| 边界偏转覆盖增量支持向量机 |
| |
| 引用本文： | 张立,孟相如,马志强,周华. 边界偏转覆盖增量支持向量机[J]. 北京邮电大学学报, 2010, 33(4): 30-34. DOI: 10.3969/j.issn.1007-5321.2010.04.006 |
| |
| 作者姓名： | 张立 孟相如 马志强 周华 |
| |
| 作者单位： | 空军工程大学,电讯工程学院,西安,710077;西安通信学院,西安,710106 |
| |
| 摘 要： | 为了利用不断积累的网络样本提高故障诊断效能，针对标准支持向量机不直接支持增量学习的问题，提出一种边界偏转覆盖增量支持向量机. 根据违背Karush Kuhn Tucker条件的新增样本在特征空间中可引起原分类边界改变的情况，设计边界偏转覆盖算法预选支持向量再生区作为增量训练工作集，解决了难以确定的非支持向量向支持向量的转化问题. 理论分析和实验结果表明，该方法能有效简化训练工作集，在保证故障诊断精度的同时大幅度提高增量训练效率.
|
| 关 键 词： | 故障诊断 支持向量机 增量学习 模型更新 |
| 收稿时间： | 2009-10-10 |
Boundary Deflection Overlay Incremental Support Vector Machine |
| |
| ZHANG Li,MENG Xiang-ru,MA Zhi-qiang,ZHOU Hua. Boundary Deflection Overlay Incremental Support Vector Machine[J]. Journal of Beijing University of Posts and Telecommunications, 2010, 33(4): 30-34. DOI: 10.3969/j.issn.1007-5321.2010.04.006 |
| |
| Authors: | ZHANG Li MENG Xiang-ru MA Zhi-qiang ZHOU Hua |
| |
| Affiliation: | ZHANG Li1,MENG Xiang-ru1,MA Zhi-qiang1,ZHOU Hua2 ( 1. Telecommunication Engineering Institute,Air Force Engineering University,Xi'an 710077,China,2. Xi'an Communications Institute,Xi'an 710106,China) |
| |
| Abstract: | In order to enhance the diagnosis efficiency with the accumulated network sample,and because the standard support vector machine doesn't support incremental learning directly,a boundary deflection overlay incremental support vector machine is proposed. According to the movement of separating hyperplane caused by the newly added training samples that violate Karush-Kuhn-Tucker conditions,the boundary deflection overlay algorithm is also designed to pre-extracts support vector reproducing region as the work s... |
| |
| Keywords: | network fault diagnosis support vector machine incremental learning model update |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《北京邮电大学学报》浏览原始摘要信息 |
|
点击此处可从《北京邮电大学学报》下载全文 |
|
