Data Clustering Optimization using Support Vector Machines
Ichrak Lafram1, Siham El Idrissi2, Aicha Marrhich3, Naoual Berbiche4, Jamila El Alami5
1Ichrak Lafram, LASTIMI Laboratory, Superior School of Technologies of Sale, Mohammadia School of Engineering, Mohamed V University City of Rabat, Morocco
2Siham El Idrissi, LASTIMI Laboratory, Superior School of Technologies of Sale, Mohammadia School of Engineering, Mohamed V University city of Rabat, Morocco.
3Aicha Marrhich, LASTIMI Laboratory, Superior School of Technologies of Sale, Mohammadia School of Engineering, Mohamed V University city of Rabat, Morocco.
4Naoual Berbiche, LASTIMI Laboratory, Superior School of Technologies of Sale, Mohammadia School of Engineering, Mohamed V University city of Rabat, Morocco.
5Jamila EL Alami, LASTIMI Laboratory, Superior School of Technologies of Sale, Mohammadia School of Engineering, Mohamed V University city of Rabat, Morocco.
Manuscript received on 13 March 2019 | Revised Manuscript received on 17 March 2019 | Manuscript published on 30 July 2019 | PP: 4453-4462 | Volume-8 Issue-2, July 2019 | Retrieval Number: B2717078219/19©BEIESP | DOI: 10.35940/ijrte.B2717.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The analysis of massive data is becoming more and more critical. One of the systems that process real-time data are computer networks. The data flowing through these networks is enormous and requires technicality to manage it better, and the most central characteristics of these systems is to ensure security. To ensure this task, administrators use intrusion detection systems (IDSs). The major problems with these systems are the false positive and the speed of the system to process data and analyze it. For this, we present an optimization of the existing methods based on artificial neural networks, through combining two machine learning procedures; unsupervised clustering followed by a supervised classification framework as a Fast, highly scalable and precise packets classification system.
Index terms: Intrusion Detection, Machine Learning, Traffic Classification, Artificial Neural Networks, Support Vector Machines, x-means
Scope of the Article: Machine Learning