Detection and Identifying of Meat Fresh Degree Based on NIR Technique

Authors:
  • GPGuo Peiyuan
    Guo Peiyuan
  • YFYuan Fang
    Yuan Fang
  • XLXiang Lingzi
    Xiang Lingzi
  • WXWang Xikun
    Wang Xikun
  • LYLin Yan
    Lin Yan
  • BMBao Man
    Bao Man

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.