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{188384,
        author = {D. Navigneshkumar},
        title = {A TWO-LEVEL ENSEMBLE LEARNING FRAMEWORK FOR IMPROVED ACCURACY AND REDUCED FALSE ALARMS IN NETWORK INTRUSION DETECTION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {2485-2489},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188384},
        abstract = {As cyber threats grow increasingly sophisticated, robust network security demands adaptive intrusion detection systems (IDS). Traditional machine learning-based IDS often struggle with high false alarm rates and poor generalization to emerging attacks, while deep learning-based IDS offer high detection accuracy but require significant computational resources. Ensemble learning techniques provide an effective balance between efficiency and accuracy, improving detection through model diversity and decision aggregation. This review explores ensemble-based intrusion detection systems, emphasizing diverse aggregation techniques, including homogeneous and heterogeneous ensemble methods. It provides an in-depth analysis of feature selection strategies, data balancing techniques, and classification models, offering a comparative assessment across benchmark datasets. Additionally, the study highlights key challenges and outlines futureresearch directions to advance ensemble learning in network intrusion detection.},
        keywords = {Ensemble Learning, NIDS, Feature Selection, Machine Learning, Data Imbalance.},
        month = {December},
        }