Trace regulation techniques for feature extraction

Author

Sha, Lifeng ; Peng, Hanchuan ; Sun, Xiao

Author_Institution

Dept. of Biomed. Eng., Southeast Univ., Nanjing, China

Volume

2

fYear

1998

fDate

1998

Firstpage

1221

Abstract

The trace neural network (TNN) and the sparse trace neural network (STNN) have been explored as good spatial-temporal invariance extractors. However, it is recognized that the overlapping of traces for rapidly varying input sample sequences will result in poor performance of the network. Here we propose trace regulation (TR) techniques to adaptively adjust the distances between traces and to adaptively cluster patterns in the volume-increased representation space. Preliminary simulation results indicate the advantages of the TRs

Keywords

feature extraction; feedforward neural nets; pattern classification; pattern clustering; sequences; signal processing; adaptive pattern clustering; feature extraction; feedforward trace neural network models; pattern classification; rapidly varying input sample sequences; signal processing; sparse trace neural network; spatial-temporal invariance extractor; trace neural network; trace regulation techniques; volume-increased representation space; Adaptive systems; Biomedical engineering; Computer networks; Feature extraction; Joining processes; Neural networks; Neurons; OFDM modulation; Sun;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-4325-5

Type

conf

DOI

10.1109/ICOSP.1998.770838

Filename

770838