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

A Study on Large Scale Data Analysis Method and Theoretical Evaluation based on Distance Metric Learning

Research Project

Project/Area Number 26750118
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeMulti-year Fund
Research Field Social systems engineering/Safety system
Research InstitutionShonan Institute of Technology (2016)
Waseda University (2014-2015)

Principal Investigator

Mikawa Kenta  湘南工科大学, 工学部, 講師 (40707733)

Project Period (FY) 2014-04-01 – 2017-03-31
Project Status Completed (Fiscal Year 2016)
Budget Amount *help
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2015: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Keywords計量距離学習 / 機械学習 / パターン認識 / 正則化 / メトリックラーニング / ベクトル空間モデル
Outline of Final Research Achievements

The development in information technology highlighted the importance of knowledge discovery from enormous electronic data. We focus on the distance metric learning which is one of the methods of machine learning. In this study, we propose the regularization methods and the way to select the suitable training data in order to reduce computational complexity of distance metric learning. In addition, we propose the way to obtain multiple distance metrics and integrate those in order to improve the classification accuracy. Consequently, we clarify the effectiveness of our proposed methods.
These methods can be used properly according to the characteristics of the analysis (e.g. to gain high performance, low computational complexity and so on). By using these method properly, it can be implemented various types of analysis.

Report

(4 results)
  • 2016 Annual Research Report   Final Research Report ( PDF )
  • 2015 Research-status Report
  • 2014 Research-status Report
  • Research Products

    (25 results)

All 2017 2016 2015 2014

All Journal Article (7 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 6 results,  Open Access: 6 results,  Acknowledgement Compliant: 5 results) Presentation (18 results) (of which Int'l Joint Research: 6 results)

  • [Journal Article] Data pair selection for accurate classification based on information-theoretic metric learning2017

    • Author(s)
      Takashi Maga, Kenta Mikawa, Masayuki Goto
    • Journal Title

      Asian J. Management Science and Applications

      Volume: 3 Issue: 1 Pages: 61-74

    • DOI

      10.1504/ajmsa.2017.083512

    • Related Report
      2016 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research / Acknowledgement Compliant
  • [Journal Article] A Study on Distance Metric Learning by using Different Metric Matrices in Each Category2016

    • Author(s)
      三川健太,後藤正幸
    • Journal Title

      Journal of Japan Industrial Management Association

      Volume: 66 Issue: 4 Pages: 335-347

    • DOI

      10.11221/jima.66.335

    • NAID

      130005127091

    • ISSN
      1342-2618, 2187-9079
    • Related Report
      2015 Research-status Report
    • Peer Reviewed / Open Access / Acknowledgement Compliant
  • [Journal Article] 計量距離学習手法によるパターン認識とその知識発見への応用2016

    • Author(s)
      三川健太
    • Journal Title

      経営システム

      Volume: Vol. 25, No. 4 Pages: 213-222

    • Related Report
      2015 Research-status Report
  • [Journal Article] Regularized Distance Metric Learning for Document Classification and Its Application2015

    • Author(s)
      Kenta Mikawa and Masayuki Goto
    • Journal Title

      Journal of Japan Industrial Management Association

      Volume: 66 Issue: 2E Pages: 190-203

    • DOI

      10.11221/jima.66.190

    • NAID

      130005097665

    • ISSN
      1342-2618, 2187-9079
    • Related Report
      2015 Research-status Report
    • Peer Reviewed / Open Access / Acknowledgement Compliant
  • [Journal Article] A Study of Learning a Sparse Metric Matrix using <i>l</i><sub>1</sub> Regularization Based on Supervised Learning2015

    • Author(s)
      三川健太,小林学,後藤正幸
    • Journal Title

      Journal of Japan Industrial Management Association

      Volume: 66 Issue: 3 Pages: 230-239

    • DOI

      10.11221/jima.66.230

    • NAID

      130005107068

    • ISSN
      1342-2618, 2187-9079
    • Related Report
      2015 Research-status Report
    • Peer Reviewed / Open Access / Acknowledgement Compliant
  • [Journal Article] Accurate Parameter Estimation Based on Latent Class Model Estimated by Combining Both Evaluation and Purchase Histories2015

