Producing Area Identification of Letinus Edodes Using Mid-Infrared Spectroscopy
ZHU Zhe-yan1, 2, ZHANG Chu2, LIU Fei2, KONG Wen-wen2, HE Yong2*
1. Zhejiang Technical Institute of Economics, Hangzhou 310018, China 2. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
摘要： 采用中红外光谱分析技术对香菇产地进行识别研究，并将相关向量机(relevance vector machine，RVM)算法应用于中红外光谱判别分析之中，取得了较好的效果。通过采集香菇粉末的中红外透射光谱，去除光谱噪声明显部分，对剩下的3 581～689 cm-1透射谱线采用多元散射校正(multiplicative scatter correction，MSC)进行预处理，并基于预处理谱线建立了香菇产地识别的偏最小二乘判别分析(partial least squares-discriminant analysis，PLS-DA)、簇类独立软模式分类(soft independent modeling of class analogy，SIMCA)、K最邻近算法(K-nearest neighbor algorithm，KNN)、支持向量机(support vector machine, SVM)、RVM模型等五种判别分析模型。所有模型的识别正确率均高于80%，KNN, SVM和RVM判别分析模型取得了相近的结果，建模集和预测集识别正确率高于90%。基于全谱的PLS-DA模型的加权回归系数，利用加权回归系数法选取了6个特征波数，并基于特征波数建立了PLS-DA, KNN, SVM和RVM模型。基于特征波数的PLS-DA模型的建模集和预测集识别正确率均低于80%，而KNN, SVM和RVM模型的建模集和预测集的识别效果相近，且都高于90%。基于全谱和特征波数的模型中，RVM算法表现出较好的效果，识别正确率优于90%。结果表明，基于中红外光谱技术能用于香菇产地的识别，特征波数的选择以及RVM算法可以有效的用于中红外光谱判别分析中。本文成功将中红外光谱用于香菇产地识别研究，为香菇品质以及其他农产品品质分析提供了一种新的想法，具有实际意义。
关键词：中红外光谱;香菇产地;相关向量机
Abstract：In the present study, Mid-infrared spectroscopy was used to identify the producing area of Letinus edodes, and relevance vector machine (RVM) was put forward to build classification models as a novel classification technique, and they obtained good performances. The head and the tail of the acquired mid-infrared spectra with the absolute noise were cut off, and the remaining spectra in the range of 3 581～689 cm-1 (full spectra) of Letinus edodes were preprocessed by multiplicative scatter correction (MSC). Five classification techniques, including partial least Squares-discriminant analysis (PLS-DA), soft independent modeling of class analogy (SIMCA), K-nearest neighbor algorithm (KNN), support vector machine (SVM) and RVM, were applied to build classification models based on the preprocessed full spectra. All classification models obtained classification accuracy over 80%, KNN, SVM and RVM models based on full spectra obtained similar and good performances with classification accuracy over 90% in both the calibration set and the prediction set. The weighted regression coefficients (Bw) were used to select effective wave numbers of mid-infrared spectra and 6 effective wave numbers in total were selected on the basis of the weighted regression coefficients of PLS-DA model based on full spectra. PLS-DA, KNN, SVM and RVM models were built using these effective wave numbers. Compared with the classification models based on full spectra, PLS-DA models based on effective wave numbers obtained relatively worse results with classification accuracy less than 80%, and KNN, SVM and RVM obtained similar results in both calibration set and prediction set with classification accuracy over 90%. RVM performed well with classification rate over 90% based on full spectra and effective wave numbers. The overall results indicated that producing area of Letinus edodes could be identified by mid-infrared spectroscopy, while wave number selection and the RVM algorithm could be effectively used in mid-infrared spectroscopy analysis. In this study, mid-infrared spectroscopy was successfully applied to identify the producing area of Letinus edodes, which could provide a new concept for quality analysis of Letinus edodes and other agricultural products, and the application of mid-infrared spectroscopy had practical significance.
Key words：Mid-infrared spectroscopy;Producing area of Letinus edodes;Relevance vector machine (RVM)
[1] LIU Chun-ru, YI Cheng(刘春如，易 诚). Quarterly of Forest By-Product and Speciality in China(中国林副特产), 2002, (1): 52. [2] XU Xiao-fei, ZHANG Bing-qing, LUO Zhen, et al(徐晓飞, 张丙青, 罗 珍, 等). Edible Fungi(食用菌), 2012, (2): 57. [3] Barron C. Journal of Agricultural and Food Chemistry, 2011, 59(19): 10442. [4] Wu D, Nie P C, He Y, et al. Food and Bioprocess Technology, 2011, 5(4): 1402. [5] Clegg I M, Daly A M, Donnelly C, et al. Applied Spectroscopy, 2012, 66(5): 574. [6] Yoshida S, Yoshida M, Yamamoto M, et al. Journal of Pharmaceutical and Biomedical Analysis, 2013, 76: 169. [7] Fudge A L, Wilkinson K L, Ristic R, et al. Journal of Agricultural and Food Chemistry, 2012, 60(1): 52. [8] Kanakis C D, Petrakis E A, Kimbaris A C, et al. Phytochemical Analysis, 2012, 23(1): 34. [9] He Y, Li X L, Deng X F. Journal of Food Engineering, 2007, 79(4): 1238. [10] Liu F, Ye X J, He Y, et al. Journal of Food Engineering, 2009, 93(2): 127. [11] Liu F, He Y. Food and Bioprocess Technology, 2011, 4(3): 387. [12] Gori A, Maggio R M, Cerretani L, et al. International Dairy Journal, 2012, 23(2): 115. [13] Balabin R M, Safieva R Z, Lomakina E I. Analytica Chimica Acta, 2010, 671(1-2): 27. [14] Mireei S A, Sadeghi M. Journal of Food Engineering, 2013, 114(3): 397. [15] Langeron Y, Doussot M, Hewson D J, et al. Engineering Applications of Artificial Intelligence, 2007, 20(3): 415. [16] Liu F, He Y. Food Research International, 2008, 41(5): 562. [17] Tipping M E. Journal of Machine Learning Research, 2001, 1(3): 211. [18] Caesarendra W, Widodo A, Yang B S. Mechanical Systems and Signal Processing, 2010, 24(4): 1161.
