[1]赵帅群,郭虎升,王文剑.采用划分融合双向控制的粒度支持向量机[J].智能系统学报,2019,14(06):1243-1254.[doi:10.11992/tis.201904047]
 ZHAO Shuaiqun,GUO Husheng,WANG Wenjian.Granular support vector machine with bidirectional control of division-fusion[J].CAAI Transactions on Intelligent Systems,2019,14(06):1243-1254.[doi:10.11992/tis.201904047]
点击复制

采用划分融合双向控制的粒度支持向量机(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年06期
页码:
1243-1254
栏目:
出版日期:
2019-11-05

文章信息/Info

Title:
Granular support vector machine with bidirectional control of division-fusion
作者:
赵帅群1 郭虎升12 王文剑2
1. 山西大学 计算机与信息技术学院, 山西 太原 030006;
2. 山西大学 计算智能与中文信息处理重点实验室, 山西 太原 030006
Author(s):
ZHAO Shuaiqun1 GUO Husheng12 WANG Wenjian2
1. School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China;
2. Key Laboratory of Computational Intelligence and Chinese Information Processing, Shanxi University, Taiyuan 030006, China
关键词:
支持向量机粒度支持向量机划分融合强信息粒弱信息粒动态机制双向控制
Keywords:
support vector machine (SVM)granular support vector machine (GSVM)divisionfusionstrong information granuleweak information granuledynamic mechanismbidirectional control
分类号:
TP18
DOI:
10.11992/tis.201904047
摘要:
粒度支持向量机(granular support vector machine,GSVM)引入粒计算的方式对原始数据集进行粒度划分以提高支持向量机(support vector machine, SVM)的学习效率。传统GSVM采用静态粒划分机制,即通过提取划分后数据簇中的代表信息进行模型训练,有效地提升了SVM的学习效率,但由于GSVM对信息无差别的粒度划分导致对距离超平面较近的强信息粒提取不足,距离超平面较远的弱信息粒被过多保留,影响了SVM的学习性能。针对这一问题,本文提出了采用划分融合双向控制的粒度支持向量机方法(division-fusion support vector machine,DFSVM)。该方法通过动态数据划分融合的方式,选取超平面附近的强信息粒进行深层次的划分,同时将距离超平面较远的弱信息粒进行选择性融合,以动态地保持训练样本规模的稳定性。通过实验表明,采用划分融合的方法能够在保证模型训练精度的条件下显著提升SVM的学习效率。
Abstract:
Granular support vector machine (GSVM) introduces the method of granular computing to divide the original dataset; therefore, GSVM improves the efficiency of the support vector machine (SVM). The traditional GSVM adopts the static granules partitioning mechanism to extract representative information from the divided data clusters for model training, which can effectively increase the learning efficiency of the SVM. However, the GSVM uses the same processing way for different information granules, which may lead to a decline in the generalization ability because of two reasons: (i) No sufficient valid information is extracted from the strong information granules that are close to the hyper-plane, and (ii) excess of the weak information of granules far from the hyper-plane is reserved. These all reduce the learning performance of the SVM. To address this problem, this study proposes a division and fusion SVM model based on dynamical granulation, namely DFSVM. With the DFSVM, the information from the strong information granules near the hyper-plane is divided in depth, and weak information from weak information granules far from the hyper-plane is selectively merged to dynamically maintain the stability of the size of the training samples. The experiments demonstrate that this model can significantly improve the SVM learning efficiency, ensuring the training precision of the model.

参考文献/References:

