Hierarchical Temporal Memory Method for Time-Series-Based Anomaly Detection

Time-series-based anomaly detection is a quite important field that has been researched over years. Many techniques have been developed and applied successfully for certain application domains. However, there are still some challenges, such as continuously learning, tolerance to noise and generaliza...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW) pp. 1167 - 1172
Main Authors Jia Wu, Weiru Zeng, Zhe Chen, Xue-Fei Tang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2016
Subjects
Algorithm design and analysis
anomaly detection
biological neural network
Detection algorithms
hierarchical temporal memory
Measurement
Neurons
Prediction algorithms
Robustness
Rocks
Online AccessGet full text

Cover

More Information
Summary:Time-series-based anomaly detection is a quite important field that has been researched over years. Many techniques have been developed and applied successfully for certain application domains. However, there are still some challenges, such as continuously learning, tolerance to noise and generalization. This paper present Hierarchical Temporal Memory, a novel biological neural network, to time-series-based anomaly detection. HTM is able to learn the changing pattern of the data and incorporate contextual information from the past to make accurate prediction. We have evaluated HTM on real and artificial datasets. The experiment results show that HTM can successfully discover anomalies in time-series data.
ISSN:2375-9259
DOI:10.1109/ICDMW.2016.0168