版权说明 帮助中心
首页 > 成果 > 详情

Developing a NIR multispectral imaging for prediction and visualization of peanut protein content using variable selection algorithms

SCI-EEI
认领
导出
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Cheng, Jun-Hu;Jin, Huali;Liu, Zhiwei
通讯作者:
Cheng, JH;Liu, ZW
作者机构:
[Jin, Huali] College of Food Science and Technology, Henan University of Technology, Zhengzhou, 450000, China
[Cheng, Jun-Hu] School of Food Science and Engineering, South China University of Technology, Guangzhou, 510641, China
[Liu, Zhiwei] College of Food Science and Technology, Hunan Agricultural University, Changsha, 410128, China
通讯机构:
[Liu, Zhiwei] Hunan Agr Univ, Coll Food Sci & Technol, Changsha 410128, Hunan, Peoples R China.
[Cheng, Jun-Hu] South China Univ Technol, Sch Food Sci & Engn, Guangzhou 510641, Guangdong, Peoples R China.
语种:
英文
关键词:
Hyperspectral imaging;Peanut;Non-destructive;Protein;Wavelength selection
期刊:
Infrared Physics and Technology
ISSN:
1350-4495
年:
2018
卷:
88
页码:
92-96
文献类别:
WOS:Article;EI:Journal article (JA)
所属学科:
ESI学科类别:物理学;WOS学科类别:Instruments & Instrumentation;Optics;Physics, Applied
入藏号:
WOS:000423650700012;EI:20174704448555
基金类别:
Natural Science Foundation of Guangdong Province [2017A030310558]; China Postdoctoral Science Foundation [2017M612672]; Fundamental Research Funds for the Central Universities [2017MS067]; Guangdong Provincial R & D Centre for the Modern Agricultural Industry on Non-destructive Detection and Intensive Processing of Agricultural Products [2016LM2154]; Common Technical Innovation Team of Guangdong Province on Preservation and Logistics of Agricultural Products [2016LM2154]
机构署名:
本校为通讯机构
院系归属:
食品科学技术学院
摘要:
The feasibility of developing a multispectral imaging method using important wavelengths from hyperspectral images selected by genetic algorithm (GA), successive projection algorithm (SPA) and regression coefficient (RC) methods for modeling and predicting protein content in peanut kernel was investigated for the first time. Partial least squares regression (PLSR) calibration model was established between the spectral data from the selected optimal wavelengths and the reference measured protein content ranged from 23.46% to 28.43%. The RC-PLSR model established using eight key wavelengths (1153, 1567, 1972, 2143, 2288, 2339, 2389 and 2446 nm) showed the best predictive results with the coefficient of determination of prediction (R<sup>2</sup><inf>P</inf>) of 0.901, and root mean square error of prediction (RMSEP) of 0.108 and residual predictive deviation (RPD) of 2.32. Based on the obtained best model and image processing algorithms, the distribution maps of protein content were generated. The overall results of this study indicated that developing a rapid and online multispectral imaging system using the feature wavelengths and PLSR analysis is potential and feasible for determination of the protein content in peanut kernels.<br/> &copy;2017 Elsevier B.V.
参考文献:
AOAC, 1999, OFF METH AN AOAC ASS
Ariana DP, 2010, J FOOD ENG, V96, P583, DOI 10.1016/j.jfoodeng.2009.09.005
Barbin D, 2012, MEAT SCI, V90, P259, DOI 10.1016/j.meatsci.2011.07.011
Biancolillo A, 2016, CHEMOMETR INTELL LAB, V156, P89, DOI 10.1016/j.chemolab.2016.05.016
Cheng JH, 2014, TRENDS FOOD SCI TECH, V37, P78, DOI 10.1016/j.tifs.2014.03.006

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com