S.A. Ahmad and P.H. Chappell (UK)
Prosthesis control, surface EMG, pattern recognition, approximate entropy, fuzzy logic
Electromyographic control systems, based on pattern recognition, have become an established technique in upper limb prosthetic control. This paper describes the development of a control system that uses pattern information from surface electromyographic signals to control a grip posture of a prosthetic hand. A different hand grip posture is discriminated using fuzzy logic by processing the surface electromyographic from wrist muscles performed at different speeds of contraction. A moving data window of two hundred values is applied to the surface electromyographic data and a new method called moving approximate entropy is used to extract information from the signals. The analyses show differences at three states of contraction (start, middle and end). Also, significant differences were determined at different speeds of contractions. Mean absolute value is also used in the extraction process to increase the performance of the system. The extracted features were then fed to the fuzzy logic classifier and the output is selected appropriately. The experimental result demonstrates the ability of the system to classify the features related to different grip postures.
Important Links:
Go Back
