薏仁是一种药食两用资源, 对其品质快速鉴别的需求也越来越多, 近红外光谱技术（near infrared spectroscopy, NIRS）作为一种快速、 无损且环保的方法正适合这一需求。 以不同产地和品种薏仁的近红外光谱为基础, 结合化学计量学方法对薏仁种类进行鉴别。 对原光谱用无监督学习算法主成分分析（principal component analysis, PCA）和有监督学习算法学习向量量化（learning vector quantization, LVQ）神经网络、 支持向量机（support vector machine, SVM）进行定性判别分析。 由于不同地区和不同品种的薏仁营养物质组成复杂且含量相近, 所选两类薏仁的特征变量很相似, 因而PCA得分图重叠严重, 很难区分; 而LVQ神经网络和SVM都能得到满意结果, LVQ神经网络的预测正确率为90.91%, SVM在经过惩罚参数和核函数参数优选后, 分类准确率能达到100%。 结果表明: 近红外光谱技术结合化学计量学方法可作为一种快速、 无损、 可靠的方法用于薏仁种类的鉴别, 并为市场规范提供技术参考。

Unsupervised learning algorithm-principal component analysis (PCA), and supervised learning algorithm-learning vector quantization (LVQ) neural network and support vector machine (SVM) were used to carry out qualitative discriminant analysis of different varieties of coix seed from different regions. Since nutrient compositions of different varieties coix seed samples from different origins were complex and the contents were similar, characteristic variables of two kinds of coix seed were alike, the scores plot of their principal components seriously overlapped and the categories of coix seed were difficult to distinguish. While satisfactory results were obtained by LVQ neural network and SVM. The accuracy of LVQ neural network prediction is 90.91%, while the classification accuracy of SVM, whose penalty parameter and kernel function parameter were optimized, can be up to 100%. The results show that NIRS combined with chemometrics can be used as a rapid, nondestructive and reliable method to identify coix seed varieties and provide technical reference for market regulation.