IEEE Transactions on Instrumentation and Measurement, vol. 74, pp. 1-16, 2025, Art no. 2517416, doi.org/10.1109/TIM.2025.3551824

High-dimensional Radio Frequency Fingerprint Synthesis for Indoor Positioning

Zhongyuan Lyu¹, Tom T.L. Chan², Gary C.M. Leung³, Y.L. Chan⁴, Daniel P.K. Lun⁴, and Michael G. Pecht^5
1 Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, China
² Centre for Advances in Reliability and Safety, Hong Kong, China
³ Blue Pin (HK) Limited, Hong Kong, China
⁴ Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, China
⁵ Center for Advanced Life Cycle Engineering, University of Maryland, College Park, MD, USA

For more information about this article and related research, please contact Prof. Michael Pecht.

Abstract:

Fingerprint-based indoor positioning systems are being explored to aid in location-based services due to their robustness in non-line-of-sight conditions. Current systems utilize high-dimensional radio frequency (HDRF) fingerprints, such as Wi-Fi channel state information, to achieve higher positioning precision. Since data acquisition is labor-intensive, researchers proposed to enrich the dataset with generative models. It however faced challenges arising from capturing the intricate HDRF distribution using simplistic models and the lack of a framework that simultaneously addresses the generative model training, sample evaluation and selection. To synthesize high-quality HDRF fingerprints, this paper proposes an HDRF fingerprint generation framework using a conditional diffusion model that learns the packet-level feature distribution by decomposing HDRF fingerprints using grid points, anchors, and frequency channel information, while preserving the feature spatial correlation within a fingerprint. A sample selection process using the Mahalanobis distance, and the Principal Component Analysis Q-statistic is used to ensure the sample fidelity. An adaptive learning strategy is further developed to integrate the generated synthetic HDRF fingerprints into downstream positioning tasks. Experimental results on two HDRF datasets quantitatively and qualitatively showcase the diversity and fidelity of the synthetic samples. Furthermore, compared to solely utilizing the original dataset, integrating the synthetic HDRF fingerprints from the developed framework to train downstream positioning models can decrease the positioning error by up to 16%.

This article is available online here and to CALCE Consortium Members for personal review.