• Swathi B V
• Pavani G V
• Divyasri M
• Prathap Patel S R
• Rajashree D Ingale

This paper consolidates studies on the application of machine learning (ML) techniques for anomaly detection in network traffic and wireless sensor networks (WSN). Anomaly detection is crucial for network security and preventing malicious attacks or errors. The challenges in this field include handling dynamic anomalies, class imbalance, feature complexity, and the need for efficient algorithms. This paper looks at how machine learning is used to find unusual activity in computer networks and wireless sensor networks. Finding these unusual activities is important for keeping networks safe and spotting harmful attacks or mistakes. It's hard to do because unusual activity can change a lot, and it's difficult to create computer programs that can detect every type of unusual activity. This paper talks about different machine learning methods, both the kind that needs examples to learn and the kind that doesn't. The study surveys various ML techniques, including supervised and unsupervised learning approaches, for detecting anomalies in network data and WSNs.

Anomaly detection, network traffic, wireless sensor networks, machine learning, supervised learning, unsupervised learning, intrusion detection , Statistical Analysis, Classification

"Anomaly detection in network using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.e467-e472, May-2025, Available :http://www.jetir.org/papers/JETIR2505525.pdf

"Anomaly detection in network using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppe467-e472, May-2025, Available at : http://www.jetir.org/papers/JETIR2505525.pdf