• DocumentCode
    3569988
  • Title

    Detection and Identifying of Meat Fresh Degree Based on NIR Technique

  • Author

    Guo Peiyuan ; Yuan Fang ; Xiang Lingzi ; Wang Xikun ; Lin Yan ; Bao Man

  • Author_Institution
    Coll. of Comput. & Inf. Eng., Beijing Technol. & Bus. Univ., Beijing, China
  • Volume
    1
  • fYear
    2013
  • Firstpage
    232
  • Lastpage
    235
  • Abstract
    In this paper, near infrared spectroscopy techniques are used for the detection of meat in the process of corruption time, studied the feasibility of pork freshness level. And the qualitative analysis model is established Based on the software OPUS. During the model establishment process, the kinds of the class of TVBN values are re-divided 5 from 3 using the SOM network clustering to better reflect level of freshness of meat. And to increase the accuracy of prognostication, the principal component analysis is used to reduce dimension except choosing the pretreatment method of the 13-point first derivative smoothing, and the result is that the rate of correct promote and the number of which of bias of predictive class is decreased.
  • Keywords
    common-sense reasoning; food products; infrared spectroscopy; pattern clustering; NIR technique; SOM network clustering; TVBN; infrared spectroscopy techniques; meat fresh; pork freshness; qualitative analysis model; software OPUS; Abstracts; Accuracy; Analytical models; Frequency synthesizers; Principal component analysis; Spectroscopy; Vectors; cluster analysis; meat freshness; near-infrared spectroscopy technique; principal component analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2013 5th International Conference on
  • Print_ISBN
    978-0-7695-5011-4
  • Type

    conf

  • DOI
    10.1109/IHMSC.2013.62
  • Filename
    6643874