The Summer Course was held on September 23rd to 25th, 2022 for both online and on-site participants at the University of Tokyo Hongo Campus. Students and researchers from different universities and organizations gathered to join the event. The 3-day course provided a vast knowledge of different behavior modeling techniques for transportation networks and insights from keynote speakers, professors, and researchers.
Short Tour to Homeikan for International Students
8:30 – 8:40 Opening Ceremony
8:40 – 10:00 Deterministic/Stochastic Demand Optimization for Urban Logistics Prof. Teodor Gabriel Crainic (Université de Montréal)
10:00 – 11:00 Coding Tutorial for Beginners
11:00 – 12:00 Feedback for Group Work (E & J)
13:30-14:00 Professor Jana 14:00-14:30 Professor Parady 14:30-14:45 Break 14:45-15:15 Professor Chikaraishi 15:15-15:45 Professor Shafique 15:45-16:15 Professor Yaginuma 16:15-16:30 Break 16:30-17:00 Professor Oyama
We had invited talks by the guests from Diponegoro University, Iwan sensei, and Wido sensei. It was a nice opportunity to understand the state-of-the-art researches in Indonesia in the field of urban and regional planning.
We also have an informal “second” final master defense for the linkage students. Well done!
Place: IDEC large conference room
Date & time: 15:00-17:45 on September 21, 2022
(1) Invited talks
15:00-15:45 Prof. Wido Prananing Tyas
“Strategy and Innovation of Micro and Small Enterprises for Local Development toward 4.0 Era”
15:45-16:30 Prof. Iwan Rudiarto
“Building Scenario for Future Spatial Formations and Development”
(2) Presentations of students under Linkage program
A recursive logit model and its extensions can be utilised for a wide range of issues in the urban and transportation field, such as modelling activity-travel behavior in a time-space prism, and modelling route choice behavior on a large-scale road network. In this study camp, we first review existing studies in details and the prepare programming codes to execute recursive logit model and its extended versions.
9:00 Gathering at IDEC
9:00-12:00 Travelling to Matsuyama
13:00-15:00 Fosgerau et al. (2013) by Zafirah binti Abdul Gani
15:30-18:30 Mai et al. (2015) by Nur Diana Safitri
18:30-20:30 Oyama and Hato (2017) by Natsuki Nagasaka
20:30 Enjoy the night
8:30-10:00 Vasberg et al. (2019) by Makoto Chikaraishi
10:00-12:00 Oyama et al. (2022) by Keishi Fujiwara
13:00-15:00 Structural estimation methods by Hiroki Noguchi
For about a quarter of a century, machine learning methods have been widely applied to traffic problems, including rule-based and activity-based model building.
For about a quarter of a century, research has been widely conducted on the application of machine learning methods to traffic problems, including the construction of rule-based activity-based models. In recent years, there have been a number of studies that extend machine learning methods in a way that is consistent with traffic theory.
Recently, there have been a number of studies that extend machine learning methods in a way that is consistent with traffic theory. Such machine learning methods that are consistent with traffic theory
with traffic theory are superior not only in terms of theoretical validity, but also in terms of improving prediction accuracy.There have been several reports on machine learning methods that are consistent with traffic theory. In this workshop, we will discuss the academic and technical aspects of the transportation field, where the use of big data and passive data is becoming more and more widespread.
The study group will review the application and extension of machine learning methods in the field of transportation, taking into account the academic and practical situation in the field of transportation, where the use of big data and passive data is becoming more and more widespread.
The aim of this workshop is to organise the application and extension of machine learning methods in the field of transportation, where the use of big data and passive data is becoming more and more widespread.
13:20-13:30 Explanation of the purpose of the study group meeting
Two lab members just finished their master thesis on August,8th.
Melanton Hendra Siregar
“The Impact of Railway Stations Development on Land Price: A Case in West Japan”
Ei Ei Tun
“Emergency Shelter Location – Allocation with Time – Varying Demand: A Case in Higashi – Hiroshima”
They did incredible work hitting this award! I’m very happy that both of them got the Excellent Master Thesis Awards (Hendra san got the First Place of Excellence, and Ei Ei san got the Second Place of Excellence). Congratulations and best wishes for your continued success in the future. I wish nothing but the best for you.
Ishii, Y., Hayakawa, K., Koide, S., & Chikaraishi, M. (2022). Entropy Tucker model: Mining latent mobility patterns with simultaneous estimation of travel impedance parameters. Transportation Research Part C: Emerging Technologies, 137, 103559.
With the rapid increase in the availability of passive data in the field of transportation, combining machine learning with transportation models has emerged as an important research topic in recent years. This study proposes an entropy Tucker model that integrates (1) a Tucker decomposition technique, i.e., an existing machine learning method, and (2) an entropy maximizing model, i.e., an existing model used for modeling trip distribution in the field of transportation. In addition, an optimization algorithm is presented to empirically identify the proposed model. The proposed model provides a solid theoretical foundation for the machine learning method, substantially improves prediction performance, and provides richer behavioral implications through empirical parameter estimation of travel impedance. We conducted a case study using public transit smart card data. The results showed that the proposed model improves the prediction performance and interpretability of the results compared to the conventional nonnegative Tucker decomposition technique. Further, we empirically confirmed that the travel impedance varies with the origin–destination pair, time of the day, and day of the week. Finally, we discussed how embedding the theoretical foundations of transport modeling into machine learning methods can facilitate the use of various passive data in wider practical contexts of transport policy decision making.
Nakayama, S., Chikaraishi, M. (2021) Doubly generalized logit: a closed-form discrete choice model system with multivariate generalized extreme value distributed utilities, Transportation Research Part C, Vol. 132, 103315.
In this study, we generalize our previous q-generalized multinomial logit model (Nakayama & Chikaraishi, 2015), in which the heteroscedastic variance and flexible shape of the utility distribution are considered, by allowing for statistical dependency of alternatives. This is achieved by introducing the q-generalization of McFadden’s multivariate Gumbel distribution. Thus, the logit model is doubly generalized; 1) each utility follows the generalized extreme value distribution that includes the Gumbel, Weibull, and Fréchet distributions; and 2) the utility distribution is multivariate, and therefore, a nested or cross-nested structure and dependency of alternatives are allowed. The proposed doubly generalized logit model system allows for deriving new closed-form discrete choice models such as the q-generalized nested logit model and q-generalized cross-nested logit (CNL) model. Furthermore, the model system includes conventional logit models such as the multinomial logit, nested logit, and CNL models as special cases as well as the new generalized logit models, while retaining a closed-form expression. We empirically confirm that the goodness-of-fit of the proposed model could be substantially better compared to that of the conventional models in some cases, though the degree of improvements varies across cases.
Congratulations on your graduation, Maya Safira (Doctor course), Faisal Ali (Master course). Dr. Maya Safira is the very first PhD student from our lab. We really appreciate her hard work and efforts. Particularly, she made a great contribution to improving our ability as a team. We will try to keep your meme in our lab. Best wishes for both of your future!