Skip to Main Content
ASME Press Select Proceedings

International Conference on Computer and Automation Engineering, 4th (ICCAE 2012)

By
Jianhong Zhou
Jianhong Zhou
Search for other works by this author on:
ISBN:
9780791859940
No. of Pages:
460
Publisher:
ASME Press
Publication date:
2012

In this paper, we introduce a new time-evolved spectral analysis-SLEX for analyzing the EMG signal. First we had review on four other common ways for feature extraction of EMG signal and last of all we focus on SLEX. Smooth Localized Complex Exponential (SLEX), is a kind of time dependent spectral analysis. Diverse from conventional Fourier method, be appropriated by two particular smooth windows on Fourier basis function and has the capability to be simultaneously orthogonal and localized. In this study we tried to show the application of the FFT, Wavelet Transform, Autoregressive, and PSE in EMG feature extraction. Each of which of these techniques for feature extraction has its own pros and cons which we brought it to the note. This method can overcome the shortcoming of conventional Fourier-based spectral analysis and accurately describe the time-dependent statistical property of EMG signal. Our conclusion table shows the best way for EMG feature extraction which is SLEX-based EMG recognition systems and it represent good performance in classifying 8 wrist motions. The classification accuracy of the 4channels is about 98% superior to the other methods.

You do not currently have access to this chapter.
Close Modal
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close Modal
Close Modal