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

Classification of New and Used Bills by Acoustic Data Using Neural Networks

Research Project

Project/Area Number 11450155
Research Category

Grant-in-Aid for Scientific Research (B).

Allocation TypeSingle-year Grants
Section一般
Research Field System engineering
Research InstitutionOsaka Prefecture University

Principal Investigator

OMATU Sigeru  Osaka Prefecture University, Graduate School of Engineering Professor, 工学研究科, 教授 (30035662)

Co-Investigator(Kenkyū-buntansha) FUJINAKA Toru  Osaka Prefecture University, Graduate School of Engineering, Lecturer, 大学院・工学研究科, 講師 (90190058)
YOSHIOKA Michifumi  Osaka Prefecture University, Graduate School of Engineering, Lecturer, 大学院・工学研究科, 講師 (70285302)
Project Period (FY) 1999 – 2000
Project Status Completed (Fiscal Year 2000)
Budget Amount *help
¥8,500,000 (Direct Cost: ¥8,500,000)
Fiscal Year 2000: ¥4,100,000 (Direct Cost: ¥4,100,000)
Fiscal Year 1999: ¥4,400,000 (Direct Cost: ¥4,400,000)
Keywordscompetitive neural network / learning control / acoustic pattern classification / learning vector quantization / generalization / new and used bills classification / ニューラルネットワーク / 紙幣金種識別 / 紙幣新旧識別 / LVQ法 / 最適化手法 / 適応フィルタ
Research Abstract

In this project, we have proposed an approach to realize an intelligent classification of new and used bill money from acoustic data via banking machines when bills are passed in those machines by using neural networks. The present project is to synthesize an intelligent classifier system based on various types of neural networks. Especially, we have adopted here three kinds of neural networks which are a layered network by the error back-propagation algorithm, a self-organizing map network, and learning vector quantization networks. To complete the project study, we have adopted the following approach to synthesize those intelligent classification systems :
(1) Feature Extraction of Acoustic Data from New and Used Bill
Using spectrum and cepstrum data, we have extracted the specific features of acoustic data obtained from the new and used bill money. Then using the self-organizing map neural network, we have classified those data into two classes which mean new bill category and used bill category.
(2) Optimization of Network Size by Genetic Algorithms
To enhance the generalization of the networks, we have applied the genetic algorithms to the layered neural networks and competitive learning networks such that the minimum cost could be obtained. Then we could reduce the network size as small as possible under some constraints.
(3) Classification by Learning Vector Quantization
To classify the acoustic data from new and used bills from the spectrum and cepstrum, we have trained the neural networks based on the learning vector quantization. Then we could obtain more than 90% classification results for test data set from real bills.
(3) Hardware Implementation of the Proposed System
To speed up the computation of the proposed algorithm and reduce the cost, we have developed the hardware of the proposed system. Then we could realized cheep and high speed hardware system to achieve the specification of the bills classification.

Report

(3 results)
  • 2000 Annual Research Report   Final Research Report Summary
  • 1999 Annual Research Report
  • Research Products

    (31 results)

All Other

All Publications (31 results)

  • [Publications] 森興志秀,吉岡理文,大松繁: "ニューラルネットワークによる関数近似のεエントロピーを用いた中間層ユニット数の決定"計測自動制御学会論文集. 35・12. 1617-1624 (1999)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 小坂利寿,竹谷紀和,大松繁,漁邦広: "信頼性評価を用いたLVQ法による米国ドル紙幣識別"電気学会論文誌C. 119-C・11. 1359-1354 (1999)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 小坂利寿,竹谷紀和,大松繁: "競合型ニューラルネットワークによるイタリア紙幣の識別"電気学会論文誌C. 119-C・8/9. 948-954 (1999)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 吉森晋,寺内篤史,高島修直,大松繁: "遺伝的緩和反復フーリエ変換アルゴリズムによるフーリエ変換振幅項からの画像再構成"電子情報通信学会論文誌D-II. J82-D-II・8. 1290-1298 (1999)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Dongshik Kang,Sigeru Omatu and Michifumi Yoshioka: "New and Used Bills Classification Using Neural Networks"IEICE Trans. Fundamentals. E82-A・8. 1511-1516 (1999)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 寺西大,大松繁,小坂利寿: "帯域音響エネルギーパターンを用いた紙幣の3疲弊度識別"電気学会論文誌C. 120-C・11. 1602-1608 (2000)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Sigeru Omatu and Yosuke Ito: "Land Cover Mapping by Neural Networks"World Scientific. 570(237-262) (1999)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] R.Palaniappan,P.Raveendran and Sigeru Omatu: "Improved Moment Invariants for Invariant Image Representation"World Scientific. 233(167-186) (2000)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Masaru TERANISHI: "Fatigue Level Classification Using Energy Patterns of Acoustic Data"Transactions on IEE of Japan. Vol.120-C, No.11. 1602-1608 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Yoshihide MORI: "Determination of Number of Neurons in the Hidden Layer for Function Approximation by Neural Networks"Transactions of SICE. Vol.35, No.12. 161-1624 (1999)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Toshihisa KOSAKA: "Bill Money Classification of US Dollar by LVQ Method Using Reliability Measure"Transactions on IEE of Japan. Vol.119-C, No.11. 1359-1354 (1999)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Toshihisa KOSAKA: "Italian Liras Classification by Competitive Neural Networks"Transactions on IEE of Japan. Vol.119-C, No.8/9. 984-954 (1999)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Susumu MORIYOSHI: "Image Reconstruction by Fourier Transform Amplitude Using Genetic Algorithms"Transactions on IEICE. Vol.J82-D-II, No.8. 1290-1298 (1999)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Dongshik KANG: "New and Used Bills Classification Using Neural Networks"Transactions on IEICE. Vol.E82-A, No.8. 151-1516 (1999)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Sigeru OMATU: "Land Cover Mapping by Neural Networks"World Scientific. 570 (1999)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] R.PALANIAPPAN: "Improved Moment Invariants for Invariant Image Representation"World Scientific. 133 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 森興志秀,吉岡理文,大松繁: "ニューラルネットワークによる関数近似のεエントロピーを用いた中間層ユニット数の決定"計測自動制御学会論文集. 35・12. 1617-1624 (1999)

