- 期刊
A Hybrid-based Feature Selection Method for Intrusion Detection System
摘要
As we know, feature selection can improve the performance of machine learning algorithms for intrusion detection. This paper proposes a hybrid feature selection method, which ranks features according to two factors: relevancy and redundancy, and then adopts the forward search strategy to select the optimal feature subset from the ranked features. Experiments on the KD-DCup' 99 dataset showed that our proposed feature selection method could get better performance on the accuracy rate and false positive rate in intrusion detection compared with other feature selection approaches.
延伸閱讀
- 李維（2020）。A Network Intrusion Detection System Using Hybrid Neural Network Models〔碩士論文，逢甲大學〕。華藝線上圖書館。https://doi.org/10.6341/fcu.M0720919
- 李思翰（2019）。An Intrusion Detection System based on Hybrid Machine Learning for Software Defined Networks〔碩士論文，淡江大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0002-2502201917205100
- 蔡秉任（2014）。Hybrid Intrusion Detection System Toward Unknown Attack Classification〔碩士論文，國立交通大學〕。華藝線上圖書館。https://doi.org/10.6842/NCTU.2014.00936
- Liao, J. M. (2017). A Hybrid Intrusion Detection System for Contemporary Network Intrusion Dataset [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU201700042
- 陳則宏、陳羿霖、張維晏、蔡崇煒（2019）。A Hybrid Classification Algorithm for Intrusion Detection System。資訊安全通訊，25(1)，14-27。https://www.airitilibrary.com/Article/Detail?DocID=a0000270-201902-201903150006-201903150006-14-27