Presentation
Energy-Efficient On-Chip Training for Customized Home-based Rehabilitation Systems
DescriptionRehabilitation is an essential process for patients complaining about motor disorders generally done by experts in a clinical environment.
Home-based rehabilitation systems allow patients to do rehabilitation without going to clinics thus, reducing the commute and healthcare costs.
Human joint estimation allows visualization of body movements required for rehabilitation.
However; without customizing for the patient, they can result in less accurate feedback.
Therefore, we propose a customized rehabilitation system that is customized to the new patients utilizing energy-efficient on-chip training with in-memory acceleration.
Experiments show that it customizes to new patients successfully and provides energy-efficient estimates of human joint coordinates.
Home-based rehabilitation systems allow patients to do rehabilitation without going to clinics thus, reducing the commute and healthcare costs.
Human joint estimation allows visualization of body movements required for rehabilitation.
However; without customizing for the patient, they can result in less accurate feedback.
Therefore, we propose a customized rehabilitation system that is customized to the new patients utilizing energy-efficient on-chip training with in-memory acceleration.
Experiments show that it customizes to new patients successfully and provides energy-efficient estimates of human joint coordinates.
Event Type
Research Manuscript
TimeThursday, July 13th11:25am - 11:40am PDT
Location3003, 3rd Floor
AI
AI/ML Application and Infrastructure