|
|||||
|
|
| 融合BVM与ELM的网络异常检测方法 | |
| 引用本文： | 蔡长宁,潘华贤,程国建.融合BVM与ELM的网络异常检测方法[J].西安石油大学学报(自然科学版),2012,27(4):97-100,119. |
| 作者姓名： | 蔡长宁 潘华贤 程国建 |
| 作者单位： | 1. 中国石油勘探开发研究院西北分院,甘肃兰州,730020 2. 西安财经学院行知学院,陕西西安,710038 3. 西安石油大学计算机学院,陕西西安,710065 |
| 基金项目： | 国家自然科学基金资助项目 |
| 摘 要： | 针对用单一分类器对网络进行异常检测时存在的检测率低、虚警率高等问题,提出了一种新的融合球向量机(BVM,Ball Vector Machine)与极限学习机(ELM,Extreme Learning Machine)的异常检测方法.该方法分别用BVM与ELM对三类网络特征进行学习,通过BP神经网络训练出相应权值来融合标签.实验表明:使用该融合方法进行网络异常检测的性能要优于使用单一的BVM或ELM;相对于融合传统的SVM与BP网络的方法,融合BVM与ELM网络异常检测方法的检测率与虚警率与传统方法相当,但其训练速度快、整体性更优. |
| 关 键 词： | 网络异常检测 球向量机 极限学习机 神经网络 数据融合 |
Fusion of BVM and ELM for anomaly detection in computer networks |
|
| CAI Chang-ning,PAN hua-xian,CHENG guo-jian.Fusion of BVM and ELM for anomaly detection in computer networks[J].Journal of Xian Shiyou University,2012,27(4):97-100,119. | |
| Authors: | CAI Chang-ning PAN hua-xian CHENG guo-jian |
| Institution: | 1.Northwest Branch,Research Institute of Petroleum Exploration and Development,CNPC,Lanzhou 730020,Gansu,China;2.Xingzi College,Xi’an University of Finance and Economics,Xi’an 710038,Shaanxi,China;3.College of Computer,Xi’an Shiyou University,Xi’an 710065,Shaanxi,China) |
| Abstract: | A new network anomaly detection method is proposed in order to deal with the low detection rate and high false alarm rate of a single classifier.Ball vector machine(BVM) and extreme learning machine(ELM) is separately applied to learn three kinds of network features,and then a BP neural network is utilized to update weights,which is used to merge with the label.The experiments show that,the performance of the new fusion method is better than that of BVM or ELM.Compared to the fusion method of SVM and BP neural network,the method proposed in this paper has a similar performance in detection rate and false alarm rate,but it has a less training time and better overall performance. |
| Keywords: | network anomaly detection ball vector machine extreme learning machine neural network data fusion |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |