Citation

Wong, De Quan and Foo, Yee Loo (2025) Improving Public Transport Service through Accurate Prediction of Its Arrival Time. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text 13.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Traffic congestion is a major problem in cities worldwide. It has a significant impact on the local gross domestic product (GDP), environment, and society. Public transport can ease traffic congestion, but one with poor punctuality is discouraging. To accurately estimate the time of arrival in a public transport system can be challenging due to many factors, including road conditions, weather conditions, incomplete data, etc. Implementing an accurate arrival time prediction system thus becomes indispensable to improve the service quality of public transport and consumer satisfaction. The research found that current ETA systems have issues such as the lack of accuracy, the slow loading time of the ETA, and the “cumbersome” interface. Possible avenues of solution are with a static list of corrected non-editable scheduled departure times in the backend, a fallback on static data list of historical bus arrival times, and a “less cumbersome” autonomous oneview ETA interface. The main contribution of this research is the use of publicly available ridership data to further support the severity of the issues investigated on hand and the application of data fallback and data visualization for service improvement in comparison to existing methods.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Public transport, prediction of bus arrival time
Subjects:	T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL1-484 Motor vehicles. Cycles
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	18 Mar 2026 08:24
Last Modified:	19 Mar 2026 02:33
URII:	http://shdl.mmu.edu.my/id/eprint/15593

Downloads

Edit (login required)