mca 23(3): e5

Research Article

Deep Model Training and Deployment in Heterogeneous IoT Networks

Download21 downloads
  • @ARTICLE{10.4108/eetmca.v7i3.2899,
        author={Bowen Lu and Shiwei Lai and Yajuan Tang and Tao Cui and Chengyuan Fan and Jianghong Ou and Dahua Fan},
        title={Deep Model Training and Deployment in Heterogeneous IoT Networks},
        journal={EAI Endorsed Transactions on Mobile Communications and Applications},
        volume={7},
        number={3},
        publisher={EAI},
        journal_a={MCA},
        year={2023},
        month={1},
        keywords={Deep learning, deep model training, deep model deployment},
        doi={10.4108/eetmca.v7i3.2899}
    }
    
  • Bowen Lu
    Shiwei Lai
    Yajuan Tang
    Tao Cui
    Chengyuan Fan
    Jianghong Ou
    Dahua Fan
    Year: 2023
    Deep Model Training and Deployment in Heterogeneous IoT Networks
    MCA
    EAI
    DOI: 10.4108/eetmca.v7i3.2899
Bowen Lu1,*, Shiwei Lai2, Yajuan Tang2, Tao Cui2, Chengyuan Fan3, Jianghong Ou4, Dahua Fan4
  • 1: Shantou University
  • 2: Guangzhou University
  • 3: Software Engineering Institute of Guangzhou, Guangzhou, China
  • 4: AI Sensing Technology, Foshan, China
*Contact email: 19bwlu@stu.edu.cn

Abstract

As a typical form of machines learning, deep learning has attracted much attention from researchers. It can independently construct (train) basic rules according to the sample data in the learning process. Especially in the field of machine vision, neural networks are usually trained by supervised learning, that is, by example data and predefined results of example data. In this paper, we firstly overview the current research progress on the deep model training and deployment on the heterogeneous Internet of Things (IoT) networks, by taking into account both the latency and energy consumption from various devices in the system. We then summarize the existing challenges on the model training and model deployment on the heterogeneous IoT devices. We further give some feasible solutions to solve the challenges on the model training and model deployment on the heterogeneous IoT devices. The study in this paper can serve as an important reference for the development of deep model training and model deployment for heterogeneous IoT networks.