Rapid and Non-destructive Prediction of Protein Content in Peanut Varieties Using Near-infrared Hyperspectral Imaging Method

作     者：WANG Yijie CHENG Junhu 

作者机构：School of Food Science and Engineering South China University of Technology 

出 版 物：《Grain & Oil Science and Technology》 (粮油科技（英文版）)

年 卷 期：2018年第1卷第1期

页      面：40-43页

学科分类：0832[工学-食品科学与工程（可授工学、农学学位）] 081704[工学-应用化学] 07[理学] 08[工学] 0817[工学-化学工程与技术] 070302[理学-分析化学] 083202[工学-粮食、油脂及植物蛋白工程] 0703[理学-化学] 

基　　金：Supported by the Natural Science Foundation of Guangdong Province(2017A030310558) China Postdoctoral Science Foundation(2017M612672) Fundamental Research Funds for the Central Universities(2017MS067) 

主　　题：Hyperspectral imaging Peanut Non-destructive Protein content Wavelength selection 

摘      要：This study was undertaken to investigate the feasibility of near-infrared(NIR) hyperspectral imaging(1 000–2 500 nm) for non-destructive and quantitative prediction of protein content in peanut kernels. Partial least squares regression(PLSR) calibration model was established between the spectral data extracted from the hyperspectral images and the reference measured protein content values, with the coefficient of determination of prediction(R_P^2) of 0.885 and root mean square error of prediction(RMSEP) of 0.465%.Regression coefficients(RC) from PLSR analysis were used to identify the most essential wavelengths that had the greatest influence on changes in the protein content. Eight optimal wavelengths were selected by RC and its corresponding simplified RC-PLSR prediction model was also obtained, showing better performance with a higher R_P^2 of 0.870 and a lower RMSEP of 0.494%. The results indicate that hyperspectral imaging with PLSR analysis can be used as a rapid and non-destructive method for predicting protein content in peanut.