Analysis of Flue-Cured Tobacco Flavor Style Features Using Near-Infrared Spectroscopy and Multiple Algorithms Fusion
LUAN Li-li1,3, WANG Yu-heng1,3, HU Wen-yan1,3, YANG Kai2, SHU Ru-xin2, LI Jun-hui1,3*, ZHAO Long-lian1,3, ZHANG Ye-hui1,3
1. College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China
2. Technology Center of Shanghai Tobacco (Group) Corporation, Shanghai 200082, China
3. Key Laboratory of Modern Pricision Agriculture System Integration Research, Ministry of Education, China Agricultural University, Beijing 100083, China
Abstract：In this paper, 3 914 near infrared spectrums of flue-cured tobacco samples was tested. These tobacco samples were collected in 17 provincial origins, including the NONG (Luzhou) flavor 865 cartons, Intermediate flavor 1 646 cartons and QING flavor (Fen) 1 646 cartons. We used near-Infrared spectroscopy and multiple algorithms fusion to analyze flue-cured tobacco flavor style features. Based on the preliminary classification of tobacco flavor according to different origins, accepting transitional and atypical flavor, tobacco flavor classification models of PPF (Projection of Basing on Principal Component and Fisher Criterion), DPLS (Partial least squares discriminant) and SVM (Support vector machine) were established respectively; and 1st and 2nd discriminant results of each algorithm can be known. Using PPF-DPLS-SVM fusion and discriminant results (1st and 2nd) of each algorithm, prediction results can be refined into typical, transitional and atypical flavor. The numbers of three flavors were 493, 392 and 115, respectively. The discriminant accuracy rate of typical flavor was improved to 92.7%. And it was improved 30.2%，15.4% and 16.6% to compared with those achieved using PPF, DPLS and SVM, respectively. The tested samples were collected in main origins of China, which were abundant with great representativeness, therefore, the analysis result had practical application. The analysis method presented greatly improved the discriminant accuracy rate of flue-cured tobacco flavor, which was better than that of the classification according to objective data. The method refining flue-cured tobacco into typical, transitional and atypical flavor, provided guidance to the scientific application and module industrial processing of raw flue-cured tobacco.
栾丽丽，王宇恒，胡文雁，杨 凯，束茹欣，李军会，赵龙莲，张晔晖. 应用近红外光谱和多算法融合方法分析烤烟的香型风格特征[J]. 光谱学与光谱分析, 2017, 37(07): 2046-2049.
LUAN Li-li, WANG Yu-heng, HU Wen-yan, YANG Kai, SHU Ru-xin, LI Jun-hui, ZHAO Long-lian, ZHANG Ye-hui. Analysis of Flue-Cured Tobacco Flavor Style Features Using Near-Infrared Spectroscopy and Multiple Algorithms Fusion. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(07): 2046-2049.
[1] DING Rui-kang, WANG Cheng-han, ZHU Zun-quan(丁瑞康, 王承瀚, 朱尊权). Cigarette Technology(卷烟工艺学). Beijing: Food Industry Press(北京：食品工业出版社), 1958.
[2] HAN Jin-feng, SONG Na-na(韩锦峰，宋娜娜). Acta Tabacaria Sinica(中国烟草学报), 2014, 20(6): 150.
[3] ZHANG Xia, ZHANG Tao, DUAN Ruan-xing, et al(张 霞, 张 涛, 段沅杏，等). Tobacco Science & Technology(烟草科技), 2015, 48(2): 37.
[4] CHANG Ai-xia, ZHANG Jian-ping, DU Yong-mei, et al(常爱霞, 张建平, 杜咏梅，等). Acta Tabacaria Sinica(中国烟草学报), 2010, 16(2): 14.
[5] SHU Ru-xin, CAI Jia-yue, YANG Zheng-yu, et al(束茹欣, 蔡嘉月, 杨征宇，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014, 34(10): 2764.
[6] Roberts C A, Workman Jr J, Reeves III J B, et al. Near-Infrared Spectroscopy in Agriculture. Madison, Wisconsin: American Society of Agronomy，Crop Science Society of America, Soil Science Society of America, 2004.
[7] Zhang Min, Cai Wensheng, Shao Xueguang. Analyst, 2011, 136(20): 4217.
[8] SONG Nan(宋 楠). Acta Tabacaria Sinica(中国烟草学报), 2015, 21(5): 16.
[9] Bigdeli B, Samadzadegan F, Reinartz P. International Journal of Applied Earth Observation and Geoinformation, 2015, 38: 309.
[10] zkan K, Ergin S, I瘙塂k 瘙塁, et al. Waste Management, 2015, 35: 29.
[11] Sarmento Júnior Mazivila, Felipe Bachion de Santana, Hery Mitsutake, et al. Fuel, 2015, 142: 222.
[12] Martens H, Naes T. Multivariate Calibration. Wiley, USA, 1989.
[13] Vapnik V N. The Nature of Statistical Learning Theory. Springer-Verlag, GER，1995.
[14] Julio López, Sebastián Maldonado. Information Sciences, 2016, 330: 328.
