期刊文献+

一类快速模糊支持向量机 被引量:4

A Kind of Fast Fuzzy Support Vector Machines
下载PDF
导出
摘要 由H.P.Huang、C.F.Lin等人和T.Inoue,S.Abe等人提出的两类模糊支持向量机是两种类型的改进支持向量机,分别克服了过学习问题和减少了多类问题分类时存在的不可分区域。如何处理异常数据和加速训练大规模数据集是支持向量机中的急需解决的两个问题。针对这两个问题,提出了一类将两类模糊支持向量机集成的快速模糊支持向量机。训练时,根据每类数据与其类中心的距离,定义隶属函数,以加大对容易被错分样本的惩罚,利用合适的参数λ选取了每类数据中隶属度值较大的边缘数据构造模糊支持向量机,测试时,利用1-a-1和模糊支持向量机的决策函数判定未知样本的类别。含有异常数据的两类问题和机器学习数据集中手写数字识别的多类问题的实验结果,验证了提出的快速模糊支持向量机减少了训练时间同时提高了学习机的推广能力。 The two kinds of Fuzzy Support Vector Machines (FSVMs) which respectively were proposed by H. E Huang, C. F. Lin, etc. and T. Inoue, S. Abe, etc. were improved Support Vector Machines (SVMs). They respectively solved the overfitting problem and reduced the unclassifiable regions of multi-class problems. It is urgent for SVMs to deal with outliers properly and speed up training for the training set of large scale. Regarding to the requirements, a kind of fast FSVMs integrating the advantages of above FSVMs was proposed During the training process, the membership functions were defined by the distance between the data and their class centers and assign the lager penalty values for the data which are easy to be misclassified The selected edge data including outliers with the lager membership values were used training FSVMs. During the testing process, the classes of the unknown data were discriminated by the 1-against-1 strategy and decision functions of FSVMs. The two-class problem including outliers and the multi-class problem, such as hand-written digit recognition in the machine learning benchmark dataset, have verified the reduced training time and the improved generalization abilities of the proposed fast FSVMs.
出处 《系统仿真学报》 CAS CSCD 北大核心 2008年第24期6664-6667,共4页 Journal of System Simulation
基金 国家自然科学基金(40701153,60572015) 武汉市国际交流项目(200770834318) 信阳师范学院青年骨干教师资助计划(2060503)
关键词 支持向量机 模糊支持向量机 隶属函数 边缘数据 SVM FSVMs membership function edge data
  • 引文网络
  • 相关文献

参考文献12

  • 1V Vapnik. The Nature of Statistical Learning Theory [M]. Berlin, Germany: Springer Verlag, 1995.
  • 2V Vapnik. Statistical Learning Theory [M]. New York, USA: John Wiley and Sons, 1998.
  • 3J Shawe-Taylor. Classification Accuracy Based on Observed Margin [J]. Algorithmica (S1432-0541), 1998, 22(1): 157-172.
  • 4J Shawe-Taylor, N Cfistianini. Further Results on the Margin Distribution [C]// Proceedings of the Conference on Computational Learning Theory. New York, USA: ACM Press, 1999: 278-285.
  • 5H P Huang, Y H Liu. Fuzzy Support Vector Machines for Pattern Recognition and Data Mining [J]. International Journal of Fuzzy Systems ($1562-2479), 2002, 4(3): 826-835.
  • 6C F Lin, S D Wang. Fuzzy Support Vector Machines [J]. IEEE Transactions on Neural Networks (S1045-9227), 2002, 13(2): 464-471.
  • 7T Inoue, S Abe. Fuzzy Support Vector Machines for Pattern Classification [C]// Proceedings of International Joint Conference on Neural Networks. New York, USA: IEEE Press, 2001: 1449-1454.
  • 8S Abe. Analysis of Multi-class Support Vector Machines [C]// Proceedings of International Conference on Computational Intelligence for Modeling Control and Automation. New York, USA: IEEE Press, 2003: 385-396.
  • 9郑宇杰,杨静宇,吴小俊,於东军.基于独立成分分析和模糊支持向量机的人脸识别方法[J].系统仿真学报,2005,17(7):1768-1770. 被引量:13
  • 10袁平,毛志忠,王福利.基于多支持向量机的软测量模型[J].系统仿真学报,2006,18(6):1458-1461. 被引量:18

二级参考文献24

  • 1孙彦广,陶百生,高克伟.基于智能技术的钢水温度软测量[J].仪器仪表学报,2002,23(z2):754-755. 被引量:6
  • 2张俊杰,王顺晃.电弧炉炼钢过程终点自适应预报及专家操作指导系统[J].自动化学报,1993,19(4):463-467. 被引量:15
  • 3Daisuke Tsujinishi,Shigeo Abe.Fuzzy lest squares support vector machines for multiclass problems[J].Neural Networks,2003,16(5-6):785-792.
  • 4Aapo Hyvarinen.Fast and robust fixed-point algorithms for independent component analysis[J].IEEE Trans Neural Networks,1999,10(3):626-634.
  • 5Wu X J,Yang J Y,Wang S T,Guo Y F,Cao Q Y.A new algorithm for generalized optimal discriminant vectors[J].J.Comput.Sci.& Technol.2002,17(3):324-330.
  • 6Turk M,Pentland A.Eigenfaces for recognition[J].Journal of Cognitive Neuroscience,1991,3(1):71-86.
  • 7Jutten C,Herault J.Independent component analysis versus PCA[C].In:Proceeding of European Signal Processing Conf,1988.287-314.
  • 8Juten C,Herault J.Blind separation of sources,part 1:An adaptive algorithm base on neuromimetic architecture[J].Signal Processing,1991,24(1):1-10.
  • 9张学工译.统计学习理论的本质(第二版)[M].北京:清华大学出版社,2000..
  • 10Shigeo Abe,Keita Sakaguchi.Generalization Improvement of a Fuzzy Classifier With Ellipsodial Regions[C].FUZZ-IEEE 2001,2001,207-210.

共引文献28

同被引文献56

引证文献4

二级引证文献952

;
使用帮助 返回顶部