DocumentCode
2641225
Title
Dimension reduction issues in classification applications
Author
Fargues, Monique P. ; Duzenli, Ozhan
Author_Institution
Dept. of Electr. & Comput. Eng., Naval Postgraduate Sch., Monterey, CA, USA
Volume
2
fYear
1998
fDate
1-4 Nov. 1998
Firstpage
1670
Abstract
A simple type of projection pursuit scheme is discussed and applied to classification applications. The proposed scheme is used to significantly reduce the number of class features obtained from the wavelet packet decomposition of the signals to be classified. Results show this scheme can be used to classify underwater data without significant loss of performance.
Keywords
feature extraction; neural nets; signal classification; wavelet transforms; dimension reduction; feature extraction; mean separator neural network; projection pursuit; signal classification applications; underwater data; wavelet packet signal decomposition; Data mining; Feature extraction; Iterative algorithms; Neural networks; Particle separators; Performance loss; Signal design; Wavelet packets;
fLanguage
English
Publisher
ieee
Conference_Titel
Signals, Systems & Computers, 1998. Conference Record of the Thirty-Second Asilomar Conference on
Conference_Location
Pacific Grove, CA, USA
ISSN
1058-6393
Print_ISBN
0-7803-5148-7
Type
conf
DOI
10.1109/ACSSC.1998.751610
Filename
751610
Link To Document