[1] VAPNIK V. The nature of statistical learning theory[M]. New York:Springer, 1995.
[2] YUAN Ruixi, LI Zhu, GUAN Xiaohong, et al. An SVM-based machine learning method for accurate internet traffic classification[J]. Information systems frontiers, 2010, 12(2):149-156.
[3] CHEN G Y, XIE W F. Pattern recognition with SVM and dual-tree complex wavelets[J]. Image and vision computing, 2007, 25(6):960-966.
[4] REYNA R A, ESTEVE D, HOUZET D, et al. Implementation of the SVM neural network generalization function for image processing[C]//Proceedings of the 5th IEEE International Workshop on Computer Architectures for Machine Perception. Padova, Italy, 2000:147-151.
[5] LIU Yang, WEN Kaiwen, GAO Quanxue, et al. SVM based multi-label learning with missing labels for image annotation[J]. Pattern recognition, 2018, 78:307-317.
[6] XIONG Xiaoxia, CHEN Long, LIANG Jun. A new framework of vehicle collision prediction by combining SVM and HMM[J]. IEEE transactions on intelligent transportation systems, 2018, 19(3):699-710.
[7] BISHWAS A K, MANI A, PALADE V. An all-pair quantum SVM approach for big data multiclass classification[J]. Quantum information processing, 2018, 17(10):282.
[8] ZHOU Xueliang, JIANG Pingyu, WANG Xianxiang. Recognition of control chart patterns using fuzzy SVM with a hybrid kernel function[J]. Journal of intelligent manufacturing, 2018, 29(1):51-67.
[9] TANG Yuchun, JIN Bo, SUN Yi, et al. Granular support vector machines for medical binary classification problems[C]//Proceedings of 2004 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology. La Jolla, USA, 2004:73-78.
[10] YU H, YANG J, HAN Jiawei. Classifying large data sets using SVMs with hierarchical clusters[C]//Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Washington, USA, 2003:306-315.
[11] WANG Wenjian, XU Zongben. A heuristic training for support vector regression[J]. Neurocomputing, 2004, 61:259-275.
[12] MAO Xueyu, SARKAR P, CHAKRABARTI D. Overlapping Clustering Models, and One (class) SVM to Bind Them All[J]. arXiv:1806.06945, 2018.
[13] DING Shifei, QI Bingjuan. Research of granular support vector machine[J]. Artificial intelligence review, 2012, 38(1):1-7.
[14] GUO Husheng, WANG Wenjian, MEN Changqian. A novel learning model-Kernel granular support vector machine[C]//Proceedings of 2009 International Conference on Machine Learning and Cybernetics. Hebei, China, 2009:930-935.
[15] 程凤伟, 王文剑, 郭虎升. 动态粒度SVM学习算法[J]. 模式识别与人工智能, 2014, 27(4):372-377 CHENG Fengwei, WANG Wenjian, GUO Husheng. Dynamic granular support vector machine learning algorithm[J]. Pattern recognition and artificial intelligence, 2014, 27(4):372-377
[16] HASSAN R, OTHMAN R M, SHAH Z A. Granular support vector machine to identify unknown structural classes of protein[J]. International journal of data mining and bioinformatics, 2015, 12(4):451-467.
[17] GUO Husheng, WANG Wenjian. Granular support vector machine:a review[J]. Artificial intelligence review, 2019, 51(1):19-32.
[18] MA Zhixian, LI Weitian, WANG Lei, et al. X-ray astronomical point sources recognition using granular binary-tree SVM[C]//Proceedings of the 13th International Conference on Signal Processing. Chengdu, China, 2017:1021-1026.
[19] GUO Husheng, WANG Wenjian. Support vector machine based on hierarchical and dynamical granulation[J]. Neurocomputing, 2016, 211:22-33.
[20] 郭虎升, 王文剑. 动态粒度支持向量回归机[J]. 软件学报, 2013, 24(11):2535-2547 GUO Husheng, WANG Wenjian. Dynamical granular support vector regression machine[J]. Journal of software, 2013, 24(11):2535-2547
[21] YAO Y. Perspectives of granular computing[C]//Proceedings of 2005 IEEE International Conference on Granular Computing. Beijing, China, 2005:85-90.
[22] TANG Yuchun, JIN Bo, ZHANG Yanqing. Granular support vector machines with association rules mining for protein homology prediction[J]. Artificial intelligence in medicine, 2005, 35(1/2):121-134.
[23] LI Boyang, WANG Qiangwei, HU Jinglu. A fast SVM training method for very large datasets[C]//Proceedings of 2009 International Joint Conference on Neural Networks. Atlanta, USA, 2009:1784-1789.
[24] LI Xiaoou, YU Wen. Fast support vector machine classification for large data sets[J]. International journal of computational intelligence systems, 2014, 7(2):197-212.
[25] LI Xiaoou, CERVANTES J, YU Wen. A novel SVM classification method for large data sets[C]//Proceedings of 2010 IEEE International Conference on Granular Computing. San Jose, USA, 2010:297-302.

