检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:王承伟[1,2] 宾俊[1,2] 范伟[1,2] 谭观萍 周冀衡[1,2]
机构地区:[1]湖南农业大学生物科学技术学院,湖南长沙410128 [2]湖南农业大学烟草研究院,湖南长沙410128
出 处:《西南农业学报》2017年第4期931-936,共6页Southwest China Journal of Agricultural Sciences
基 金:湖南省研究生科研创新项目"烟草烘烤过程近红外光谱在线无损监测及变化规律的研究"(CX2015B237)
摘 要:【目的】成熟度是烟叶品质的中心因素,田间成熟是获得优质烟叶的前提和基础,如何准确判断烟叶成熟程度是一个难题。【方法】本文利用近红外光谱技术结合化学计量学方法对不同成熟度的新鲜烟叶进行了探讨。【结果】随机森林(RF)分类模型参数优化简单、泛化能力强、预测结果较好,能有效识别不同成熟程度的烟叶样本,实现烟叶成熟度的快速判别,上、中和下部烟叶不同成熟度模型预测集的分类正确率分别为0.9231、0.90和0.9091,预测正确率优于主成分分析(PCA)、K最近邻(KNN)和支撑向量机(SVM)等方法。【结论】因此,近红外光谱技术结合随机森林方法简单、快速、准确,可为客观辨别烟叶成熟度的等级、优劣等问题提供了一种新的、便捷的辅助手段。[ Objective ] Maturity is the center of the tobacco leaf quality factors, and the maturity in field is the promise and foundation to obtain high quality tobacco leaf, but how to accurately determine tobacco maturity is a difficult problem. [ Method ] A new method by using near infrared spectroscopy combined with chemometrics for classifying different maturity of fresh tobacco leaves was proposed in this paper. [ Resuit] Compared with principal component analysis( PCA), K nearest neighbor (KNN) and support vector machine (SVM) qualitative models, the random forest models for maturity had the advantages of automatic parameter optimization, better performance, stronger generalization ability and better accurate prediction results, by which the maturity classification of upper, middle and low leaves achieved the accuracy of 0. 9231,0.90 and 0. 9091, respectively. [ Conclusion] Near infrared technology in combination with random forests could thus accurately identify tobacco maturity level, which would provide the new and convenient means of auxiliary.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.229