A Hybrid Approach of Fuzzy C-mean Clustering and Genetic Algorithm (GA) to Improve Intrusion Detection Rate

This paper describes a hybrid approach of Fuzzy C-means clustering and Genetic Algorithm (GA) is proposed that provides better accuracy & increases the intrusion detection rate. This approach provides better accuracy of detection as compared to K-means and FCM Clustering. With this proposed approach intrusion detection rate is improved considerably. A brief overview of a hybrid approach of genetic algorithm and fuzzy c-means clustering to improve anomaly or intrusion is presented. This paper proposes genetic algorithm and fuzzy c-means clustering to generate to detect intrusions. The goal of intrusion detection is to monitor network activities automatically, detect malicious attacks and to establish a proper architecture of the computer network security. We have been using fuzzy data mining techniques to extract patterns that represent normal behavior for intrusion detection. We describe a variety of modifications that we have made to the data mining algorithms in order to improve accuracy and efficiency.