Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{177157,
        author = {Nyarkisa Christopher Sebit Elias and Diko Francis Michael Peter and Omkar Pattnaik and Laureen Kalakaw George and Luany Yiek Juor},
        title = {A Comparative Study of Machine Learning and Deep Learning Methods in Anomaly Detection for Expanding Network Infrastructures},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {918-925},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177157},
        abstract = {With the increased infrastructure in IoT device networks and SDN and the necessity of the security and trustworthiness of these networks to increase, there is mounting demand for smart network traffic analysis and anomaly detection. Machine learning (ML) and deep learning are prominent components in studies in the context of anomaly detection and botnet prevention. Wong and Arjunan demonstrated scalability's importance through creating a model of deep learning-based anomaly detection for big-scale data environments. Liu and Park also illustrated the possibility of reinforcing anonymous traffic detection accuracy, and Shoman and Wang proposed a model of video captioning for intelligent transportation surveillance, in real-time. Ghamri-Douden presented a visual method for identifying botnet activity in IoT technologies, and Arnold and Gromov proposed a CNN solution for detecting botnets in IoT to reduce the vulnerabilities of IoT. These studies illustrate the importance of AI-based techniques for the quick identification of botnet attacks.},
        keywords = {Supervision training, Neural Networks, Intrusion Detection Systems (IDS)},
        month = {May},
        }