LSTM Learning with Bayesian and Gaussian Processing for Anomaly Detection in Industrial IoT

Di Wu, Zhongkai Jiang, Xiaofeng Xie, Xuetao Wei, Weiren Yu, Renfa Li

Research output: Contribution to journalArticlepeer-review


The data generated by millions of sensors in Industrial Internet of Things (IIoT) is extremely dynamic, heterogeneous, and large scale. It poses great challenges on the real-time analysis and decision making for anomaly detection in IIoT. In this paper, we propose a LSTM-Gauss-NBayes method, which is a synergy of the long short-term memory neural network (LSTM-NN) and the Gaussian Bayes model for outlier detection in IIoT. In a nutshell, the LSTM-NN builds model on normal time series. It detects outliers by utilising the predictive error for the Gaussian Naive Bayes model. Our method exploits advantages of both LSTM and Gaussian Naive Bayes models, which not only has strong prediction capability of LSTM for future time point data, but also achieves an excellent classification performance of Gaussian Naive Bayes model through the predictive error. Empirical studies demonstrate our solution outperforms the best-known competitors, which is a preferable choice for detecting anomalies.
Original languageEnglish
Pages (from-to)5244-5253
Number of pages10
JournalIEEE Transactions on Industrial Informatics
Issue number8
Early online date11 Nov 2019
Publication statusPublished - Aug 2020

Bibliographical note

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Funding: HuXiang Youth Talent Program; National Natural Science Foundation of China.


Dive into the research topics of 'LSTM Learning with Bayesian and Gaussian Processing for Anomaly Detection in Industrial IoT'. Together they form a unique fingerprint.

Cite this