ISSN: 0973-7510

E-ISSN: 2581-690X

Sun Jun1,2 , Jin Xiaming1, Mao Hanping2 and Wu Xiaohong1
1School of Electrical and Information Engineering of Jiangsu University, Zhenjiang 212013,P.R. China.
2Laboratory Venlo of Modern Agricultural Equipment, Jiangsu University, Zhenjiang 212013,P.R. China.
J Pure Appl Microbiol. 2013;7(Spl. Edn.: November):747-752
© The Author(s). 2013
Received: 27/09/2013 | Accepted: 04/11/2013 | Published: 30/11/2013
Abstract

Based on differences in near infrared spectroscopy of lettuce leaf in different storage time, the non-destructive identification method of lettuce storage time was researched. Because there are various noises in lettuce leaf spectroscopy coming from external environmental factors, chemical composition and photoelectric detection circuit, several pretreatment methods, such as smoothing, MSC (Multiplication scatter correction           ), SNV (Standard Normalized Variable), BC (Baseline Correction), VN (Vector Normalize), FD (First Derivative) and SD (Second Derivative) were studied and used to pre-treat lettuce leaf spectroscopy respectively. PCA (Principal Component Analysis) method was used to reduce dimension and extract feature of spectroscopy pretreated. Finally, the identification model was built based on SVM(Support Vector Machine).Test results showed that, the model based on lettuce leaf spectroscopy pretreated by SD is best because its lettuce storage time accuracy was 100%,which was better than those of other models. The result also showed that, the spectrum noise factors affected the modeling accuracy, so it is important to select an appropriate pretreatment method, and SD+PCA+SVM is an effective identification model of lettuce storage time based on Near Infrared Spectroscopy.

Keywords

Near Infrared Spectrum, Lettuce, Storage Time

Article Metrics

Article View: 783

Share This Article

© The Author(s) 2013. Open Access. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License which permits unrestricted use, sharing, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.