    • Related Report
      2000 Annual Research Report
  • [Publications] 小坂利寿,竹谷紀和,大松繁,漁邦広: "信頼性評価を用いたLVQによる米国ドル紙幣識別"電気学会論文誌C. 119-C・11. 1359-1354 (1999)

    • Related Report
      2000 Annual Research Report
  • [Publications] 小坂利寿,竹谷紀和,大松繁: "競合型ニューラルネットワークによるイタリア紙幣の識別"電気学会論文誌C. 119-C・8/9. 948-954 (1999)

    • Related Report
      2000 Annual Research Report
  • [Publications] 吉森晋,寺内篤史,高島修直,大松繁: "遺伝的緩和反復フーリエ変換アルゴリズムによるフーリエ変換振幅項からの画像再構成"電子情報通信学会論文誌 D-II. J82-D-II・8. 1290-1298 (1999)

    • Related Report
      2000 Annual Research Report
  • [Publications] Dongshik Kang,Sigeru Omatu,and Michifumi Yoshioka: "New and Used Bills Classification Using Neural Networks"IEICE Trans.Fundamentals. E82-A・8. 1511-1516 (1999)

    • Related Report
      2000 Annual Research Report
  • [Publications] 寺西大,大松繁,小坂利寿: "帯域音響エネルギーパターンを用いた紙幣の3疲弊度識別"電気学会論文誌C. 120-C・11. 1602-1608 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] Sigeru Omatu and Yosuke Ito: "Land Cover Mapping by Neural Networks (分担:pp.237-262)"World Scientific. 570 (1999)

    • Related Report
      2000 Annual Research Report
  • [Publications] R.Palaniappan,P.Raveendran,and Sigeru Omatu: "Improved Moment Invariants for Invariant Image Representation (分担:167-186)"World Scientific. 233 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] Yosuke Ito and Sigeru Omatu: "Extended LVQ Neural Network Approach to Land Cover Mapping"IEEE Transactions on Geoscience and Remote Sensing. 37・1. 313-317 (1999)

    • Related Report
      1999 Annual Research Report
  • [Publications] Fumiaki Takeda, Toshihiro Nishikage,and Sigeru Omatu: "Bank Note Recognition by Means of Optimized Masks, Neural Networks and Genetic Algorithms"Engineering Applications of Artificial Intelligence. 12・2. 175-184 (1999)

    • Related Report
      1999 Annual Research Report
  • [Publications] 寺西 大,大松 繁,小坂 利寿: "音響ケプストラムを用いた紙幣の新旧識別"電気学会論文誌C,. 119C・8/9. 955-961 (1999)

    • Related Report
      1999 Annual Research Report
  • [Publications] 小坂 利寿,竹谷 紀和,大松 繁,漁 邦広: "信頼性評価を用いたLVQ法による米国ドル紙幣識別"電気学会論文誌C. 119C・11. 1395-1364 (1999)

    • Related Report
      1999 Annual Research Report
  • [Publications] Dongshik Kang, Sigeru Omatu, and Michifumi Yoshioka: "New and Used Bills Classification Using Neural Networks"IEICE Trans. Fundamentals. E82-A・8. 1511-1516 (1999)

    • Related Report
      1999 Annual Research Report
  • [Publications] 森 興志秀,吉岡 理文,大松 繁: "ニューラルネットワークによる関数近似のεエントロピーを用いた中間層ユニット数の決定"計測自動制御学会論文集. 35・12. 1617-1624 (1999)

    • Related Report
      1999 Annual Research Report
  • [Publications] Sigeru Omatu and Yosuke Ito: "Information Processing for Remote Sensing"World Scientific Publishing Co.. 570 (1999)

    • Related Report
      1999 Annual Research Report

URL: 

Published: 1999-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi