Abstract
Fourier transformation near-infrared (FT-NIR) spectroscopy as an analytical tool combined with supervised pattern recognition was attempted to classify four different brands of Chinese soybean paste in this work. Three supervised pattern recognition methods, which were K-nearest neighbors (KNN), error back-propagation neural network (BP-NN), and support vector machines (SVM), were used to develop the identification models based on principal component analysis. Some parameters of the algorithms and also the number of principal components (PCs) were optimized by cross-validation in developing models. The performances of three identification models were compared. Experimental results showed that the performance of SVM model was superior to KNN and BP-NN models. The optimal SVM model achieved when the 5 PCs were included, and the identification rates both were 100% in the training and validation sets. This work demonstrated that FT-NIR spectroscopy technique coupled with SVM algorithm could be successfully used to discriminate different brands of Chinese soybean paste.
Similar content being viewed by others
References
Balabin RM, Safieva RZ, Lomakina EI (2010) Anal Chim Acta 671:27–35
Berrueta L, Alonsosalces R, Heberger K (2007) J Chromatogr A 1158:196–214
Candolfi A, Maesschalck RD, Hailey PA, Harrington ACE (1999) J Pharmaceut Biomed 19:923–935
Cen H, He Y (2007) Trends Food Sci Tech 18:72–83
Chen Q, Zhao J, Lin H (2009) Spectrochim Acta A 72:845–850
Chen Q, Cai J, Wan X, Zhao J (2011) LWT-Food Sci Technol 44:2053–2058
Cleve E, Bach E, Schollmeyer E (2000) Anal Chim Acta 420:163–167
Cocchi M, Corbellini M, Foca G, Lucisano M, Pagani MA, Tassi L, Ulrici A (2005) Anal Chim Acta 544:100–107
Cocchi M, Durante C, Foca G, Marchetti A, Tassi L, Ulrici A (2006) Talanta 68:1505–1511
Cortes C, Vapnik V (1995) Mach Learn 20:273–297
Di Egidio V, Sinelli N, Limbo S, Torri L, Franzetti L, Casiraghi E (2009) Postharvest Biol Tec 54:87–92
Dou Y, Qu N, Wan B, Chi YZ, Ren YL (2007) Eur J Pharm Sci 32:193–199
Fang S, Wang M, Qi W, Zheng F (2008) Comp Mater Sci 44:647–655
Jalali-Heravi M, Masoum S, Shahbazikhah P (2004) J Magn Reson 171:176–185
Krämer K, Ebel S (2000) Anal Chim Acta 420:155–161
Langeron Y, Doussot M, Hewson D, Duchene J (2007) Eng Appl Artif Intel 20:415–427
Lee S, Ahn B (2009) Food Chem 114:600–609
Lee M, Nelson S (2008) Artif Intell Med 43:61–74
Lin H-T, Lin C-J (2003) Technical report: Department of Computer Science and Information Engineering, National Taiwan University
Lin H, Chen Q, Zhao J, Zhou P (2009) J Pharmaceut Biomed 50:803–808
Lin H, Zhao J, Chen Q, Zhou F, Sun L (2011) Spectrochim Acta A 79:1381–1385
Luypaert J, Heuerding S, Heyden YV, Massart DL (2004) J Pharmaceut Biomed 36:495–503
Macho S, Larrechi MS (2002) Trac-Trend Anal Chem 21:799–806
Marini F, Balestrieri F, Bucci R, Magrì AL, Marini D (2003) Microchem J 74:239–248
Marini F, Balestrieri F, Bucci R, Magrì AD, Magrì AL, Marini D (2004) Chemometr Intell Lab Syst 73:85–93
Odlare M, Svensson K, Pell M (2005) Geoderma 126:193–202
Park MK, Cho IH, Lee S, Choi H-K, Kwon D-Y, Kim Y-S (2010) Food Chem 122:1313–1319
Reboucas MV, dos Santos JB, Domingos D, Massa ARCG (2010) Vib Spectrosc 52:97–102
Rodriguez-Saona LE, Fry FS, McLaughlin MA, Calvey EM (2001) Carbohyd Res 336:63–74
Roggo Y, Duponchel L, Huvenne J-P (2003) Anal Chim Acta 477:187–200
Sathiya Keerthi S, Lin C-J (2003) Neural Comput 15:1667–1689
Shaffer RE, Rose-Pehrsson SL, Angrew McGill R (1999) Anal Chim Acta 384:305–317
Shukla S, Choi TB, Park H-K, Kim M, Lee IK, Kim J-K (2010a) Food Chem Toxicol 48:2005–2010
Shukla S, Park H-K, Kim J-K, Kim M (2010b) Food Chem Toxicol 48:1191–1195
Tewari JC, Dixit V, Cho B-K, Malik KA (2008) Spectrochim Acta A 71:1119–1127
Thissen U (2004) Chemometr Intell Lab Syst 73:169–179
Tsoumanis CM, Giokas DL, Vlessidis AG (2010) Talanta 82:575–581
Wilson J, Hardy K, Allen R, Copeland L, Wrangham R, Collins M (2010) J Archaeol Sci 37:594–604
Wu C, Chau K, Li Y (2008) J Hydrol 358:96–111
Zhao J, Lin H, Chen Q, Huang X, Sun Z, Zhou F (2010) J Food Eng 98:408–414
Acknowledgments
This work was financially supported by the Graduate Scientific Research and Innovation from Jiangsu Province Colleges (grant no. CXZZ11_0572), the Priority Academic Program Development of Jiangsu Higher Education Institutions (grant no. PAPD [2011]6), and the Agriculture Science and Technology of Zhenjiang (grant no. NY2010017). The authors gratefully acknowledged the website http://www.csie.ntu.edu.tw/∼cjlin/libsvm/ for the LibSVM MatLab codes downloaded free of charge.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jiang, H., Liu, G., Xiao, X. et al. Classification of Chinese Soybean Paste by Fourier Transform Near-Infrared (FT-NIR) Spectroscopy and Different Supervised Pattern Recognition. Food Anal. Methods 5, 928–934 (2012). https://doi.org/10.1007/s12161-011-9331-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12161-011-9331-0