相似文献/References:

[1]王书舟,伞 冶.支持向量机的训练算法综述[J].智能系统学报,2008,3(06):467.
 WANG Shu-zhou,SAN Ye.A survey on training algorithms for support vector machine[J].CAAI Transactions on Intelligent Systems,2008,3(06):467.
[2]陈小娥,陈昭炯.多类SVM在图像艺术属性分类中的应用研究[J].智能系统学报,2009,4(02):157.
 CHEN Xiao-e,CHEN Zhao-jiong.An application of multiclass SVM in the classification of artistic attributes of images[J].CAAI Transactions on Intelligent Systems,2009,4(06):157.
[3]黄剑华,唐降龙,刘家锋,等.一种基于Homogeneity的文本检测新方法[J].智能系统学报,2007,2(01):69.
 HUANG Jian-hua,TANG Xiang-long,LIU Jia-feng,et al.A new method for text detection based on Homogeneity[J].CAAI Transactions on Intelligent Systems,2007,2(06):69.
[4]吴 青,刘三阳,郑 巍.基于乘性规则的支持向量机[J].智能系统学报,2007,2(02):74.
 WU Qing,LIU San-yang,ZHENG Wei.Support vector machines based on multiplicative updates[J].CAAI Transactions on Intelligent Systems,2007,2(06):74.
[5]张 亮,朱振峰,赵 耀,等.基于镜头的鲁棒视频广告检测[J].智能系统学报,2007,2(02):83.
 ZHANG Liang,ZHU Zhen-feng,ZHAO Yao,et al.Video commercial detection based on the robustness of sho t[J].CAAI Transactions on Intelligent Systems,2007,2(06):83.
[6]赵春晖,陈万海,万 建.一种改进的多类支持向量机超光谱图像分类方法[J].智能系统学报,2008,3(01):77.
 ZHAO Chun-hui,CHEN Wan-hai,WAN jian.An improved hyperspectral image classification method for a multiclass support vector machine[J].CAAI Transactions on Intelligent Systems,2008,3(06):77.
[7]杨志豪,洪 莉,林鸿飞,等.基于支持向量机的生物医学文献蛋白质关系抽取[J].智能系统学报,2008,3(04):361.
 YANG Zhi-hao,HONG L i,L IN Hong-fei,et al.Extraction of information on prote in2prote in interaction from biomedical literatures using an SVM[J].CAAI Transactions on Intelligent Systems,2008,3(06):361.
[8]刘 琚,乔建苹.基于学习的超分辨率重建技术[J].智能系统学报,2009,4(03):199.
 LIU Ju,QIAO Jian-ping.Learningbased superresolution reconstruction[J].CAAI Transactions on Intelligent Systems,2009,4(06):199.
[9]刘 胜,李高云,江 娜.SVM性能的免疫鱼群多目标优化研究[J].智能系统学报,2010,5(02):144.
 LIU Sheng,LI Gao-yun,JIANG Na.Multiobjective optimization of an immune fish swarm algorithm to improve support vector machine performance[J].CAAI Transactions on Intelligent Systems,2010,5(06):144.
[10]杨振兴,刘久富,孙 琳.不变量的程序潜在错误预测[J].智能系统学报,2010,5(04):327.
 YANG Zhen-xing,LIU Jiu-fu,SUN Lin.Using invariants to predict the potential for errors in programs[J].CAAI Transactions on Intelligent Systems,2010,5(06):327.
[11]黄华娟,韦修喜,周永权.基于模糊核聚类粒化的粒度支持向量机[J].智能系统学报,2019,14(06):1271.[doi:10.11992/tis.201904048]
 HUANG Huajuan,WEI Xiuxi,ZHOU Yongquan.Granular support vector machine based on fuzzy kernel clustering granulation[J].CAAI Transactions on Intelligent Systems,2019,14(06):1271.[doi:10.11992/tis.201904048]

备注/Memo

备注/Memo:
收稿日期:2019-04-19。
基金项目:国家自然科学基金项目(61673249,61503229,U1805263);山西省回国留学人员科研基金项目(2016-004).
作者简介:赵帅群,男,1993年,硕士研究生,主要研究方向为机器学习;郭虎升,男,1986年,副教授,博士,主要研究方向为机器学习与数据发掘。主持国家自然科学基金项目1项、省部级项目多项。发表学术论文30余篇;王文剑,女,1968年,教授,博士,主要研究方向为计算智能、机器学习与数据挖掘。主持国家自然科学基金项目4项、省部级项目及企事业委托项目20余项。发表学术论文150余篇
通讯作者:王文剑.E-mail:wjwang@sxu.edu.cn
更新日期/Last Update: 2019-12-25