As the network architecture becomes more and more complex, network intrusion behavior tends to diversify. In view of the characteristics that the era of big data is coming, it is imperative to find tools that can better protect current network security. In order to solve this problem, this paper proposes an improved K-means algorithm in the field of intrusion detection for network security, which is based on Intersection over Union in order to optimize initial clustering centers, with the consideration that the more different the data are, the more suitable the data act as the initial cluster centers. Experimental results show that, the improved K-means algorithm is superior to the original K-means algorithm in terms of overall precision, recall rate and F1_score under the same number of iterations through the data set of KDD CUP99.
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL
₹10000 (INR)
2019