Abstract:To explore the feasibility of rapid detection of the origin and quality of walnut by using mid-infrared spectroscopy, mid-infrared spectroscopy and chemometrics algorithms were used to classify walnuts of ten varieties from four major origins and finally good results were achieved. After extracting the transmittance spectra of walnut powder, the apparent noise was removed in the head and the tail of the original spectrum, and the remaining spectrum of 700~3 450 cm-1 was denoised by wavelet transform (WT) algorithm. The spectral characteristic wavenumber was extracted by uninformative variable elimination combined withsuccessive projections algorithm (UVE-SPA). Qualitative analysis of the spectrum was performed by principal component analysis (PCA). Back propagation neural network (BPNN), extreme learning machine (ELM), random forests (RF), radial basis function neural network (RBFNN) and partial least squares discrimination analysis (PLS-DA) were used for modeling based on the full spectrum and characteristic wavenumbers. For the discrimination of four different origins, 12 characteristic wavenumbers were selected: 803, 1 355, 1 418, 1 541, 1 580, 1 727, 1 747,1 868, 2 338, 2 462, 2 824, and 3 166 cm-1, the discrimination accuracy of characteristic wavenumbers was much higher than that of full spectrum, and the accuracy of BPNN algorithm combined with characteristic wavenumbers reached 97%. The result of RF algorithm was the worst, and the accuracy was only 69.70%. For the discrimination of ten varieties, 10 characteristic wavenumbers were selected: 903, 1 275, 1 507, 1 541, 1 563, 1 671, 1 868, 2 311, 2 845, 3 437 cm-1, the discrimination accuracy of characteristic wavenumbers was still much higher than that of full spectrum. The accuracy of BPNN algorithm combined with characteristic wavenumbersreached 83.3%. In terms of the versatility of characteristic wavenumbers, there were two same characteristic wavenumbers in the two sets of characteristic wavenumbers: 1 541 and 1 868 cm-1, and most of the other characteristic wavenumbers were similar. The spectra based on characteristic wavenumbers of 10 varieties were used as input variables to discriminate walnuts’ origins, and the result was poor. Therefore, the characteristic wavenumbers selected under the supervisory value of 10 varieties could not be applied to discriminate 4 types of producing origins. Even with the same original data, characteristic wavenumbers selected based on different discriminant problems were less versatile in modeling. After extracting the characteristic wavenumbers by UVE-SPA algorithm, the discrimination results showed that the number of variables can be reduced by more than 99%, which effectively simplified the model, reduced the amount of calculation, and improved the stability of prediction. In general, the performance of each classifier is: BPNN>RBFNN>ELM>PLS-DA>RF. The experimental results showed that the identification of walnut origins and varieties can be realized effectively based on wavelet transform, characteristic wavenumber selection and back propagation neural network algorithm.
[1] Rajaram S, Haddad E H, MejiaA, et al. American Journal of Clinical Nutrition, 2009, 89(5): 1657S.
[2] Papoutsi Z, KassiE, Chinou I, et al. British Journal of Nutrition, 2008, 99(4): 715.
[3] Sze-Tao KW C, Sathe S K. Journal of the Science of Food and Agriculture, 2000, 80(9): 1393.
[4] Pan A, Sun Q, Manson J A E, et al. Journal of Nutrition, 2013, 143(4): 512.
[5] Regueiro J, Sánchezgonzález C, Vallverdúqueralt A, et al. Food Chemistry, 2014, 152: 340.
[6] Banel D K, Hu F B. American Journal of Clinical Nutrition, 2009, 90(1): 56.
[7] Vermeulen P, Pierna J A F, Abbas O, et al. Food Chemistry, 2015, 189: 19.
[8] HE Yong, LIU Fei, LI Xiao-li, et al(何 勇,刘 飞,李晓丽,等). Spectroscopy and Imaging Technology in Ariculture(光谱及成像技术在农业中的应用). Beijing:Science Press(北京:科学出版社),2016. 27.
[9] WU Di, HE Yong, FENG Shui-juan, et al(吴 迪,何 勇,冯水娟,等). Journal of Infrared and Millimeter Waves(红外与毫米波学报), 2008, 27(3): 180.
[10] Clegg I M, Daly AM, Donnelly C, et al. Applied Spectroscopy, 2012, 66(5): 574.
[11] Botelho B G, Reis N, Oliveira L S, et al. Food Chemistry, 2015, 181: 31.
[12] Zhou X F, Yang Z L, Haughey S A, et al. Food Chemistry, 2014, 189: 13.
[13] Kanakis, C D, Petrakis E A, Kimbaris A C, et al. Phytochemical Analysis, 2012, 23(1): 34.
[14] JIA Chang-lu, GAO Shan, ZHANG Hong, et al(贾昌禄,高 山,张 宏,等). Hubei Agricultural Sciences(湖北农业科学), 2016, 55(10): 2560.
[15] Luna A S, Da S A, Pinho J S, et al. Spectrochimica Acta Part A Molecular & Biomolecular Spectroscopy, 2013, 100(12): 115.
[16] Dong W, Ni Y, Kokot S. Journal of Agricultural and Food Chemistry, 2013, 61(3): 540.
[17] Ding S F, Zhao H, Zhang Y N, et al. Artificial Intelligence Review, 2015, 44(1): 103.
[18] Zhang C, Ma Y. Random Forests//Ensemble Machine Learning. Boston, MA, USA: Springer, 2012. 157.
[19] Wang L, Lee F S C, Wang X, et al. Food Chemistry, 2006, 95(3): 529.
[20] Gong A P, Qiu Z J, He Y, et al. Spectrochim Acta A Mol. Biomol. Spectrosc., 2012, 99(99C): 7.
[21] Wythoff B J. Chemometrics and Intelligent Laboratory Systems, 1993, 18(2): 115.
[22] Mohammadi R, Ghomi S M T F, Zeinali F. Engineering Applications of Artificial Intelligence, 2014, 36: 204.