2026-10-14T06:48:19Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34033824 2026-09-30T16:32:01Z category_29236 item_type_14 month_year_09_2026

A Multi-Stage Machine Learning and Post-Processing Pipeline for Indoor Ranging and Localization Using Bluetooth 6.0 Channel Sounding Anas Djobbi (25133463) Hend Fourati (25144902) thierry val (25144865) Other information and computing sciences not elsewhere classified Bluetooth 6.0 Channel Sounding Machine learning Localisation 2D/3D IA LOS NLOS Min-Max Algorithm <p dir="ltr">Indoor localization remains a challenging problem due to the lack of a universal standard and the limitations of existing technologies such as RSSI, UWB, and classical Bluetooth. This paper presents a multi-stage hybrid system combining Bluetooth 6.0 Channel Sounding (BCS) with machine learning and a post-processing pipeline for high-precision indoor ranging and localiza tion. The BCS technology provides two complementary distance measurements: Round-Trip Timing (RTT) and Phase-Based Ranging (PBR). We first characterize the behavior of these measurements across multiple experi mental scenarios, including Line-of-Sight (LOS) and Non Line-of-Sight (NLOS) conditions, both indoors and out doors, and in an anechoic chamber. A Kalman filter is then applied to reduce noise and detect outliers, fol lowed by an XGBoost regression model that predicts the real distance from the RTT and PBR features. A post processing consensus algorithm is designed to stabilize predictions and converge toward the real distance. The system is deployed on a 1D positioning testbed, achiev ing a mean absolute error (MAE) of 6.25cm in LOS and 3.40cm in NLOS after post-processing. A compara tive study with Ultra-Wideband (UWB) shows that the hybrid BCS+AI system approaches UWB accuracy in NLOS scenarios, with an MAE of 7.33cm versus 5.42cm for UWB. Finally, two 2D localization methods—Min Max and a trigonometric approach—are implemented and compared. The results confirm the potential of BCS com bined with AI as a cost-effective alternative to UWB for indoor localization.</p> 2026-09-30T16:32:01Z Text Conference contribution 10.6084/m9.figshare.34033824.v1 https://figshare.com/articles/conference_contribution/A_Multi-Stage_Machine_Learning_and_Post-Processing_Pipeline_for_Indoor_Ranging_and_Localization_Using_Bluetooth_6_0_Channel_Sounding/34033824 CC BY 4.0