Abdul Baset Sarker

Children born with upper limb deficiencies often struggle with conventional prosthetic solutions, especially EEG- or EMG-based systems, which require brain or muscle signals and training, making adaptation difficult. AI vision-based systems offer an alternative to address this challenge. AI vision-enabled pediatric prosthetic hand is designed for children aged 10-12. The project focuses on developing a low-power, FPGA-based system with a camera for object detection and grasping, along with a soft structure suitable for children. Key features include: a) A wrist-mounted camera for artificial sensing in various hand tasks, b) Real-time object detection and distance estimation for grasping, and c) Low-power operation to function within resource constraints.

Today’s session will demonstrate a low-power FPGA-based system with optimized deep-learning models for real-time object detection in pediatric prosthetic hands. We will highlight how quantization and pruning techniques are used to run efficiently on resource-constrained edge devices. Key topics include multi-sensor systems for adaptive grasping, lightweight model deployment in the deep-learning processor unit (DPU), and balancing computational efficiency with accuracy for affordable, child-friendly prosthetics.

Biography:

Md Abdul Baset Sarker is currently pursuing his PhD in Electrical and Computer Engineering at Clarkson University, Potsdam, New York. Originally from Bangladesh, he has a background in Electronics and Communication Engineering and over six years of industrial experience. His research primarily focuses on Computer Vision and Artificial Intelligence based solutions to run on edge devices. His interdisciplinary approach, based on optimizing neural networks contributes to scalable technologies addressing social needs.