• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Human behavior modeling with hierarchical Bayesian models

Research Project

Project/Area Number 20700181
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeSingle-year Grants
Research Field Perception information processing/Intelligent robotics
Research InstitutionThe University of Tokyo

Principal Investigator

SHIMOSAKA Masamichi  The University of Tokyo, 大学院・情報理工学系研究科, 助教 (40431796)

Project Period (FY) 2008 – 2009
Project Status Completed (Fiscal Year 2009)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2009: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2008: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Keywords統計的情報処理 / 機械学習 / 行動モデリング
Research Abstract

In this research, a statistical approach of human behavior modeling is proposed and verified. In this study, issues on automatic extraction of latent factors from human behavior data are focused. In contrast to the conventional human behavior modeling where behavior models are estimated independently from each individual, the proposed model, which is formulated with Dirichlet process priors, automatically couples similar human behavior and provides robust estimation from the coupled behavior data. Empirical evaluation using human behavior sensor data shows that our model improves better estimation accuracy.

Report

(3 results)
  • 2009 Annual Research Report   Final Research Report ( PDF )
  • 2008 Annual Research Report
  • Research Products

    (11 results)

All 2010 2009 2008

All Journal Article (2 results) (of which Peer Reviewed: 2 results) Presentation (9 results)

  • [Journal Article] Discriminative Data Visualization for Daily Behavior Modeling2009

    • Author(s)
      Masamichi Shimosaka, Taketoshi Mori, Akinori Fujii, Tomomasa Sat
    • Journal Title

      Advanced Robotics Vol.23,No.4

      Pages: 429-441

    • NAID

      10027462749

    • Related Report
      2009 Final Research Report
    • Peer Reviewed
  • [Journal Article] Discriminative Data Visualization for Daily Behavior Modeling2009

    • Author(s)
      Masamichi Shimosaka and Taketoshi Mori and and Akinori Fuiii Tomomasa Sato
    • Journal Title

      Advanced Robotics 23 23(印刷中)(掲載確定)

    • NAID

      10027462749

    • Related Report
      2008 Annual Research Report
    • Peer Reviewed
  • [Presentation] Detecting human activity profiles with Dirichlet enhanced inhomogeneous Poisson processes2010

    • Author(s)
      Masamichi Shimosaka, Takahito Ishino, Hiroshi Noguchi, Tomomasa Sato, Taketoshi Mori
    • Organizer
      20th International Conference on Pattern Recognition (ICPR 2010)
    • Place of Presentation
      Istanbul, Turkey
    • Related Report
      2009 Final Research Report
  • [Presentation] Detecting human activity profiles with Dirichlet enhanced in homogeneous Poisson processes2010

    • Author(s)
      Masamichi Shimosaka, Takahito Ishino, Hiroshi Noguchi, Tomomasa Sato, Taketoshi Mori
    • Organizer
      20^<th> International Conference on Pattern Recognition(ICPR 2010)
    • Place of Presentation
      Istanbul, Turkey(採録決定済)
    • Related Report
      2009 Annual Research Report
  • [Presentation] 活動量センサの長期記録からのディリクレ拡張時変ポワソン過程に基づく生活パターンマイニング2009

    • Author(s)
      下坂正倫, 佐藤知正, 森武俊
    • Organizer
      第10回(社)計測自動制御学会システムインテグレーション部門講演会(SI2009)
    • Place of Presentation
      東京
    • Year and Date
      2009-12-24
    • Related Report
      2009 Annual Research Report 2009 Final Research Report
  • [Presentation] Fast Online Action Recognition with Efficient Structured Boosting2009

    • Author(s)
      Masamichi Shimosaka, Yu Nejigane, Taketoshi Mori, Tomomasa Sato
    • Organizer
      The 2009 IEEE International Conference on Multimedia & Expo (ICME 2009)
    • Place of Presentation
      New York City, United States
    • Year and Date
      2009-07-01
    • Related Report
      2009 Final Research Report
  • [Presentation] Fast Online Action Recognition with Efficient Structured Boosting2009

    • Author(s)
      Masamichi Shimosaka, Yu Nejigane, Taketoshi Mori, Tomomasa Sato
    • Organizer
      The 2009 IEEE International Conference on Multimedia & Expo(ICME 2009)
    • Place of Presentation
      New York City, United States of America
    • Year and Date
      2009-07-01
    • Related Report
      2009 Annual Research Report
  • [Presentation] 3D Voxel Based Online Human Pose Estimation via Robust and Efficient Hashing2009

    • Author(s)
      Masamichi Shimosaka, Yuichi Sagawa, Taketoshi Mori, Tomomasa Sato
    • Organizer
      The 2009 IEEE International Conference on Robotics and Automation (ICRA 2009)
    • Place of Presentation
      神戸市
    • Year and Date
      2009-05-16
    • Related Report
      2009 Final Research Report
  • [Presentation] 3D Voxel Based Online Human Pose Estimation via Robust and Efficient Hashing2009

    • Author(s)
      Masamichi Shimosaka, Yuichi Sagawa, Taketoshi Mori, Tomomasa Sato
    • Organizer
      The 2009 IEEE International Conference on Robotics and Automation(ICRA 2009)
    • Place of Presentation
      Kobe, Japan
    • Year and Date
      2009-05-16
    • Related Report
      2009 Annual Research Report
  • [Presentation] Robust indoor activity recognition via boosting2008

    • Author(s)
      Masamichi Shimosaka, Taketoshi Mori, Tomomasa Sato
    • Organizer
      19th International Conference on Pattern Recognition (ICPR2008)
    • Place of Presentation
      Tampa, United States
    • Year and Date
      2008-12-08
    • Related Report
      2009 Final Research Report
  • [Presentation] Robust indoor activity recognition via boosting2008

    • Author(s)
      Masamichi Shimosaka and Tak etoshi Mori and Tomomasa Sato
    • Organizer
      19th International Conference on Pattern Recognition (ICPR2008)
    • Place of Presentation
      米国フロリダタンパ
    • Year and Date
      2008-12-08
    • Related Report
      2008 Annual Research Report

URL: 

Published: 2008-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi