Clustering of Vehicle Waveform Based on Principal Component Analysis and ART2 Neural Network

Author

Yanchao Shen ; Qing Ye ; Wang Lv

Author_Institution

Changsha Univ. of Sci. & Technol., Changsha, China

Volume

1

fYear

2010

fDate

13-14 March 2010

Firstpage

792

Lastpage

795

Abstract

Principal Component Analysis can reduce the dimension of data and eliminate the data correlation with retaining the most information. The dimension of vehicle waveform data was reduced by Principal Component Analysis and a new sample space was created. The new sample space which was produced by Principal Component Analysis is employed as the inputs of ART2 network. Hence, to the same recognition right-rate, the construction of ART2 network is simplified, and the convergent speed of the ART2 network is enhanced greatly due to the number of the ART2 inputs is reduced.

Keywords

ART neural nets; principal component analysis; traffic engineering computing; waveform analysis; ART2 network; data correlation elimination; data dimension reduction; principal component analysis; sample space; vehicle waveform clustering; Coils; Eddy currents; Electromagnetic induction; Frequency; Induction generators; Insulation; Magnetic fields; Neural networks; Principal component analysis; Vehicle detection; ART2 NeuralNetwork; Principal Component Analysis; Vehicle Detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Measuring Technology and Mechatronics Automation (ICMTMA), 2010 International Conference on

Conference_Location

Changsha City

Print_ISBN

978-1-4244-5001-5

Electronic_ISBN

978-1-4244-5739-7

Type

conf

DOI

10.1109/ICMTMA.2010.776

Filename

5458955