A NOVEL APPROACH TO CLASSIFY THE SHOULDER MOTION OF UPPER LIMB AMPUTEES

Wavelet transform (WT) is a powerful statistical tool used in applied mathematics for signal and image processing. The different mother wavelet basis function has been compared to select the optimal wavelet function that represents the Electromyogram signal characteristics of upper limb amputees. Four different EMG electrode has placed on different location of shoulder muscles. Twenty one wavelet functions from different wavelet families were investigated. These functions included Daubechies (db1–db10), Symlets (sym1–sym5), Coiflets (coif1–coif5) and Discrete Meyer. Using mean square error value, the significance of the mother wavelet functions has been determined for Teres, Pectorials and Infraspinatus around shoulder muscles. The most compatible wavelet families Daubechies families were selected to achieve the classification of the shoulder movement.