SVM-Based Qualitative Analysis of Muscat Hamburg Wine Produced in Tianjin Region
ZHANG Jun1, 2, WANG Fang2, WEI Ji-ping3, LI Chang-wen3, YANG Hua1, SHAO Chun-fu3, ZHANG Fu-qing2, YIN Ji-tai2, XIAO Dong-guang1
1. Institute of Bio-engineering, Tianjin University of Science and Technology, Key Laboratory of Industrial Microbiology, Ministry of Education, Tianjin 300222, China 2. Sino-French Joint-Venture Dynasty Winery LTD, Tianjin 300402, China 3. Department of Food Research, TASLY Group Co., Ltd, Tianjin 300410, China
Abstract：The purpose was to achieve the identification of Muscat Hamburg wines produced in Tianjin region through scanning and analyzing dry white wine samples of different grape varieties and regions by infrared spectroscopy technology. A support vector machine (SVM) based method was introduced to analyze infrared spectra of dry white wines. The pretreatment processes of the IR spectra were also elaborated, including baseline adjustment, noise Elimination, standard normalization and eliminating the main component of abnormal sample points. The authors selected great quantity of dry white wine samples of different grape regions including 511 Muscat Hamburg wine samples, 438 Italian Riesling wine samples, 307 Chardonnay wine samples, 29 Ugni Blanc wine samples, 44 Rkatsiteli wine samples, 31 longan wine samples and 79 ZeHong wine samples. According to different classification problems, 80% of IR spectra of the wine samples were used to establish discrimination models with SVM-based method, and the remaining 20% of IR spectra were used for the validation of the discrimination models. Experimental results showed that the proposed method is effective, since high classification accuracy, identification rate and rejecting rate were achieved: over 97% for the white wine samples of different grape varieties, meanwhile over 98% for the Muscat Hamburg wine samples produced in different regions. So the method developed in this paper played a good role in the qualitative classification and discrimination of Muscat Hamburg wines produced in Tianjin region. This novel method has a considerable potential and a rosy application future due to the expeditiousness, stability and easy-operation of FTIR method, as well as the veracity and credibility of SVM method.
[1] ZHANG Fu-qing，LI Wei，TIAN Wei-dong，et al(张福庆，李 巍，田卫东，等). Sino-Overseas Grapevine and Wine(中外葡萄与葡萄酒)，2007，(5)： 39. [2] LI Hua(李 华). Study of Red Wine Tasting(葡萄酒品尝学). Beijing： Science Press(北京： 科学出版社)，2006. [3] LI Hua，WANG Hua，YUAN Chun-long，et al(李 华，王 华，袁春龙，等). Red Wine Chemistry(葡萄酒化学). Beijing： Science Press(北京： 科学出版社)，2005. [4] WANG Fang，WANG Wei，WANG Shu-sheng，et al(王 方，王 伟，王树生，等). Liquor-Making Science and Technology(酿酒科技)，2007，(5)： 71. [5] Setkova Lucie，Risticevic Sanja，Pawliszyn Janusz. Journal of Chromatography，2007，A1147(2)： 224. [6] Palma M，Barroso C G. Talanta，2002，58： 265. [7] Liu L，Cozzolino D. Journal of Agricultural and Food Chemistry，2006，54(18)： 6754. [8] Cozzolino D，Smyth H E，Gishen M. Journal of Agricultural and Food Chemistry，2003，51(26)： 7703. [9] Capron X，Smeyers-Verbeke J. Food Chemistry，2007，101(4)： 1585. [10] Vapnik V N. Statistical Learning Theory. New York： Wiley，1998. [11] Cortes C，Vapnik V. Machine Learning，1995，20： 273. [12] Ovidiu Ivanciuc. Reviews in Computational Chemistry，2007，23： 291. [13] B M Wise，N B Gallagher. Journal of Process Control，1996，6(6)： 329. [14] MacGregor J F，Kourti T. Control Engineering Practice，1995，3(3)： 403.
