基于近红外光谱的桃果实冷害识别分析

该文采用近红外(near infrared,NIR)光谱技术对水蜜桃低温冷害褐变进行识别分析。分别建立了水蜜桃低温贮藏期间不同冷害阶段的两分类和多分类模型,讨论了不同光谱预处理方法对模型的影响,并比较偏最小二乘判别分析(partial least squares-discriminant analysis,PLS-DA)、主成分判别分析(principal component discriminant analysis,PCA-DA)、K-最邻近(K-nearest neighbor,K-NN)、簇类独立软模式(soft independent modeling of class analogy,SIMCA)4种建模方法的分类效果。结果表明,采用PLS-DA模型效果最好,两分类和多分类模型的总准确率为分别为0.93和0.71。两分类模型可较准确地对冷害褐变进行快速识别分类,多分类模型可用于水蜜桃低温贮藏期间不同冷害阶段的初步筛查。

Identification of chilling injury of peach fruit based on near infrared spectroscopy

The chilling injury of juicy peach caused by low temperature was identified and analyzed by near infrared(NIR)spectroscopy.In this paper,two-classification and multi-classification models of different chilling injury stages of juicy peach were established during low temperature storage,and the effects of different spectral pretreatment methods on the model were discussed.The classification performance of partial least squares discriminant analysis(PLS-DA),principal component discriminant analysis(PCA-DA),K-nearest neighbor(K-NN)and SIMCA modeling methods were compared.The results showed that the performance of PLS-DA model was the best,and the total accuracy of two-classification model and multi-classification model were 0.93 and 0.71,respectively.The two-classification model could be used for rapid and accurate identification of cold injury browning,while multi-classification model could be used for preliminary screening of different chilling injury stages of juicy peach during low temperature storage.