eprintid: 4523 rev_number: 2 eprint_status: archive userid: 1 dir: disk0/00/00/45/23 datestamp: 2023-11-09 16:16:12 lastmod: 2023-11-09 16:16:12 status_changed: 2023-11-09 15:58:37 type: article metadata_visibility: show creators_name: Adil, S.H. creators_name: Ali, S.S.A. creators_name: Raza, K. creators_name: Hussaan, A.M. title: An improved intrusion detection approach using synthetic minority over-sampling technique and deep belief network ispublished: pub keywords: Classification (of information); Mercury (metal); Recurrent neural networks, Class imbalance problems; DBN; Deep belief network (DBN); Intrusion detection approaches; Multi layer perceptron; Multi-layer perceptron networks; Network intrusion detection; Synthetic minority over-sampling techniques, Intrusion detection note: cited By 9; Conference of 13th International Conference on New Trends in Intelligent Software Methodology Tools, and Techniques, SoMeT 2014 ; Conference Date: 22 September 2014 Through 24 September 2014; Conference Code:116901 abstract: This paper presents a network intrusion detection technique based on Synthetic Minority Over-Sampling Technique (SMOTE) and Deep Belief Network (DBN) applied to a class imbalance KDD-99 dataset. SMOTE is used to eliminate the class imbalance problem while intrusion classification is performed using DBN. The proposed technique first resolves the class imbalance problem in the KDD-99 dataset followed by DBN to estimate the initial model. The accuracy is further enhanced by using multilayer perceptron networks. The obtained results are compared with the existing best technique based on reduced size recurrent neural network. The study shows that our approach is competitive and efficient in classifying both intrusion and normal patterns in KDD-99 dataset. © 2014 The authors and IOS Press. All rights reserved. date: 2014 publisher: IOS Press official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84948783277&doi=10.3233%2f978-1-61499-434-3-94&partnerID=40&md5=95f8ccf40d3162ffa742623976dd0f66 id_number: 10.3233/978-1-61499-434-3-94 full_text_status: none publication: Frontiers in Artificial Intelligence and Applications volume: 265 pagerange: 94-102 refereed: TRUE isbn: 9781614994336 issn: 09226389 citation: Adil, S.H. and Ali, S.S.A. and Raza, K. and Hussaan, A.M. (2014) An improved intrusion detection approach using synthetic minority over-sampling technique and deep belief network. Frontiers in Artificial Intelligence and Applications, 265. pp. 94-102. ISSN 09226389