Copyright © 2025 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{164462,
        author = {K.Vigneshwar Reddy and P.Sravya Sree               and Ch. Sriram Reddy and G Rakesh Reddy   },
        title = {Hybrid Ensemble Network Intrusion Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {10},
        number = {12},
        pages = {1652-1659},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=164462},
        abstract = {In recent years, the exponential growth of networked devices has revolutionized everyday life. However, it has also attracted the attention of cybercriminals, which has caused an increase in the number and sophistication of attacks against these devices. Network Intrusion Detection System (NIDS) has become an essential part of network applications to detect such attacks. However, network devices generate huge amounts of high-dimensional data, which makes it difficult to detect known and unknown attacks with greater accuracy. Additionally, the complicated nature of network data complicates the NIDS feature selection procedure. In this work, Our proposal is an autonomous feature selection and two-stage hybrid ensemble learning machine learning-based intrusion detection system. The suggested system performs automatic feature selection based on the capacity of four distinct machine learning classifiers to identify the most important features. The hybrid ensemble learning algorithm is designed in two stages: the first stage is built using classifiers that are created by modifying the One-vs-One framework, and the second stage is built using classifiers that are created by combining different attack classes. In comparison to other similar studies found in the literature, the evaluation of the proposed framework on two well-referenced datasets for both wired and wireless applications demonstrates that the two-stage ensemble learning system paired with an automatic feature selection module has superior attack detection ability.},
        keywords = {},
        month = {},
        }