Title: ADLoc: an angle-delay fingerprint localisation method for MIMO-OFDM systems

Authors: Chenlin He; Xiaojun Wang; Jiyu Jiao; Lei Wang; Youjia Tong

Addresses: National Mobile Communications Research Laboratory, Southeast University, Nanjing 211189, China; Advanced Interdisciplinary Studies Research Center, Purple Mountain Laboratories, Nanjing 211111, China ' National Mobile Communications Research Laboratory, Southeast University, Nanjing 211189, China; Advanced Interdisciplinary Studies Research Center, Purple Mountain Laboratories, Nanjing 211111, China ' National Mobile Communications Research Laboratory, Southeast University, Nanjing 211189, China; Advanced Interdisciplinary Studies Research Center, Purple Mountain Laboratories, Nanjing 211111, China ' National Mobile Communications Research Laboratory, Southeast University, Nanjing 211189, China; Advanced Interdisciplinary Studies Research Center, Purple Mountain Laboratories, Nanjing 211111, China ' Portland College, Nanjing University of Posts and Telecommunications, Nanjing 210023, China

Abstract: Fingerprint localisation has garnered increasing research interest owing to its exceptional reliability within non-line-of-sight scenarios. This paper introduces ADLoc, a novel angle-delay fingerprint localisation method for multiple input multiple output - orthogonal frequency division multiplexing systems. We extract an angle delay channel frequency power fingerprint matrix from the system's channel state information. Chi-square distance is introduced as a fingerprint similarity criterion due to its good performance in classification problems. Then, a convolutional neural network classification-based method is proposed. Simulation results indicate that ADLoc demonstrates commendable efficacy in enhancing localisation accuracy and time.

Keywords: fingerprint localisation; convolutional neural network; CNN; area classification; multiple-input multiple-output; MIMO; channel state information; CSI; non-line-of-sight; NLoS; angle delay channel frequency power fingerprint; ADCFP.

DOI: 10.1504/IJSNET.2024.138912

International Journal of Sensor Networks, 2024 Vol.45 No.2, pp.115 - 125

Received: 19 Jan 2024
Accepted: 26 Jan 2024
Published online: 03 Jun 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article