An intrusion detection method based on rough set and SVM algorithm
Hong Jian Peng, Dongna Zhang, Tiefeng Wu · 2004
This paper proposes an intrusion detection method that combines rough sets and SVM algorithm. By virtue of the ability rough sets have to decrease the amount of data and get rid of redundancy, the method can reduce the amount of training data and overcome the SVM defect of slow running speed when processing large datasets. At the same time, by the aid of the SVM algorithm the method can classify the core of the property set to have extensiveness and high identification rate, and avoid disturbances. Experimental results show this method is better than other methods reported in the literature in terms of detection resolution.