基于BGSA算法的SVM分类模型设计研究

详细信息    查看全文 | 推荐本文 |

英文篇名：Research on the SVM classification model design based on BGSA 作者：赵东升 ; 李艳军 英文作者：Zhao Dongsheng;Li Yanjun;Beijing Jinghang Research Institute of Computing and Communication;The Classified Information Carrier Safety Management Engineering Technology Research Center of Beijing; 关键词：万有引力搜索算法 ; 群体智能 ; 支持向量机 ; 参数优化 英文关键词：gravitational search algorithm(GSA);;group intelligence;;support vector machine(SVM);;parameter optimization 中文刊名：DZCL 英文刊名：Electronic Measurement Technology 机构：北京京航计算通讯研究所;北京市涉密信息载体安全管理工程技术研究中心; 出版日期：2019-03-08 出版单位：电子测量技术 年：2019 期：v.42;No.313 语种：中文; 页：DZCL201905014 页数：4 CN：05 ISSN：11-2175/TN 分类号：62-65

摘要

为了设计性能更优的支持向量机(SVM)分类模型,对影响其分类性能的参数和样本特征子集进行优化选择,对支持向量机理论和万有引力搜索算法(GSA)进行了研究,提出了一种基于二进制万有引力搜索算法(BGSA)的支持向量机分类模型构建方法,能够对影响支持向量机分类性能的相关参数及有效样本特征子集同时进行优化选择,获得最优组合解,并通过实验对其有效性进行了对比分析和验证。实验结果表明,所提出的BGSA-SVM分类模型能够有效提高支持向量机的分类性能,可进一步推广到工程实际中应用。
        In order to design a support vector machine(SVM) classification model with better performance, the parameters and sample feature subsets that affect its classification performance are optimized, and the support vector machine theory and gravitational search algorithm(GSA) were studied. The optimal combination solution can be obtained by simultaneously optimizing the relevant parameters and effective sample feature subsets which affect the classification performance of SVM. Its effectiveness is compared and verified by experiments. The experimental results show that the proposed BGSA-SVM classification model can effectively improve the classification performance of support vector machines, which can be further extended to engineering applications.

引文

[1] 胡冬梅,宋路,牛国成.基于支持向量机的波片相位延迟测量新方法[J].仪器仪表学报,2016,37(7):1517-1523.
    [2] 梅恒荣,殷礼胜,刘冬梅,等.改进粒子群算法优化的SVM模拟电路故障诊断[J].电子测量与仪器学报,2017,31(8):1239-1246.
    [3] 王福忠,石秀立.改进PSO-SVM算法的变压器分接开关故障诊断[J].电子测量技术,2016,39(11):190-194.
    [4] 谈利芳,刘蓉,黄刚,等.基于遗传优化的多级SVM语音情感识别[J].电子测量技术,2017,40(10):122-126.
    [5] 黄挺,王元庆,张自豪.基于GS-SVM的彩色图像分割算法[J].电子测量技术,2017,40(7):105-108,112.
    [6] RASHEDI E, NEZAMABADI S, SARYAZDI S. GSA: A gravitational search algorithm [J]. Information Sciences, 2009, 179(13): 2232-2248.
    [7] RASHEDI E, NEZAMABADI-POUR H, SARYAZDI S. Filter modeling using gravitational search algorithm [J]. Engineering Applications of Artificial Intelligence, 2011, 24(1):117-122.
    [8] DUMAN S, GüVEN? U, S?NMEZ Y, et al. Optimal power flow using gravitational search algorithm[J]. Energy Conversion & Management, 2012, 59(59):86-95.
    [9] BHATTACHARYA A, ROY P K. Solution of multi-objective optimal power flow using gravitational search algorithm[J]. IET Generation Transmission & Distribution, 2012, 6(8): 751-763.
    [10] SHUKLA A, SINGH S N. Multi-objective unit commitment with renewable energy using GSA algorithm[J]. Inae Letters, 2016, 1(1):21-27.
    [11] RASHEDI E, NEZAMABADI-POUR H, SARYAZDI S. BGSA: binary gravitational search algorithm[J]. Natural Computing, 2010, 9(3):727-745.
    [12] LIU C, NIU P, LI G, et al. A hybrid heat rate forecasting model using optimized LSSVM based on improved GSA[J]. Neural Processing Letters, 2017, 45(1):299-318.
    [13] DAS P K, BEHERA H S, PANIGRAHI B K. A hybridization of an improved particle swarm optimization and gravitational search algorithm for multi-robot path planning[J]. Swarm & Evolutionary Computation, 2016, 28:14-28.
    [14] ELAZIM S M A, ALI E S. Optimal SSSC design for damping power systems oscillations via gravitational search algorithm[J]. International Journal of Electrical Power & Energy Systems, 2016, 82:161-168.
    [15] MAHMOUDI S M, AGHAIE M, BAHONAR M, et al. A novel optimization method, gravitational search algorithm(GSA), for PWR core optimization[J]. Annals of Nuclear Energy, 2016, 95:23-34.