Machaka, PBagula, ANelwamondo, Fulufhelo V2017-07-282017-07-282016-11Machaka, P., Bagula, A. and Nelwamondo, F.V. 2016. Using exponentially weighted moving average algorithm to defend against DDoS attacks. 2016 International Conference on Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech), 30 November to 2 December 2016, Stellenbosch, South Africa, Cape Town. 10.1109/RoboMech.2016.7813157978-1-5090-3336-2http://ieeexplore.ieee.org/document/7813157/10.1109/RoboMech.2016.7813157http://hdl.handle.net/10204/93162016 International Conference on Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech), 30 November to 2 December 2016, Stellenbosch, South Africa, Cape TownThis paper seeks to investigate the performance of the Exponentially Weighted Moving Average (EWMA) for mining big data and detection of DDoS attacks in Internet of Things (IoT) infrastructure. The paper will investigate the tradeoff between the algorithm’s detection rate, false alarm and detection delay. The paper seeks to further investigate how the performance of the algorithm is affected by the tuning parameters and how various network attack intensity affect its performance. The performance results are analyzed and discussed and further suggestion is also discussed.enChange detectionDistributed denial of serviceTCP-SYN floodingExponentially weighted moving averageEWMA2016 International Conference on Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech)Conference PresentationMachaka, P., Bagula, A., & Nelwamondo, F. V. (2016). Using exponentially weighted moving average algorithm to defend against DDoS attacks. IEEE. http://hdl.handle.net/10204/9316Machaka, P, A Bagula, and Fulufhelo V Nelwamondo. "Using exponentially weighted moving average algorithm to defend against DDoS attacks." (2016): http://hdl.handle.net/10204/9316Machaka P, Bagula A, Nelwamondo FV, Using exponentially weighted moving average algorithm to defend against DDoS attacks; IEEE; 2016. http://hdl.handle.net/10204/9316 .TY - Conference Presentation AU - Machaka, P AU - Bagula, A AU - Nelwamondo, Fulufhelo V AB - This paper seeks to investigate the performance of the Exponentially Weighted Moving Average (EWMA) for mining big data and detection of DDoS attacks in Internet of Things (IoT) infrastructure. The paper will investigate the tradeoff between the algorithm’s detection rate, false alarm and detection delay. The paper seeks to further investigate how the performance of the algorithm is affected by the tuning parameters and how various network attack intensity affect its performance. The performance results are analyzed and discussed and further suggestion is also discussed. DA - 2016-11 DB - ResearchSpace DP - CSIR KW - Change detection KW - Distributed denial of service KW - TCP-SYN flooding KW - Exponentially weighted moving average KW - EWMA KW - 2016 International Conference on Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech) LK - https://researchspace.csir.co.za PY - 2016 SM - 978-1-5090-3336-2 T1 - Using exponentially weighted moving average algorithm to defend against DDoS attacks TI - Using exponentially weighted moving average algorithm to defend against DDoS attacks UR - http://hdl.handle.net/10204/9316 ER -