Anomaly Detection in Time Series data using Hierarchical Temporal Memory Model

In this data-driven world, the Anomaly detection technique plays a key role in various domains. Since the amount of generated data is huge, conventional anomaly detection techniques using batch processing are inefficient since the cost of storing and processing large amounts of data incurs various costs. Therefore, the best algorithm for this task should be able to detect anomalies in a real-time manner and with no human intervention. In this paper, we discuss the application of the Hierarchical Temporal Memory algorithm to detect anomalies in real time and in an unsupervised manner. We applied this algorithm to the stock market dataset and analyzed the performance. We also applied the algorithm on an artificially created dataset with a known point anomaly. This work tests the performance of the algorithm for real-world applications and detects anomalies.

[1]  Shilin He,et al.  Experience Report: System Log Analysis for Anomaly Detection , 2016, 2016 IEEE 27th International Symposium on Software Reliability Engineering (ISSRE).

[2]  Ernest Fokoué,et al.  A Mathematical Formalization of Hierarchical Temporal Memory’s Spatial Pooler , 2017, Front. Robot. AI.

[3]  Subutai Ahmad,et al.  Properties of Sparse Distributed Representations and their Application to Hierarchical Temporal Memory , 2015, ArXiv.

[4]  Scott Purdy.  Encoding Data for HTM Systems , 2016, ArXiv.

[5]  Yuwei Cui,et al.  The HTM Spatial Pooler – a neocortical algorithm for online sparse distributed coding , 2016, bioRxiv.

[6]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[7]  Subutai Ahmad,et al.  Unsupervised real-time anomaly detection for streaming data , 2017, Neurocomputing.

[8]  V. P. Mohandas,et al.  Modeling and predicting stock returns using the ARFIMA-FIGARCH , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[9]  Subutai Ahmad,et al.  Why Neurons Have Thousands of Synapses, a Theory of Sequence Memory in Neocortex , 2015, Front. Neural Circuits.

[10]  P. Bagavathi Sivakumar,et al.  Efficient Real-Time Decision Making Using Streaming Data Analytics in IoT Environment , 2019 .

[11]  Kerrie Mengersen,et al.  A framework for automated anomaly detection in high frequency water-quality data from in situ sensors. , 2018, The Science of the total environment.

[12]  Vipin Kumar,et al.  Comparative Evaluation of Anomaly Detection Techniques for Sequence Data , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[13]  George K. Karagiannidis,et al.  An Improved Approximation for the Gaussian Q-Function , 2007, IEEE Communications Letters.