Multiple regression analysis of anthocyanin content of winegrape skins using hyper-spectral image technology

被引：0

作者：

Liu, Xu ^{[1
,2
]}

Wu, Di ^{[3
]}

Liang, Man ^{[1
]}

Yang, Shuqin ^{[4
]}

Zhang, Zhenwen ^{[1
]}

Ning, Jifeng ^{[3
]}

机构：

[1] College of Enology, Northwest A and F University, Yangling

[2] Shaanxi Engineering Research Center for Viti-Viniculture, Yangling

[3] College of Information Engineering, Northwest A and F University, Yangling

[4] College of Mechanical and Electronic Engineering, Northwest A and F University, Yangling

来源：

Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2013年 / 44卷 / 12期

关键词：

Anthocyanin; BP neural network; Hyperspectral image; Partial least squares regression; Support vector regression; Winegrape;

D O I：

10.6041/j.issn.1000-1298.2013.12.030

中图分类号：

学科分类号：

摘要：

This work aimed to determine the anthocyanin content in skin based on hyperspectral imaging technology. The grapes of Cabernet Sauvignon (Vitis vinifera L.) produced in Shaanxi province were used as experimental materials. Hyperspectral images of 60 groups of grape samples were collected by near infrared hyperspectral camera (900-1700 nm). After then, the anthocyanin content of skin was detected by pH-differential method. The grape berry regions of hyperspectral images were extracted as region of interest (ROI) in which its average spectrum was calculated. Moreover, different preprocessing methods were used to improve the signal noise ratio (SNR) including Savitzky-Golay smoothing, normalization and multiplicative scatter correction, et al. Prediction model was established for determining anthocyanin content by the partial least squares regression (PLSR), least squares support vector regression (SVR) and BP neural network (BPNN). It was shown that prediction coefficient of determination (P-R2) of BPNN model built by the thirteen latent variables recommended by PLSR model was 0.9102 and the root mean square error of prediction (RMSEP) was 0.3795.

引用

页码：180 / 186+139

共 25 条

[1]

Hardie W.J., Obrien T.P., Jaudzems V.G., Morphology, anatomy and development of the pericarp after anthesis in grape, Vitis vinifera L., Australian Journal of Grape and Wine Research, 2, 2, pp. 97-142, (1996)

[2]

Downey M.O., Dokoozlian N.K., Krstic M.P., Cultural practice and environmental impacts on the flavonoid composition of grapes and wine: A review of recent research, American Journal of Enology and Viticulture, 57, 3, pp. 257-268, (2006)

[3]

Ribereau-Gayon P., Glories Y., Maujean A., Et al., Handbook of Enology: The Chemistry of Wine Stabilization and Treatments, pp. 136-139, (2006)

[4]

Revilla E., Garcia-Beneytez E., Cabello F., Anthocyanin fingerprint of clones of Tempranillo grapes and wines made with them, Australian Journal of Grape and Wine Research, 15, 1, pp. 70-78, (2009)

[5]

Saint-Cricq de Gaulejac N., Vivas N., Glories Y., Maturation phénolique des raisins rouges relation avec la qualité des vins comparaison des cépages Merlot et Tempranillo, Progrès Agricole et Viticole, 115, 2, pp. 306-318, (1998)

[6]

Liang Z.C., Wu B.H., Fan P.G., Et al., Anthocyanin composition and content in grape berry skin in Vitis germplasm, Food Chemistry, 111, 4, pp. 837-844, (2008)

[7]

Sun D., Hyperspectral Imaging for Food Quality Analysis and Control, (2010)

[8]

Luo Y., He J., He X., Et al., Applied research of agricultural product non-destructive detection using hyperpectral Imaging technology, Journal of Agricultural Mechanization Research, 6, pp. 1-7, (2013)

[9]

Monteiro S.T., Minekawa Y., Kosugi Y., Et al., Prediction of sweetness and amino acid content in soybean crops from hyperspectral imagery, ISPRS Journal of Photogrammetry & Remote Sensing, 62, 1, pp. 2-12, (2007)

[10]

Wu J., Wu S., Liu C., Et al., Explorations of wheat grain protein content prediction using NIR and hyperspectrum technology, Transducer and Microsystem Technologies, 32, 2, pp. 60-62, (2013)

← 1 2 3 →