基于边界样本选择的支持向量机加速算法.pdf

Computer Engineering and Applications 计算机工程与应用 2017 ，53（3 ） 169 基于边界样本选择的支持向量机加速算法 胡小生，钟 勇 HU Xiaosheng, ZHONG Yong 佛山科学技术学院 电子与信息工程学院，广东 佛山 528000 College of Electronic and Information Engineering, Foshan University, Foshan, Guangdong 528000, China HU Xiaosheng, ZHONG Yong. SVM accelerated training algorithm based on border sample selection. Computer Engineering and Applications, 2017, 53 （3 ）：169-173. Abstract: Support Vector Machine（SVM）is a powerful instrument for solving pattern classification problem, but it is not suitable for large-scale data, due to the drawbacks of slow training speed, large computational cost and low generalization. An accurate support vector machine algorithm is proposed, which uses training samples lying close to the separation boundary. First of all, K-means clustering is performed to the initial training data, and then the boundary samples are se- lected in each cluster by K-nearest neighbor algorithm, two cluster factors, the degree of mixing and support, are defined to determine the boundary width. These boundary samples are then used in the training of the SVM classifier. The experi- ments on some benchmark datasets show that the proposed method not only makes computational complexities decreased, but also makes classification power of traditional SVM invariant. Key words: Support Vector Machine（SVM）; large-scale classification; boundary samples; clustering 摘 要：针对支持向量机（Support Vector Machine ，SVM ）处理大规模数据集的学习时间长、泛化能力下降等问题， 提出基于边界样本选择的支持向量机加速算法。首先，进行无监督的K 均值聚类；然后，在各个聚簇内依照簇的混 合度、支持度因素应用K 近邻算法剔除非边界样本，获得最终的类别边界区域样本，参与SVM 模型训练。在标准数 据集上的实验结果表明，算法在保持传统支持向量机的分类泛化能力的同时，显著降低了模型训练时间。 关键词：支持向量机；大规模分类；边界样本；聚类 文献标志码：A 中图分类号：TP 181 doi ：10.3778/j.issn. 1002-8331.1507-0245 1 引言 大，所以不适合用来处理大规模数据集。如何借鉴成熟 [1] 的机器学习方法来提高SVM 处理大规模数据的效率成