Recognition of alcohol-free beer by fluorescent spectroscopy and probabilistic neural network

WEI Bai-lin; CHEN Guo-qing; XU Jiang-cai; YAN Guan-feng; MA Chao-qun; ZHU Tuo; GAO Shu-mei

doi:10.3969/j.issn.1001-3806.2010.06.020

In order to identify alcohol-free beer and ordinary beer quickly and accurately,a recognition model of the alcohol-free beer was established,which was based on fluorescent spectroscopy and probabilistic neural network.It was found experimentally that both alcohol-free beer and ordinary beer excited by ultraviolet-visible light could generate strong fluorescence. The fluorescent spectrum for alcohol-free beer is within a range from 420nm to 620nm,its peak wavelength of the fluorescence is about 490nm.The approximate coefficients,obtained by wavelet transform,were used as the network data,and a probabilistic neural network was trained and constructed.The trained probabilistic neural network was employed to recognize sixty beer samples,and the recognition rate was up to 98.33%.The whole research outcomes will provide a new method for recognizing alcohol-free beer.

Recognition of alcohol-free beer by fluorescent spectroscopy and probabilistic neural network

Corresponding author: CHEN Guo-qing, cgq2098@163.com;

1. School of Science, Jiangnan University, Wuxi 214122, China

Received Date: 2009-11-25

Accepted Date: 2010-01-15

Available Online: 2010-11-25

Abstract: In order to identify alcohol-free beer and ordinary beer quickly and accurately,a recognition model of the alcohol-free beer was established,which was based on fluorescent spectroscopy and probabilistic neural network.It was found experimentally that both alcohol-free beer and ordinary beer excited by ultraviolet-visible light could generate strong fluorescence. The fluorescent spectrum for alcohol-free beer is within a range from 420nm to 620nm,its peak wavelength of the fluorescence is about 490nm.The approximate coefficients,obtained by wavelet transform,were used as the network data,and a probabilistic neural network was trained and constructed.The trained probabilistic neural network was employed to recognize sixty beer samples,and the recognition rate was up to 98.33%.The whole research outcomes will provide a new method for recognizing alcohol-free beer.

HTML

Reference (17)

[1]	GU E D,SHI A M,ZHU T,et al.Study on three-dimensional fluorescence spectra of yanghe classical distilled spirits[J].Spectroscopy and Spectral Analysis,2008,28(12):2916-2920(in Chinese).
[2]	LIU Zh Y,ZHU T,GU E D,et al.Study on fluorescence spectra of Chinese rice wine[J].Spectroscopy and Spectral Analysis,2008,28(10):2409-2412(in Chinese).
[3]	TAN K,DU P J.Hyperspectral remote sensing image classification based on radical basis function neural network[J].Spectroscopy and Spectral Analysis,2008,28(9):2009-2013(in Chinese).
[4]	WANG Y Y,HE Y,SHAO Y N,et al.Discrimination among different brands of coffee by using vis-near infrared spectra[J].Spectroscopy and Spectral Analysis,2007,24(4):702-706(in Chinese).
[5]	HAN Y Zh,LI S M,ZHANG Y X,et al.Neural network generalization analysis of recognition for gas impurity in air[J].Journal of Optoelectronics·Laser,2005,16(6):718-721(in Chinese).
[6]	LI Q B,LI X,ZHANG G J,et al.Application of probabilistic neural networks method to gastric endoscope samples diagnosis based on FTIR spectroscopy[J].Spectroscopy and Spectral Analysis,2009,29(6):1553-1557(in Chinese).
[7]	DONG Ch H.MATLAB neural network and application[M].Beijing:National Defense Industry Press,2007:127(in Chinese).
[8]	JIANG J F,XIAO Sh P,YANG D Q.Texture image recognition based on modified probabilistic neural network[J].Computer Engineering and Applications,2008,44(10):48-50(in Chinese).
[9]	ZHANG W,HAO J F,XIANG J P,et al.Predicting type of protein-protein interaction based on probabilistic neural network[J].Computer Engineering and Applications,2008,44(10):98-103(in Chinese).
[10]	YUAN J,ZHOU Y.Damage identification by probabilistic neural networks based on latent components for time-varying structure system[J].Journal of Nanjing University of Aeronautics Astronautics,2009,47(3):402-407(in Chinese).
[11]	DONG Y H,BAI W X,ZHANG J P.Research on application of probability neural network in hyperspetral image classification[J].Journal of Jilin University (Information Science Edition),2008,26(2):122-125(in Chinese).
[12]	CHRISTENSEN J,LADEFOGED A M,NΦRGAARD L.Determination of bitterness in beer using fluorescence spectroscopy and chemometrics[J].Journal of the Institute of Brewing,2005,111(1):3-10.
[13]	SIKORSKA E,GÓRECKI T,KHMELINSKII I V,et al.Fluorescence spectroscopy for characterization and differentiation of beer[J].Journal of the Institute of Brewing,2004,110(4):267-275.
[14]	APPERSON K,LEIPER K A,MCKEOWN I P,et al.Fluorescence and the isolation,characterization and silica adsorption of haze-active beer proteins[J].Journal of the Institute of Brewing,2002,108(2):193-199.
[15]	ZHAO M H,YOU Zh Sh,ZHAO Y G,et al.Face recognition based on NSA multiscale model[J].Laser Technology,2006,30(1):107-109(in Chinese).
[16]	HE Ch T,MA Z,CHEN J G,et al.Recognition of film laser damage based on wavelet transform[J].Laser Technology,2007,31(2):131-136(in Chinese).
[17]	LIU D M,SHEN J Y,WANG L J.Application of the wavelet transform to pattern correlation recognition[J].Laser Technology,2004,28(6):641-644(in Chinese).

Recognition of alcohol-free beer by fluorescent spectroscopy and probabilistic neural network

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views