Estimating Congestion in a Fixed-Route Bus by Using BLE Signals

Area of Science:

• Transportation Engineering
• Computer Science
• Public Health

Background:

• Public transportation systems require real-time congestion data for efficient operation, especially during health crises like COVID-19.
• Manual monitoring of bus occupancy is impractical and resource-intensive.
• Existing systems may raise privacy concerns or incur high installation costs.

Purpose of the Study:

• To develop an automated system for estimating bus congestion levels with acceptable accuracy.
• To design a privacy-preserving and cost-effective solution for monitoring passenger density on buses.
• To leverage Bluetooth low-energy (BLE) signals for non-intrusive sensing.

Main Methods:

• Proposed a system utilizing BLE signals emitted from passengers' mobile devices as sensing data.
• Implemented a sensing mechanism to acquire BLE signals within the bus.
• Developed a mechanism to estimate congestion levels based on the acquired BLE signal data.

Main Results:

• The system demonstrated the ability to estimate the number of passengers on a bus route.
• Achieved a mean absolute error of 2.49 passengers, corresponding to an error rate of 38.8%.
• Data collection and validation were conducted on an actual bus route in collaboration with Nara Kotsu Co., Ltd.

Conclusions:

• The proposed BLE-based system offers a viable method for automatic bus congestion estimation.
• The system effectively balances the need for occupancy data with passenger privacy and cost considerations.
• Further refinement could improve accuracy for enhanced public transport management.