Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 18, Issue 9, Pages 5728-5737Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2022.3155656
Keywords
Industrial Internet of Things; Data models; Deep learning; Security; Hidden Markov models; Predictive models; Informatics; Deep generative model (DGM); generative adversarial networks (GANs); industrial Internet of Things (IIoT); survey
Categories
Funding
- Spanish Ministry of Economy and Competitiveness [PID2019-109644RB-I00/AEI]
- ERIC [LifeWatch-2019-10-UGR-01]
Ask authors/readers for more resources
This article reviews the latest technologies and applications of deep generative models (DGMs) in industrial Internet of Things (IIoT), categorizing the discussed works into application areas such as anomaly detection, trust-boundary protection, network traffic prediction, and platform monitoring. After analyzing existing implementations, challenges that need to be addressed are identified, and potential research directions are proposed.
Advances in communication technologies and artificial intelligence are accelerating the paradigm of industrial Internet of Things (IIoT). With IIoT enabling continuous integration of sensors and controllers with the network, intelligent analysis of the generated Big Data is a critical requirement. Although IIoT is considered a subset of IoT, it has its own peculiarities in terms of higher levels of safety, security, and low-latency communication in an environment of critical real-time operations. Under these circumstances, discriminative deep learning (DL) algorithms are unsuitable due to their need for large amounts of labeled and balanced training data, uncertainty of inputs, etc. To overcome these issues, researchers have started using deep generative models (DGMs), which combine the flexibility of DL with the inference power of probabilistic modeling. In this article, we review the state of the art of DGMs and their applicability to IIoT, classifying the reviewed works into the IIoT application areas of anomaly detection, trust-boundary protection, network traffic prediction, and platform monitoring. Following an analysis of existing IIoT DGM implementations, we identify challenges (i.e., weak discriminative capability, insufficient interpretability, lack of generalization ability, generated data vulnerability, privacy concern, and data complexity) that need to be investigated in order to accelerate the adoption of DGMs in IIoT and also propose some potential research directions.
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