融合PCA和LDA的入侵检测算法

Fusion of PCA and LDA for Intrusion Detection

针对目前单个IDS在入侵特征提取和检测效率上存在的问题,提出了一种融合主成分分析(PCA)和线性判别分析(LDA)的入侵检测算法。利用PCA和LDA提取入侵特征,通过KNN分类器给出初步的识别结果,接着采用D-S证据理论对识别结果进行融合,得出最终识别结果。通过在KDD CUP’99的标准入侵检测数据集上的实验表明,该方法提高了入侵检测率,同时降低了误报率,性能优于单一的分类器。

To solve the difficulty of feature extraction and the low performance in single IDS,an intrusion detection method based on the fusion of principal component analysis（PCA）and liner discriminate analysis（LDA）is presented. Firstly, PCA and LDA is applied to network intrusion feature extraction. Then, initial intrusion detection result is done by two KNN classifiers. Next, the D - S evidence theory is adopted to fuse these results for two classifiers can overcome the shortcomings of each other. Experiment has been done on dataset in KDD- 99 and the results show that the performance of the proposed method is superior to that of the single classifier.