An Unsupervised Real-time Anomaly Detection of Furnace System based on HTM

@article{ART002418263},
author={ Ky Vannroath and 배종민 and 강현석 },
title={An Unsupervised Real-time Anomaly Detection of Furnace System based on HTM},
journal={한국지식정보기술학회 논문지},
issn={1975-7700},
year={2018},
volume={13},
number={6},
pages={657-664},
doi={10.34163/jkits.2018.13.6.002},
url={http://dx.doi.org/10.34163/jkits.2018.13.6.002}

TY - JOUR
AU - Ky Vannroath
AU - 배종민
AU - 강현석
TI - An Unsupervised Real-time Anomaly Detection of Furnace System based on HTM
T2 - 한국지식정보기술학회 논문지
PY - 2018
VL - 13
IS - 6
PB - 한국지식정보기술학회
SP - 657-664
SN - 1975-7700
AB - The immediate recognition of abnormal temperatures in the furnace system is very important for timely disaster control. Conventional abnormal temperature detection techniques typically use pre-programmed thresholds to identify abnormal patterns from a stream of temperature data in a statistical manner. Therefore, it is not suitable for use in a heating furnace system in which abnormal patterns must be detected in real time. Hierarchical Temporal Memory (HTM) is one of the machine learning models with excellent ability to analyze patterns of stream data. This model is a new machine intelligence technique that uses unsupervised continuous learning using Cortical Learning Algorithm (CLA), which is a time-based learning algorithm, and Spare Distributed Representation (SDR), which stores temporal and spatial patterns. This HTM, which is distinguished from existing deep learning or artificial neural network model, is capable of real-time continuous prediction from input of stream data and can be used to recognize abnormal states in various fields. HTM can be used as a robust model to detect abnormalities in successive temperature data in a heating furnace system because the furnace system continues to generate temperature stream data with a certain pattern over time. Here we developed an HTM-based, unsupervised, real-time anomaly detection system for heating furnaces. Performance evaluation shows that the suggested system can perform excellent abnormal real-time detection.
KW - Anomaly detection, Real-time, Unsupervised, Furnace systems, HTM, Machine learning
DO - 10.34163/jkits.2018.13.6.002
UR - http://dx.doi.org/10.34163/jkits.2018.13.6.002
ER -

Ky Vannroath , 배종민 and 강현석 (2018). An Unsupervised Real-time Anomaly Detection of Furnace System based on HTM. 한국지식정보기술학회 논문지, 13( 6), 657- 664.

Ky Vannroath , 배종민 and 강현석 . 2018, “An Unsupervised Real-time Anomaly Detection of Furnace System based on HTM”, 한국지식정보기술학회 논문지, vol. 13, no. 6, pp. 657-664. Available from: doi:10.34163/jkits.2018.13.6.002

Ky Vannroath 배종민 et al. 강현석 “An Unsupervised Real-time Anomaly Detection of Furnace System based on HTM” 한국지식정보기술학회 논문지 13.6 pp. 657-664 (2018): 657.

Ky Vannroath , 배종민 , 강현석 . An Unsupervised Real-time Anomaly Detection of Furnace System based on HTM 한국지식정보기술학회 논문지 [Internet]. 2018; 13( 6), : 657-664. Available from: doi:10.34163/jkits.2018.13.6.002

Ky Vannroath , 배종민 and 강현석 . “An Unsupervised Real-time Anomaly Detection of Furnace System based on HTM” 한국지식정보기술학회 논문지 13, no.6 (2018): 657-664. doi: 10.34163/jkits.2018.13.6.002

홈 권호 목록 논문 목록 논문 상세

An Unsupervised Real-time Anomaly Detection of Furnace System based on HTM

한국지식정보기술학회 논문지

약어 : 한국지식정보기술학회 논문지

2018, vol.13, no.6, pp.657 - 664

DOI : 10.34163/jkits.2018.13.6.002

발행기관 : 한국지식정보기술학회

연구분야 : 학제간연구

Ky Vannroath¹ , 배종민² , 강현석³

¹경상대학교

²경상대학교

³경상대학교

인용한 논문 수 : 1 서지 간략 보기

초록

The immediate recognition of abnormal temperatures in the furnace system is very important for timely disaster control. Conventional abnormal temperature detection techniques typically use pre-programmed thresholds to identify abnormal patterns from a stream of temperature data in a statistical manner. Therefore, it is not suitable for use in a heating furnace system in which abnormal patterns must be detected in real time. Hierarchical Temporal Memory (HTM) is one of the machine learning models with excellent ability to analyze patterns of stream data. This model is a new machine intelligence technique that uses unsupervised continuous learning using Cortical Learning Algorithm (CLA), which is a time-based learning algorithm, and Spare Distributed Representation (SDR), which stores temporal and spatial patterns. This HTM, which is distinguished from existing deep learning or artificial neural network model, is capable of real-time continuous prediction from input of stream data and can be used to recognize abnormal states in various fields. HTM can be used as a robust model to detect abnormalities in successive temperature data in a heating furnace system because the furnace system continues to generate temperature stream data with a certain pattern over time. Here we developed an HTM-based, unsupervised, real-time anomaly detection system for heating furnaces. Performance evaluation shows that the suggested system can perform excellent abnormal real-time detection.

키워드

Anomaly detection, Real-time, Unsupervised, Furnace systems, HTM, Machine learning

참고문헌(16)

[단행본] K. Korb / 2011 / Bayesian artificial intelligence, Chapman & Hall CRC Computer Science and Data Analysis / CRC Press
[학술대회] A. Soule / 2005 / Combining filtering and statistical methods for anomaly detection / Proceedings of the 5th ACM SIGCOMM Conference on Internet Measurement : 31
[학술대회] V. Chandola / 2008 / Comparative evaluation of anomaly detection techniques for sequence data / Proceedings of the 2008 8th IEEE International Conference on Data Mining : 743 ~ 748
[학술지] H. Akouemo / 2015 / Probabilistic anomaly detection in natural gas time series data / International Journal of Forecast : 948 ~ 956
[학술대회] M. Çelik / 2011 / Anomaly detection in temperature data using DBSCAN algorithm / International Symposium on Innovations in Intelligent Systems and Applications : 91 ~ 95
[학술지] Z. Zhao / 2015 / Ensemble algorithms for unsupervised anomaly detection / Lecture Notes in Computer Science 9101 : 514 ~ 525
[단행본] V. Mountcastle / 1997 / The columnar organization of the neocortex / Oxford University Press : 701 ~ 722
[단행본] J. Hawkins / 2012 / On intelligence / Times Books Henry Holt and Company
[인터넷자료] J. Hawkins / Hierarchical temporal memory (HTM)
[인터넷자료] S. Purdy / Encoding data for HTM systems
[학술지] Y. Cui / 2017 / The HTM spatial pooler - A neocortical algorithm for online sparse distributed coding / Frontiers in Computational Neuroscience 110 : 1 ~ 15
[학술지] Y. Cui / 2016 / Continuous online sequence learning with an unsupervised neural network model / Neural Computation 28 : 2474 ~ 2504
[인터넷자료] S. Ahmad / Properties of sparse distributed representations and their application to hierarchical temporal memory
[학술지] Y. LeCun / 2015 / Deep learning / Nature 521 : 436 ~ 444
[학술지] R. Douglas / 2004 / Neuronal circuits of the neocortex / Annual Review of Neuroscience 27 : 419 ~ 451
[학위논문] K. Vannroath / 2018 / An unsupervised real-time anomaly detection application of furnace system based on HTM