Neural networks, genetic algorithms and the K-means algorithm: in search of data classification

Author

Schizas, Christos N. ; Pattichis, C.S. ; Middleton, L.T.

Author_Institution

Cyprus Univ., Nicosia, Cyprus

fYear

1992

fDate

6/6/1992 12:00:00 AM

Firstpage

201

Lastpage

222

Abstract

Neural networks, genetic algorithms, and the K-means clustering algorithm have been used in this study for the classification of quantitative electromyographic data. The results that have been independently obtained by the above methods are presented and the relative advantages and disadvantages are discussed. The comparative study of these methods guidance in choosing the most appropriate method for the classification of electromyographic data. It is also suggested that the problem of medical diagnosis can be handled better by combining more than one method

Keywords

bioelectric potentials; genetic algorithms; medical diagnostic computing; muscle; neural nets; pattern recognition; K-means algorithm; bioelectric potentials; data classification; electromyographic data; genetic algorithms; medical diagnosis; medical diagnostic computing; muscle; neural nets; pattern recognition; Area measurement; Clustering algorithms; Electromyography; Genetic algorithms; Intelligent networks; Length measurement; Machine learning algorithms; Muscles; Neural networks; Phase measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Combinations of Genetic Algorithms and Neural Networks, 1992., COGANN-92. International Workshop on

Conference_Location

Baltimore, MD

Print_ISBN

0-8186-2787-5

Type

conf

DOI

10.1109/COGANN.1992.273938

Filename

273938