Title :
A neural network based classifier for the identification of simple finger motion
Author :
Heinz, Michael ; Knapp, R. Benjamin
Author_Institution :
Dept. of Electr. Eng., San Jose State Univ., CA, USA
Abstract :
The question of whether electromyographic (EMG) data from a single region of the forearm can be used to distinguish between various simple classes of finger motion is examined. Extensive clustering of data is performed to identify useful features for pattern classification. Sets of neural networks are trained to classify movements from each possible pairing of fingers. A multilayered network is constructed to distinguish between all five possible feature types
Keywords :
biomechanics; data acquisition; electromyography; feature extraction; feedforward neural nets; medical computing; pattern classification; EMG data; data acquisition; data clustering; electromyographic data; feature selection; finger motion; forearm; multilayer neural network; muscle contraction; neural classifier; pattern classification; Biological control systems; Data acquisition; Electromyography; Fingers; Frequency; Medical signal detection; Neural networks; Position measurement; Sequential analysis; Signal analysis;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549140
