Development of an environmentally friendly ICT platform for transport management and analysis of user preferences

Research Project

Project/Area Number	22K14339
Research Category	Grant-in-Aid for Early-Career Scientists
Allocation Type	Multi-year Fund
Review Section	Basic Section 22050:Civil engineering plan and transportation engineering-related
Research Institution	Hiroshima University
Principal Investigator	VARGHESE VARUN 広島大学, 先進理工系科学研究科(国), 助教 (40834718)
Project Period (FY)	2022-04-01 – 2024-03-31
Project Status	Granted (Fiscal Year 2022)
Budget Amount *help	¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000) Fiscal Year 2023: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000) Fiscal Year 2022: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Keywords	Transportation Planning / Machine Learning / ICT / Emissions / Randomized Control Trial
Outline of Research at the Start	The goals of the research will be achieved through two objectives. The first objective of the research is to develop an ICT platform that implements an ethical, attractive, and personalized algorithm that will prioritize the reduction of CO2 emissions. The ICT platform will provide users with a choice between the novel algorithm and traditional algorithms (such as profit maximization and travel time reduction). The second objective of the research is to conduct a randomized control trial in Higashihiroshima to quantitatively evaluate the adoption and effectiveness of the ICT platform.
Outline of Annual Research Achievements	Firstly, based on a two-week field experiment in Hiroshima, an empirical analysis established positive impact of monetary incentives on mode choice utility. Meanwhile, people with pro-environmental attitudes were observed to be less likely to choose cars and more likely to choose public transit and non-motorized transport modes. The findings were presented at the 102nd TRB annual meeting. Second analysis in the project, tested the impact of data preprocessing and GPS data frequency on accuracy and interpretability using machine learning models. The results show that data preprocessing have a larger impact as compared to GPS data frequency. Third analysis involves a comprehensive review of literature on travel mode recommender systems, which summarizes the different algorithms, data types, and impacts of such tools. One manuscript is currently under review and two under preparation.
Current Status of Research Progress	Current Status of Research Progress 2: Research has progressed on the whole more than it was originally planned. Reason The project is progressing as per plan. Background work to understand the impact of monetary incentive provision and personal preferences on mode choice was finished. The relative contribution of both of these important variables on predicted transport mode shares was also evaluated. In addition, the impact of data collection frequency and data preprocessing on model prediction accuracy and interpretability was also analyzed. A review of previous literature on existing tools was also conducted as per plan.
Strategy for Future Research Activity	In the second year of the project, the coding work on the algorithm development will be done. This part would entail development of the ICT platform which recommends travel mode to people based on CO2 emission minimization. Upon completion of the ICT platform, the platform will be tested through a trial survey in Higashihiroshima, Japan. The findings of the project will be summarized in papers and will be presented in peer-reviewed conferences and published in journals.