Tags

Type your tag names separated by a space and hit enter

[NIR spectroscopy based on least square support vector machines for quality prediction of tomato juice].
Guang Pu Xue Yu Guang Pu Fen Xi. 2009 Apr; 29(4):931-4.GP

Abstract

The application of least square support vector machines (LS-SVM) regression method based on statistics study theory to the analysis with near infrared (NIR) spectra of tomato juice was introduced in the present paper. In this method, LS-SVM was used for establishing model of spectral analysis, and was applied to predict the sugar contents (SC) and available acid (VA) in tomato juice samples. NIR transmission spectra of tomato juice were measured in the spectral range of 800-2,500 nm using InGaAs detector. The radial basis function (RBF) was adopted as a kernel function of LS-SVM. Sixty seven tomato juice samples were used as calibration set, and thirty three samples were used as validation set. The results of the method for sugar contents (SC) and available acid (VA) prediction were: a high correlation coefficient of 0.9903 and 0.9675, and a low root mean square error of prediction (RMSEP) of 0.0056 degree Brix and 0.0245, respectively. And compared to PLS and PCR methods, the performance of the LSSVM method was better. The results indicated that it was possible to built statistic models to quantify some common components in tomato juice using near-infrared (NIR) spectroscopy and least square support vector machines (LS-SVM) regression method as a nonlinear multivariate calibration procedure, and LS-SVM could be a rapid and accurate method for juice components determination based on NIR spectra.

Authors+Show Affiliations

Huang K
College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310029, China. huangkang23@hotmail.com
Wang HJ
No affiliation info available
Xu HR
No affiliation info available
Wang JP
No affiliation info available
Ying YB
No affiliation info available

MeSH

BeveragesCarbohydratesLeast-Squares AnalysisLycopersicon esculentumQuality ControlSpectroscopy, Near-Infrared

Pub Type(s)

Evaluation Study
Journal Article
Research Support, Non-U.S. Gov't

Language

chi

PubMed ID

19626875

Citation

Huang, Kang, et al. "[NIR Spectroscopy Based On Least Square Support Vector Machines for Quality Prediction of Tomato Juice]." Guang Pu Xue Yu Guang Pu Fen Xi = Guang Pu, vol. 29, no. 4, 2009, pp. 931-4.
Huang K, Wang HJ, Xu HR, et al. [NIR spectroscopy based on least square support vector machines for quality prediction of tomato juice]. Guang Pu Xue Yu Guang Pu Fen Xi. 2009;29(4):931-4.
Huang, K., Wang, H. J., Xu, H. R., Wang, J. P., & Ying, Y. B. (2009). [NIR spectroscopy based on least square support vector machines for quality prediction of tomato juice]. Guang Pu Xue Yu Guang Pu Fen Xi = Guang Pu, 29(4), 931-4.
Huang K, et al. [NIR Spectroscopy Based On Least Square Support Vector Machines for Quality Prediction of Tomato Juice]. Guang Pu Xue Yu Guang Pu Fen Xi. 2009;29(4):931-4. PubMed PMID: 19626875.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - [NIR spectroscopy based on least square support vector machines for quality prediction of tomato juice]. AU - Huang,Kang, AU - Wang,Hui-jun, AU - Xu,Hui-rong, AU - Wang,Jian-ping, AU - Ying,Yi-bin, PY - 2009/7/25/entrez PY - 2009/7/25/pubmed PY - 2010/5/26/medline SP - 931 EP - 4 JF - Guang pu xue yu guang pu fen xi = Guang pu JO - Guang Pu Xue Yu Guang Pu Fen Xi VL - 29 IS - 4 N2 - The application of least square support vector machines (LS-SVM) regression method based on statistics study theory to the analysis with near infrared (NIR) spectra of tomato juice was introduced in the present paper. In this method, LS-SVM was used for establishing model of spectral analysis, and was applied to predict the sugar contents (SC) and available acid (VA) in tomato juice samples. NIR transmission spectra of tomato juice were measured in the spectral range of 800-2,500 nm using InGaAs detector. The radial basis function (RBF) was adopted as a kernel function of LS-SVM. Sixty seven tomato juice samples were used as calibration set, and thirty three samples were used as validation set. The results of the method for sugar contents (SC) and available acid (VA) prediction were: a high correlation coefficient of 0.9903 and 0.9675, and a low root mean square error of prediction (RMSEP) of 0.0056 degree Brix and 0.0245, respectively. And compared to PLS and PCR methods, the performance of the LSSVM method was better. The results indicated that it was possible to built statistic models to quantify some common components in tomato juice using near-infrared (NIR) spectroscopy and least square support vector machines (LS-SVM) regression method as a nonlinear multivariate calibration procedure, and LS-SVM could be a rapid and accurate method for juice components determination based on NIR spectra. SN - 1000-0593 UR - https://www.unboundmedicine.com/medline/citation/19626875/[NIR_spectroscopy_based_on_least_square_support_vector_machines_for_quality_prediction_of_tomato_juice]_ DB - PRIME DP - Unbound Medicine ER -