2018 6th Learning Seminar: “Parameter Estimation for NL and NXL Models”
[2018/05/18]
In the 6th seminar, Mr. Kawai (M1) and Ms. Koike (M1) in Asakura Laboratory were in charge of parameter estimation of Nested Model and Cross Nested Model.
This model is used when there is some correlation between alternatives when people make decisions. Mr. Kawai used Python biogeme, while Ms. Koike used R to estimate the model using the maxLik function introduced in the previous session.
The 3rd Lab Seminar in 2018 (Azarel, Salsa)
[2018年5月16日]
This seminar was in charge by Mr. Azarel (M2) and Ms. Salsa (M1).
Azarel is an M2 student who admitted in the fall and will finish in July of this year, so he gave a report on the status of his ongoing research. He is conducting a research on “creating a new means of transportation for residents in a remote town by considering carpooling service as a social infrastructure” and is now examining the validity of the model he has constructed using the data of BlaBlaCar collected in Spain.
Ms. Salsa was enrolled in the fall too. She is in the second semester of her M1 course. She introduced us with various indicators in the process of creating an evaluation model for development along the rail line.
2018 5th Learning Seminar “Derivation and Parameter Estimation of MNL”
[2018/05/14]
The introduction has been completed up to the 4th seminar, and in the 5th and subsequent basic seminars, students will learn some specialized contents along with programming. This time it was “Derivation and Parameter Estimation of MNL”. Mr. Koizumi (M1) and Mr. Muro (M1) from Asakura Laboratory (a laboratory belonging to TSU) were in charge of this seminar.
The main feature was the introduction of the “maxLik” package in R statistical software. The “Optim” package used in the past had a problem of producing erroneous estimation results in transportation mode choice models when the sample to be analyzed differed depending on the mode of transportation. The new “maxLik” package was introduced to deal with this problem.
2018 4th Learning Seminar: “Document creation and document management software using LaTeX”
[2018/05/08]
The title of the 4th learning seminar was “Document creation and document management software using LaTeX”. Mr. Imaoka (M2) and Mr. Shiroma (M1) were in charge of this seminar.
Mr. Imaoka introduced the basic commands of LaTeX, which will be useful for writing graduation theses, master’s theses, and other research papers. Mr. Shiroma introduced two applications: Zotero, which allows users to easily retrieve bibliographic information from websites such as Transportatin Research, and JabRef, which is used to manage bibliographic information.
The 2nd Lab Seminar in 2018 (Imaoka, Kaneko)
[2018/05/07]
Mr. Imaoka-kun (M2) and Ms. Kaneko (M2) were in charge of this seminar, and since they are M2s, their presentations focused on their master’s research plans.
Mr. Imaoka is going to do his master’s research on “Modeling of Railway Delay”, while Ms. Kaneko, who studied abroad in Switzerland in the second semester of last year, is developing a plan for “Theory of Recursive Logit Model and its Applications”. This is a very difficult subject, but let’s do our best!
The 1st Lab Seminar in 2018 (Hirabayashi, Suzuki)
[2018/05/02]
Sorry for the late update. The first lab seminar of this year was led by Ms. Hirabayashi (M2) and Mr. Suzuki (M2). The presentations consisted of two parts: past researches and master’s thesis plans.
The position of the laboratory seminar is to provide a platform to share the contents of one’s own research with the members. In other words, it is an opportunity to explain the research flow in a broad sense, rather than explaining detailed research methods, etc. Each person has one hour, with 30 minutes for a presentation and 30 minutes for a question-and-answer session.
Ms. Hirabayashi introduced her work on “research for reducing traffic congestion in urban areas based on MFD theory” and “pedestrian model” as a concept he worked on last year. On the other hand, Mr. Suzuki presented “Research on Data Fusion of Inter-Urban Flow” as the former and “Creation of Optimal Inter-Urban Networks” as the latter. Let’s do our best in the master’s research.
2018 Suzukake Peripatos Ekiden (Relay Race)
[2018/05/06]
We participated in the 2nd “Suzukake Peripatos Ekiden” held at the Suzukakedai Campus as a team from the Fukuda Lab! We got the 6th place in Block B!
There was a strong wind blowing that day, but the weather was fine and it was a perfect day for the road relay race. This is a 1.9km route consisting of 99% slopes, which is 4 laps by 4 people. Our laboratory consists of Mr. Shiroma (M1) > Mr. Gohyaku (M1) & Nacchan (elementary school student) > Mr. Imaoka (M2) > Ms. Hirabayashi (M2). It was a very hard course, but I feel that we were able to enjoy an active event suitable for the last day of Golden Week. Let’s keep a good balance between our studies and work hard on our research!
2018 3rd Learning Seminar “Regression Analysis & Causal Effect Analysis”
[2018/05/01]
The 3rd Basic Seminar was “Regression Analysis” and “Causal Effect Analysis”. Mr. Suzuki explained the former, while Mr. Shiroma explained the latter.
In the “regression analysis” part, participants were listened to a brief explanation of the theory and executing code in R.
In “causal effects analysis” part, the theory was explained and packages were introduced, and the seminar ended with a lengthy discussion on the control variable method. The instrumental variable method seems to be a method used in ordinary regression analysis when there is a correlation between the explanatory variable and the error term. However, it does not seem to be very versatile, for example, it is difficult to find a control variable, and it is not necessary to use it if panel data are available. As my understanding is insufficient, I would appreciate it if someone could teach me in details.
2018 2nd Learning Seminar “Big Data Processing & Basic operations of QGIS”
[2018/04/27].
The second learning seminar was held. The contents were “Big Data Processing” by Mr. Koizumi of Asakura Lab, and “Basic operations of QGIS” by Ms. Salsa and Mr. Azarel.
R and Python were used for “Big Data Processing” and there was a comparison of calculation speeds and introduction of effective packages.
In “Basic Operations of QGIS,” the participants installed plug-ins for OpenStreetMap and basic analysis, read shapefiles, and narrowed down conditions on the attribute table. This was especially important in the field of transportation, where large amounts of data are frequently handled and visualized on maps. Mr. Koizumi, Ms. Salsa, and Mr. Azarel all explained in an easy-to-understand manner, and I feel that this seminar was very fruitful!
2018 1st Learning Seminar “Introduction to R and Python”
[2018/04/25]
We’ve started this academic year’s learning seminar! The first learning seminar was an introduction to R and Python. We will have external students and new 4th year undergraduate students learn R and Python first through the basic seminar. Let’s acquire skills and knowledge one by one!
※As a start-up, Fukuda Laboratory conducts a basic seminar on the three basic theories (travel behavior, traffic flow, and traffic network) necessary for traffic analysis in the first two to three months of the school year. In 2017, we held a seminar on basic theory and applied methods (programming) for “travel behavior analysis” and “traffic network analysis”. ［The seminar was held in the graduate course of Prof. Marco Nie on “Traffic Flow Theory.”]
