基于双参照点灰色关联度的模糊支持向量机改进方法

J4 ›› 2016, Vol. 38 ›› Issue (06): 1244-1251.

基于双参照点灰色关联度的模糊支持向量机改进方法

衣柏衡1，朱建军1，张世涛1,2

（1.南京航空航天大学经济与管理学院，江苏南京 211106；2.安徽工业大学数理科学与工程学院，安徽马鞍山 243002）

收稿日期:2015-04-16 修回日期:2015-08-19 出版日期:2016-06-25 发布日期:2016-06-25
基金资助:
国家社会科学基金重点项目（14AZD049）；国家自然科学基金（71171112，71401064）；中央高校基本科研业务费专项资金资助（NS2014086）；广义虚拟经济研究专项（GX20131017 (M)）
通信地址：211106 江苏省南京市南京航空航天大学经济与管理学院

Improved fuzzy support vector machine based on
grey incidence degree with dual reference points

YI Baiheng1,ZHU Jianjun1,ZHANG Shitao1,2

（1.School of Economics and Management,Nanjing University of Aeronautics and Astronautics,Nanjing 211106;
2.School of Mathematics & Physics Science and Engineering,Anhui University of Technology,Ma’anshan 243002,China）

Received:2015-04-16 Revised:2015-08-19 Online:2016-06-25 Published:2016-06-25

摘要/Abstract

摘要：

改进了模糊支持向量机隶属度函数设计方法。考虑样本分布不确定的问题，使用灰色关联度代替现有方法中的欧氏距离，定义了样本的平均灰色绝对关联度；针对噪声识别过程中支持向量对分类贡献被削弱的问题，提出了基于同类中心和异类中心双参照点的噪声判别方法；分析了模糊支持向量机求解对偶问题中参数与支持向量的对应关系，进而给出新的隶属度函数设置步骤。实验结果说明了方法的有效性及实用性。关键词：模糊支持向量机；灰色关联度；隶属度；双参照点

Abstract:

We improve the membership setting method for the fuzzy support vector machine (FSVM). Given the distribution uncertainty of training sets, we replace the classical Euclidean distance with grey incidence degree, and define the mean grey absolute incidence degree of samples. To overcome the disadvantages in traditional methods and ensure a greater contribution of support vectors to the classification results, we present a new approach for distinguishing noises based on the dual reference points of the same center and the different center. The relationship between the parameters in solving the FSVM and the corresponding support vectors is analyzed, and the steps of setting the fuzzy membership are given. Experimental results demonstrate the effectiveness and practicability of this approach.

Key words: fuzzy support vector machine；grey incidence degree；membership；dual reference points

衣柏衡1，朱建军1，张世涛1,2. 基于双参照点灰色关联度的模糊支持向量机改进方法[J]. J4, 2016, 38(06): 1244-1251.

YI Baiheng1,ZHU Jianjun1,ZHANG Shitao1,2. Improved fuzzy support vector machine based on
grey incidence degree with dual reference points [J]. J4, 2016, 38(06): 1244-1251.

