College of Agronomy and Biotechnology, Yunnan Agricultural University, Kunming 650201, China; Institute of Medicinal Plants, Yunnan Academy of Agricultural Sciences, Kunming 650200, China.
College of Resources and Environment, Yuxi Normal University, Yuxi 653100, China.
Spectrochim Acta A Mol Biomol Spectrosc. 2018 Jun 5;198:257-263. doi: 10.1016/j.saa.2018.03.018. Epub 2018 Mar 10.
Boletus griseus and Boletus edulis are two well-known wild-grown edible mushrooms which have high nutrition, delicious flavor and high economic value distributing in Yunnan Province. In this study, a rapid method using Fourier transform infrared (FT-IR) and ultraviolet (UV) spectroscopies coupled with data fusion was established for the discrimination of Boletus mushrooms from seven different geographical origins with pattern recognition method. Initially, the spectra of 332 mushroom samples obtained from the two spectroscopic techniques were analyzed individually and then the classification performance based on data fusion strategy was investigated. Meanwhile, the latent variables (LVs) of FT-IR and UV spectra were extracted by partial least square discriminant analysis (PLS-DA) and two datasets were concatenated into a new matrix for data fusion. Then, the fusion matrix was further analyzed by support vector machine (SVM). Compared with single spectroscopic technique, data fusion strategy can improve the classification performance effectively. In particular, the accuracy of correct classification of SVM model in training and test sets were 99.10% and 100.00%, respectively. The results demonstrated that data fusion of FT-IR and UV spectra can provide higher synergic effect for the discrimination of different geographical origins of Boletus mushrooms, which may be benefit for further authentication and quality assessment of edible mushrooms.
灰树花和美味牛肝菌是两种著名的野生食用蘑菇，分布于云南省，具有高营养、美味和高经济价值。在本研究中，采用傅里叶变换红外（FT-IR）和紫外（UV）光谱结合数据融合的快速方法，利用模式识别方法对来自七个不同地理来源的牛肝菌进行鉴别。首先，对两种光谱技术获得的 332 个蘑菇样本的光谱进行了单独分析，然后研究了基于数据融合策略的分类性能。同时，采用偏最小二乘判别分析（PLS-DA）提取 FT-IR 和 UV 光谱的潜在变量（LVs），将两个数据集拼接成一个新的融合矩阵进行数据融合。然后，用支持向量机（SVM）对融合矩阵进行进一步分析。与单一光谱技术相比，数据融合策略能有效提高分类性能。特别是 SVM 模型在训练集和测试集中的正确分类准确率分别为 99.10%和 100.00%。结果表明，FT-IR 和 UV 光谱的数据融合可为不同地理来源的牛肝菌鉴别提供更高的协同效应，可能有助于进一步鉴定和评估食用蘑菇的质量。
