Target Area Detection Based on Piecewise Membership FSVM

Abstract:

Aiming at the target detection technique is time-consuming, noise and other issues, improved the application of FSVM in target detection, a piecewise fuzzy membership function is proposed based on LDA algorithm. The algorithm projected the original high-dimensional samples onto a one-dimensional space by LDA ,the original sample’s fuzzy weights is segment calculated based on the distribution of the projection point, reduce the impact of noise and outliers on classification results. In the simulation experiments, this method can effectively reduce the impact of unbalanced data to FSVM, improve the classification accuracy.

• Periodical: Applied Mechanics and Materials (Volume 577)
• Pages: 685-688
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.577.685
• Online since: July 2014
• Authors: Zhong Hai Li*, Hong Yan Cao, Xing Yuan Kou, Xiang Man
• Keywords: Classification Accuracy, FSVM, Fuzzy Weight, LDA

References

[1] Zhimin Yang, Yuanhai Shao, Jing Liang, Acta automatica sinica, Vol. 39 No. 6, 895-901 (2013). In Chinese.

[2] Cruz, J.A., Wishart, D.S., 2006. Applications of machine learning in cancer prediction and prognosis. Cancer Inform. 2, 59–78.

[3] Zhijun Chen, Computer Applications and Software, Vol. 30, No. 5, 145-148 (2013). In Chinese.

[4] Xiang Zhang, Xiaoling Xiao, Guangyou Xu , Journal of Image and Graphics, Vol. 11, No. 8, 1188-1192 (2006). In Chinese.

[5] Wen Ju, Juan Shan, Changhui Yan, H.D. Cheng, Pattern Recognition Letters 30(2009) 391–396.

[6] Jing Yang, Xu Yu, Zhiqiang Xie, Chinese journal of computers , Vol. 35, No. 5, 1002-1010 (2012). In Chinese.