A Study of Intrusion Detection System (IDS) through Machine Learning Algorithm
ID, machine learning, NSL-KDD dataset, feature selection.
Due to the advancement of internet, the number of attacks over internet has also increased. To ensure the security of a network a good Intrusion Detection System (IDS) is required. The aim of IDS is to monitor the processes prevailing in a network and to analyse them for signs of any possible deviations. Some studies have been done in this field but a deep and exhaustive work has still not been done. This paper proposes an IDS using machine leaning for network with a good union of feature selection technique and classifier by studying the combinations of most of the popular feature selection techniques and classifiers. A set of significant features is selected from the original set of features using feature selection techniques and then the set of significant features is used to train different types of classifiers to make the IDS. Intrusion detection is performed on the dataset which contain Test data and Training data. It is finally observed that K-NN classifier produces better performance than others and, among the feature selection methods, information gain ratio based feature selection method is better.
"A Study of Intrusion Detection System (IDS) through Machine Learning Algorithm", IJNRD - INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (www.IJNRD.org), ISSN:2456-4184, Vol.8, Issue 3, page no.d227-d231, March-2023, Available :https://ijnrd.org/papers/IJNRD2303333.pdf
Volume 8
Issue 3,
March-2023
Pages : d227-d231
Paper Reg. ID: IJNRD_189356
Published Paper Id: IJNRD2303333
Downloads: 000118910
Research Area: Computer Engineering
Country: Ghaziabad, Uttar Pradesh, India
DOI: http://doi.one/10.1729/Journal.33436
ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJNRD (IJ Publication) Janvi Wave
