Shintaro Fukushima

Shintaro Fukushima

  • Machine learning
    Data mining

Mathematical theory and computers have been important domains to me ever since I was a graduate student. Recently, I have been conducting research and development on machine learning, data mining and AI. I try to appreciate on-premise issues and the characteristics of the data, bearing in mind that the solutions will be used in real society, in addition to theories and algorithms.

  • Department

  • Biography

    • Ph.D. (Information Science and Technology)

    • 2023-

      Project Associate Professor, Data Science and AI Innovation Research Promotion Center, Shiga University

    • 2015-

      Engaged in research and development on analysis of automobile driving history and dashboard camera data, quality assurance and management of machine learning, materials informatics, abnormaly and change detection, and causal inference with factory data

    • 2017-
      2020

      Ph.D., Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo (change detection and change sign detection in data streams)

    • 2010-
      2014

      Conducted research, development, consulting and business planning associated with machine learning, data mining and services and platforms for analyzing big data for a wide range of areas including manufacturing, finance, Web and medicine, at an electronics manufacturer and think tank

    • 2006-
      2009

      Engaged in research and development on financial engineering at a think tank (built models for derivative pricing and risk measurement)

    • 2004-
      2006

      MS, The Department of Complexity Science and Technology, Graduate School of Frontier Sciences, The University of Tokyo (non-linear mechanics, chaos theory and numerical computations)

    • 2000-
      2004

      BS, Department of Physics, Faculty of Science, The University of Tokyo

  • Publication List/Conference presentation

    Paper

    • Graph Community Augmentation with GMM-based Modeling in Latent Space, 24th IEEE International Conference on Data Mining (ICDM) (selected as one of the best-ranked papers), 2024

    • A Convenient Approach for Lane-Level Congestion Detection with On-Board Camera Images and Vehicle Data, IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), 2024

    • Empirical data-driven approach to eco-friendly deceleration, IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), 2024

    • Network-wide traffic volume estimation using joint matrix factorization with traffic flow conservation law, IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), 2024

    • Estimating Reduction in Travel Time Based on Large Scale Driving Data from Connected Vehicles, IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), 2024

    • POI search log analysis by text embedding contrastive learning, ERTICO - ITS Europe, The 30th ITS World Congress in Dubai, 2024

    • Efficient and Effective Data Collection and Utilization IoT Platform for Connected Cars, ERTICO - ITS Europe, The 30th ITS World Congress in Dubai, 2024

    • Fine-grained spatio-temporal traffic jam detection with connected vehicle driving data, ERTICO - ITS Europe, The 30th ITS World Congress in Dubai, 2024

    • Improvement of corrective operation for in-car voice response systems through sentence clustering, ERTICO - ITS Europe, The 30th ITS World Congress in Dubai, 2024

    • Does experience affect route choice? An instance-based learning approach using vehicle trajectory data, The National Academies of Sciences, Engineering, and Medicine, The 103rd Transportation Research Board Annual Meeting, 2024

    • Balancing summarization and change detection in graph streams. In Proceedgins of 23rd International Conference on Data Mining (ICDM), 2023

    • Revisiting mobility modeling with graph: a graph transformer model for next point-of-interest recommendation, In Proceedings of 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL), 94, pp.1-10, 2023

    • Finding energy-efficient and fast detour routes in unusual traffic events, 26th IEEE International Conference on Intelligent Transportation Systems (ITSC), 2023

    • Spatio-Temporal Meta-Graph Learning for Traffic Forecasting, In Proceedings of 37th AAAI conference on Artificial Intelligence (AAAI), 2023

    • Estimating total traffic volume with statistical modeling approach, In Proceedings of 25th IEEE International Conference on Intelligent Transportation Systems (ITSC), pp.304-309, 2022

    • Graph summarization with latent variable probabilistic models, The 10th International Conference on Complex Networks and their Applications (ComplexNetworks), Springer, pp. 428-440, 2021

    • Change sign detection with differential MDL change statistics and its application to covid-19 pandemic analysis. Scientific Reports, 11(1):19795, 2021

    • Detecting hierarchical changes in latent variable models, In Proceedings of 20th IEEE International Conference on Data Mining (ICDM), pp.1028-1033, 2020

    • Detecting metachanges in data streams from the viewpoint of the MDL principle, Entropy, 21(12), 1134, 2019

    • Model change detection with the MDL principle, IEEE Transactions on Information Theory, 64(9), pp. 6115 - 6126, 2018

    • “Numerical calculation of topological entropy using turning points of a curve transformed by a map.” IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences (Japanese Edition), Vol. J90-A No.12, pp.932-939,2007

    • etc.

    Books and Articles

    • Data utilization, human resource development, and intellectual property utilization for social systems and connected domains, Intellectual Property Association of Japan, Journal of Intellectual Property Association of Japan, vol.20 No.3, pp.45-54, 2024

    • Human Resource Development for Data Utilization in Connected Domain, TECHNICAL INFORMATION INSTITUTE CO.,LYD., Research and development leader, 2022

    • Python Machine Learning (supervision of Japanese translation), Impress, 2016(1st ed.), 2018(2nd ed.), 2020(3rd ed.), 2022(scikit-learn & PyTorch ed.)

    • Pandas for everyone: Python data analysis (supervision of Japanese translation), Impress, 2019(1st ed.), 2023(2nd ed.)

