• Home
  • Search
  • Machine Learning-based Optimal Framework for Internet of Things Networks
  • https://doi.org/10.32604/cmc.2022.024093Copy DOI Icon

Machine Learning-based Optimal Framework for Internet of Things Networks

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Deep neural networks (DNN) are widely employed in a wide range of intelligent applications, including image and video recognition. However, due to the enormous amount of computations required by DNN. Therefore, performing DNN inference tasks locally is problematic for resource-constrained Internet of Things (IoT) devices. Existing cloud approaches are sensitive to problems like erratic communication delays and unreliable remote server performance. The utilization of IoT device collaboration to create distributed and scalable DNN task inference is a very promising strategy. The existing research, on the other hand, exclusively looks at the static split method in the scenario of homogeneous IoT devices. As a result, there is a pressing need to investigate how to divide DNN tasks adaptively among IoT devices with varying capabilities and resource constraints, and execute the task inference cooperatively. Two major obstacles confront the aforementioned research problems: 1) In a heterogeneous dynamic multi-device environment, it is difficult to estimate the multi-layer inference delay of DNN tasks; 2) It is difficult to intelligently adapt the collaborative inference approach in real time. As a result, a multi-layer delay prediction model with fine-grained interpretability is proposed initially. Furthermore, for DNN inference tasks, evolutionary reinforcement learning (ERL) is employed to adaptively discover the approximate best split strategy. Experiments show that, in a heterogeneous dynamic environment, the proposed framework can provide considerable DNN inference acceleration. When the number of devices is 2, 3, and 4, the delay acceleration of the proposed algorithm is 1.81 times, 1.98 times and 5.28 times that of the EE algorithm, respectively.

Similar Papers
  • Conference Article
  • Citations3

Energy Profiling based Load-Balancing Approach in IoT-Edge for Split Computing

  • Dec 19, 2021
  • Jyotirmoy Karjee +2
  • Conference Article
  • Citations1

Split Computing based Quantized PoseNet Model for Distributed AI Architecture in IoT-Edge

  • Jan 03, 2023
  • Jyotirmoy Karjee +5
  • Research Article
  • Citations5

Toward Automatically Connecting IoT Devices with Vulnerabilities in the Wild

  • Oct 19, 2023
  • ACM Transactions on Sensor Networks
  • Jinke Song +5
  • Conference Article
  • Citations15

2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency

  • Oct 17, 2021
  • Yonggan Fu +4
  • Research Article
  • Citations24

Deep Learning on Energy Harvesting IoT Devices: Survey and Future Challenges

  • Jan 01, 2022
  • IEEE Access
  • Mingsong Lv +1
  • Research Article
  • Citations18

Distributed Inference in Resource-Constrained IoT for Real-Time Video Surveillance

  • Mar 01, 2023
  • IEEE Systems Journal
  • Muhammad Asif Khan +3
  • Research Article
  • Citations1

Connecting food supply chains

  • Sep 01, 2022
  • Food Science and Technology
  • Conference Article
  • Citations15

Split Computing: Dynamic Partitioning and Reliable Communications in IoT-Edge for 6G Vision

  • Aug 01, 2021
  • Jyotirmoy Karjee +5
  • Research Article
  • Citations21

Low-Latency Privacy-Preserving Outsourcing of Deep Neural Network Inference

  • Jun 18, 2020
  • IEEE Internet of Things Journal
  • Yifan Tian +3
  • Conference Article
  • Citations8

TrustServing: A Quality Inspection Sampling Approach for Remote DNN Services

  • Jun 01, 2020
  • Xueyu Hou +1
  • Research Article

Internet of things: a cloud-MANET communication framework

  • Feb 09, 2021
  • Computer Science and Information Technologies
  • Tanweer Alam
  • Research Article

Classification of cyber threats for internet of things

  • Dec 15, 2023
  • Bulletin of the National Engineering Academy of the Republic of Kazakhstan
  • S T Tleuberdin +1
  • Research Article
  • Citations20

Content-Aware Adaptive Device–Cloud Collaborative Inference for Object Detection

  • Nov 01, 2023
  • IEEE Internet of Things Journal
  • Youbing Hu +5
  • Research Article
  • Citations5

MicroNets: A multi-phase pruning pipeline to deep ensemble learning in IoT devices

  • Nov 08, 2021
  • Computers & Electrical Engineering
  • Besher Alhalabi +2
  • Conference Article
  • Citations19

PaperW8

  • Aug 25, 2020
  • Calvin Brierley +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.