S-BLE: A Participatory BLE Sensory Data Set Recorded from Real-World Bus Travel Events

2025-12-26

AI Summary

To address the insufficient robustness of Be-In-Be-Out (BIBO) systems in bus transit environments, this paper proposes the first crowdsourced, multi-modal BLE sensing framework tailored to real-world commuting scenarios. We collected synchronized BLE beacon RSSI, GPS trajectories, and IMU data from 28 participants across 20 campus shuttle buses, yielding the first large-scale, high-quality, publicly available BLE boarding dataset with spatiotemporal annotations—comprising tens of thousands of valid boarding sessions. Our contributions are threefold: (1) a novel participatory sensing paradigm enabling multi-source, time-synchronized data acquisition under realistic bus conditions; (2) a systematic methodology for beacon deployment, cross-sensor spatiotemporal alignment, and collaborative ground-truth annotation; and (3) significant improvements in BIBO station entry/exit recognition accuracy, alongside enhanced generalizability across diverse vehicles and bus routes.

Technology Category

Intelligent Robots: Multimodal Perception & Sensor FusionPlanning, Routing, and Scheduling: Optimization of Spatio-temporal SystemsComputer Vision: Multi-modal Vision

Application Category

Security and Privacy: Large-scale security measurementsSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applicationsSearch and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

This contribution describes S-BLE, a data set created for supporting the design of robust and reliable Be-In-Be-Out systems in public transit. S-BLE was recorded by the smartphones of 28 participants during their daily transit routines in a university campus setting. 20 shuttle bus vehicles in the campus fleet were equipped with two Bluetooth low energy (BLE) beacons each. RSSI data from these beacons was recorded during regular rides, along with odometry information (from GPS) and data from the smartphone's inertial sensors. The article describes the system used for data collection and presents some statistics of interest for the recorded data.

Problem

• Designing robust Be-In-Be-Out systems for public transit
• Collecting participatory BLE sensory data from real-world bus travel
• Providing a dataset with RSSI, GPS, and inertial sensor data

Innovation

• Smartphones record BLE beacon RSSI data
• Vehicles equipped with dual BLE beacons
• Combines BLE, GPS, and inertial sensor data