    • Let's try machine learning, Software Design separate volume, Gijutsu-Hyohron, 2019

    • A new data analysis text book with Python, Shoeisha, 2018(1st ed.), 2022(2nd ed.)

    • “Why Python is the Best for Machine Learning.” Software Design, June 2017 issue, 2017

    • Perfect R, Gijutsu-Hyohron, 2017

    • Advanced R (Japanese translation), Kyoritsu Shuppan, 2016

    • Data Scientist Learning Handbook—Introduction to Machine Learning. Gijutsu-Hyohron, 2015

    • Data Analysis Process. Kyoritsu Shuppan, 2015

    • Data Scientist Learning Handbook—Utilization of R, Gijutsu-Hyohron, 2014

    • High-Performance Computing with R. Socym, 2014

    • R package guidebook, Tokyo-Tosho, 2011

    • etc.

    Invited Conference presentation / Lecture

    • Vehicle data analysis and utilization in the areas of connected and social systems, Hara Research Foundation, Frontiers in automotive vehicles and smart mobility, 2024

    • Issues and Challenges of Anomaly and Its Sign Detection for SM and SHM in Vehicle and Production, Japan Society for Artificial Intelligence, Smart Manufacturing and System Health Management (SIG-SMSHM), 1st Conference on Smart Manufacturing and System Health Management (SIG-SMSHM), 2024

    • Trends and Activities in Machine Learning Quality Management and Assurance, Shiga University, Lecture "AI and Information Ethics", 2024

    • Data Analysis and Utilization of Huge-Scale Vehicle Data, PC Cluster Consortium Workshop, PCCC workshop in Osaka2023「Big Data and HPC」, 2023

    • Trends and Activities in Machine Learning Quality Management and Assurance, Data Science Seminar, Shiga University, 2023

    • Vehicle data analysis and utilization in Toyota Motor Corporation, Japan Research Institute for New Systems of Society, SSK Seminar, 2023

    • Development and Outlook on Machine Learning Technique with The Book "Python Machine Learning", Start Python Club, 2023

    • Vehicle data utilization and outlook in Toyota, Japan Planning Institute, JPI seminar, 2022

    • Trends and activities of quality management and assurance of AI and machine learning, TECHNICAL INFORMATION INSTITUTE CO.,LYD., Seminar "Ethical Problems of AI(Artificial Intelligence) and Necessary Actions of Companies", 2022

    • A once-in-a-century period of great change: Data analysis and outlook in the connected domain, Graduate School of Information Science and Technology, DSS Symposium, 2022

    • Vehicle data analysis and utilization in Toyota Motor Corporation, Graduate school lecture: Applied Artificial Intelligence and Data Science D,, School of Computing Department of Computer Science,, Tokyo Institute of Technology, 2022

    • Trends and Activities of Quality Management and Assurance of Machine Learning, DBSJ Seminar, The Database Society of Japan, 2022

    • Important points and use cases in data analysis in TOYOTA, DataRobot Japan Inc., DataRobot Japan Seminar, 2021

    • Key points and case studies in data analysis in TOYOTA, Nagoya University, Mathematical and Data Science Center, Practical Data Scientist Training Program, 2021

    • Trends and activities in materials search and retrosynthetic planning, Materials Informatics Seminar, 2021

    • Trends and Activities of Quality Management and Assurance of Machine Learning, National Institute of Informatics (NII) AI/Iot system symposium executive committee et al., The 2nd AI / IoT System Safety and Security Symposium(AIS^3), 2020

    • Trends and activities in quality management and assurance of machine learning, PyData.Tokyo, 2020

    • “Prospects in Machine Learning Application—Trends and Technologies of AI Quality Assurance,” guest lecture at AI Management Conference, Nikon Corporation, 2019

    • Quality Assurance of Machine Learning AI, CEATEC 2018

    • Materials Informatics and Python -Intesection of condensed matter physics and material science, and data science-, PyData.Tokyo One Day Conference, 2018

    • An Introduction to Machine Learning, Invited talk in Financial dealings and the market economy(2), Graduate School of Commerce, Chuo University, 2018

    • Ideal Image and Development of Human Resources for Data Utilization, guest lecture at 5th Biannual Conference of Transdisciplinary Federation of Science and Technology (Oukan Conference), 2014

    • etc.

    Others

    • Tackling against the era of data localizations: Federated Learning Taskforce approaches, Woven by Toyota. Toyota Global Summit 2023, 2023

  • Commendation/Memberships

    • Visiting Researcher, The University of Tokyo（2020-2022)

    • Visiting Researcher, National Institute of Advanced Industrial Science and Technology (AIST)(FY2019-2023)

    • Committee Member, AI Quality Management Study Committee, Research and Development on Quality Assurance of Machine Learning AI (under the advanced research themes aimed at social implementation of next-generation artificial intelligence technology by the New Energy and Industrial Technology Development Organization and the National Institute of Advanced Industrial Science and Technology)(FY2019-2023)

    • Editorial Committee Member of Academic Journal in The Japan Society for Industrial and Applied Mathematics(FY2021-2023)

    • Research Collaborator, Discrete Geometric Analysis for Materials Design, Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area) (“B01-1 Searching for materials based on analysis of complex networks,” B01 Information Science for Materials Science)(FY2018-2022)

    • Top 10 Books, Technical and Business Books Recommended for IT Specialists 2017, Shoeisha (Python Machine Learning) (2017)

Members List