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.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.