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
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;
Conference_Titel :
Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2013 5th International Conference on
Print_ISBN :
978-0-7695-5011-4
DOI :
10.1109/IHMSC.2013.62