Fuzzy EMG classification for prosthesis control

Proposes a fuzzy approach to classify single-site electromyograph (EMG) signals for multifunctional prosthesis control. While the classification problem is the focus of this paper, the ultimate goal is to improve myoelectric system control performance, and classification is an essential step in the...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on rehabilitation engineering Vol. 8; no. 3; pp. 305 - 311
Main Authors Chan, F.H.Y., Yong-Sheng Yang, Lam, F.K., Yuan-Ting Zhang, Parker, P.A.
Format Journal Article
LanguageEnglish
Published United States IEEE 01.09.2000
Subjects
Algorithms
Artificial Limbs
Artificial neural networks
Backpropagation
Bias
Cluster Analysis
Clustering algorithms
Control systems
Delay
Electric Stimulation Therapy - methods
Electromyography
Electromyography - classification
Electromyography - methods
Electrophysiology
Feedback
Fuzzy control
Fuzzy Logic
Fuzzy systems
Humans
Neural networks
Neural Networks (Computer)
Pattern recognition
Prosthetics
Signal Processing, Computer-Assisted
Software Validation
Time Factors
Online AccessGet full text
ISSN1063-6528
DOI10.1109/86.867872

Cover

More Information
Summary:Proposes a fuzzy approach to classify single-site electromyograph (EMG) signals for multifunctional prosthesis control. While the classification problem is the focus of this paper, the ultimate goal is to improve myoelectric system control performance, and classification is an essential step in the control. Time segmented features are fed to a fuzzy system for training and classification. In order to obtain acceptable training speed and realistic fuzzy system structure, these features are clustered without supervision using the Basic Isodata algorithm at the beginning of the training phase, and the clustering results are used in initializing the fuzzy system parameters. Afterwards, fuzzy rules in the system are trained with the back-propagation algorithm. The fuzzy approach was compared with an artificial neural network (ANN) method on four subjects, and very similar classification results were obtained. It is superior to the latter in at least three points: slightly higher recognition rate; insensitivity to overtraining; and consistent outputs demonstrating higher reliability. Some potential advantages of the fuzzy approach over the ANN approach are also discussed.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ObjectType-Undefined-3
ISSN:1063-6528
DOI:10.1109/86.867872