Please use this identifier to cite or link to this item:
Title: Classification of EMG Signals using Wavelet Features and Fuzzy Logic Classifiers
Keywords: Surface Electromyography, Signal processing, Wavelet transform, Feature Extraction, Type-1 and Type-2 Fuzzy classifiers, Assistive device.
Issue Date: 9-Jun-2009
Citation: NITHYA GNANASSEGARANE (2009-06-09). Classification of EMG Signals using Wavelet Features and Fuzzy Logic Classifiers. ScholarBank@NUS Repository.
Abstract: This thesis describes the surface electromyography (SEMG) signal processing techniques and steps involved in developing rule based fuzzy SEMG classifiers. We have developed both Type-1 and Interval Type-2 fuzzy classifiers (singleton and non-singleton) for motion recognition using the EMG signals. SEMG signals measured from both healthy and post-stroke subjects have been used in this work. The feasibility of wavelet coefficients (obtained from Coiflet wavelet) as features for EMG signal classification has been tested in this work. A detailed description of the appropriate feature extraction methods using Continuous Wavelet Transform and the performance of these fuzzy classifiers are presented here. The post-stroke subjects muscle behavior before and after rehabilitation training shall be discussed to gain an insight into their biomechanics. This work contributes in developing and controlling assistive and rehabilitation devices for post-stroke subjects to regain their lost muscular activity.
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Abstract.pdf10.06 kBAdobe PDF


NithyaGnanassegarane.pdf469.73 kBAdobe PDF



Page view(s)

checked on Nov 17, 2018


checked on Nov 17, 2018

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.