| SVM-KNN分类器在异常行为检测中的应用 |
| |
| 引用本文： | 林春丽,齐欣,王克成.SVM-KNN分类器在异常行为检测中的应用[J].鞍山科技大学学报,2010(5). |
| |
| 作者姓名： | 林春丽 齐欣 王克成 |
| |
| 作者单位： | 哈尔滨工程大学自动化学院;辽宁科技大学高等职业技术学院;辽宁科技大学电子与信息工程学院; |
| |
| 摘 要： | 提出了一种新的异常行为检测方法,将SVM算法和KNN算法结合,在对识别样本判别时,当其与最优分类面的距离大于给定阈值时,采用SVM分类算法,否则采用KNN算法,从而减少了SVM算法的错误率。实验结果表明,SVM-KNN算法对异常行为检测的准确率达到95.86%。
|
| 关 键 词： | 支持向量机 K近邻算法 分类器 异常行为检测 |
Application of SVM-KNN classifier on abnormal behavior detection |
| |
| LIN Chun-li,QI Xin,WANG Ke-cheng.Application of SVM-KNN classifier on abnormal behavior detection[J].Journal of Anshan University of Science and Technology,2010(5). |
| |
| Authors: | LIN Chun-li QI Xin WANG Ke-cheng |
| |
| Institution: | LIN Chun-li1,2,QI Xin3,WANG Ke-cheng3(1.College of Automation,Harbin Engineering University,Harbin 150001,China,2.School of Higher Vocational Education,University of Science , Technology Liaoning,Anshan 114051,3.School of Electric , Information Engineering,China) |
| |
| Abstract: | An abnormal behavior detection method is proposed by combining SVM algorithm with KNN algorithm.During the preprocessing phase,when the distance from the test samples to the optimal hyper plane is greater than the given threshold,SVM algorithm is applied to classify test samples,otherwise KNN algorithm would be used to reduce the misclassification probability.Results of experiments show this method of SVM-KNN algorithm has gained the accuracy of 95.86% on abnormal behavior detection. |
| |
| Keywords: | SVM KNN classificator abnormal behavior |
| 本文献已被 CNKI 等数据库收录！ |
|
