摘要
为解决烟叶分级所需特征多、计算量大、训练模型复杂等问题,基于主成分分析(PCA)、遗传算法(GA)和支持向量机(SVM)提出了一种烟叶分级方法,利用PCA对烟叶特征进行降维以去除交叉冗余信息,将降维后的15个烟叶特征输入SVM,利用GA对SVM模型的惩罚参数C和核函数参数g进行优化;结合烟叶质量分级实际需求对比识别率和运行时间,确定PCbest及其对应的Cbest和gbest,并以PCbest作为降维后的主成分标准。以Cbest和gbest作为SVM模型的参数训练模型,利用训练后模型对测试集样本进行实验,结果表明:与SVM模型和GA-SVM模型相比较,PCA-GA-SVM模型的烟叶识别率和分级效率分别提高24.86%和35.64%。该方法可为提高烟叶分级效率和准确度提供技术支持。
Leaf tobacco grading involves multiple leaf characters and a great number of computation,the training model becomes very complex,a grading method on the basis of principal component analysis (PCA), genetic algorithm (GA)and support vector machine (SVM)was proposed.PCA was used to remove cross redundant information via dimension reduction,the resulted 15 leaf characters were input into SVM.The penalty parameter C and kernel function parameter g in the SVM model were optimized by GA.In combination with the actual demands of leaf tobacco grading,and comparing the identification rate with running time,PC best and corresponding C best and g best,were determined,and PC best was taken as the principal component standard after dimension reduction.C best and g best,were used as the parameter training models of SVM model,and the test set samples were tested by the trained model.The results showed that comparing with SVM model and GA-SVM model,the identification rate and grading efficiency of PCA-GA-SVM model promoted by 24.86% and 35.64%, respectively.This method provides technical supports for promoting leaf tobacco grading efficiency and accuracy.
作者
姚学练
贺福强
平安
罗红
管琪明
YAO Xuelian;HE Fuqiang;PING An;LUO Hong;GUAN Qiming(School of Mechanical Engineering,Guizhou University,Guiyang 550025,China)
出处
《烟草科技》
EI
CAS
CSCD
北大核心
2018年第12期98-105,共8页
Tobacco Science & Technology
基金
贵州省科技重大专项"优质烤烟农机农艺融合研究与示范"(黔科合重大专项字[2014]6015-6号)
贵州省烟草公司科技项目"烟叶等级自动识别技术研究"(中烟黔科[2014]2号)
关键词
烟叶分级
主成分分析法
遗传算法
支持向量机
训练模型
Leaf tobacco grading
Principal component analysis
Genetic algorithm
Support vector machine
Training model
