TY - GEN
T1 - Deep Augmentation for Electrode Shift Compensation in Transient High-density sEMG
T2 - 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
AU - Sun, Tianyun
AU - Libby, Jacqueline
AU - Rizzo, John-Ross
AU - Atashzar, S. Farokh
N1 - Funding Information:
Tianyun Sun is with Facebook, USA, and was with the Department of Electrical and Computer Engineering, New York University, New York, NY 11201, USA. Jacqueline Libby is with the NYU Center for Urban Science and Progress (CUSP), New York, NY, USA. JohnRoss Rizzo with the NYU School of Medicine, New York NY, 10016. S. Farokh Atashzar is with the Department of Electrical and Computer Engineering, and with the Department of Mechanical and Aerospace Engineering, and with NYU WIRELESS, and also with the NYU Center for Urban Science and Progress (CUSP), New York University, New York, NY 11201 USA (e-mail: f.atashzar@nyu.edu). This material is based upon work supported by the US National Science Foundation under grants no # 2037878 and # 2031594, and # 2121391. The work is also partially supported by NYUAD Center for Artificial Intelligence and Robotics (CAIR) award # CG010. ∗ Corresponding author: f.atashzar@nyu.edu.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Going beyond the traditional sparse multi-channel peripheral human-machine interface that has been used widely in neurorobotics, high-density surface electromyography (HD-sEMG) has shown significant potential for decoding upper-limb motor control. We have recently proposed heterogeneous temporal dilation of LSTM in a deep neural network architecture for a large number of gestures (>60), securing spatial resolution and fast convergence. However, several fundamental questions remain unanswered. One problem targeted explicitly in this paper is the issue of 'electrode shift,' which can happen specifically for high-density systems and during doffing and donning the sensor grid. Another real-world problem is the question of transient versus plateau classification, which connects to the temporal resolution of neural interfaces and seamless control. In this paper, for the first time, we implement gesture prediction on the transient phase of HD-sEMG data while robustifying the human-machine interface decoder to electrode shift. For this, we propose the concept of deep data augmentation for transient HD-sEMG. We show that without using the proposed augmentation, a slight shift of 10mm may drop the decoder's performance to as low as 20%. Combining the proposed data augmentation with a 3D Convolutional Neural Network (CNN), we recovered the performance to 84.6% while securing a high spatiotemporal resolution, robustifying to the electrode shift, and getting closer to large-scale adoption by the end-users, enhancing resiliency.
AB - Going beyond the traditional sparse multi-channel peripheral human-machine interface that has been used widely in neurorobotics, high-density surface electromyography (HD-sEMG) has shown significant potential for decoding upper-limb motor control. We have recently proposed heterogeneous temporal dilation of LSTM in a deep neural network architecture for a large number of gestures (>60), securing spatial resolution and fast convergence. However, several fundamental questions remain unanswered. One problem targeted explicitly in this paper is the issue of 'electrode shift,' which can happen specifically for high-density systems and during doffing and donning the sensor grid. Another real-world problem is the question of transient versus plateau classification, which connects to the temporal resolution of neural interfaces and seamless control. In this paper, for the first time, we implement gesture prediction on the transient phase of HD-sEMG data while robustifying the human-machine interface decoder to electrode shift. For this, we propose the concept of deep data augmentation for transient HD-sEMG. We show that without using the proposed augmentation, a slight shift of 10mm may drop the decoder's performance to as low as 20%. Combining the proposed data augmentation with a 3D Convolutional Neural Network (CNN), we recovered the performance to 84.6% while securing a high spatiotemporal resolution, robustifying to the electrode shift, and getting closer to large-scale adoption by the end-users, enhancing resiliency.
UR - http://www.scopus.com/inward/record.url?scp=85146337856&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85146337856&partnerID=8YFLogxK
U2 - 10.1109/IROS47612.2022.9981786
DO - 10.1109/IROS47612.2022.9981786
M3 - Conference contribution
AN - SCOPUS:85146337856
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 6148
EP - 6153
BT - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 23 October 2022 through 27 October 2022
ER -