Classification of Tea Varieties Via FTIR Spectroscopy Based on Fuzzy Uncorrelated Discriminant C-Means Clustering
WU Xiao-hong1, 2, ZHAI Yan-li1, WU Bin3, SUN Jun1, 2, DAI Chun-xia1,4
1. School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China
2. Key Laboratory of Facility Agriculture Measurement and Control Technology and Equipment of Machinery Industry, Jiangsu University, Zhenjiang 212013, China
3. Department of Information Engineering, Chuzhou Vocational Technology College, Chuzhou 239000, China
4. School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, China
Abstract:Tea, as a kind of healthy drink, is loved by many people. But its function and effect vary from different varieties. Therefore, it is of great significance to find a fast, easy and simple method for the identification of tea varieties. In order to classify different tea varieties quickly and accurately, fuzzy uncorrelated discriminant c-means clustering algorithm (FUDCM) was proposed based on the fuzzy uncorrelated discriminant transformation (FUDT) algorithm and fuzzy c-means clustering (FCM) algorithm in this paper. FUDCM can extract the fuzzy uncorrelated discriminant information from spectral data dynamically in the process of fuzzy clustering. To start with, Fourier transform infrared spectroscopy (FTIR) data of three kinds of tea samples (i. e. Emeishan Maofeng, high quality Leshan trimeresurus and low quality Leshan trimeresurus) was collected using FTIR-7600 spectrometer in the wave number range of 4 001.569~401.121 1 cm-1,. Secondly, multiple scattering correction (MSC) was applied to preprocess these spectra. Thirdly, principal component analysis (PCA) was employed to reduce the dimensionality of spectral data from 1 868 to 20 and linear discriminant analysis (LDA) was used to extract the identification information of the spectral data. Finally, FCM and FUDCM were performed to identify the tea varieties respectively. The experimental results showed that when the weight index m=2, the clustering accuracy rate of FCM was 63.64% and that of FUDCM was 83.33%. After 67 iterations, FCM achieved convergence while FUDCM did that after only 17 iterations. Tea varieties could be quickly and efficiently identified by combining FTIR technology with PCA, LDA and FUDCM, and the identification accuracy of FUDCM was higher than that of FCM.
[1] Panigrahi N, Bhol C S, Das B S, et al. Journal of Food Engineering, 2016, 190: 101.
[2] Wu X H, Wu B, Sun J, et al. International Journal of Food Properties, 2016, 19: 1016.
[3] YANG Xin-he, WANG Li-li, HUANG Jian-an, et al(杨新河,王丽丽,黄建安,等). Food Science(食品科学), 2012, 33(14): 203.
[4] Ayvaz H, Bozdogan A, Giusti M M, et al. Food Chemistry, 2016, 211: 374.
[5] ZHANG Rong-xiang, ZHANG Wei, ZHANG Yan-wei, et al(张荣香,张 玮,张艳伟,等). Infrared Technology(红外技术), 2013, 35(5): 304.
[6] Cai J X, Wang Y F, Xia X G, et al. International Journal of Biological Macromolecules, 2015, 78: 439.
[7] Mecozzi M, Sturchio E. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2015, 137: 90.
[8] Kokalj M, Stih K, Kreft S. Planta Medica, 2014, 80(12): 1023.
[9] Jiang X, Li S, Xiang G, et al. Food Chemistry, 2016, 212: 585.
[10] Xing Z, Du C, Tian K, et al. Talanta, 2016, 158: 262.
[11] Salman A, Shufan E, R. K. Sahu R K, et al. Vibrational Spectroscopy, 2016, 83: 17.
[12] Wang Y, Shui P, Fan X, et al. Electronics Letters, 2016, 52(7): 513.
[13] Hou S, Riley C B. Chemometrics and Intelligent Laboratory Systems, 2015, 142: 49.
[14] WU Xiao-hong, WU Bin, ZHOU Jian-jiang(武小红,武 斌,周建江). Chinese Journal of Image and Graphics(中国图形图像学报), 2009, 14(9): 1832.
[15] Anjos O, Campos M G, Ruiz P C, et al. Food Chemistry, 2015, 169: 218.