参考文献［19］

［1］	Vapnik V.The nature of statistical learning theory ［M］.New York:SpringerVerlag,1995.
［2］	Zhang Xuegong. Pattern recognition ［M］.3rd Edtion. Beijing:Tsinghua University,2010.(in Chinese)
［3］	Lv Chengshu.Shilling attack detection method of recommender systems based on costsensitive SVM ［J］.Computer Engineering & Science,2014,36(4):697701.(in Chinese)
［4］	Meng Qian, Ma Xiaoping. Software defect prediction using rough sets and support vector machine ［J］.Computer Engineering & Science,2015,37(1):9398.(in Chinese)
［5］	Tong M,Liu K,Xu C,et al.An ensemble of SVM classifiers based on gene pairs ［J］.Computers in Biology and Medicine,2013,43(6):729737.
［6］	Lin C F,Wang S D.Fuzzy support vector machines ［J］.IEEE Transactions on Neural Networks,2002,13(2):464471.
［7］	Jiang X F,Yi Z,Lv J C.Fuzzy SVM with a new fuzzy membership function ［J］.Neural Computation and Application,2006,3(15):268276.
［8］	Chaudhuri A. Modified fuzzy support vector machine for credit approval classification ［J］.AI Communications,2014,27(2):189211.
［9］	Ha Minghu, Peng Guibing, Zhao Qiuhuan, et al.A new fuzzy support vector machine ［J］.Computer Engineering and Applications,2009,45(25):151153.(in Chinese)
［10］	Du Zhe, Liu Sanyang, Qi Xiaogang. Fuzzy support vector machine with new membership function ［J］.Journal of System Simulation,2009,21(7):19011903.(in Chinese)
［11］	An W J,Liang M G.Fuzzy support vector machine based on withinclass scatter for classification problems with outliers or noises ［J］.Neurocomputing,2013,110(13):101110.
［12］	Tang W M.Fuzzy SVM with a new fuzzy membership function to solve the twoclass problems ［J］.Neural Processing Letters,2011,34(3):209219.
［13］	Xia S Y,Xiong Z Y,Luo Y G,et al.Relative density based support vector machine ［J］.Neurocomputing,2015,149(Part C):14241432.
［14］	Liu S F,Lin Y.Grey information theory and practical applications ［M］.London:SpringerVerlag,2009.
［15］	Zhou Huaping,Li Jingzhao.An integrated prediction model using multistage gray model and support vector machine ［J］.Computer Engineering & Science,2015,37(3):539546.(in Chinese)
［16］	Guo Le,Jia Zhenhong,Qin Xizhong,et al.A multifactor grey model based on SVM residual error compensation for telephone traffic prediction ［J］.Computer Engineering & Science,2014,36(7):13301335.(in Chinese)
［17］	Zhu Shuang,Zhou Jianzhong,Meng Changqing,et al.Study and application of fuzzy support vector machine based on gray correlation analysis to stream flow forecasting ［J］.Journal of Hydroelectric Engineering,2015,34(6):16.(in Chinese)
［18］	Chen Wei,Jia Qingxuan,Sun Hanxu.Bearing fault classification using support vector machine decision tree and grey correlation information entropy ［J］.Journal of Vibration,Measurement and Diagnosis,2013,33(3):504508.(in Chinese)
［19］	Wu Qiang, Li Jianping, Hu Xiaorong, et al.Determination analysis of fuzzy membership for SVM based on the grey connection analysis ［J］.Mathematical Theory and Applications,2007,27(2):108111.(in Chinese)
［20］	Sevakula R K,Verma N K.Clustering based outlier detection in fuzzy SVM［C］∥Proc of 2014 IEEE International Conference on Fuzzy Systems (FUZZIEEE),2014:11721177.
［21］	Bache K, Lichman M. UCI machine learning repository ［DB/OL］.［20130413］.http://archive.ics.uci.edu/ml,Irvine,CA:University of California.
［22］	Chang C C,Lin C J.LIBSVM:A library for support vector machines ［J］.ACM Transactions on Intelligent Systems and Technology,2011,2(3):127.
	附中文参考文献：
［2］	张学工.模式识别［M］.第三版.北京:清华大学出版社,2010.
［3］	吕成戍.基于代价敏感支持向量机的推荐系统托攻击检测方法［J］.计算机工程与科学,2014,36(4):697701.
［4］	孟倩,马小平.基于粗糙集支持向量机的软件缺陷预测［J］.计算机工程与科学,2015,37(1):9398.
［9］	哈明虎,彭桂兵,赵秋焕,等.一种新的模糊支持向量机［J］.计算机工程与应用,2009,45(25):151153.
［10］	杜喆,刘三阳,齐小刚.一种新隶属度函数的模糊支持向量机［J］.系统仿真学报,2009,21(7):19011903.
［15］	周华平,李敬兆.多阶灰色支持向量机集成预测模型研究［J］.计算机工程与科学,2015,37(3):539546.
［16］	郭勒,贾振红,覃锡忠,等.支持向量机补偿的多因素灰色模型话务量预测［J］.计算机工程与科学,2014,36(7):13301335.
［17］	朱双,周建中,孟长青,等.基于灰色关联分析的模糊支持向量机方法在径流预报中的应用研究［J］.水力发电学报,2015,34(6):16.
［18］	陈伟,贾庆轩,孙汉旭.基于灰关联信息熵的SVM决策树轴承故障分类［J］.振动、测试与诊断,2013,33(3):504508.
［19］	吴强,李建平,胡小荣,等.基于灰色关联分析的模糊支持向量机中隶属度的确定［J］.数学理论与应用,2007,27(2):108111.