Tags

Type your tag names separated by a space and hit enter

Application of invasive weed optimization and least square support vector machine for prediction of beef adulteration with spoiled beef based on visible near-infrared (Vis-NIR) hyperspectral imaging.
Meat Sci. 2019 May; 151:75-81.MS

Abstract

Different multivariate data analysis methods were investigated and compared to optimize rapid and non-destructive quantitative detection of beef adulteration with spoiled beef based on visible near-infrared hyperspectral imaging. Four multivariate statistical analysis methods including partial least squares regression (PLSR), support vector machine (SVM), least squares support vector machine (LS-SVM) and extreme learning machine (ELM) were carried out in developing full wavelength models. Good prediction was obtained by applying LS-SVM in the spectral range of 496-1000 nm with coefficients of determination (R2) of 0.94 and 0.94 as well as root-mean-squared errors (RMSEs) of 5.39% and 6.29% for calibration and prediction, respectively. To reduce the high dimensionality of hyperspectral data and to establish simplified models, a novel method named invasive weed optimization (IWO) was developed to select key wavelengths and it was compared with competitive adaptive reweighted sampling (CARS) and genetic algorithm (GA). Among the four multivariate analysis models based on important wavelengths determined by IWO, the LS-SVM simplified model performed best where R2 of 0.97 and 0.95 as well as RMSEs of 4.74% and 5.67% were attained for calibration and prediction, respectively. The optimum simplified model was applied to hyperspectral images in pixel-wise to visualize the distribution of spoiled beef adulterant in fresh minced beef. The current study demonstrated that it was feasible to use Vis-NIR hyperspectral imaging to detect homologous adulterant in beef.

Authors+Show Affiliations

College of Engineering, Huazhong Agricultural University, Wuhan, Hubei, China.College of Engineering, Huazhong Agricultural University, Wuhan, Hubei, China; Key Laboratory of Agricultural Equipment in Mid-lower Yangtze River, Ministry of Agriculture, Wuhan, Hubei, China. Electronic address: yaoze.feng@mail.hzau.edu.cn.College of Engineering, Huazhong Agricultural University, Wuhan, Hubei, China.College of Engineering, Huazhong Agricultural University, Wuhan, Hubei, China; Key Laboratory of Agricultural Equipment in Mid-lower Yangtze River, Ministry of Agriculture, Wuhan, Hubei, China.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

30716565

Citation

Zhao, Hai-Tao, et al. "Application of Invasive Weed Optimization and Least Square Support Vector Machine for Prediction of Beef Adulteration With Spoiled Beef Based On Visible Near-infrared (Vis-NIR) Hyperspectral Imaging." Meat Science, vol. 151, 2019, pp. 75-81.
Zhao HT, Feng YZ, Chen W, et al. Application of invasive weed optimization and least square support vector machine for prediction of beef adulteration with spoiled beef based on visible near-infrared (Vis-NIR) hyperspectral imaging. Meat Sci. 2019;151:75-81.
Zhao, H. T., Feng, Y. Z., Chen, W., & Jia, G. F. (2019). Application of invasive weed optimization and least square support vector machine for prediction of beef adulteration with spoiled beef based on visible near-infrared (Vis-NIR) hyperspectral imaging. Meat Science, 151, 75-81. https://doi.org/10.1016/j.meatsci.2019.01.010
Zhao HT, et al. Application of Invasive Weed Optimization and Least Square Support Vector Machine for Prediction of Beef Adulteration With Spoiled Beef Based On Visible Near-infrared (Vis-NIR) Hyperspectral Imaging. Meat Sci. 2019;151:75-81. PubMed PMID: 30716565.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Application of invasive weed optimization and least square support vector machine for prediction of beef adulteration with spoiled beef based on visible near-infrared (Vis-NIR) hyperspectral imaging. AU - Zhao,Hai-Tao, AU - Feng,Yao-Ze, AU - Chen,Wei, AU - Jia,Gui-Feng, Y1 - 2019/01/30/ PY - 2018/05/29/received PY - 2019/01/02/revised PY - 2019/01/28/accepted PY - 2019/2/5/pubmed PY - 2019/3/20/medline PY - 2019/2/5/entrez KW - Beef adulteration KW - Extreme learning machine KW - Invasive weed optimization KW - Least squares support vector machine KW - Variable selection SP - 75 EP - 81 JF - Meat science JO - Meat Sci VL - 151 N2 - Different multivariate data analysis methods were investigated and compared to optimize rapid and non-destructive quantitative detection of beef adulteration with spoiled beef based on visible near-infrared hyperspectral imaging. Four multivariate statistical analysis methods including partial least squares regression (PLSR), support vector machine (SVM), least squares support vector machine (LS-SVM) and extreme learning machine (ELM) were carried out in developing full wavelength models. Good prediction was obtained by applying LS-SVM in the spectral range of 496-1000 nm with coefficients of determination (R2) of 0.94 and 0.94 as well as root-mean-squared errors (RMSEs) of 5.39% and 6.29% for calibration and prediction, respectively. To reduce the high dimensionality of hyperspectral data and to establish simplified models, a novel method named invasive weed optimization (IWO) was developed to select key wavelengths and it was compared with competitive adaptive reweighted sampling (CARS) and genetic algorithm (GA). Among the four multivariate analysis models based on important wavelengths determined by IWO, the LS-SVM simplified model performed best where R2 of 0.97 and 0.95 as well as RMSEs of 4.74% and 5.67% were attained for calibration and prediction, respectively. The optimum simplified model was applied to hyperspectral images in pixel-wise to visualize the distribution of spoiled beef adulterant in fresh minced beef. The current study demonstrated that it was feasible to use Vis-NIR hyperspectral imaging to detect homologous adulterant in beef. SN - 1873-4138 UR - https://www.unboundmedicine.com/medline/citation/30716565/Application_of_invasive_weed_optimization_and_least_square_support_vector_machine_for_prediction_of_beef_adulteration_with_spoiled_beef_based_on_visible_near_infrared__Vis_NIR__hyperspectral_imaging_ L2 - https://linkinghub.elsevier.com/retrieve/pii/S0309-1740(18)30546-1 DB - PRIME DP - Unbound Medicine ER -