Vision Transformer Based User Equipment Positioning

Shah, Parshwa, Patel, Dhaval K, Soni, Brijesh, Lopez-Benitez, Miguel ORCID: 0000-0003-0526-6687 and Govindasamy, Siddhartan (2025) Vision Transformer Based User Equipment Positioning In: 2026 IEEE 23rd Consumer Communications & Networking Conference (CCNC), 2026-1-9 - 2026-1-12.

Text CCNC_2026_2.pdf - Author Accepted Manuscript Available under License Creative Commons Attribution. Download (126kB) | Preview

Abstract

Recently, Deep Learning (DL) techniques have been used for User Equipment (UE) positioning. However, the key shortcomings of such models is that: i) they weigh the same attention to the entire input; ii) they are not well suited for non-sequential data, e.g., when only instantaneous Channel State Information (CSI) is available. In this context, we propose an attention-based Vision Transformer (ViT) architecture that focuses on the Angle Delay Profile (ADP) from CSI matrix. Our approach, validated on the 'DeepMIMO' and 'ViWi' ray-tracing datasets, achieves Root Mean Squared Error (RMSE) of 0.55m indoors, 13.59m outdoors in DeepMIMO, and 3.45m in ViWi's outdoor blockage scenario. The proposed scheme outperforms state-of-the-art schemes by ∼ 38%. It also performs substantially better than other approaches that we have considered in terms of the distribution of error distance.

Item Type:	Conference Item (Unspecified)
Uncontrolled Keywords:	Positioning, Localization, Vision Transformer, Attention Mechanism, 5G/6G
Divisions:	Faculty of Science & Engineering Faculty of Science & Engineering > School of Computer Science & Informatics Faculty of Science & Engineering > School of Computer Science & Informatics > Trustworthy Computing
Depositing User:	Symplectic Admin
Date Deposited:	17 Nov 2025 08:42
Last Modified:	23 May 2026 11:16
DOI:	10.1109/CCNC65079.2026.11366356
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3195440
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.