EMG Based Gesture Recognition Using Noise Removal
- Authors
- Kang, K.; Shin, H.-C.
- Issue Date
- Jan-2021
- Publisher
- IEEE Computer Society
- Keywords
- EMG; feature calibration; gesture recognition; linear discriminant analysis; noise removal
- Citation
- International Conference on Information Networking, v.2021-January, pp.640 - 643
- Journal Title
- International Conference on Information Networking
- Volume
- 2021-January
- Start Page
- 640
- End Page
- 643
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/40630
- DOI
- 10.1109/ICOIN50884.2021.9333873
- ISSN
- 1976-7684
- Abstract
- We propose a feature calibration method for the electromyography (EMG) based gesture recognition to be robust to noise. The proposed method is to subtract the feature of noise calculated in resting period from the signal feature. For the performance evaluation, we compare the recognition accuracy of the feature calibration applied with that of the feature calibration not applied. As noise level increases, the result of the proposed feature calibration method applied shows clear improvement in accuracy. When SNR is 0dB, the recognition result of the proposed method applied shows about 20% improvement in average accuracy compared to that of the proposed method not applied. © 2021 IEEE.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Information Technology > ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/40630)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.