Edge Ai Inference

Edge AI Inference is a computational process in which a trained artificial intelligence model performs real-time decision-making or prediction at the network edge, distinguished from cloud-based inference by its execution on resource-constrained, geographically distributed edge devices to minimize latency, bandwidth usage, and privacy exposure.

93

Publications

8.9K

Citations

508

Authors

185

Institutions

Publications per year

2017–2026

92

Authors

508

  1. YS
    Yuanming Shi

    ShanghaiTech University, China

    7 publications · 1.5K citations

    7

    h-index

  2. KB
    Khaled B. Letaief

    Hong Kong University of Science and Technology, Hong Kong SAR China

    4 publications · 1.2K citations

    4

    h-index

  3. JZ
    Jun Zhang

    Hong Kong University of Science and Technology, Hong Kong SAR China

    4 publications · 689 citations

    4

    h-index

  4. MC
    Meng‐Fan Chang

    National Tsing Hua University, Taiwan

    3 publications · 488 citations

    3

    h-index

  5. GZ
    Guangxu Zhu

    Shenzhen Research Institute of Big Data, China

    3 publications · 260 citations

    3

    h-index

1–5 of 508

Venues

  1. arXiv (Cornell University)

    Repository · 7 publications · 148 citations

    7

    h-index

  2. IEEE Transactions on Wireless Communications

    4 publications · 1.1K citations

    4

    h-index

  3. IEEE Internet of Things Journal

    3 publications · 1.1K citations

    3

    h-index

  4. Computers and Electronics in Agriculture

    2 publications · 189 citations

    2

    h-index

  5. Sensors

    2 publications · 154 citations

    2

    h-index

1–5