基于SVM和GA-SVM的NIR光谱柑橘产地鉴别模型研究

A Study on Identification Model of NIR Spectroscopy Oranges Origin Place Based on SVM and GA-SVM

为了建立更准确、高效的柑橘产地鉴别模型,提出了基于支持向量机(Support Vector Machine,SVM)的遗传算法(Genetic Algorithm,GA)SVM(GA-SVM)。该算法结合基因优化选择,对SVM算法进行了改进,实验结果显示,采用GA-SVM对16个地区柑橘样本开展NIR的产地鉴别,能得到比SVM更高的识别率。

In order to establish a more accurate and efficient identification model of oranges origin place,a Genetic Algorithm(GA)SVM(GA-SVM)based on Support Vector Machine(SVM)was proposed.This algorithm improves the SVM algorithm by combining gene optimization selection.The experimental results show that a higher recognition rate than SVM is obtained in identifying origin places of oranges samples NIR from 16 different regions by adopting GA-SVM.