Total Margin Based Fuzzy Hypersphere Learning Machine
TAO Jian-Wen1,2, WANG Shi-Tong1
1.School of Information Engineering,Jiangnan University,Wuxi 214122 2.School of Information Engineering,Zhejiang Business Technology Institute,Ningbo 315012
Abstract There are several problems in classical support vector machines, such as overfitting problem resulted from the outlier and class imbalance learning and the loss of the statistics information of training examples. Aiming at these problems, a total margin based fuzzy hypersphere learning machine (TMF-SSLM) is proposed by constructing a minimum hypersphere in Mercer kernel-induced feature space. The main idea of TMF-SSLM is that one class of binary patterns is enclosed in the minimum hypersphere, from which another one is separated away with maximum margin. Thus both maximum between-class margin and minimum within-class volume are implemented. The proposed TMF-SSLM solves the overfitting problem resulted from outliers by employing both the fuzzification of the penalty and total margin algorithm, as well as the imbalanced problem by using different cost algorithm. Theoretical analysis justifies that TMF-SSLM obtains a lower generalization error bound. The exprimental results obtained on real datasets show that the proposed algorithm is stable and superior to other related diagrams.
[1] Wen Chuanjun,Zhan Yongzhao,Chen Changjun.Maximal-Margin Minimal-Volume Hypersphere Support Vector Machine.Control and Decision,2010,25(1): 79-83 (in Chinese) (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) [2] Chung F L,Wang Shitong,Deng Zhaohong,et al.Fuzzy Kernel Hyperball Perceptron.Applied Soft Computing,2004,5(1): 67-74 [3] Wu Mingrui,Ye Jieping.A Small Sphere and Large Margin Approach for Novelty Detection Using Training Data with Outliers.IEEE Trans on Pattern Analysis and Machine Intelligence,2009,31(11): 2088-2092 [4] Schlkopf B,Smola A J,Williamson R,et al.New Support Vector Algorithms.Neural Computation,2000,12(5): 1207-1245 [5] Deng Zhaohong,Chung F L,Wang Shitong.FRSDE: Fast Reduced Set Density Estimator Using Minimal Enclosing Ball Approximation.Pattern Recognition,2008,41(1): 1363-1372 [6] Peng Xinjun,Wang Yifei.Total Margin v-Support Vector Machine and Its Geometric Problem.Pattern Recognition and Artificial Intelligence,2009,22(1): 8-16 (in Chinese) (彭新俊,王翼飞.总间隔v-支持向量机及其几何问题.模式识别与人工智能,2009,22(1): 8-16) [7] Lin C F,Wang S D.Fuzzy Support Vector Machines.IEEE Trans on Neural Network,2002,13(2): 464-471 [8] Liu Y H,Chen Y T.Face Recognition Using Total Margin-Based Adaptive Fuzzy Support Vector Machines.IEEE Trans on Neural Networks,2007,18(1): 178-192 [9] Yoon M,Yun Y,Nakayama H.A Role of Total Margin in Support Vector Machines // Proc of the International Joint Conference on Neural Network.Atlanta,USA,2003,III: 2049-2053 [10] Yoo M,Yun Y,Nakayama H.Total Margin Algorithms in Support Vector Machines.IEICE Trans on Information and Systems,2004,87(5): 1223-1230 [11] Liu Y H,Chen Y T.Total Margin Based Adaptive Fuzzy Support Vector Machines for Multi-View Face Recognition // Proc of the IEEE International Conference on Systems,Man and Cybernetics.Hawaii,USA,2005,II: 1704-1711 [12] Peng Xinjun,Wang Yifei.Geometric Algorithms to Large Margin Classifier Based on Affine Hulls.IEEE Trans on Neural Networks and Learning Systems,2012,23(2): 236-246 [13] Tax D M J,Duin R P W.Support Vector Data Description.Machine Learning,2004,54(1): 45-66 [14] Chung F L,Deng Zhaohong,Wang Shitong.From Minimum Enclosing Ball to Fast Fuzzy Inference System Training on Large Datasets.IEEE Trans on Fuzzy System,2009,17(1): 173-184 [15] Wang J G,Neskovic P,Cooper L N.Pattern Classification via Single Sphere // Proc of the 8th International Conference on Discovery Science.Singapore,Singapore,2005: 241-252 [16] Hao P Y,Chiang J H,Lin Y H.A New Maximal Margin Spherical-Structured Multi-Class Support Vector Machine.Applied Intelligence,2009,30(2): 98-111 [17] Liu Y,Zheng Y F.Minimum Enclosing and Maximum Excluding Machine for Pattern Description and Discrimination // Proc of the 18th International Conference on Pattern Recognition.Hong Kong,China,2006,III: 129-132 [18] Ge Lei,Wu Huizhong.A Kernel-Based Fuzzy Greedy Multiple Hyperspheres Covering Algorithm for Pattern Classification.Neurocomputing,2008,72(1/2/3): 313-320. [19] Burges C J C.A Tutorial on Support Vector Machines for Pattern Recognition.Data Mining and Knowledge Discovery,1998,2(2): 955-974 [20] Vapnik V,Chapelle O.Bounds on Error Expectation for Support Vector Machines.Neural Computation,2000,12(1): 2013-2036
2012, Vol. 25 
