Title :
Classification of prehensile EMG patterns with simplified fuzzy ARTMAP networks
Author :
Vuskovic, Marko ; Du, Sijiang
Author_Institution :
Dept. of Comput. Sci., San Diego State Univ., CA, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
Simplified fuzzy ARTMAP networks (SFAM) typically generate a large number of output neurons and require a large number of input neurons due to the input complementation. We propose a modification of SFAM, which uses activation and matching functions based on the Mahalanobis distance. This modification considerably reduces the network size and increases the efficiency in training and classification. The new network has shown an excellent performance in classification of prehensile motions based on EMG patterns
Keywords :
ART neural nets; artificial limbs; biocontrol; biomechanics; electromyography; feature extraction; fuzzy neural nets; medical signal processing; pattern classification; signal classification; EMG patterns; Mahalanobis distance; activation functions; efficiency; human-machine interface; matching functions; multifunctional hand prostheses; network size; patterns classification; prehensile motions; simplified fuzzy ARTMAP networks; Computer science; Electrodes; Electromyography; Feature extraction; Fuzzy neural networks; Man machine systems; Multilayer perceptrons; Neurons; Pattern recognition; Prosthetics;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007543
