Abstract—Network devices including firewall, QoS, Anti-Virus wall, IDS and so on were developed to help administrators monitor internet usage behaviors in response to network applications. However, it requires administrators to log on different network devices for acquiring associated usage logs for further respective analysis whenever abnormal network usage behavior occurred. It is both difficult and time consuming for administrators to manage usage logs from all the devices within a network. Therefore, how to provide administrators integrated information through one single platform for more effective management and efficient data inquiry is the aim of this research. This study proposed the measure that the usage logs from network devices can be stored in the data warehouse where the necessary information within a specific timeframe was acquired by business intelligence system for further comparison and integration. It can save the time for log inquiries and assist efficient network users behavior analysis.
Index Terms—Audit, business intelligence, network security.
W. Y. Chen is with the Department of Information Management, Tatung University and also with the Department of Mass Communication, Chinese Culture University, Taipei, Taiwan (e-mail: firstname.lastname@example.org).
S. H. Li is with the Department of Accounting Information, National Taipei University of Business, Taipei, Taiwan (e-mail: email@example.com).
M. J. Hsiao is with the Department of Information Management, Kang-Ning Junior College of Medical Care and Management, Taipei, Taiwan (e-mail: firstname.lastname@example.org).
C. C. Hu is with the Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan (e-mail: email@example.com).
K. C. Tu is with the Department of Information Management, Tatung University, Taipei, Taiwan (e-mail: firstname.lastname@example.org).
Cite: Wei-Yu Chen, Shing-Han Li, Mann-Jung Hsiao, Chung-Chiang Hu, and Kuo-Ching Tu, "Network Security Analysis by Using Business Intelligence," International Journal of Machine Learning and Computing vol.5, no. 6, pp. 431-438, 2015.