通信学报2026，Vol.47Issue(3)：209-218,10.DOI:10.11959/j.issn.1000-436x.2026047
工业雾霾环境下多模态语义辅助的毫米波波束预测方法
Multi-modal semantics aided mmWave beam prediction method in industrial haze environment
摘要
Abstract
To address the issue of decreased accuracy of existing environment semantics aided millimeter wave(mmWave)beam prediction methods in industrial haze environments,a multi-modal semantics aided beam prediction method was proposed.Firstly,a Lite-DHNet module was designed to perform end-to-end dehazing reconstruction on haze images.Then,the dehazed images were fused with localization data within the environment semantics.Finally,a masked image feature extraction network and a beam index inference network were designed to achieve mmWave beam prediction.Experimental results demonstrate that the proposed approach achieves high beam prediction accuracy with low computational overhead,and its Top-3 prediction accuracy reaches up to 99.5%,effectively mitigating the impact of haze environments on beam prediction accuracy.关键词
毫米波通信/波束预测/深度学习/环境语义Key words
mmWave communication/beam prediction/deep learning/environment semantics分类
信息技术与安全科学引用本文复制引用
谢鑫,杨迪寒,王一凡,王恒..工业雾霾环境下多模态语义辅助的毫米波波束预测方法[J].通信学报,2026,47(3):209-218,10.基金项目
国家自然科学基金资助项目(No.U23B2003,No.62402081) （No.U23B2003,No.62402081）
重庆市自然科学基金资助项目(No.CSTB2024NSCQ-LZX0127,No.CSTB2025NSCQ-LZX0149) （No.CSTB2024NSCQ-LZX0127,No.CSTB2025NSCQ-LZX0149）
重庆市教委科学技术研究基金资助项目(No.KJQN202400645) The National Natural Science Foundation of China(No.U23B2003,No.62402081),The Natural Science Founda-tion of Chongqing(No.CSTB2024NSCQ-LZX0127,No.CSTB2025NSCQ-LZX0149),The Science and Technology Research Pro-gram of Chongqing Municipal Education Commission(No.KJQN202400645) （No.KJQN202400645）
