CSI-BERT2: A BERT-Inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing
IEEE Transactions on Mobile Computing · 2026-05 · 25 (5) · 7241-7257
DOI: 10.1109/tmc.2025.3640420 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-05. Verfasst von Zijian Zhao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Young Talent Research Project, Shenzhen-Hong Kong-Macau Technology Research Programme.
Abstract (Originalsprache)
Channel state information (CSI) is a fundamental component in both wireless communication and sensing systems, enabling critical functions such as radio resource optimization and environmental perception. In wireless sensing, data scarcity and packet loss hinder efficient model training, while in wireless communication, high-dimensional CSI matrices and short coherent times caused by high mobility present challenges in CSI etimation. To address these issues, we propose a unified framework named CSIBERT2 for CSI prediction and classification tasks, built on our previous work CSIBERT. We introduce a two-stage training method that first uses a mask language model (MLM) to enable the model to learn general feature extraction from scarce datasets in an unsupervised manner, followed by fine-tuning for specific downstream tasks. Specifically, we extend MLM into a mask prediction model (MPM), which efficiently addresses the CSI prediction task. To further enhance the representation capacity of CSI data, we introduce an adaptive re-weighting layer (ARL) to enhance subcarrier representation and a MLP-based temporal embedding module to mitigate temporal information loss problem inherent in the original Transformer. Extensive experiments demonstrate that CSI-BERT2 achieves state-of-the-art performance across all tasks. Our results further show that CSI-BERT2 generalizes effectively across varying sampling rates and robustly handles discontinuous CSI sequences caused by packet loss—challenges that conventional methods fail to address.
Förderung
- National Natural Science Foundation of China
- Guangdong Young Talent Research Project
- Shenzhen-Hong Kong-Macau Technology Research Programme
- Shenzhen Science and Technology Program
- Young Elite Scientists Sponsorship Program by CAST
Zitieren
APA
Zhao, Z., Meng, F., Lyu, Z., Li, H., Li, X., & Zhu, G. (2026). CSI-BERT2: A BERT-Inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing. IEEE Transactions on Mobile Computing, 25(5), 7241-7257. https://doi.org/10.1109/tmc.2025.3640420
Vancouver
Zhao Z, Meng F, Lyu Z, Li H, Li X, Zhu G. CSI-BERT2: A BERT-Inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing. IEEE Transactions on Mobile Computing. 2026;25(5):7241-7257. doi:10.1109/tmc.2025.3640420
BibTeX
@article{Zhao2026,
author = {Zhao, Zijian and Meng, Fanyi and Lyu, Zhonghao and Li, Hang and Li, Xiaoyang and Zhu, Guangxu},
title = {CSI-BERT2: A BERT-Inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {5},
pages = {7241--7257},
doi = {10.1109/tmc.2025.3640420}
}
EUVIMED