Emerging Trends of ML-based Intelligent Services for Industrial Internet of Things (IIoT)
Authors:
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 135-139
Abstract
Intelligent information technology is a notable feature in the context of industry 4.0. A key factor in obtaining intelligent industrial Internet of things (IIoT) services is to integrate machine learning (ML) into IIoT. With the increasing scale of deployed terminals, IIoT becomes heterogeneous, diverse, and dynamically changeable. Traditional optimization methods are difficult to deal with the emerging network problems. This paper first proposes a ML-based IIoT architecture for intelligent IIoT services and expounds two ML methods for IIoT analysis, namely, deep learning (DL) and reinforcement learning (RL). Secondly, advanced applications and development trends of ML in industrial field are summarized. Opportunities and challenges of ML for IIoT analysis are discussed finally. The purpose of this paper is to point out the role of artificial intelligence (AI) technology in IIoT from the macroscopic view.Keywords
This publication has 21 references indexed in Scilit:
- RescueNet: Reinforcement-learning-based communication framework for emergency networkingComputer Networks, 2016
- Internet of Things to Smart IoT Through Semantic, Cognitive, and Perceptual ComputingIEEE Intelligent Systems, 2016
- Machine learning: Trends, perspectives, and prospectsScience, 2015
- Deep learningNature, 2015
- Human-level control through deep reinforcement learningNature, 2015
- Context-aware vehicular cyber-physical systems with cloud support: architecture, challenges, and solutionsIEEE Communications Magazine, 2014
- From machine learning to machine reasoningMachine Learning, 2013
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Using Feedback in Collaborative Reinforcement Learning to Adaptively Optimize MANET RoutingIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2005
- A knowledge plane for the internet2003