TY - GEN
T1 - Machine Learning for Motor Learning
T2 - 8th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics, BioRob 2020
AU - Kumar, Neelesh
AU - Michmizos, Konstantinos P.
N1 - Funding Information:
*This work is supported through Grant K12HD093427 from the National Center for Medical Rehabilitation Research, NIH/NICHD. NK and KM are with the Computational Brain Lab, Department of Computer Science, Rutgers University, New Jersey, USA
Publisher Copyright:
© 2020 IEEE.
PY - 2020/11
Y1 - 2020/11
N2 - Although cognitive engagement (CE) is crucial for motor learning, it remains underutilized in rehabilitation robots, partly because its assessment currently relies on subjective and gross measurements taken intermittently. Here, we propose an end-to-end computational framework that assesses CE in near real-time, using electroencephalography (EEG) signals as objective measurements. The framework consists of i) a deep convolutional neural network that extracts task-discriminative spatiotemporal EEG features to predict the level of CE for two classes- cognitively engaged vs. disengaged; and ii) a novel sliding window method that predicts continuous levels of CE in short time intervals. We evaluated our framework on 8 healthy subjects using an in-house Go/No-Go experiment that adapted its gameplay parameters to induce cognitive fatigue. The proposed CNN had an average leave-one-subject-out accuracy of 88.19%. The CE prediction correlated well with a commonly used behavioral metric based on self-reports taken every 5 minutes (p =0.93). Our results objectify CE measurement in near real-time and pave the way for using CE as a rehabilitation parameter for tailoring robotic therapy to each patient's needs and skills.
AB - Although cognitive engagement (CE) is crucial for motor learning, it remains underutilized in rehabilitation robots, partly because its assessment currently relies on subjective and gross measurements taken intermittently. Here, we propose an end-to-end computational framework that assesses CE in near real-time, using electroencephalography (EEG) signals as objective measurements. The framework consists of i) a deep convolutional neural network that extracts task-discriminative spatiotemporal EEG features to predict the level of CE for two classes- cognitively engaged vs. disengaged; and ii) a novel sliding window method that predicts continuous levels of CE in short time intervals. We evaluated our framework on 8 healthy subjects using an in-house Go/No-Go experiment that adapted its gameplay parameters to induce cognitive fatigue. The proposed CNN had an average leave-one-subject-out accuracy of 88.19%. The CE prediction correlated well with a commonly used behavioral metric based on self-reports taken every 5 minutes (p =0.93). Our results objectify CE measurement in near real-time and pave the way for using CE as a rehabilitation parameter for tailoring robotic therapy to each patient's needs and skills.
UR - http://www.scopus.com/inward/record.url?scp=85095614107&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85095614107&partnerID=8YFLogxK
U2 - 10.1109/BioRob49111.2020.9224368
DO - 10.1109/BioRob49111.2020.9224368
M3 - Conference contribution
AN - SCOPUS:85095614107
T3 - Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics
SP - 521
EP - 526
BT - 2020 8th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics, BioRob 2020
PB - IEEE Computer Society
Y2 - 29 November 2020 through 1 December 2020
ER -