• Rega Janasri
• Dr S. Jhansi Rani

In the previous decades, the fast development of Intrusion Detection and Prevention systems played a crucial role in computer networks and security. The Intrusion Detection Systems (IDS) helps to implement several incorporate methods to identify and find intrusive and non-intrusive actions involved in network. The most existing systems based on human experts to analyses the network traffic and system logs to identify the intrusive patterns. But it is a big problem for human to detect the intrusions for a numerous data of network traffic. An IDS has the ability to perform autonomously over the huge network without having intervention of human. The Intrusion detection techniques based on soft computing and machine learning techniques used to detect anonymous data. The IDS can be designed efficiently using soft computing techniques. The main function of Intrusion Detection System is to protect the resources from threats. It analyses and predicts the behaviors of users, and then these behaviors will be considered an attack or a normal behavior. In this paper, we analyses the results of the attacks classified using Intrusion Detection System, and the training time of machine algorithms are measured by increasing the size of the KDD dataset in intervals thereby observing the changes in the final evaluation metrics obtained

Classification, Intrusion detection system, KDD dataset, Evaluation metrics

"Intrusion detection for computer network Using machine learning algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.645-650, June 2019, Available :http://www.jetir.org/papers/JETIR1907396.pdf

"Intrusion detection for computer network Using machine learning algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp645-650, June 2019, Available at : http://www.jetir.org/papers/JETIR1907396.pdf