Research on multi-dimensional data-based 5G base station electromagnetic radiation intensity prediction model using improved graph neural network

Jie Tian; Zhaojie Liang; Yan Li

doi:10.1117/12.3034855

7 August 2024 Research on multi-dimensional data-based 5G base station electromagnetic radiation intensity prediction model using improved graph neural network

Jie Tian, Zhaojie Liang, Yan Li

Author Affiliations +

Proceedings Volume 13224, 4th International Conference on Internet of Things and Smart City (IoTSC 2024); 132240M (2024) https://doi.org/10.1117/12.3034855
Event: 4th International Conference on Internet of Things and Smart City, 2024, Hangzhou, China

Abstract

The rapid rollout of 5G networks has heightened the necessity for accurate forecasting of electromagnetic radiation (EMR) intensity emanating from 5G base stations. In this paper, we introduce a cutting-edge Enhanced Graph Neural Network (GNN) model specifically designed for predicting EMR intensity. This model tackles the intricate spatial and network interactions inherent to 5G infrastructure. By harnessing the capabilities of Graph Neural Networks in analyzing multifaceted data, our approach marks a substantial advancement over traditional predictive frameworks. Comprehensive empirical tests showcase the model's remarkable precision in EMR intensity prediction when pitted against standard machine learning practices and a baseline neural network. This paper not only facilitates the safe rollout and governance of 5G networks but also underscores the utilization of sophisticated machine learning paradigms in the telecommunications realm. The revelations carry profound ramifications for public health and safety, regulatory adherence, and the subsequent evolution of wireless communication networks.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jie Tian, Zhaojie Liang, and Yan Li "Research on multi-dimensional data-based 5G base station electromagnetic radiation intensity prediction model using improved graph neural network", Proc. SPIE 13224, 4th International Conference on Internet of Things and Smart City (IoTSC 2024), 132240M (7 August 2024); https://doi.org/10.1117/12.3034855

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available