PerMTL: A Multi-Task Learning Framework for Skilled Human Performance Assessment
Dec 1, 2022·,
,,·
0 min read
Indrajeet Ghosh
Avijoy Chakma
Sreenivasan Ramasamy Ramamurthy
Nirmalya Roy
Nicholas Waytowich
Abstract
PerMTL is a multi-task learning framework for assessing skilled human performance from sensor data, jointly learning shared representations across related assessment tasks to improve performance over single-task baselines.
Type
Publication
2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)
Authors
Assistant Professor (Tenure-Track) of Computer Science
Sreenivasan Ramasamy Ramamurthy is an Assistant Professor (Tenure-Track) of Computer Science at Bowie State University. His research interests include Human-Centered Intelligent Systems, Embodied AI and Robotics, Edge Intelligence, and Human-Machine Teaming. He received his Ph.D. in Information Systems from UMBC, a Master’s in Biomedical Engineering from VIT University, and a Bachelor’s in Electronics and Instrumentation Engineering from Amrita Vishwa Vidyapeetham. He is a recipient of grants from NAVAIR, Army Research Laboratory, and the Department of Energy in support of his research.