三维荧光光谱结合PCA-SVM对几种浓香型白酒的鉴别

doi:10.3964/j.issn.1000-0593(2016)04-1021-06

Abstract
References
Related Citation (15)

Download: PDF (3867 KB)
Export: BibTeX | EndNote (RIS)

Abstract In this paper, a method for discrimination of different bands liquor with strong aroma type based on three-dimensional fluorescence spectrum technology was developed. Firstly, the three-dimensional fluorescence spectra of seven different brands liquor were measured by the FLS920 fluorescence spectrometer which produced by Edinburgh in England. The spectral shows that different bands liquors have similar fluorescence characteristics and it’s difficult to distinguish them only with Fluorescent characteristic parameters. Because of this, the first-order and second-order partial derivatives respect to fluorescence emission wavelength on each of the excitation wavelength were carried out in this paper. Daubechies-7 (db7) orthonormal wavelet with compact support was used to compress the spectral data. The forth approximate coefficients were finally chosen as the new data matrix. Then the new data matrix was analyzed by principal component analysis (PCA) and the principal components were extracted to be used as the inputs of support vector machine (SVM). The K-fold cross validation was applied to optimize the parameters c and γ and the prediction model was constructed in the end. Fourteen samples were selected randomly from each brand that in total of ninety-eight samples were selected as the training set, and the rest forty-two samples were collected as the prediction set. The effect of three different spectral data after processing on the model is compared: original data, the first-order and second-order partial derivatives on the spectral data. The results show that the three-dimensional fluorescence spectra with the pretreatment of second-order partial derivatives coupled with PCA and SVM can make a good performance on the brands identification of strong aroma type liquors, the accuracy of the established model and prediction accuracy were 98.98% and 100%, respectively. This method has the advantage of easy operation, high speed, low cost and provides a good help in the detection and identification of Chinese liquor.

Key words：Chinese Strong aroma type liquors;Three-dimensional fluorescence spectroscopy;Principal component analysis;Support vector machine

Received: 2014-12-18 Accepted: 2015-04-16

ZTFLH:

O657.34

Corresponding Authors: CHEN Guo-qing E-mail: cgq2098@163.com

Cite this article:

XU Rui-yu,ZHU Zhuo-wei,HU Yang-jun, et al. The Discrimination of Chinese Strong Aroma Type Liquors with Three-Dimensional Fluorescence Spectroscopy Combined with Principal Component Analysis and Support Vector Machine[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(04): 1021-1026.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2016)04-1021-06 OR https://www.gpxygpfx.com/EN/Y2016/V36/I04/1021

[1] HAO Jian-yu, ZHANG Su-yi, SHUI Liang-yang, et al(郝建宇，张宿义，税梁扬，等). Liquor-Making Science & Technology(酿酒科技), 2012, 215(5): 92.
[2] CHENG Ping-yan, FAN Wen-lai, XU Yan(程平言, 范文来, 徐岩). Science and Technology of Food Industry(食品工业科技), 2014, 35(8): 49.
[3] CHENG Ping-yan, FAN Wen-lai, XU Yan(程平言, 范文来, 徐岩). Journal of Chinese Mass Spectrometry Society(质谱学报), 2014, 35(1): 32.
[4] DAI Xin, YU Hai-yan, XIAO Zuo-bing(戴鑫, 于海燕, 肖作兵). Food and Fermentation Industries Editorial Staff(食品与发酵工业)，2012, 38(8): 114.
[5] CHENG Ping-yan, FAN Wen-lai, XU Yan(程平言, 范文来, 徐岩). Food and Fermentation Industries Editorial Staff(食品与发酵工业)，2013, 39(6): 169.
[6] NI Li-jun, ZHANG Li-guo(倪力军, 张立国). Basic Chemometrics and Its Application(基础化学计量学及其应用). Shanghai: East China University of Science and Technology Press(上海：华东理工大学出版社), 2011. 56.
[7] XU Jin-gou, WANG Zun-ben(许金钩, 王尊本). Fluorescence Analysis(荧光分析法). Beijing: Science Press(北京：科学出版社), 2006. 299.
[8] DU Shu-xin, JIANG Dan-hong(杜树新, 蒋丹红). Journal of Optoelectronics·Laser(光电子·激光), 2014, 25(3): 545.
[9] CHEN Gui-ping, TONG Pei-jin, GENG Jin-pei, et al(陈贵平, 童佩瑾, 耿金培, 等). Journal of Instrumental Analysis(分析测试学报), 2012, 31(5): 605.
[10] DING Shi-fei, QI Bing-juan, TAN Hong-yan(丁世飞，齐丙娟，谭红艳). Journal of University of Electronic Science and Technology of China(电子科技大学学报), 2011, 40(1): 2.
[11] XU Guo-gen, JIA Ying(许国根, 贾瑛). The Realization of Pattern Recognition and Intelligent Computing Technology of Matlab(模式识别与智能计算的Matlab技术实现). Beijing: Beihang University Press(北京：北京航天航空大学出版社), 2011. 40.
[12] CHEN Yong-yi, XIONG Qiu-fen(陈永义, 熊秋芬). Application of Support Vector Machine Method Tutorial(支持向量机方法应用教程). Beijing: Meteorological Press(北京：气象出版社), 2011. 5.
[13] ZENG Mao-mao, LI Yang, HE Zhi-yong, et al(曾茂茂, 李洋, 何志勇，等). Chinese Journal of Analytical Chemistry(分析化学), 2014, 42(1): 71.
[14] LI Miao-yun, TIAN Lu, HUANG Xian-qing, et al(李苗云, 田璐, 黄现青，等). Food and Fermentation Industries(食品与发酵工业), 2014, 40(2): 37.
[15] MA Yuan-liang, PEI Sheng-lei(马元良，裴生雷). Computer Simulation(计算机仿真), 2010, 27(8): 150.
[16] YU Ming, AI Yue-qiao(于明，艾月乔). Journal of Optoelectronics·Laser(光电子·激光), 2012, 23(2): 374.
[17] SHI Feng, WANG Xiao-chuan, YU Lei(史峰, 王小川, 郁磊). Matlab Neural Network Analysis of 30 Cases(MATLAB神经网络30个案例分析). Beijing: Beihang University Press(北京: 北京航空航天大学出版社), 2010. 112.