The study of Intrusion detection system plays a vital role in research due to the increasing amount of security threats. In our proposed study, the training and testing process is executed on standard dataset NSL-KDD based on neighbourhood component analysis and neural network technique, where neural network used as a classification strategy and NCA as a feature selection technique to finalize dataset features. We have used neural network to classify the network traffic in attacks and normal conditions. The objective of this paper is to study the combined impact of feature selection and classification techniques. The study aims to improve the efficiency, recognition of malicious traffic exploratory assessment performed using the parameters, viz. false positive rate, detection rate & accuracy. The experimental results of proposed method show the improvement in the detection rate, accuracy as well as false positive rate
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|