An efficient and optimized cooperative indoor localization for B5G communication

Abstract

SummaryUltra‐accurate indoor localization/positioning technology is rapidly gaining interest in 5G and beyond (B5G) communications. Achieving 0.1 m level of precise indoor localization is a significant challenge that can be resolved using channel state information (CSI) of wireless signals from nearby access points. The complex indoor propagation issues like shadowing, blockage effects, and multi‐path fading diminish CSI, affecting precise position/location accuracy. Thus, to achieve ultra‐accurate localization, a novel MOIL framework is proposed using a deep learning BiLSTM model and CSI features in an efficient and optimized manner. The proposed MOIL integrates two functional blocks, SecLOP and CordNet. SecLOP conceals multi‐path effects and noise to optimize the input information using sequential responses of signals. CordNet minimizes precise position/location errors by taking all combinations of optimized signal features from the SecLOP block. Extensive simulation experiments were conducted to validate MOIL in different indoor scenarios, such as line‐of‐sight (LOS) and non‐line‐of‐sight (NLOS). Moreover, through a substantial ablation study, the efficiency of the proposed framework is validated/verified. The results outperformed existing works by providing cm‐level accuracy of 1 cm in LOS and 1.5 cm in NLOS scenarios. The proposed work outperformed the literature by 31.3% in LOS and 25.30% in NLOS scenarios.