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

Rule Insertion and Extraction in Evolutionary Neural Networks for Image Retrieval

Research Project

Project/Area Number 13680448
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionThe University of Tokushima

Principal Investigator

FUKUMI Minoru  The University of Tokushima Faculty of Engineering Associate Professor, 工学部, 助教授 (80199265)

Co-Investigator(Kenkyū-buntansha) KITA Kenji  The Univesity of Tokushima Center for Admanced Intormation Technology Professor, 高度情報化基盤センター, 教授 (10243734)
AKAMATSU Norio  The Univesity of Tokushima Faculty of Engineering Professor, 工学部, 教授 (20035629)
MITSUKURA Yasue  The Univesity of Tokushima Faculty of Engineering Instructor, 工学部, 助手 (60314845)
Project Period (FY) 2001 – 2002
Project Status Completed (Fiscal Year 2002)
Budget Amount *help
¥3,300,000 (Direct Cost: ¥3,300,000)
Fiscal Year 2002: ¥1,500,000 (Direct Cost: ¥1,500,000)
Fiscal Year 2001: ¥1,800,000 (Direct Cost: ¥1,800,000)
KeywordsNeural Network / Evolutionary Method / Rule Extraction / Image / Knowledge Extraction / Image Retrieval / Learning / Internet / 進化的アルゴリズム
Research Abstract

This study presents a new knowledge incorporation and rule extraction method to deal with knowledge in neural networks for image retrieval in the Internet. The rule form of an if-then type can be inserted into a neural network (NN) as knowledge of a problem. NN is then trained by using a set of training samples. In this case the structure learning algorithm with forgetting is used to generate a small-sized NN system. After the NN training, rules are extracted from it. Furthemore evolutionary methods are used to train the neural network structure. The results of computer simulations for pattern recognition and chaos show that this approach can generate obvious network architectures and as a result simple rules compared with conventional rule extraction methods.
On the one hand, a method for image classification by neural networks which uses characteristic data extracted from images is studied. And also rule extraction from images has be done by neural network learning. Accuracy for image classification and key word extraction is about 70%.
In the future, these techniques must be unified and implemented for image retrieval.

Report

(3 results)
  • 2002 Annual Research Report   Final Research Report Summary
  • 2001 Annual Research Report
  • Research Products

    (14 results)

All Other

All Publications (14 results)

  • [Publications] 福見 稔, 満倉 靖恵: "ニューラルネットワークへの知識の埋込とルール抽出"高速信号処理応用技術学会論文誌(電子技術). Vol.12. 13-18 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] M.Fukumi, Y.Mitsukura, N.Akamatsu: "A Knowledge Processing Method in Neural Networks"Proc. of KES'2001, osaka. Vol.3. 1493-1498 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] M.Shinmoto, Y.Mitsukura, M.Fukumi, N.Akamatsu: "A Neural Network Approach to Color Image Classification"CD-ROM Proc. of ICONIP 2002, Singapore #1319, pp.1-5. (CD-ROM). 1-5 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 西山拓志, 福見 稔: "ニューラルネットワークを用いた画像からのキーワード抽出"計測自動制御学会システムインテグレーション講演論文集. Vol.3. 327-328 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Minoru Fukumi, Yasue Mitsukura: "Knowledgs Insertion and Rule Extraction in Neural Networks"Trans of FSPATJ. 4, No.4. 13-18 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] M.Fukumi, Y.Mitsukura, N.Akamatsu: "A Knowledge Processing Method in Neural Networks"Proc of KEN'2001. 3. 1493-1498 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] M.Shinmoto, Y.Mitsukura, M.Fukumi, N.akamatsu: "A Neural Network Approach to Color Image Classification"CD-ROM Proc of ICONIP'2002, Singapore. ♯1319. 1-5 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] H.Nishiyama, M.Fukumi: "Keywords Extraction from Images by Using Neural Networks"Proc of SICE System Integration Division Annual Conference. 3. 327-328 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 福見 稔, 満倉 靖恵: "ニューラルネットワークへの知識の埋込とルール抽出"高速信号処理応用技術学会論文誌(電子技術). Vol.12. 13-18 (2001)

    • Related Report
      2002 Annual Research Report
  • [Publications] M.Fukumi, Y.Mitsukura, N.Akamatsu: "A Knowledge Processing Method in Neural Networks"Proc. of KES' 2001. 1493-1498 (2001)

    • Related Report
      2002 Annual Research Report
  • [Publications] M.Shinmoto, Y.Mitsukura, M.Fukumi, N.Akamatsu: "A Neural Network Approach to Color Image Classification"CD-ROM Proc. of ICONIP'2002, Singapore, #1319, pp.1-5. (CD-ROM). 1-5 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 西山拓志, 福見稔: "ニューラルネットワークを用いた画像からのキーワード抽出"計測自動制御学会システムインテグレーション講演論文集. Vol.3. 327-328 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 福見 稔, 満倉 靖恵: "ニューラルネットワークへの知識の埋込とルール抽出"電子技術(高速信号処理応用技術学会論文誌). Vol.12. 13-18 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] M.Fukumi, Y.Mitsukura, N.Akamatsu: "A knowledge processing method in neural networks"Proc. of KES' 2001. 1493-1498 (2001)

    • Related Report
      2001 Annual Research Report

URL: 

Published: 2001-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi