Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/106546
Title: The real time classification of vehicle by combination of GA, PCA and improved SVM
Authors: Zhang, C.
Chen, Y. 
Cao, W.
Keywords: GA
Improved SVM
PCA
SVM
Vehicle classification
Issue Date: 2010
Citation: Zhang, C.,Chen, Y.,Cao, W. (2010). The real time classification of vehicle by combination of GA, PCA and improved SVM. Proc. - 6th Intl. Conference on Advanced Information Management and Service, IMS2010, with ICMIA2010 - 2nd International Conference on Data Mining and Intelligent Information Technology Applications : 414-419. ScholarBank@NUS Repository.
Abstract: There are important significance and social benefit of the application for real-time classification by using of the combination of GA, PCA and Improved SVM in a road ramp. The eight test points were put on the both sides of the road ramp, extracted feature vectors. The acoustic and seismic signals ware used to research the classification in real-time. Because the dimension of feature vectors is too high, GA and PCA were used to reduce the dimension of feature vectors, and then SVM and improved SVM ware used to classify the feature vector. The classification accuracy was greatly improved. The highest classification accuracy of acoustic and seismic signals obtained by experiments was 92.0% and 76.1%. The dimension of feature vectors of acoustic and seismic signals was meantime reduced to 26 and 21 respectively, and the corresponding ratio is 95% and 99%, and the corresponding classification accuracy of independent set was 87.5% and 71.3%. Experiment result shows that: The classification accuracy by use of the combination of GA, PCA and improved SVM method is much higher than the single PCA, GA as well as combination of both.
Source Title: Proc. - 6th Intl. Conference on Advanced Information Management and Service, IMS2010, with ICMIA2010 - 2nd International Conference on Data Mining and Intelligent Information Technology Applications
URI: http://scholarbank.nus.edu.sg/handle/10635/106546
ISBN: 9788988678312
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

47
checked on Oct 12, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.