained from scratch. The development of these models marks a pivotal shift in AI research and application, pushing the boundaries of what machines can understand and do. However, due to the huge size of foundation model, they are very demanding in terms of computation, memory footprint and bandwidth. For this reason, foundation models face significant computational challenges. These models are typically trained on massive clusters equipped with thousands of advanced GPUs. Moreover, they require cloud services for inference as well. Artificial Intelligence and Signal and Image Processing ETH Zurich (ETHZ), Master Thesis