Journal of Quality Engineering Society
Online ISSN : 2189-9320
Print ISSN : 2189-633X
ISSN-L : 2189-633X
Search
Advanced search
OR
Browse
Search
Volume 2, Issue 4
Displaying 1-4 of 4 articles from this issue
Show all abstracts
    • |<
    • <
    • 1
    • >
    • >|
  • Diagnosis and Signal-to-Noise Ratio
    Genichi Taguchi
    1994 Volume 2 Issue 4 Pages 2-7
    Published: August 01, 1994
    Released on J-STAGE: December 24, 2016
    DOIhttps://doi.org/10.18890/qes.2.4_2
    JOURNAL FREE ACCESS
    Show abstractHide abstract

    The medical diagnosis is a multi-step complicatd decision making process to take into consideration all personal medical data. The role of Quality Engineering is to give a measure of distance of each person to be diagnosed from the ideal conditions. The purpose of this paper is to propose touse the Mahalanobis Distance as a generalysed variance where we have a set of multi-vaiate physical measurements. The core of this paper is to use Mahalanobis Space obtained from the data of healthy normal people.

    How to define and calculate the Mahalanobis Distance is explained in this paper with a case study given by Dr.Tatsuji Kanetaka.

    View full abstract
    Download PDF (1463K)
  • Optimization　of　Paper　Money　Recognition　System By　Artificial　Neural　Network
    Shoichi Teshima, Yukinori Kakazu
    1994 Volume 2 Issue 4 Pages 24-31
    Published: August 01, 1994
    Released on J-STAGE: March 24, 2016
    DOIhttps://doi.org/10.18890/qes.2.4_24
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    Artificial　Neural　Network　is　an　information　treatment　theory　based　on　the　nerve　circuit　in　biology.　Since　it　has　pattern　learning　function,　many　studies　have　been　made　and　applied　for　various pattern　recognition　systems.　lt　has　been　reported　that　the　theory　can　also　be　applied　for　paper　money　recognition. In　this　paper,　a　new　approach　is　proposed　to　optimize　the　location　of　sensing　lines　that　is　required in　the　development　of　paper　money　recognition　system　with　Artificial　Neural　Network.　Up　to　present,　there　is　no　definition　to　quantify　the　ability　of　recognition,　therefore,　the　location　of　sensing lines　has　been　decided　by　try　and　error.　Our　approach　consists　of　two　processes:　firstly,　S/N　ratio　is used　to　express　the　robustness　of　recognition,　and　secondly,　the　selection　process　of　the　number　and location　of　sensing　lines　was　optimized.　The　correlation　between　the　S/N　ratios　of　different　sensing lines　was　analysed　using　orthogonal　arrays.　Already　circulated　notes　were　used　in　the　experiment as　a　noise　factor.　The　results　showed　a　good　correspondence　with　theoretical　values.
    View full abstract
    Download PDF (1905K)
  • Study　of　Numeral's　Shape　Legibility structed　of　7　Segments
    Kazunori Hiza
    1994 Volume 2 Issue 4 Pages 32-38
    Published: August 01, 1994
    Released on J-STAGE: March 24, 2016
    DOIhttps://doi.org/10.18890/qes.2.4_32
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    One　of　quality　evaluation　methods　is　the　sensory　evaluation(sensory　inspection).　Then,　it　is　often used　for　the　depelopment　of　consumer　products.　This　report　applies　sensory　evaluation　data　to Quality　Engineering　method(Parameter　design)　.　ln　the　concrete,　I　investigated　the　cause　of　legibility　about　Numeral's　Shape　structed　of　7　Segments　used　by　indicator.
    View full abstract
    Download PDF (1264K)
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top