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

MARE: Recognition and Discovery Techniques for Giving Awarenesss

Research Project

Project/Area Number 19H04128
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 61010:Perceptual information processing-related
Research InstitutionHokkaido University

Principal Investigator

Kudo Mineichi  北海道大学, 情報科学研究院, 教授 (60205101)

Co-Investigator(Kenkyū-buntansha) 今井 英幸  北海道大学, 情報科学研究院, 教授 (10213216)
中村 篤祥  北海道大学, 情報科学研究院, 教授 (50344487)
Project Period (FY) 2019-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥17,030,000 (Direct Cost: ¥13,100,000、Indirect Cost: ¥3,930,000)
Fiscal Year 2023: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2022: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2021: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2020: ¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2019: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Keywords不頻出事象 / マルチラベル分類 / 希少疾患の発見 / 高齢者の異変検知 / 異変検出 / 希少疾患 / 独居高齢者 / 可視化 / パターン認識 / ロングテール分布 / 異変検知 / 認知症 / インバランス問題 / ロングテイル / ロングテール / オーバーラップ問題 / 不頻出事象の予測 / マイノリティクラス / データマイニング
Outline of Research at the Start

非頻出なコトやモノの認識や予測を行うことは、希少疾患の発見や見逃していた事項の想起、新しい着想への手がかりの入手、など、「気づき」や「発見」を与える上で有効である。しかし一方では、非頻出ゆえのデータ不足や見分けの難しさなど、固有の難しさを抱える。本研究では、パターン認識分野とデータマニング分野において、この挑戦的課題に取り組む。
基本方針は、他の多数の候補から非頻出事象を「識別」するのではなく、個々の非頻出事象が該当するどうかを「同定」する点にあり、疑わしい場合、更なる証拠を調査して「確定」する。本研究グループの有するこれまでの技術を動員して効果のある方法論を新しく築く。

Outline of Final Research Achievements

On the standing point that rare events, such as rare diseases, anomaly of elderly living alone and interesting but unknown area, are more important than usual events, we have developed techniques for discovering rare events and classifying them. The reasons of occurrence of rare events were revealed to be "new" and devised from the necessity of finer labels. Accordingly, on the basis of these reasons, we developed some classifiers, but only a small amount of improvement was achieved by them.
As an application, on discovery of rate diseases, we have shown that visualization is useful for distinguishing rate events from ordinary events. For detecting anomalies of elderly living alone, we have developed a behavior simulator in a virtual smart home and detection algorithms of anomaly detection.

Academic Significance and Societal Importance of the Research Achievements

不頻出事象はこの世界にあまねく存在するものの、その希少性により扱いが難しい。本研究はそれらの分類についての方法論を深化させた。特に、専門家でも難しい希少疾患の発見の一助になる方法を提示できたこと、スマートホームを利用して独居高齢者の異変を検知する試みの基本的有効性を示せたことの意義は大きい。

Report

(6 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Annual Research Report
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • 2019 Annual Research Report
  • Research Products

    (34 results)

All 2024 2023 2022 2021 2020 2019

All Journal Article (14 results) (of which Int'l Joint Research: 3 results,  Peer Reviewed: 14 results,  Open Access: 2 results) Presentation (20 results) (of which Int'l Joint Research: 16 results)

  • [Journal Article] Robust embedding regression for semi-supervised learning2024

    • Author(s)
      Bao Jiaqi、Kudo Mineichi、Kimura Keigo、Sun Lu
    • Journal Title

      Pattern Recognition

      Volume: 145 Pages: 109894-109894

    • DOI

      10.1016/j.patcog.2023.109894

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Redirected transfer learning for robust multi-layer subspace learning2024

    • Author(s)
      Bao Jiaqi、Kudo Mineichi、Kimura Keigo、Sun Lu
    • Journal Title

      Pattern Analysis and Applications

      Volume: 27 Issue: 1

    • DOI

      10.1007/s10044-024-01233-8

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Efficient Leave-One-Out Evaluation of Kernelized Implicit Mappings2023

    • Author(s)
      Mineichi Kudo, Keigo Kimura, Shumpei Morishita and Lu Sun
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 13813 Pages: 223-232

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Retargeted Regression Methods for Multi-label Learning2023

    • Author(s)
      Kimura Keigo, Bao Jiaqi, Kudo Mineichi and Sun Lu
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 13813 Pages: 203-212

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Realization of Autoencoders by Kernel Methods2023

    • Author(s)
      Shumpei Morishita, Mineichi Kudo, Keigo Kimura, and Lu Sun
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 13813 Pages: 1-10

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Kernelized Supervised Laplacian Eigenmap for Visualization and Classification of Multi-Label Data2022

    • Author(s)
      Tai Mariko、Kudo Mineichi、Tanaka Akira、Imai Hideyuki、Kimura Keigo
    • Journal Title

      Pattern Recognition

      Volume: 123 Pages: 108399-108399

    • DOI

      10.1016/j.patcog.2021.108399

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Sensor Data Simulation with Wandering Behavior for the Elderly Living Alone2022

    • Author(s)
      Tanaka Kai、Kudo Mineichi、Kimura Keigo
    • Journal Title

      Proc. of the 26TH International Conference on Pattern Recognition

      Volume: 2022 Pages: 885-891

    • DOI

      10.1109/icpr56361.2022.9956332

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] AdaLSH: Adaptive LSH for Solving <i>c</i>-Approximate Maximum Inner Product Search Problem2021

    • Author(s)
      LU Kejing、KUDO Mineichi
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E104.D Issue: 1 Pages: 138-145

    • DOI

      10.1587/transinf.2020EDP7132

    • NAID

      130007965130

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2021-01-01
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] HVS: Hierarchical Graph Structure Based on Voronoi Diagrams for Solving Approximate Nearest Neighbor Search2021

    • Author(s)
      Kejing Lu, Mineichi Kudo, Chuan Xiao, Yoshiharu Ishikawa
    • Journal Title

      Proceedings of the VLDB Endowment

      Volume: 15 Issue: 2 Pages: 246-258

    • DOI

      10.14778/3489496.3489506

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Balancing of Samples in Class Hierarchy2021

    • Author(s)
      Aoki Shuhei、Kudo Mineichi
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 13055 Pages: 219-228

    • DOI

      10.1007/978-3-030-89691-1_22

    • ISBN
      9783030896904, 9783030896911
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Feature Selection with Class Hierarchy for Imbalance Problems2021

    • Author(s)
      Horio Tomoya、Kudo Mineichi
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 13055 Pages: 229-238

    • DOI

      10.1007/978-3-030-89691-1_23

    • ISBN
      9783030896904, 9783030896911
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] SVM Based EVM for Open Space Problems2021

    • Author(s)
      Kaneko Yasuyuki、Kudo Mineichi
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 13055 Pages: 239-248

    • DOI

      10.1007/978-3-030-89691-1_24

    • ISBN
      9783030896904, 9783030896911
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] MLSH: Mixed Hash Function Family for Approximate Nearest Neighbor Search in Multiple Fractional Metrics2021

    • Author(s)
      Lu Kejing、Kudo Mineichi
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 12682 Pages: 569-584

    • DOI

      10.1007/978-3-030-73197-7_38

    • ISBN
      9783030731960, 9783030731977
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] VHP: Approximate Nearest Neighbor search via Virtual Hypersphere partitioning2020

    • Author(s)
      Lu Kejing、Wang Hongya、Wang Wei、Kudo Mineichi
    • Journal Title

      Proceedings of the VLDB Endowment

      Volume: 13 Issue: 9 Pages: 1443-1455

    • DOI

      10.14778/3397230.3397240

    • NAID

      120006896741

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Presentation] Partial Multi-label Learning with a Few Accurately Labeled Data2023

    • Author(s)
      Mizuguchi Haruhi、Kimura Keigo、Kudo Mineichi、Sun Lu
    • Organizer
      the 20th Pacific Rim International Conference on Artificial Intelligence (PRICAI2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Daily Gait Recording Using Infrared Analog Sensors2023

    • Author(s)
      Satoshi Nozu, Mineichi Kudo, Keigo Kimura
    • Organizer
      the 5th International Conference on Activity and Behavior Computing (ABC2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Efficient Leave-One-Out Evaluation of Kernelized Implicit Mappings2022

    • Author(s)
      Mineichi Kudo, Keigo Kimura, Shumpei Morishita and Lu Sun
    • Organizer
      S+SSPR2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Retargeted Regression Methods for Multi-label Learning2022

