摘要
本文基于电子鼻~([1])数据应用支持向量机算法~([2])建立猪肉菌落总数的快速定量预报模型。建模、留一法和独立测试结果的相关系数分别为0.94、0.88和0.89。可以看出:电子鼻结合支持向量机可以简单、快速的预测猪肉的细菌数量。
The aim of this paper was to predict the bacteria number in pork by using support vector machine(SVM) based on Electronic Nose(EN).The correlation coefficients of training set,LOOCV and test set were 0.94,0.88 and 0.89 respectively.It can be understood that the SVM combined with electronic nose system can become a simple and rapid technique for the prediction of the bacteria number in pork.
引文
[1]Dutta,R.,D.Morgan,et al.Sensors and Actuators B:Chemical.2005,109(2):355-362
[2]Wencong Lu,Xiaobo Ji,Minjie Li,Liang Liu.Advances in Manufacturing.2013,1(2):151-159