Next Article in Journal
Optimized Seam-Driven Image Stitching Method Based on Scene Depth Information
Previous Article in Journal
Design of Switched-Capacitor DC-DC Voltage-Down Converters Driven by Highly Resistive Energy Transducer
Previous Article in Special Issue
Adaptation Scheduling for Urban Traffic Lights via FNT-Based Prediction of Traffic Flow
Article

A Novel Bus Arrival Time Prediction Method Based on Spatio-Temporal Flow Centrality Analysis and Deep Learning

by 1 and 2,3,*
1
NetcoreTech Co., Ltd., 1308, Seoulsup IT Valley (Seongsu-dong 1-ga) 77, Seongsuil-ro, Seongdong-gu, Seoul 04790, Korea
2
Department of Computer Engineering, Hongik University, 94 Wausan-ro, Mapo-gu, Seoul 04068, Korea
3
Neouly Incorporated, 94 Wausan-ro, Mapo-gu, Seoul 04068, Korea
*
Author to whom correspondence should be addressed.
Academic Editors: Lei Zhang and Nikolay Hinov
Electronics 2022, 11(12), 1875; https://doi.org/10.3390/electronics11121875
Received: 30 April 2022 / Revised: 11 June 2022 / Accepted: 12 June 2022 / Published: 14 June 2022
(This article belongs to the Special Issue AI-Based Transportation Planning and Operation, Volume II)
This paper presents a method for predicting bus stop arrival times based on a unique approach that extracts the spatio-temporal dynamics of bus flows. Using a new technique called Bus Flow Centrality Analysis (BFC), we obtain the low-dimensional embedding of short-term bus flow patterns in the form of IID (Individual In Degree) and IOD (Individual Out Degree) and TOD (Total Out Degree) at every station in the bus network. The embedding using BFC analysis well captures the characteristics of every individual flow and aggregate pattern. The latent vector returned by the BFC analysis is combined with other essential information such as bus speed, travel time, wait time, dispatch intervals, the distance between stations, seasonality, holiday status, and climate information. We employed a family of recurrent neural networks such as LSTM, GRU, and ALSTM to model how these features change over time and to predict the time the bus takes to reach the next stop in subsequent time windows. We experimented with our solution using logs of bus operations in the Seoul Metropolitan area offered by the Bus Management System (BMS) and the Bus Information System (BIS) of Korea. We predicted arrival times for more than 100 bus routes with a MAPE of 1.19%. This margin of error is 74% lower than the latest work based on ALSTM. We also learned that LSTM performs better than GRU with a 40.5% lower MAPE. This result is even remarkable considering the irregularity in the bus flow patterns and the fact that we did not rely on real-time GPS information. Moreover, our approach scales at a city-wide level by analyzing more than 100 bus routes, while previous studies showed limited experiments on much fewer bus routes. View Full-Text
Keywords: bus flow centrality; bus arrival time prediction; spatio-temporal data; artificial neural network; deep learning bus flow centrality; bus arrival time prediction; spatio-temporal data; artificial neural network; deep learning
Show Figures

Figure 1

MDPI and ACS Style

Lee, C.; Yoon, Y. A Novel Bus Arrival Time Prediction Method Based on Spatio-Temporal Flow Centrality Analysis and Deep Learning. Electronics 2022, 11, 1875. https://doi.org/10.3390/electronics11121875

AMA Style

Lee C, Yoon Y. A Novel Bus Arrival Time Prediction Method Based on Spatio-Temporal Flow Centrality Analysis and Deep Learning. Electronics. 2022; 11(12):1875. https://doi.org/10.3390/electronics11121875

Chicago/Turabian Style

Lee, Chanjae, and Young Yoon. 2022. "A Novel Bus Arrival Time Prediction Method Based on Spatio-Temporal Flow Centrality Analysis and Deep Learning" Electronics 11, no. 12: 1875. https://doi.org/10.3390/electronics11121875

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop