spacer


Takahiko Kusakabe / Assistant Professor / Spatial Information Science
Department of Socio-Cultural Environmental Studies / / Urban Mobility, Transportation Science, ITS
http://www.csis.u-tokyo.ac.jp/~t.kusakabe/index_en.html

Career Summary
2006: Graduated from Dept. of Civil Engineering, Faculty of Engineering, Kobe University
2008: M.Eng. from Dept. of Architecture and Civil Engineering, Graduate School of Science and Technology, Kobe University
2010: Dr.Eng. from Dept. of Civil Engineering, Graduate School of Engineering, Kobe University
2010: Research Fellow (JSPS)
2011-16: Assistant Professor (Graduate School of Science and Engineering, Tokyo Institute of Technology)
2015: Visiting Fellow (Civil Engineering and The Built Environment, Queensland University of Technology)
2016: Assistant Professor (University of Tokyo)
Educational Activities
Graduate School: Urban and Regional Spatial Information Analysis
Research Activities
Recent advances with information technologies (such as the Internet of Things (IoT)) enable us to collect massive dynamic spatial information relating to human and automobile behavior. Dr. Kusakabefs study topics are related to the development of methodologies for implementing such advanced technologies for urban transport networks and travel behavior analysis by using data-fusion, data mining, and machine-learning methods.


Understanding human behavior from massive dynamic spatial information
This study introduced a visualization method and data mining analysis for large historical datasets related to transportation systems, including traffic detector data collected at urban expressways, transit smart card data of public transport, and probe vehicle data. Results showed that the proposed methods were able to reveal the spatiotemporal characteristics of transport systems. Furthermore, models of travel patterns and their variability over long-term periods were developed to clarify changes in travel demand. In future study, simulation models based on massive datasets will be investigated in order to estimate and predict human behavior in urban transport networks.

Developing data fusion method

Recently in the field of transport engineering, passive datasets such as traffic detector data, smart card data, probe vehicle data, Wi-Fi, and Bluetooth can be automatically and continuously collected while systems are operating. Most of these data provide continuous and long-term travel information, which is difficult to achieve with a simple survey. However, they are too fragmentary when it comes to analyzing human behavior. In contrast, while conventional datasets of human travel behavior collected by designed surveys include sufficient information about travel for analyzing travel behavior, it is difficult to conduct continuous and long-term surveys due to their cost and the burden on respondents. To overcome the shortcomings of each type of dataset and to fuse the advantages, we developed a data fusion method using transit smart cards and household survey data. The empirical data mining analysis showed that the proposed methodology can be applied to find and interpret the behavioral features observed in smart card data that had been difficult to obtain from each independent dataset. In future study, methodologies to fuse larger datasets (e.g., probe vehicle data) with various spatial information (e.g., weather data) will be investigated.
Literature
1) T. Kusakabe, T. Iryo, and Y. Asakura (2010) Data Mining For Traffic Flow Analysis: Visualization Approach. In: Barcelo, M. Kuwahara (eds.), Traffic Data Collection and its Standardization. Springer Series, pp. 57-72
2) T. Kusakabe, T. Iryo, and Y. Asakura (2010) Estimation Method for Railway Passengersf Train Choice Behavior with Smart Card Transaction Data. Transportation, Vol. 37 (5), pp. 731-749
3) T. Kusakabe and Y. Asakura (2014) Behavioural Data Mining of Transit Smart Card Data: A Data Fusion Approach. Transportation Research Part C: Emerging Technologies, Vol. 46, pp. 179-191
4) T. Seo, T. Kusakabe, and Y. Asakura (2015) Estimation of flow and density using probe vehicles with spacing measurement equipment. Transportation Research Part C: Emerging Technologies, Vol. 53, pp. 134-150
5) T. Kusakabe and Y. Nakano (2015) Information provision strategies eliminating deluded equilibrium caused by travellers' misperception. Transportation Research Part C: Emerging Technologies, Vol. 59, pp. 278-291
6) T. Seo, T. Kusakabe, and Y. Asakura (2015) Probe vehicle-based traffic state estimation method with spacing information and conservation law. Transportation Research Part C: Emerging Technologies, Vol. 59, pp. 391-403
7) Y. Asakura, T. Kusakabe, N.X. Long, and T. Ushiki (2016) Incident Detection Methods using Probe Vehicles with on-board GPS Equipment. Transportation Research Part C: Emerging Technologies, in press.
8) T. Kusakabe and Y. Asakura (2016) Combination of Smart Card Data with Person Trip Survey Data. In: Fumitaka Kurauchi, Jan-Dirk Schmocker (eds.), Public Transport Planning with Smart Card Data, CRC Press, pp. 73-92
Other Activities
Japan Society of Civil Engineers (JSCE)
Japan Society of Traffic Engineers (JSTE)
Association for Planning and Transportation Studies
Eastern Asia Society for Transportation Studies (EASTS)
Information Processing Society of Japan (IPSJ)
World Conference on Transport Research Society (WCTRS)
Institute of Electrical and Electronics Engineers (IEEE)
spacer
Future Plan
Our study topics are related to the development of methodologies for implementing advanced technologies for urban transport network system analysis and travel behavior analysis. These methodologies will be applied to the system analysis of future mobility systems.
Messages to Students
Our research includes various activities such as field surveys, programming, and mathematical modeling relating to computer science, spatial information science, transportation science/engineering, and econometrics. We welcome various students who have different backgrounds and fields of expertise.
top