Support vector machine integrated CCA for classification of complex chemical patterns
S Xiao-Feng, SK Halgamuge, C De-Zhao, H Shang-Xu
Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008 and BSBT 2008: 2008 International Conference on Bio-Science and Bio-Technology | Published : 2008
SVM for classification is sensitive to noise and multicollinearity between attributes. Correlative component analysis (CCA) was used to eliminated multicollinearity and noise of original sample data before classified by SVM. To improve the SVM performance, Eugenic Genetic Algorithm (EGA) was used to optimize the parameters of SVM. Finally, a typical example of two classes natural spearmint essence was employed to verify the effectiveness of the new approach CCA-EGA-SVM. The accuracy is much better than that obtained by SVM alone or selforganizing map (SOM) Integrated with CCA. © 2008 IEEE.