An investigation of scalable anomaly detection techniques for a large network of Wi-Fi hotspots

Machaka, PBagula, A2015-08-192015-08-192015Machaka, P and Bagula, A. 2015. An investigation of scalable anomaly detection techniques for a large network of Wi-Fi hotspots. In: Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Scalable Information Systems, vol. 139, pp 71-79978-3319-168678http://link.springer.com/chapter/10.1007%2F978-3-319-16868-5_7http://hdl.handle.net/10204/8101Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Vol. 139, pp 71-79. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's websiteThe paper seeks to investigate the use of scalable machine learning techniques to address anomaly detection problem in a large Wi-Fi network. This was in the efforts of achieving a highly scalable preemptive monitoring tool for wireless networks. The Neural Networks, Bayesian Networks and Artificial Immune Systems were used for this experiment. Using a set of data extracted from a live network of Wi-Fi hotspots managed by an ISP; we integrated algorithms into a data collection system to detect anomalous performance over several test case scenarios. The results are revealed and discussed in terms of both anomaly performance and statistical significance.enPerformance MonitoringNeural NetworksArtificial Immune SystemsBayesian NetworksAnomaly Performance DetectionMultilayer PerceptronNaive BayesAIRS2An investigation of scalable anomaly detection techniques for a large network of Wi-Fi hotspotsConference PresentationMachaka, P., & Bagula, A. (2015). An investigation of scalable anomaly detection techniques for a large network of Wi-Fi hotspots. Springer. http://hdl.handle.net/10204/8101Machaka, P, and A Bagula. "An investigation of scalable anomaly detection techniques for a large network of Wi-Fi hotspots." (2015): http://hdl.handle.net/10204/8101Machaka P, Bagula A, An investigation of scalable anomaly detection techniques for a large network of Wi-Fi hotspots; Springer; 2015. http://hdl.handle.net/10204/8101 .TY - Conference Presentation AU - Machaka, P AU - Bagula, A AB - The paper seeks to investigate the use of scalable machine learning techniques to address anomaly detection problem in a large Wi-Fi network. This was in the efforts of achieving a highly scalable preemptive monitoring tool for wireless networks. The Neural Networks, Bayesian Networks and Artificial Immune Systems were used for this experiment. Using a set of data extracted from a live network of Wi-Fi hotspots managed by an ISP; we integrated algorithms into a data collection system to detect anomalous performance over several test case scenarios. The results are revealed and discussed in terms of both anomaly performance and statistical significance. DA - 2015 DB - ResearchSpace DP - CSIR KW - Performance Monitoring KW - Neural Networks KW - Artificial Immune Systems KW - Bayesian Networks KW - Anomaly Performance Detection KW - Multilayer Perceptron KW - Naive Bayes KW - AIRS2 LK - https://researchspace.csir.co.za PY - 2015 SM - 978-3319-168678 T1 - An investigation of scalable anomaly detection techniques for a large network of Wi-Fi hotspots TI - An investigation of scalable anomaly detection techniques for a large network of Wi-Fi hotspots UR - http://hdl.handle.net/10204/8101 ER -