Identification of Edible-vegetable-oil Types Based on Multi-kernel Learning and Multi-spectral Fusion

2018 3rd International Conference on Insulating Materials, Material Application and Electrical Engineering

材料科学;无线电电子学;电工学

Chen, Yang^1 ; Wang, Jie^1 ; Xu, Qiang^1 ; Luo, Qingsong^1 ; Zheng, Xiao^1

School of Mechanical Engineering, Wuhan Polytechnic University, Wuhan, Hubei

430023, China^1

关键词: Edible vegetable oil;    Generalization ability;    Identification model;    Multi-kernel learning;    Multi-spectral data;    Near infrared spectral;    Prediction accuracy;    Spectral modeling;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/452/2/022054/pdf
DOI  :  10.1088/1757-899X/452/2/022054

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

Aiming at the identification of edible oil quality, this study proposed a multi-spectral data fusion combined with multi-kernel learning support vector machine (SVM) method. This method used serial and wavelet fusion approaches to fuse Raman and near infrared spectral data, and established an identification model for edible-oil types, with the aid of the multi-kernel learning support vector machine (MKL-SVM). The performances of the single spectral model and spectral fusion model were compared, demonstrating that the spectral fusion could effectively improve the prediction accuracy and generalization ability of the model.