Fast Nondestructive Identification of Endothelium Corneum Gigeriae Galli Using Visible/Near-Infrared Spectroscopy
ZHANG Xiao-Yan1, MENG Yao-Yong1,2**, ZHANG Hao1,3, OU Wen-Juan1, LIU Song-Hao1
1College of Biophotonics, South China Normal University, Guangzhou 510631 2Experimental Center, South China Normal University, Guangzhou 510006 3School of Physics and Engineering, Sun Yat-sen University, Guangzhou 510725
Fast Nondestructive Identification of Endothelium Corneum Gigeriae Galli Using Visible/Near-Infrared Spectroscopy
ZHANG Xiao-Yan1, MENG Yao-Yong1,2**, ZHANG Hao1,3, OU Wen-Juan1, LIU Song-Hao1
1College of Biophotonics, South China Normal University, Guangzhou 510631 2Experimental Center, South China Normal University, Guangzhou 510006 3School of Physics and Engineering, Sun Yat-sen University, Guangzhou 510725
摘要Vis/NIR spectroscopy, in combination with partial least square (PLS) analysis and a back-propagation neural network, is investigated to identify endothelium corneum gigeriae galli (ECGG). The spectral features of ECGGs and their counterfeits are reasonably differentiated in vis/NIR region, which provides enough qualitative information to establish the relationship between the spectra and samples for identification. After pretreatment of the spectral data, cross validation is implemented for extracting the best number of principal components. Then the calibration and validation set are performed well. The PLS and back propagation neural network (BPNN) model gives the BPNN to be 0.9941 and the root mean square residual (RMSR) to be 0.0775 for the calibration set, and the multiple correlation coefficient (MCC) to 0.9874 and the RMSE to 0.1134 for the validation set. Thus the PLS and BPNN model is reliable and practicable. Through testing, a recognition accuracy of 100% is achieved. The present study could offer a new approach for fast and nondestructive discrimination of ECGG and its counterfeit.
Abstract:Vis/NIR spectroscopy, in combination with partial least square (PLS) analysis and a back-propagation neural network, is investigated to identify endothelium corneum gigeriae galli (ECGG). The spectral features of ECGGs and their counterfeits are reasonably differentiated in vis/NIR region, which provides enough qualitative information to establish the relationship between the spectra and samples for identification. After pretreatment of the spectral data, cross validation is implemented for extracting the best number of principal components. Then the calibration and validation set are performed well. The PLS and back propagation neural network (BPNN) model gives the BPNN to be 0.9941 and the root mean square residual (RMSR) to be 0.0775 for the calibration set, and the multiple correlation coefficient (MCC) to 0.9874 and the RMSE to 0.1134 for the validation set. Thus the PLS and BPNN model is reliable and practicable. Through testing, a recognition accuracy of 100% is achieved. The present study could offer a new approach for fast and nondestructive discrimination of ECGG and its counterfeit.
[1] Liu Z W and Liu L 2009 Essentials of Chinese Medicine (Berlin: Springer-Verlag) p 183195
[2] Li S Z 1982 Compendium of Materia Medica 2nd edn (Beijing: People's Medical Publishing House) p 2595
[3] Li P et al 2008 Trends Anal. Chem. 27 66
[4] Zhou G B et al 2007 J. Chromatogr. A 1142 236
[5] Li N et al 2006 J. Chromatogr. A 1133 29
[6] Tian R T et al 2009 J. Chromatogr. A 1216 2150
[7] Nordström A et al 2006 Anal. Chem. 78 3289
[8] Han J et al 2007 J. Pharm. Biomed. Anal. 44 430
[9] He Y et al 2007 J. Food Eng. 79 1238
[10] Sakudo A et al 2006 Biochem. Biophys. Res. Commun. 341 279
[11] Gomez A H et al 2006 J. Food Eng. 77 313
[12] Xing J et al 2007 J. Food Eng. 82 135
[13] Nojima J et al 2007 Biochem. Biophys. Res. Commun. 362 522
[14] Skala M C et al 2007 Opt. Express. 15 7863
[15] Wang B et al 2009 J. Pharm. Biomed. Anal. 50 158
[16] Lilledahl M B et al 2006 J. Biomed. Opt. 11 1
[17] Mouazen A M et al 2010 Geoderma 158 23
[18] Baffi G et al 1999 Comput. Chem. Eng. 23 1293
[19] Afkhami A et al 2008 Talanta 75 91
[20] Fang B and Ma S F 2009 Lect. Notes Comput. Sci. 5553 1082
[21] Pérez-Marín D et al 2007 Talanta 72 28
[22] Walczak S and Cerpa N 1999 Inform. Software. Tech. 41 107
[23] Ramadan Z et al 2005 Chemom. Intell. Lab. Syst. 75 23