    • Author(s)
      大井貴裕,三川健太,後藤正幸
    • Journal Title

      Journal of Japan Industrial Management Association

      Volume: 65 Issue: 4 Pages: 286-293

    • DOI

      10.11221/jima.65.286

    • NAID

      130005002554

    • ISSN
      1342-2618, 2187-9079
    • Related Report
      2014 Research-status Report
    • Peer Reviewed / Open Access / Acknowledgement Compliant
  • [Journal Article] Proposal of a Semiautomatic Classification Method for Systematization of Large-scale Text Data based on Machine Learning2014

    • Author(s)
      下村 良,三川健太,後藤正幸
    • Journal Title

      Journal of Japan Industrial Management Association

      Volume: 65 Issue: 2 Pages: 51-60

    • DOI

      10.11221/jima.65.51

    • NAID

      130004684284

    • ISSN
      1342-2618, 2187-9079
    • Related Report
      2014 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] A Study on Distance Metric Learning using Distance Structure among Category Centroids2016

    • Author(s)
      Kenta Mikawa, Manabu Kobayashi, Masayuki Goto, Shigeichi Hirasawa
    • Organizer
      The 17th Asia Pacific Industrial Engineering and Management Systems Conference (APIEMS 2016
    • Place of Presentation
      Taipei, Taiwan
    • Year and Date
      2016-12-07
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Distance Metric Learning based on Different l1 Regularized Metric Matrices in Each Category2016

    • Author(s)
      Kenta Mikawa, Manabu Kobayashi, Masayuki Goto, Shigeichi Hirasawa
    • Organizer
      2016 International Symposium on Information Theory and its Applications
    • Place of Presentation
      Monterey, California, USA
    • Year and Date
      2016-10-30
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A study of Improving Classification Accuracy of k-nearest Neighbor Based on Local Metric Learning and Adaptive Weighted Ensemble2016

    • Author(s)
      Shuhei Nakano, Seiya Nagamori, Kenta Mikawa, Masayuki Goto
    • Organizer
      The 7th Forum for Council of Industrial Engineering and Logistics Management Department Heads (CIEDH2016) & The 5th Institute of Industrial and Systems Engineering Asian Conference (IISEAsia2016)
    • Place of Presentation
      Hong Kong
    • Year and Date
      2016-07-21
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 代表元間の距離構造を用いた計量距離学習に関する一考察2015

    • Author(s)
      三川健太.小林学,後藤正幸,平澤茂一
    • Organizer
      日本経営工学会平成27年度秋季研究大会
    • Place of Presentation
      金沢
    • Year and Date
      2015-11-28
    • Related Report
      2015 Research-status Report
  • [Presentation] 局所的構造をモデル化可能な計量距離学習に関する一考察2015

    • Author(s)
      齋藤洋,三川健太,後藤正幸
    • Organizer
      日本経営工学会平成27年度秋季研究大会
    • Place of Presentation
      金沢
    • Year and Date
      2015-11-28
    • Related Report
      2015 Research-status Report
  • [Presentation] 複数の局所距離構造を考慮した計量距離学習に関する一考察2015

    • Author(s)
      齋藤洋,三川健太,後藤正幸
    • Organizer
      第38回情報理論とその応用シンポジウム
    • Place of Presentation
      岡山
    • Year and Date
      2015-11-24
    • Related Report
      2015 Research-status Report
  • [Presentation] A Study of Distance Metric Learning by Considering the Distances between Category Centroids2015

    • Author(s)
      Kenta Mikawa, Manabu Kobayashi, Masayuki Goto, and Shigeichi Hirasawa
    • Organizer
      2015 IEEE International Conference on Systems, Mans and Cybanetics
    • Place of Presentation
      中国,香港
    • Year and Date
      2015-10-09
    • Related Report
      2015 Research-status Report
    • Int'l Joint Research
  • [Presentation] Data pair selection for improving classification accuracy of Information-Theoretic Metric Learning2015

    • Author(s)
      Takashi Maga, Kiichiro Yukawa, Kenta Mikawa, Masayuki Goto
    • Organizer
      Asian Conference of Management Science & Applications (ACMSA2015)
    • Place of Presentation
      中国,大連
    • Year and Date
      2015-09-12
    • Related Report
      2015 Research-status Report
    • Int'l Joint Research
  • [Presentation] A Proposal of Classification Method Based on Local Metric Matrices2015

    • Author(s)
      Hiroshi Saito, Kenta Mikawa, Masayuki Goto
    • Organizer
      Asian Conference of Management Science & Applications (ACMSA2015)
    • Place of Presentation
      中国,大連
    • Year and Date
      2015-09-12
    • Related Report
      2015 Research-status Report
    • Int'l Joint Research
  • [Presentation] Information-Theoretic Metric Learningの分類精度向上を目的とした学習データペアの選択法2015

