TY - GEN
T1 - Optimizing Input for Gesture Recognition using Convolutional Networks on HD-sEMG Instantaneous Images
AU - Houston, Michael
AU - Wu, Albon
AU - Zhang, Yingchun
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Hand gesture recognition using high-density surface electromyography (HD-sEMG) has gained increasing attention recently due its advantages of high spatio-temporal resolution. Convolutional neural networks (CNN) have also recently been implemented to learn the spatio-temporal features from the instantaneous samples of HD-sEMG signals. While the CNN itself learns the features from the input signal it has not been considered whether certain pre-processing techniques can further improve the classification accuracies established by previous studies. Therefore, common pre-processing techniques were applied to a benchmark HD-sEMG dataset (CapgMyo DB-a) and their validation accuracies were compared. Monopolar, bipolar, rectified, common-average referenced, and Laplacian spatial filtered configurations of the HD-sEMG signals were evaluated. Results showed that the baseline monopolar HD-sEMG signals maintained higher prediction accuracies versus the other signal configurations. The results of this study discourage the use of extra pre-processing steps when using convolutional networks to classify the instantaneous samples of HD-sEMG for gesture recognition.
AB - Hand gesture recognition using high-density surface electromyography (HD-sEMG) has gained increasing attention recently due its advantages of high spatio-temporal resolution. Convolutional neural networks (CNN) have also recently been implemented to learn the spatio-temporal features from the instantaneous samples of HD-sEMG signals. While the CNN itself learns the features from the input signal it has not been considered whether certain pre-processing techniques can further improve the classification accuracies established by previous studies. Therefore, common pre-processing techniques were applied to a benchmark HD-sEMG dataset (CapgMyo DB-a) and their validation accuracies were compared. Monopolar, bipolar, rectified, common-average referenced, and Laplacian spatial filtered configurations of the HD-sEMG signals were evaluated. Results showed that the baseline monopolar HD-sEMG signals maintained higher prediction accuracies versus the other signal configurations. The results of this study discourage the use of extra pre-processing steps when using convolutional networks to classify the instantaneous samples of HD-sEMG for gesture recognition.
KW - Classification
KW - Convolutional Network
KW - Gesture
KW - High-density Surface EMG
UR - http://www.scopus.com/inward/record.url?scp=85122539829&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122539829&partnerID=8YFLogxK
U2 - 10.1109/EMBC46164.2021.9630558
DO - 10.1109/EMBC46164.2021.9630558
M3 - Conference contribution
C2 - 34892607
AN - SCOPUS:85122539829
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 6539
EP - 6542
BT - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
Y2 - 1 November 2021 through 5 November 2021
ER -