International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Hybrid Boosted Forest Approach for Intrusion Detection in High Velocity Networks Using SMOTE and Chi-Square Feature Selection |
|---|---|
| ABSTRACT | The rapid expansion of high-velocity networks driven by cloud computing, Internet of Things (IoT) devices, and large-scale enterprise infrastructures has rendered intrusion detection both a critical necessity and a formidable challenge. Conventional Intrusion Detection Systems (IDS) struggle with two persistent limitations: highly imbalanced datasets, in which rare but critical attack classes are underrepresented, and redundant or noisy feature spaces, which increase computational overhead and reduce classification accuracy. This paper proposes a Hybrid Boosted Forest Approach that integrates three complementary techniques. The Synthetic Minority Oversampling Technique (SMOTE) addresses class imbalance by generating synthetic minority-class samples. Chi-Square feature selection eliminates statistically irrelevant attributes, reducing dimensionality and improving efficiency. A boosted forest ensemble combining Random Forest and Gradient Boosting provides robust, scalable classification resilient to overfitting. Experiments conducted on the UNSW-NB15 benchmark dataset validate the proposed approach. The optimised model achieves 98.30% accuracy, precision of 98.30%, recall of 98.30%, F1-score of 98.29%, and an RMSE of 0.1305, outperforming existing methods. These results demonstrate the framework's suitability for real-time deployment in high-velocity network environments. |
| AUTHOR | MUMMAREDDY BALA SOWMYA M. Tech Scholar, Department of CSE, Sir C R Reddy College of Engineering, Eluru, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405012 |
| pdf/12_A Hybrid Boosted Forest Approach for Intrusion Detection in High Velocity Networks Using SMOTE and Chi-Square Feature Selection.pdf | |
| KEYWORDS | |
| References | [1] A. Ahmim, L. Maglaras, M. A. Ferrag, M. Derdour, and H. Janicke (2019) A novel hierarchical Intrusion detection system based on decision tree and rules-based models. In: 2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS), Santorini Island, Greece, Greece, 29–31 May 2019. [2] Saber M, Chadli S, Emharraf M, El Farissi I (2015) Modeling and implementation approach to evaluate the intrusion detection system. In: International conference on networked systems, pp 513–517. [3] Lin W-C, Ke S-W, Tsai C-F (2015) CANN: an intrusion detection system based on combining cluster centers and nearest neighbors. Knowl based Syst 78:1321. [4] Zhang J, ZulkernineM (2006) A hybrid network intrusion detection technique using random forests. In: First international conference on availability, reliability and security(ARES’06),2006,p8. [5] DhaliwalSS,NahidA-A,AbbasR(2018).AneffectiveintrusiondetectionsystemusingXGBoost. Information9(7):149 |
