Determination of Wine Varieties with NIR and Fusion of Multiple Classifiers
LI Kai1, LI Xue-ying1, LUAN Li-li1, HU Wen-yan1, WANG Yu-heng1, LI Jing-ming2*, LI Jun-hui1, LAO Cai-lian1, ZHAO Long-lian1*
1. College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China 2. College of Food Science & Nutrition Engineering, China Agricultural University, Beijing 100083, China
Abstract：The conventional qualitative analysis of near infrared spectroscopy (NIR) commonly uses one single classification model. This paper focused on the fusion of multiple classifiers based on different single classifiers by using the fused classifier to determine different varieties of red-wines. NIR spectra of 170 red-wine samples were collected by using Fourier transform near-infrared spectrometer. Red-wine classification models were established respectively, based on PLS-DA, SVM, Fisher and AdaBoost. Then these models were selected to obtain some different base classifiers according to Diversity Measure Feature Selective (DMFS). The highest accuracy rate of determining different varieties of red-wine test samples of four single base classifiers was up to 88.24%, and at the same time the lowest discriminant accuracy rate was 81.18%. At last, we got the fused classifier, which combined four base classifiers with weighted voting principle, and determined its test set again by using the fused classifier. The final classification accuracy rate for red-wine varieties increased to 92.94%, In contrast with one single classifier, the lowest misjudged number of fused classifiers decreased from 9 to 6.These results suggested that the performance of fused classifier is superior to one single classifier. It is feasible to use fused classifier combined with near infrared spectroscopy to determine different varieties of red-wines.
李 凯1，李雪莹1，栾丽丽1，胡文雁1，王宇恒1，李景明2*，李军会1，劳彩莲1，赵龙莲1* . 近红外光谱和多分类器融合的葡萄酒品种判别研究 [J]. 光谱学与光谱分析, 2016, 36(11): 3547-3551.
LI Kai1, LI Xue-ying1, LUAN Li-li1, HU Wen-yan1, WANG Yu-heng1, LI Jing-ming2*, LI Jun-hui1, LAO Cai-lian1, ZHAO Long-lian1*. Determination of Wine Varieties with NIR and Fusion of Multiple Classifiers. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(11): 3547-3551.
[1] LI Hua(李 华). Wine Testing(葡萄酒品尝学). Beijing: Science Press(北京: 科学出版社), 2006. [2] PENG De-hua, CAO Jian-hong(彭德华，曹建宏). A Free Discussion about Self-Brewed Wine(葡萄酒自酿漫谈). Beijing: Chemical Industry Press(北京：化学工业出版社), 2012. [3] Shipp C A，Kuncheva L I. Information Fusion, 2002, 3(2): 135. [4] YANG Yan, NIE Peng-cheng, YANG Hai-qing，et al(杨 燕，聂鹏程，杨海清，等). Transactions of the CSAE(农业工程学报), 2010，26(3): 238. [5] ZHU Zhi-hui, XIE De-jun, LI Wan-qing, et al(祝志慧, 谢德君, 李婉清，等). Transactions of the CSAE(农业工程学报)，2015, 31(2): 312. [6] TAO Si-jia, LI Meng-hua, LI Jing-ming, et al(陶思嘉，李梦华，李景明，等). Chinese Journal of Analytical Chemistry(分析化学), 2014, 42(2): 215. [7] Altincay H, Demirekler. Pattern Recognition Letters，2003，24(9-10): 1163. [8] CAO Ying, MIAO Qi-guang, LIU Jia-chen, et al(曹 莹, 苗启广, 刘家辰，等). Acta Automatica Sinica(自动化学报), 2013, 39(6): 745. [9] Chen Xiaojing, Wu Di, He Yong, et al. Analytica Chimica Acta, 2009, 638(1): 16. [10] FAN Shu-xiang, HUANG Wen-qian, LI Jiang-bo, et al(樊书详，黄文倩，李江波，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014, 34(10): 2707. [11] Kuncheva L I, Whitaker C J. Machine Learning, 2003，51(2)：181. [12] XUE Mei, ZHENG Quan-di(薛 梅，郑全弟). Computer Engineering and Design(计算机工程与设计), 2010, 31(23)：5104. [13] Kittler J, Hatef M, Duin, R P W, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(3): 226. [14] Sun S. Pattern Recognition Letters, 2010, 31(2): 119.
