局部保留最大信息差υ-支持向量机

陶剑文; 王士同

doi:10.3724/SP.J.1004.2012.00097

局部保留最大信息差υ-支持向量机

doi: 10.3724/SP.J.1004.2012.00097

陶剑文^1,2,
王士同^1, ,

1.
江南大学信息工程学院无锡 214122;
2.
浙江工商职业技术学院信息工程学院宁波 315012

详细信息

通讯作者:
王士同江南大学信息工程学院教授. 主要研究方向为人工智能,机器学习.本文通信作者.E-mail: wxwangst@yahoo.com.cn

计量
- 文章访问数: 2024
- HTML全文浏览量: 93
- PDF下载量: 741
- 被引次数: 0
出版历程
- 收稿日期: 2010-12-08
- 修回日期: 2011-07-01
- 刊出日期: 2012-01-20

Locality-preserved Maximum Information Variance υ-support Vector Machine

TAO Jian-Wen^1,2,
WANG Shi-Tong^{1
, ,}

1.
School of Information Engineering, Southern Yangtze University, Wuxi 214122;
2.
School of Information Engineering, Zhejiang Business Technology Institute, Ningbo 315012

摘要

摘要: 针对现有模式分类方法不能较好地保持数据空间的局部流形信息或差异信息等问题,提出一种基于流形学习的局部保留最大信息差υ-支持向量机(Locality-preserved maximum information variance υ-support vector machine,υ-LPMIVSVM).对于模式分类问题,v-LPMIVSVM引入局部同类离散度和局部异类离散度概念,分别体现输入空间局部流形结构和局部差异(或判别)信息,通过最小化局部同类离散度和最大化局部异类离散度,优化分类器的投影方向.同时,υ-LPMIVSVM采用适于流形数据的测地线距离来度量数据点对间的相似性,以更好地反映流形数据的本质结构.人造和实际数据集实验结果显示所提方法具有良好的泛化性能.
- 局部保留投影 /
- υ-支持向量机 /
- 流形学习 /
- 局部同类离散度 /
- 局部异类离散度
Abstract: The state-of-the-art pattern classifiers can not efficiently preserve the local geometrical structure or the diversity (or discriminative) information of data points embedded in high-dimensional data space, which is useful for pattern recognition. A novel so-called locality-preserved maximum information variance υ-support vector machine (υ-LPMIVSVM) algorithm is presented based on manifold learning to address those problems mentioned above. The υ-LPMIVSVM introduces within-locality homogeneous scatter and within-locality heterogeneous scatter, which respectively denote the within-locality manifold information of data points and the within-locality diversity information of data points, thus constructing an optimal classifier with optimal projection weight vector by minimizing the within-locality homogeneous scatter and simultaneously maximizing the within-locality heterogeneous scatter. Meanwhile, the υ-LPMIVSVM adopts geodesic distance metric to measure the distance between data in the manifold space, which can reflect the true geometry of the manifold. Experimental results on artificial and real world problems show the outperformed or comparable effectiveness of υ-LPMIVSVM.
- Locality preserving projections /
- υ-support vector machine (υ-SVM) /
- manifold learning /
- within-locality homogeneous scatter /
- within-locality heterogeneous scatter

HTML全文

参考文献(1)

[1]

Tao J W,Wang S T,Hu W J,Ying W H. ρ-margin kernel learning machine with magnetic field effect for both binary classification and novelty detection. International Journal of Software and Informatics,2010,4(3):305-324[2] Vapnik V N. The Nature of Statistical Learning Theory. New York:Springer-Verlag,1995. 69-83[3] Wen Chuan-Jun,Zhan Yong-Zhao,Chen Chang-Jun. Maximal-margin minimal-volume hypersphere support vector machine. Control and Decision,2010,25(1):79-83(文传军,詹永照,陈长军. 最大间隔最小体积球形支持向量机. 控制与决策,2010,25(1):79-83)[4] Wu M R,Ye J P. A small sphere and large margin approach for novelty detection using training data with outliers. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(11):2088-2092[5] Scholkopf B,Smola A J,Williamson R C,Bartlett P L. New support vector algorithms. Neural Computation,2000,12(5):1207-1245[6] Shivaswamy P K,Jebara T. Maximum relative margin and data-dependent regularization. Journal of Machine Learning Research,2010,11:747-788[7] Zafeiriou S,Tefas A,Pitas I. Minimum class variance support vector machines. IEEE Transactions on Image Processing,2007,16(10):2551-2564[8] Cai D,He X F,Zhou K,Han J W,Bao H J. Locality sensitive discriminant analysis. In:Proceedings of the 20th International Joint Conference on Artificial Intelligence. Hyderabad,India:IJCAI Press,2007. 708-713[9] He X F,Yan S C,Hu Y X,Niyogi P,Zhang H J. Face recognition using Laplacianfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(3):328-340[10] Tenenbaum J B,Silva V,Langford J C. A global geometric framework for nonlinear dimensionality reduction. Science,2000,290(5500):2319-2323[11] Belkin M,Niyogi P,Sindhwani V. Manifold regularization:a geometric framework for learning from labeled unlabeled examples. Journal of Machine Learning Research,2006,7:2399-2434[12] Gao Jun,Wang Shi-Tong,Deng Zhao-Hong. Global and local preserving based semi-supervised support vector machine. Acta Electronica Sinica,2010,38(7):1626-1634(皋军,王士同,邓赵红. 基于全局和局部保持的半监督支持向量机. 电子学报,2010,38(7):1626-1634)[13] Wang X M,Chung F L,Wang S T. On minimum class locality preserving variance support vector machine. Pattern Recognition,2010,43(8):2753-2762[14] Wang H X,Chen S,Hu Z L,Zheng W M. Locality-preserved maximum information projection. IEEE Transactions on Neural Networks,2008,19(4):571-585[15] Li H F,Jiang T,Zhang K S. Efficient and robust feature extraction by maximum margin criterion. IEEE Transactions on Neural Networks,2006,17(1):157-165[16] Gao Quan-Xue,Xie De-Yan,Xu Hui,Li Yuan-Zheng,Gao Xi-Quan. Supervised feature extraction based on information fusion of local structure and diversity information. Acta Automatica Sinica,2010,36(8):1107-1114(高全学,谢德燕,徐辉,李远征,高西全. 融合局部结构和差异信息的监督特征提取算法. 自动化学报,2010,36(8):1107-1114)[20] Jun G,Chung F L,Wang S T. Matrix pattern based minimum within-class scatter support vector machines. Applied Soft Computing,2011,11(8):5602-5610[17] Muller K R,Mika S,Ratsch G,Tsuda K,Scholkopf B. An introduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks,2001,12(2):181-201[18] Scholkopf B,Herbrich R,Smola A J. A generalized representer theorem. In:Proceedings of the 14th Annual Conference on Computational Learning Theory and 5th European Conference on Computational Learning Theory. Amsterdam,Netherlands:Springer,2001. 416-426[19] Cai D,He X F,Han J W,Zhang H J. Orthogonal Laplacianfaces for face recognition. IEEE Transactions on Image Processing,2006,15(11):3608-3614

施引文献

资源附件(0)

访问统计