AIRR  >> Vol. 2 No. 1 (February 2013)

    新型二分类支持向量机P2M-SVM
    New Binary Classifier P2M-SVM

  • 全文下载: PDF(256KB) HTML   XML   PP.67-70   DOI: 10.12677/AIRR.2013.21012  
  • 下载量: 1,361  浏览量: 5,631   国家自然科学基金支持

作者:  

梁锦锦:西安石油大学理学院,西安;
吴德:西安电子科技大学计算机学院,西安

关键词:
可能性二均值聚类半监督二分类支持向量机全局最优稳健性泛化能力P2M; Semi-Supervised; SVM; Robustness; Generalization Ability

摘要:

提出基于可能性二均值聚类(Possibilistic Two Means, P2M)的二分类支持向量机(Support Vector Machine, SVM)。该算法先用P2M对未知类别的二分类数据进行划分,然后利用支持向量机对划分后的数据进行训练。人造数据和UCI数据上的分类实验表明,该算法综合利用了P2M聚类的稳健性和SVM分类的强泛化能力,提高了传统聚类的分类精度并降低了SVM的类别采集代价。

A semi-supervised binary support vector machine (SVM) is proposed based on possibilistic two-means (P2M) clustering. First, divide the unlabeled data using PCM; then, train the labeled data using SVM. Experiments on artificial and UCI data show the superiority over existing algorithm. P2M-SVM utilizes both the robustness of P2M for binary clustering and the strong generalization ability of SVM for classification thus increases the classification accuracy of traditional clustering and reduces the cost of sample collecting of the SVM.

文章引用:
梁锦锦, 吴德. 新型二分类支持向量机P2M-SVM[J]. 人工智能与机器人研究, 2013, 2(1): 67-70. http://dx.doi.org/10.12677/AIRR.2013.21012

参考文献

[1] N. Vanik. 统计学习理论[M]. 许建华, 张学工, 译. 北京: 电子工业出版社, 2004.
[2] N. Cristianini, J. S. Taylor. An introduction to support vector machines. Cambridge University Press, Cambridge, 2000.
[3] V. N. Vapnik. An overview of statistical learning theory. IEEE Transactions on NN, 1999, 10(3): 988-999.
[4] Y. Jin, Y. Ma and L. Zhao. A modified self-training semi-super- vised SVM algo-rithm. Proceedings of the International Confer- ence on Communica-tion Systems and Network Technologies, 2012: 224-228.
[5] K. L. Wu, M. S. Yang. Alternative c-means clustering algorithms. Pattern Recognition, 2002, 35(10): 2267-2278.
[6] 张敏, 于剑. 基于划分的模糊聚类算法[J]. 软件学报, 2004, 15(6): 858-868.
[7] J. C. Bezdek. Pattern recognition with fuzzy objective function algorithms. New York: Plenum, 1981.
[8] J. C. Dunn. Some recent investigations of a new fuzzy partion algorithm and its application to pattern classifi-cation problems. Journal of Cybernetics, 1974, 4: 1-15.
[9] R. Krishnarpuram, J. Keller. A possibilistic approach to cluster- ing. IEEE Transactions on Fuzzy Systems, 1993, 1(2): 98-110.
[10] N. Pal, K. Pal, J. Keller and J. Bezdek. A possinilistic fuzzy c- means clustering algorithm. IEEE Transactions on Fuzzy Sys- tems, 2005, 13(4): 517-530.