    • Author(s)
      Kimura Keigo, Bao Jiaqi, Kudo Mineichi and Sun Lu
    • Organizer
      S+SSPR2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Realization of Autoencoders by Kernel Methods2022

    • Author(s)
      Shumpei Morishita, Mineichi Kudo, Keigo Kimura, and Lu Sun
    • Organizer
      S+SSPR2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Sensor Data Simulation with Wandering Behavior for the Elderly Living Alone2022

    • Author(s)
      Tanaka Kai、Kudo Mineichi、Kimura Keigo
    • Organizer
      ICPR2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] MLSH: Mixed Hash Function Family for Approximate Nearest Neighbor Search in Multiple Fractional Metrics2021

    • Author(s)
      Lu Kejing、Kudo Mineichi
    • Organizer
      26th International Conference (DASFAA 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Balancing of Samples in Class Hierarchy2021

    • Author(s)
      Aoki Shuhei、Kudo Mineichi
    • Organizer
      7th International Workshop on Artificial Intelligence and Pattern Recognition (IWAIPR2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] SVM Based EVM for Open Space Problems2021

    • Author(s)
      Kaneko Yasuyuki、Kudo Mineichi
    • Organizer
      7th International Workshop on Artificial Intelligence and Pattern Recognition (IWAIPR2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Feature Selection with Class Hierarchy for Imbalance Problems2021

    • Author(s)
      Horio Tomoya、Kudo Mineichi
    • Organizer
      7th International Workshop on Artificial Intelligence and Pattern Recognition (IWAIPR2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] R2LSH: A Nearest Neighbor Search Scheme Based on Two-dimensional Projected Spaces2020

    • Author(s)
      Lu Kejing、Kudo Mineichi
    • Organizer
      ICDE 2020
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Data-Dependent Conversion to a Compact Integer-Weighted Representation of a Weighted Voting Classifier2020

    • Author(s)
      Mitsuki Maekawa, Atsuyoshi Nakamura, Mineichi Kudo
    • Organizer
      Proceedings of The 12th Asian Conference on Machine Learning
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Supervised Laplacian Eigenmaps Algotithm for Visualization of Multi-label Data: SLE-ML2019

    • Author(s)
      Mariko Tai and Mineichi Kudo
    • Organizer
      24th Iberoamerican Congress on Pattern Recognition
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Conversion from a Real-Weighted Majority Voting Classifier to a Small-Non-Negative-Integer-Weighted Thresholded Voting Classifier2019

    • Author(s)
      M Maekawa, A Nakamura, M Kudo
    • Organizer
      ACML 2019 Workshop on Statistics & Machine Learning Researchers in Japan
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Fast Approximate Algorithm for k-Median Problem on a Graph.2019

    • Author(s)
      K Todo, A Nakamura, M Kudo
    • Organizer
      15th International Workshop on Mining and Learning with Graphs
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Learning a Nonlinear Model of Subgraph Features Using Monte Carlo Tree Search2019

    • Author(s)
      R Shirakawa, A Nakamura, M Kudo
    • Organizer
      ACML 2019 Workshop on Statistics & Machine Learning Researchers in Japan
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] ルールアンサンブル法を用いたマイノリティクラスの識別,2019

    • Author(s)
      横山祐也, 工藤峰一
    • Organizer
      電子情報通信学会技術研究報告, PRMU
    • Related Report
      2019 Annual Research Report
  • [Presentation] マルチラベル判別ラプラシアン固有マップのカーネル化2019

    • Author(s)
      田井茉莉子, 工藤峰一
    • Organizer
      電子情報通信学会技術研究報告, PRMU-59
    • Related Report
      2019 Annual Research Report
  • [Presentation] 微小なうなずきの検出精度向上2019

    • Author(s)
      小城佑樹, 工藤峰一
    • Organizer
      電子情報通信学会技術研究報告, PRMU-59
    • Related Report
      2019 Annual Research Report
  • [Presentation] ブラックボックス関数のノイズ入り関数値からの閾値以上の値の存在チェック2019

    • Author(s)
      伊藤直輝, 中村篤祥, 工藤峰一
    • Organizer
      第22回情報論的学習理論ワークショップ
    • Related Report
      2019 Annual Research Report

URL: 

Published: 2019-04-18   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi