Federated Learning Based on CTC for Heterogeneous Internet of Things

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

7 Scopus Citations
View graph of relations

Author(s)

  • Demin Gao
  • Haoyu Wang
  • XiuZhen Guo
  • Lei Wang
  • Guan Gui
  • Shuai Wang
  • Yunhuai Liu
  • Tian He

Related Research Unit(s)

Detail(s)

Original languageEnglish
Journal / PublicationIEEE Internet of Things Journal
Publication statusOnline published - 14 Aug 2023

Abstract

Federated Learning (FL) is a machine learning technique that allows for on-site data collection and processing without sacrificing data privacy and transmission. Heterogeneity is a key challenge in federated settings. Recently, Cross-Technology Communication (CTC) has emerged as a solution for IoT heterogeneity, enabling direct communication between different wireless devices without the need for hardware modifications or gateway intervention. For example, a sophisticated WiFi device can serve as a central coordinator for other heterogeneous devices such as LoRa, ZigBee, Bluetooth, and LTE, leading to more efficient and ubiquitous cross-network information exchange. However, heterogeneous wireless technologies present different data transmission rates and computing resources, making it difficult to achieve high accuracy in predictions due to large amounts of multidimensional data, communication delays, transmission latency, limited processing capacity, and data privacy concerns. In this work, we propose a federated learning framework based on CTC for heterogeneous IoT applications, called FLCTC. To demonstrate the usability of FLCTC, we implemented FLCTC and a specific solution for forest fire prediction. FLCTC was concretely implemented as a federal deep learning based on long and short-term memory and used for forest fire prediction, addressing the challenge of data characterization in heterogeneous IoT networks. FLCTC promises to improve communication efficiency and prediction accuracy. Our platform-based evaluation results show that FLCTC is feasible, with a recall of 96% and an accuracy of 88%, offering valuable insights into the use of federated learning with CTC for heterogeneous IoT applications. © 2023 IEEE

Research Area(s)

  • Cross-Technology Communication, Federated learning, Federated Learning, Forestry, Heterogeneous IoT Networks, Internet of Things, Servers, Wireless communication, Wireless fidelity, Zigbee

Citation Format(s)

Federated Learning Based on CTC for Heterogeneous Internet of Things. / Gao, Demin; Wang, Haoyu; Guo, XiuZhen et al.
In: IEEE Internet of Things Journal, 14.08.2023.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review