Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 17, Issue 5, Pages 3469-3477Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3022432
Keywords
Anomaly detection; Feature extraction; Intrusion detection; Dimensionality reduction; Neural networks; Estimation; Anomaly detection; feature representation; industrial big data (IBD); long short-term memory (LSTM); variational Bayes
Categories
Funding
- National Key R&D Program of China [2017YFE0117500]
- Natural Science Foundation of Hunan Province of China [2019JJ40150]
- National Natural Science Foundation of China [61702183]
- Key R&D Project - Hunan Provincial Science & Technology Department [2019GK2131]
- Key Project of Hunan Provincial Education Department [17A113]
Ask authors/readers for more resources
The article introduces a VLSTM model to address imbalance and high-dimension issues in industrial big data, which significantly improves accuracy and reduces false positives in anomaly detection.
With the increasing population of Industry 4.0, industrial big data (IBD) has become a hotly discussed topic in digital and intelligent industry field. The security problem existing in the signal processing on large scale of data stream is still a challenge issue in industrial internet of things, especially when dealing with the high-dimensional anomaly detection for intelligent industrial application. In this article, to mitigate the inconsistency between dimensionality reduction and feature retention in imbalanced IBD, we propose a variational long short-term memory (VLSTM) learning model for intelligent anomaly detection based on reconstructed feature representation. An encoder-decoder neural network associated with a variational reparameterization scheme is designed to learn the low-dimensional feature representation from high-dimensional raw data. Three loss functions are defined and quantified to constrain the reconstructed hidden variable into a more explicit and meaningful form. A lightweight estimation network is then fed with the refined feature representation to identify anomalies in IBD. Experiments using a public IBD dataset named UNSW-NB15 demonstrate that the proposed VLSTM model can efficiently cope with imbalance and high-dimensional issues, and significantly improve the accuracy and reduce the false rate in anomaly detection for IBD according to F1, area under curve (AUC), and false alarm rate (FAR).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available