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

Yuji Kanamitsu,Koki Tachibana,Yuki Matsuda,Hirohiko Suwa,Eigo Taya,Yugo Nakamura,Keiichi Yasumoto

doi:10.3390/s22030881

Abstract

Information on congestion of buses, which are one of the major public transportation modes, can be very useful in light of the current COVID-19 pandemic. Because it is unrealistic to manually monitor the number of riders on all buses in operation, a system that can automatically monitor congestion is necessary. The main goal of this paper’s work is to automatically estimate the congestion level on a bus route with acceptable performance. For practical operation, it is necessary to design a system that does not infringe on the privacy of passengers and ensures the safety of passengers and the installation sites. In this paper, we propose a congestion estimation system that protects passengers’ privacy and reduces the installation cost by using Bluetooth low-energy (BLE) signals as sensing data. The proposed system consists of (1) a sensing mechanism that acquires BLE signals emitted from passengers’ mobile terminals in the bus and (2) a mechanism that estimates the degree of congestion in the bus from the data obtained by the sensing mechanism. To evaluate the effectiveness of the proposed system, we conducted a data collection experiment on an actual bus route in cooperation with Nara Kotsu Co., Ltd. The results showed that the proposed system could estimate the number of passengers with a mean absolute error of 2.49 passengers (error rate of 38.8%).

Highlights

Buses are one of the main forms of public transportation
In order to deal with these problems, we propose a machine learning-based estimation that uses the total number of addresses and information specific to the bus route as features
We proposed a system for estimating the degree of congestion on a bus route using Bluetooth low-energy (BLE) signals as sensing data to protect passengers’ privacy and reduce installation costs, taking into account that the system will be installed on a bus that is in operation

Summary

Introduction

Buses are one of the main forms of public transportation. Information on crowding, or congestion, on buses can be very useful in light of the current COVID-19 pandemic for both users and society in terms of avoiding congestion for individuals and equalizing congestion in society. There is a need for a service that visualizes real-time bus congestion information, a route recommendation service that considers the degree of crowding to minimize the risk of infection, and a service that predicts the degree of crowding in the future. To provide these services, it is necessary to obtain congestion information for a bus in advance. It is possible to obtain the number of bus users on particular routes using information from prepaid transportation cards.

Methods

Results

Discussion

Conclusion