SFSU Engineering Achieves Major Milestone with Sony SSUP Collaboration

School of Engineering faculty and students have developed the first high-density electromyography (HD-EMG)-based real-time neural-machine interface using the Sony Spresense edge board. This is a milestone for the SOE project Neural²: Efficient Deep Neural Network for Neural-controlled Bionic Arm with Spresense Microcontroller, led by Engineering Assistant Professor Zhuwei Qin and Professor Xiaorong Zhang as part of an ongoing collaboration with Sony’s Sensing Solutions University Program (SSUP).   

This groundbreaking innovation integrates deep learning techniques to enable precise hand gesture recognition by processing HD-EMG signals from human subjects’ forearm muscles in real time. The system’s deep learning compression techniques ensure that the neural network models run efficiently on the resource-constrained microcontroller board, offering the potential for real-time movement intent-controlled systems, such as bionic arms and rehabilitation applications. In September, graduate research assistant Peter Chudinov presented the project to Sony’s Japan and Europe teams at the SSUP U.S. end-year review meeting. 

In addition to research, the collaboration has led to the Sony Spresense product being integrated into Engineering curriculum, undergraduate capstone projects and outreach activities with community college and high school students participating in research. The Sony collaboration will continue in an expanded project, “Efficient and Robust Deep Learning Models for Neural-Machine Interfaces with Spresense Microcontroller.” 

Visit the School of Engineering website to learn more about the project.