• G.Mahalakshmi
• Dr.E.Uma

The network is a key in the modern world thereby controlling all human activities, where all the communications are happening via the internet. Since people rely on digital communication of pieces of information, creates the necessity for security. The Information passing over the air fabricates the information threat or attack on the network. From this, it is understandable the vital of rendering security to prevent attacks or threats. There are various security mechanisms are available like firewalls, anti-virus, IDSs, and many others. The most commonly used mechanism is Intrusion Detection System. There are different flavors of IDSs available. In this paper, a Network-based Anomaly Detection System is proposed. An intrusion detection system utilizing machine learning-based classification makes for an effective decision-making process for identifying the attacker nodes. The proposed IDS uses the novel machine learning algorithm for classifying the normal data packets and attacker data packets. The proposed system aims in reducing the False Positive rate and Increasing the packet delivery ratio.

IDS, Chi2FSACA, False Positive, Packet Delivery Ratio

"Anomaly Based Intrusion Detection System Using Machine Learning Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.f777-f799, April-2022, Available :http://www.jetir.org/papers/JETIR2204599.pdf

"Anomaly Based Intrusion Detection System Using Machine Learning Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppf777-f799, April-2022, Available at : http://www.jetir.org/papers/JETIR2204599.pdf