Lightweight Non-Line-of-Sight Channel Detection for ML-assisted Bluetooth Direction Finding

2026-06-17

AI Summary

This study addresses the challenge of angle estimation bias in BLE direction finding under multipath environments, where reflections and scattering degrade accuracy, and the absence of lightweight line-of-sight (LOS)/non-line-of-sight (NLOS) detection methods suitable for narrowband signals. The authors construct a controlled BLE measurement setup to collect and annotate CTE IQ data, proposing a lightweight LOS/NLOS detection pipeline tailored for narrowband channels. Their approach leverages quantization normalization, principal component analysis (PCA), and adaptive kernel density estimation to extract robust features, and employs Nyström kernel approximation to construct a low-rank nonlinear mapping, which is then integrated with a support vector classifier for efficient discrimination. The proposed method achieves significantly reduced inference complexity and memory overhead while maintaining high accuracy, yielding a 7–14% relative improvement in accuracy over baseline feature representations and demonstrating superior suitability over models like MLPs in resource-constrained scenarios.

Abstract

Bluetooth Low Energy (BLE) direction-finding is promising for indoor industrial localization, but its accuracy degrades in multipath environments where reflections and scattering bias angle estimates. Although line-of-sight (LOS) and non-line-of-sight (NLOS) detection is well studied for wide-band radios, BLE direction-finding still lacks narrow-band channel-feature representations, scalable kernel-based feature transformations, and dedicated datasets for data-driven, lightweight channel classification. To address this gap, the work introduces a controlled BLE measurement setup that generates labeled LOS/NLOS data in two distinct propagation environments. A quality-driven machine learning (ML)-based pipeline is then developed for BLE Constant Tone Extension (CTE) In-phase-Quadrature (IQ) features. First, robust quantile-based standardization is applied to reduce the influence of outliers and heavy-tailed effects. The standardized features are then analyzed using Principal Component Analysis (PCA) and Adaptive Kernel Density Estimation (AKDE) to verify scenario-dependent statistics and reveal LOS/NLOS separability. Next, Nyström Kernel Approximation (NKA) constructs low-rank nonlinear feature maps followed by a lightweight Support Vector Classifier (SVC) head for LOS/NLOS detection. This classifier is compared with Random Forest (RF) and Multilayer Perceptron (MLP) models. Results show that NKA improves accuracy by about 7-14% relative to the raw baseline. Although the MLP achieves higher absolute accuracy, the Nyström--SVC approach offers a more favorable trade-off between training complexity, inference cost, and memory footprint. Finally, several pipeline-calibrated posterior probabilities are utilized for cost-aware threshold selection and efficient real-time LOS/NLOS detection in resource-constrained localization systems.

Problem

• BLE direction-finding
• NLOS detection
• multipath environments
• channel classification
• lightweight ML

Innovation

• NLOS detection
• BLE direction finding
• Nyström Kernel Approximation
• lightweight ML
• CTE IQ features