    • Author(s)
      馬賀嵩士,湯川輝一朗,三川健太,後藤正幸
    • Organizer
      日本経営工学会平成27年度春季研究大会
    • Place of Presentation
      東京
    • Year and Date
      2015-05-16
    • Related Report
      2015 Research-status Report
  • [Presentation] An Analysis of Purchasing and Browsing Histories on an EC Site Based on a New Latent Class Model2014

    • Author(s)
      Masayuki Goto, Kenta Mikawa, Manabu Kobayashi, Shunsuke Horii, Tota Suko, Shigeichi Hirasawa
    • Organizer
      The 1st East Asia Workshop on Industrial Engineering
    • Place of Presentation
      Hiroshima, Japan
    • Year and Date
      2014-11-07 – 2014-11-09
    • Related Report
      2014 Research-status Report
  • [Presentation] A Prediction Method based on Weighted Ensemble of Decision Trees on Alternating Decision Forests.2014

    • Author(s)
      Shotaro Misawa, Naohiro Fujiwara, Kenta Mikawa, Masayuki Goto
    • Organizer
      15th Asia Pacific Industrial Engineering and Management Society
    • Place of Presentation
      Jeju, Korea
    • Year and Date
      2014-10-12 – 2014-10-15
    • Related Report
      2014 Research-status Report
  • [Presentation] A New Estimation Method of Latent Class Model with High Accuracy by Using Both Browsing and Purchase Histories2014

    • Author(s)
      Naohiro Fujiwara, Kenta Mikawa, Masayuki Goto
    • Organizer
      15th Asia Pacific Industrial Engineering and Management Society
    • Place of Presentation
      Jeju, Korea
    • Year and Date
      2014-10-12 – 2014-10-15
    • Related Report
      2014 Research-status Report
  • [Presentation] A Statistical Model for Recommender System to Maximize Sales Amount Focusing on Characteristics of EC Site Data2014

    • Author(s)
      Kan Yamagami, Naohiro Fujiwara, Kenta Mikawa, Masayuki Goto
    • Organizer
      15th Asia Pacific Industrial Engineering and Management Society
    • Place of Presentation
      Jeju, Korea
    • Year and Date
      2014-10-12 – 2014-10-15
    • Related Report
      2014 Research-status Report
  • [Presentation] Distance Metric Learning with Low Computational Complexity based on Ensemble of the Low-dimensional Matrixes2014

    • Author(s)
      Hiroshi Saito, Fumihiro Yamazaki, KentaMikawa, Masayuki Goto
    • Organizer
      15th Asia Pacific Industrial Engineering and Management Society
    • Place of Presentation
      Jeju, Korea
    • Year and Date
      2014-10-12 – 2014-10-15
    • Related Report
      2014 Research-status Report
  • [Presentation] Statistical Model Selection of Liner Regression for Privacy Preserving Data Mining2014

    • Author(s)
      Kiichiro Yukawa, Kenta Mikawa, Masayuki Goto
    • Organizer
      15th Asia Pacific Industrial Engineering and Management Society
    • Place of Presentation
      Jeju, Korea
    • Year and Date
      2014-10-12 – 2014-10-15
    • Related Report
      2014 Research-status Report
  • [Presentation] A Proposal of l1 Regularized Distance Metric Learning for High Dimensional Sparse Vector Space2014

    • Author(s)
      Kenta Mikawa, Manabu Kobayashi, Masayuki Goto, Shigeichi Hirasawa
    • Organizer
      IEEE International Conference on Systems, Mans and Cybanetics
    • Place of Presentation
      San Diego, USA
    • Year and Date
      2014-10-05 – 2014-10-08
    • Related Report
      2014 Research-status Report
  • [Presentation] A Modified Aspect Model for Simulation Analysis2014

    • Author(s)
      Masayuki Goto, Kazushi Minetoma, Manabu Kobayashi, Shigeichi Harasawa
    • Organizer
      IEEE International Conference on Systems, Mans and Cybanetics
    • Place of Presentation
      San Diego, USA
    • Year and Date
      2014-10-05 – 2014-10-08
    • Related Report
      2014 Research-status Report

URL: 

Published: 2014-04-04   Modified: 2018-03-22  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi