Adaptive and Redundancy-Aware Multimodal Fusion for Sensing-Assisted Beam Prediction
IEEE Sensors Journal · 2026-11 · 26 (21) · 31758-31768
DOI: 10.1109/jsen.2025.3632913 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, 2026-11. Verfasst von Qiyue Ma und 3 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
As wireless systems evolve toward higher frequency bands with narrower beams and increased mobility, ensuring accurate beam prediction is crucial for optimizing network performance and improving signal transmission efficiency. Recently, sensing-assisted communication has gained attention for leveraging environmental sensing data to enhance wireless decision-making. However, existing works mainly focus on incorporating more modalities while neglecting the negative impact of modality redundancy. In practice, certain modalities may contribute little to target tasks and introduce unnecessary computational overhead. To address such an issue, we will investigate the representational effectiveness of diverse sensing modalities. Driven by numerical observations, we design a novel model architecture, termed as low-rank fusion and cross-Transformer-based multimodal selection (LRCT-MS), that integrates a low-rank fusion (LRF) mechanism with a cross-modal Transformer to adaptively select the most task-relevant modality. Simulation results on a real-world multimodal dataset demonstrate the advantages of our proposed model in achieving accurate and efficient beam prediction.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Ma, Q., Han, F., Chen, W., & Deng, H. (2026). Adaptive and Redundancy-Aware Multimodal Fusion for Sensing-Assisted Beam Prediction. IEEE Sensors Journal, 26(21), 31758-31768. https://doi.org/10.1109/jsen.2025.3632913
Vancouver
Ma Q, Han F, Chen W, Deng H. Adaptive and Redundancy-Aware Multimodal Fusion for Sensing-Assisted Beam Prediction. IEEE Sensors Journal. 2026;26(21):31758-31768. doi:10.1109/jsen.2025.3632913
BibTeX
@article{Ma2026,
author = {Ma, Qiyue and Han, Fengxia and Chen, Weichao and Deng, Hao},
title = {Adaptive and Redundancy-Aware Multimodal Fusion for Sensing-Assisted Beam Prediction},
journal = {IEEE Sensors Journal},
year = {2026},
volume = {26},
number = {21},
pages = {31758--31768},
doi = {10.1109/jsen.2025.3632913}
}
EUVIMED