基于无机元素分析对地理标志五常大米鉴别技术的研究

五常大米是我国著名地理标志产品之一，品质高、产量低，导致制假售假的现象严重。为维护五常大米的品牌形象和消费者利益，急需一种有效鉴别五常大米的方法。应用电感耦合等离子体光谱及电感耦合等离子体质谱测定大米中无机元素含量，结合主成分分析(PCA)、Fisher判别、人工神经网络(ANN)对五常大米鉴别模型进行研究。结果表明：PCA法对样品的分类效果较差，采用Fisher判别和ANN则可准确识别五常地区的大米样品和其他地区的大米样品。Fisher判别法对校正集和验证集样品平均准确识别率分别为93.5%，而ANN法对同样的校正集和验证集样品的平均准确识别率为96.4%，优于Fisher判别法。可准确对五常大米进行鉴别，为该产品的地理标志保护提供了一种技术手段。

Study on the Identification of Geographical Indication Wuchang Rice Based on the Content of Inorganic Elements

Wuchang rice is a geographical indication product in China. Due to its high quality and low production, the phenomenon of fake is more and more serious. An effective identification method of Wuchang rice is urgent needed, for the maintenance of its brand image and interest of consumers. Base on the content of inorganic elements which are analyzed by ICP-AES and ICP-MS in rice, the identification model of Wuchang rice is studied combining with principal component analysis (PCA), Fisher discrimination and artificial neural network (ANN) in this paper. The effect on the identification of samples is poor through PCA, while the samples from Wuchang area and other areas can be identified accurately through Fisher discrimination and ANN. The average accurate identification ratio of training and verification set through Fisher discrimination is 93.5%, while the average accurate identification ratio through ANN is 96.4%. The ability to identify of ANN is better than Fisher discrimination. Wuchang rice can be identified accurately through the result of this research which provides a technology for the protection of geographical indications of this product.