\r\nproblems, we propose the use of Hierarchical Temporal Memory

\r\nAlgorithm (HTM) which is a real time anomaly detection algorithm.

\r\nHTM is a cortical learning algorithm based on neocortex used for

\r\nanomaly detection. In other words, it is based on a conceptual theory

\r\nof how the human brain can work. It is powerful in predicting unusual

\r\npatterns, anomaly detection and classification. In this paper, HTM

\r\nhave been implemented and tested on ECG datasets in order to detect

\r\ncardiac anomalies. Experiments showed good performance in terms

\r\nof specificity, sensitivity and execution time.","references":"[1] Chandola, V., Banerjee, A. and Kumar, V. (2009). Anomaly detection: A\r\nsurvey, ACM Computing Surveys (CSUR). 41(3), 1\u201372.\r\n[2] Acuna, E. and Rodriguez, C. (2004). A meta analysis study of outlier\r\ndetection methods in classification, Technical paper, Department of\r\nMathematics, University of Puerto Rico at Mayaguez.\r\n[3] Chandore, P. R. and Chatur, D. P. N. (2013). Hybrid approach for\r\noutlier detection over wireless sensor network real time data. International\r\nJournal Of Computer Science And Applications, 6(2).\r\n[4] Malhotra, P., Vig, L., Shroff, G. and Agarwal, P. (2015, April). Long\r\nshort term memory networks for anomaly detection in time series. In\r\nProceedings (p. 89). Presses universitaires de Louvain.\r\n[5] Jankov, D., Sikdar, S., Mukherjee, R., Teymourian, K. and Jermaine, C.\r\n(2017, June). Real-time High Performance Anomaly Detection over Data\r\nStreams: Grand Challenge. In Proceedings of the 11th ACM International\r\nConference on Distributed and Event-based Systems (pp. 292-297). ACM.\r\n[6] Loganathan, G., Samarabandu, J. and Wang, X. (2018, May). Sequence to\r\nSequence Pattern Learning Algorithm for Real-Time Anomaly Detection\r\nin Network Traffic. In 2018 IEEE Canadian Conference on Electrical and\r\nComputer Engineering (CCECE) (pp. 1-4). IEEE.\r\n[7] Edgeworth, F. Y. (1887). On discordant observations, Philosophical\r\nMagazine. To Appear in ACM Computing Surveys, 09 2009. 23(5),\r\n364\u2013375.\r\n[8] Ahmad, S., Lavin, A., Purdy, S. and Agha, Z. (2017). Unsupervised\r\nreal-time anomaly detection for streaming data. Neurocomputing.\r\n[9] Lavin, A. and Ahmad, S. (2015). Evaluating Real-Time Anomaly\r\nDetection Algorithms\u2013The Numenta Anomaly Benchmark. In Machine\r\nLearning and Applications (ICMLA), 2015 IEEE 14th International\r\nConference on (pp. 38-44). IEEE.\r\n[10] Ahmad, S. and Purdy, S. (2016). Real-Time Anomaly Detection for\r\nStreaming Analytics. arXiv preprint arXiv:1607.02480.\r\n[11] Kerner, M. and Tammeme K. (2017). Hierarchical temporal memory\r\nimplementation on FPGA using LFSR based spatial pooler address space\r\ngenerator. In Design and Diagnostics of Electronic Circuits and Systems\r\n(DDECS), 2017 IEEE 20th International Symposium on pp. 92\u201395. IEEE.\r\n[12] M. Putic,A. J. Varshneya and M. R. Stan (2017). Hierarchical Temporal\r\nMemory on the Automata Processor. IEEE Micro, 37(1), 52-59.\r\n[13] Fan, D., Sharad, M., Sengupta, A., and Roy, K. (2016). Hierarchical\r\ntemporal memory based on spin-neurons and resistive memory for\r\nenergy-efficient brain-inspired computing. IEEE transactions on neural\r\nnetworks and learning systems, 27(9), 1907-1919.\r\n[14] Hawkins, J., and Ahmad, S. (2016). Why neurons have thousands of\r\nsynapses, a theory of sequence memory in neocortex. Frontiers in neural\r\ncircuits, 10.\r\n[15] Ahmad, S., and Hawkins, J. (2016). How do neurons operate on sparse\r\ndistributed representations? A mathematical theory of sparsity, neurons\r\nand active dendrites. arXiv preprint arXiv:1601.00720. [16] Wu, J., Zeng, W., Chen, Z., and Tang, X. F. (2016, December).\r\nHierarchical Temporal Memory Method for Time-Series-Based Anomaly\r\nDetection. In Data Mining Workshops (ICDMW), 2016 IEEE 16th\r\nInternational Conference on (pp. 1167-1172). IEEE.\r\n[17] Nouira, K. and Trabelsi, A. (2012). Intelligent monitoring system for\r\nintensive care units. Journal of medical systems, 36(4), 2309-2318.\r\n[18] Hawkins, J., Ahmad, S. and Dubinsky, D. (2011). Cortical learning\r\nalgorithm and hierarchical temporal memory, Numenta Whitepaper, 1-68.\r\n[19] Antic, S. D., Zhou,W. L., Moore, A. R., Short, S. M. and Ikonomu, K. D.\r\n(2010). The decade of the dendritic NMDA spike, Journal of neuroscience\r\nresearch, 88(14), 2991-3001.\r\n[20] Major, G., Larkum, M. E. and Schiller, J. (2013). Active properties of\r\nneocortical pyramidal neuron dendrites. Annual review of neuroscience,\r\n36, 1-24.\r\n[21] Cui, Y., Ahmad, S. and Hawkins, J. (2016). Continuous online sequence\r\nlearning with an unsupervised neural network model. Neural computation,\r\n28(11), 2474-2504.\r\n[22] Chen, X., Li, B., Shamsabardeh, M., Proietti, R., Zhu, Z. and Yoo,\r\nS. J. B. (2018, March). On real-time and self-taught anomaly detection\r\nin optical networks using hybrid unsupervised\/supervised learning. In\r\nEuropean Conf. Optical Communications.\r\n[23] A. Frank and A. Asuncion (2013). UCI machine learning repositor,\r\nhttp:\/\/archive.ics.uci.edu\/ml.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 149, 2019"}