计算机科学 ›› 2012, Vol. 39 ›› Issue (Z11): 36-38.
• 综述 • 上一篇 下一篇
张立伟 戴磊 侯一凡
出版日期:
发布日期:
Online:
Published:
摘要： 入侵检测系统需要处理大量冗余与无关数据，使得系统耗用的计算资源很大，导致系统训练时间长、实时性 差、检测效果不佳。提出一种轻量级的入侵检测技术，该技术首先采用快速相关性特征选择方法消除冗余及无关特 征，然后采用主成分分析对特征进行抽取。实验结果表明，此方法能够大量消减入侵检测系统需要处理的数据量，有 效提升了系统性能。
关键词: 快速相关性特征选择，主成分分析，C4. 5决策树
Abstract: hhe intrusion detection system deals with huge amount of data which contains redundant and noisy data eau- sing slow training and testing process,high resource consumption as well as poor detection rate. This paper proposed a lightweight intrusion detection method. This method adapts fast correlation based features selection (FCI3F) to reduce redundant and noisy data and compress data using principle component analysis (PCA). Experiments results demon- strate that the proposed method is efficiency in reducing the amount of data to be treat of and suitable for intrusion de- tection system
Key words: FCBF, PCA, C4. 5 deciding tree
张立伟 戴磊 侯一凡. 一种轻量级入侵检测技术[J]. 计算机科学, 2012, 39(Z11): 36-38. https://doi.org/
0 / / 推荐
导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks
链接本文: https://www.jsjkx.com/CN/
https://www.jsjkx.com/CN/Y2012/V39/IZ11/36
Cited
首页