Simple and Computationally Efficient Movement Classification

The aim of this paper is to propose an exploratory study on simple, accurate and 19 computationally efficient movement classification technique for prosthetic hand application. The 20 surface myoelectric signals were acquired from 2 muscles – Flexor Carpi Ulnaris and Extensor Carpi 21 Radialis of 4 normal-limb subjects. These signals were segmented and the features extracted using a 22 new combined time-domain method of feature extraction. The fuzzy C-mean clustering method and 23 scatter plots were used to evaluate the performance of the proposed multi-feature versus other 24 accurate multi-features. Finally, the movements were classified using the adaptive neuro-fuzzy 25 inference system (ANFIS) and the artificial neural network. Comparison results indicate that ANFIS 26 not only displays higher classification accuracy (88.90%) than the artificial neural network, but it also 27 improves computation time significantly. 28 29 30