Abstract

Collision hazard detection in industrial work zones faces challenges from signal instability, mobility-induced fluctuations, and nonline-of-sight (NLOS) conditions. While Bluetooth low energy (BLE) offers cost-effective proximity sensing, its received signal strength indicator (RSSI) variability - fluctuating by ±10 dBm even at fixed distances - limits reliability in safety-critical applications. This article presents AlertBLE, a hybrid BLE-based hazard detection system that combines extended Kalman filter (EKF) and adaptive moving average (AMA) algorithms to achieve up to 94% RSSI variance reduction in static NLOS conditions. The system introduces speed-aware safety thresholds based on reaction time and braking distance models, dynamically expanding hazard zones from 5 m (static) to 8.19 m (at 10 km/h), ensuring adequate safety margins across operational speeds. AlertBLE employs K-means clustering to identify line-of-sight (LOS)/NLOS propagation environments, integrating this context as features for supervised learning. Among four evaluated classifiers [K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost)], KNN demonstrates optimal performance with an efficiency score of 12.8, balancing 82.74% recall with minimal computational requirements (156-KB memory and 1.01-ms inference). Field evaluation using 44774 samples across diverse outdoor conditions demonstrates 88.63% overall detection accuracy with 63-ms system latency - well below the 250-ms safety threshold. The multilayered error mitigation framework, incorporating temporal smoothing, confidence thresholding, and state machine logic, achieves a 75.6% reduction in combined false positives (FPs) and false negatives (FNs). Despite 170.8% average RSSI degradation under severe NLOS conditions, AlertBLE maintains 82% detection accuracy within the critical 5-m zone. The article also presents a comprehensive security framework addressing BLE vulnerabilities, providing a roadmap for production deployment enhancements.

Department(s)

Computer Science

Keywords and Phrases

Bluetooth low energy (BLE); extended Kalman filter (EKF); hazard classification; IoT safety; machine learning (ML)

International Standard Serial Number (ISSN)

2327-4662

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

01 Jan 2025

Download

Full Text Link

Share

 
COinS