Open Access Open Access  Restricted Access Subscription Access
Cover Image

An Intelligent Temporal Adaptive Genetic Fuzzy Classification Algorithm for Effective Intrusion Detection

Brindha Devi.V., Shunmuganathan K. L.


Intrusion detection systems (IDSs) areplaying a major role for detecting the various types of attacks on. computer network traffic and computer usage which is difficult to detect by a conventional security mechanisms Recently, most of the IDSs are developed based on data mining and machine learning techniques. In the past, the combination of fuzzy logic and genetic algorithms were used to discover fuzzy association rules that can be applied to detect intrusions. However, the existing systems have not achieved the required detection accuracy. For achieving better detection accuracy,we propose an Intelligent Temporal Adaptive Genetic Fuzzy Classification Algorithm (ITAGFCA) which can optimize rules and membership functions for providing effective network data classification. The aims of this research work are 1) Generating rules from data and to select optimal number of rules using genetic algorithms. 2) Proposing a simple technique for scheming of membership function and Discretization, and 3) Designing a fitness function by allowing the frequency of occurrence of the rules in the training data. This system establishes the efficiency of the proposed classifier by evaluation. The experimental results based on the NSL-KDD-Cup 99 dataset show that the proposed ITAGFS is not only performing better than the existing classifiers in terms of classification accuracy, detection rates, and false alarms.

Full Text:



  • There are currently no refbacks.