Study on Diversified Adulteration of Ganoderma Lucidum Spore Oil by RVM and New Clustering Algorithms
WANG Wu1, 2, WANG Jian-ming1, 2, LI Ying3, LI Xiang-hui4, LI Yu-rong1, 2
1. College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350116, China
2. Fujian Key Lab of Medical Instrument and Pharmaceutical Technology, Fuzhou 350002, China
3. College of Biological Science and Engineering, Fuzhou University, Fuzhou 350116, China
4. Medical Technology and Engineering College, Fujian Medical University, Fuzhou 350004, China
摘要： 食品掺假种类众多，手段隐蔽，成为食品安全检测一个重要难题。为摆脱传统模型识别食品中是否存在新掺假类别的局限性，实验以纯净的灵芝孢子油和掺杂不同比例花生油、玉米油、薏仁油、地沟油的五种类别为研究对象，采用傅里叶变换近红外光谱(Fourier transform near infrared spectroscopy, FT-NIR)收集12 400～4 000 cm-1范围内的近红外光谱。假设掺杂地沟油为新掺假类别，利用前四种类别的校正集样本构建相关向量机(RVM)多分类器，分别对建模的预测集样本和掺杂地沟油样本进行判别，并借助新聚类算法对判别为纯净的灵芝孢子油的样本做进一步分析验证。研究表明，RVM分类器对于建模的预测集样本判别准确率高达93.75%，说明模型有较强的判别能力，但由于模型局限性，掺杂地沟油样品被误判为纯净的灵芝孢子油；在新聚类算法的决策图上，纯净灵芝孢子油校正集和预测集混合样本的聚类中心数为1，而纯净灵芝孢子油校正集和掺杂了地沟油混合样本聚类中心数为2，直观验证判别结果的准确性。结果表明利用FT-NIR技术结合RVM分类器与新聚类算法对于灵芝孢子油掺假能够有效识别，并且能够定性识别新型掺假类型，为解决食品掺假多样化问题提供一种新思路。
关键词：食品掺假；FT-NIR；RVM；新聚类算法
Abstract：In recent years, food adulteration of various kinds has become a severe problem in food safety detection. In order to get rid of the limitations of traditional qualitative identification of new food adulteration, Fourier transform near-infrared spectroscopy (FT-NIR) was used to collect the spectrum ranging from 12 400 to 4 000 cm-1. The pure ganoderma lucidum spore oil adulterated with peanut oil, corn oil, coix seed oil, and hogwash oil were investigated in this study, where the ganoderma lucidum spore oil adulterated with hogwash oil was taken as the new category of food adulteration. Then, Multiple Relevance Vector Machine (RVM) classifiers were constructed with calibration samples of the first 4 categories. The prediction samples and ganoderma lucidum spore oil adulterated with hogwash oil were discriminated by the 4 kinds of classifier. In addition, the discriminated results were further verified with new clustering algorithm. Results showed that the discriminant accuracy of the first four categories was close to 93.75% with RVM classifier, but the ganoderma lucidum spore oil adulterated with hogwash oil was mistaken for pure ganoderma lucidum spore oil because of the limitations of model. So a new clustering algorithm based on local density and distance decision graph was applied to verify that. It was found that the cluster centers were 1 when the samples only contained pure ganoderma lucidum spore oil, however, the cluster centers were 2 when the samples mixed with pure ganoderma lucidum spore and adulterated with hogwash oil. The results demonstrated the FT-NIR in combination with RVM classifier and new clustering algorithm could be used for the identification of the adulterant in the pure ganoderma lucidum spore oil and qualitatively identify new category of food adulteration, providing a new method to solve the problem of food diversified adulteration.
Key words：Food adulteration; FT-NIR; RVM; New clustering algorithm
王 武，王建明，李 颖，李祥辉，李玉榕. 傅里叶变换近红外光谱结合RVM与新聚类算法鉴别灵芝孢子油多样掺假类别[J]. 光谱学与光谱分析, 2017, 37(04): 1064-1068.
WANG Wu, WANG Jian-ming, LI Ying, LI Xiang-hui, LI Yu-rong. Study on Diversified Adulteration of Ganoderma Lucidum Spore Oil by RVM and New Clustering Algorithms. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(04): 1064-1068.
[1] SONG Yu-feng, WANG Wei-shan, YANG Xue-jun, et al(宋玉峰, 王微山, 杨学军, 等). Food and Nutrition in China(中国食物与营养)，2012，18(3)：9.
[2] HU Yan-yun，XU Hui-qun，SONG Wei，et al(胡艳云，徐慧群，宋 伟，等). Food Science(食品科学)，2014，35(6)：176.
[3] Cercaci L，Rodriguez-Estrada M T，Lercker G. Journal of Chromatography A，2003，985：211.
[4] Zabaras D，Gordon M H. Food Chemistry，2004，84：475.
[5] WANG Shi-cheng，FAN Jing-shan，WANG Yan-hong，et al(王世成，范津衫，王颜红，等). Chinese Journal of Analytical Chemistry(分析化学)，2014，42(5)：741.
[6] SUN Tong, HU Tian, XU Wen-li, et al(孙 通, 胡 田, 许文丽). China Oils and Fats(中国油脂)，2013，38(10)：75.
[7] Zhang L G，Zhang X，Ni L J，et al. Food Chemistry，2014，145：342.
[8] ZHANG Yan-nan，CHEN Lan-zhen，XUE Xiao-feng，et al(张妍楠，陈兰珍，薛晓锋，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2015，35(9)：032.
[9] Tipping M E. Journal of Machine Learning Research，2001，1(3)：211.
[10] Caesarendra W，Widodo A，Yang B S. Mechanical Systems and Signal Processing，2010，24(4)：1161.
[11] Rodriguez A，Laio A. Science，2014，344(6191)：1492.
[12] WU Jing-zhu，SHI Rui-jie，CHEN Yan，et al(吴静珠，石瑞杰，陈 岩，等). Journal of the Chinese Cereals and Oils Association(中国粮油学报)，2015，30(2)：118.
