Rapid diagnosis of rice bacterial diseases is critical for early warning and precise management during their initial phases.The use of rapid nucleic acid detection on paper-based platforms is an innovative technique t...Rapid diagnosis of rice bacterial diseases is critical for early warning and precise management during their initial phases.The use of rapid nucleic acid detection on paper-based platforms is an innovative technique that offers simplicity,portability,and affordability.However,the temperature dependence of the amplification process and variations in paper device technologies hinder on-site detection of pathogens using paper-based platforms.展开更多
为更合理有效实现鸡蛋品种分类,研究一种介电特性无损鉴别鸡蛋品种方法。本实验以4组不同品种鸡蛋(江苏镇江洋鸡蛋、江苏镇江草鸡蛋、安徽老南沟草鸡蛋、江苏东台草鸡蛋)为研究对象,采用平行极板法测量4组鸡蛋在10~200 k Hz条件下的介...为更合理有效实现鸡蛋品种分类,研究一种介电特性无损鉴别鸡蛋品种方法。本实验以4组不同品种鸡蛋(江苏镇江洋鸡蛋、江苏镇江草鸡蛋、安徽老南沟草鸡蛋、江苏东台草鸡蛋)为研究对象,采用平行极板法测量4组鸡蛋在10~200 k Hz条件下的介电特性参数,并利用支持向量机(support vector machine,SVM)算法建立鸡蛋品种鉴别分类检测模型。研究不同核函数(线性核函数、多项式核函数、RBF核函数和Sigmoid核函数)、不同参数寻优算法(网格搜索法、遗传算法和粒子群算法)选择对分类模型准确率的影响。结果表明,以线性核函数为SVM核函数、粒子群算法为SVM参数寻优算法时,建立的鸡蛋品种SVM分类模型的性能最优,其训练集正确率为95.83%,测试集正确率为95.83%。利用介电特性无损检测技术结合SVM算法,取得了很好的分类效果,为鸡蛋品种鉴别提供了一种新的快速有效的方法。展开更多
基金supported by the National Natural Science Foundation of China(Grant No.32171895)National Key Research and Development Program for Young Scientists,China(Grant No.2022YFD2000200)Jiangsu Province Key Reserch and Development Program Project,China(Grant No.BE2022052-2).
文摘Rapid diagnosis of rice bacterial diseases is critical for early warning and precise management during their initial phases.The use of rapid nucleic acid detection on paper-based platforms is an innovative technique that offers simplicity,portability,and affordability.However,the temperature dependence of the amplification process and variations in paper device technologies hinder on-site detection of pathogens using paper-based platforms.
文摘为更合理有效实现鸡蛋品种分类,研究一种介电特性无损鉴别鸡蛋品种方法。本实验以4组不同品种鸡蛋(江苏镇江洋鸡蛋、江苏镇江草鸡蛋、安徽老南沟草鸡蛋、江苏东台草鸡蛋)为研究对象,采用平行极板法测量4组鸡蛋在10~200 k Hz条件下的介电特性参数,并利用支持向量机(support vector machine,SVM)算法建立鸡蛋品种鉴别分类检测模型。研究不同核函数(线性核函数、多项式核函数、RBF核函数和Sigmoid核函数)、不同参数寻优算法(网格搜索法、遗传算法和粒子群算法)选择对分类模型准确率的影响。结果表明,以线性核函数为SVM核函数、粒子群算法为SVM参数寻优算法时,建立的鸡蛋品种SVM分类模型的性能最优,其训练集正确率为95.83%,测试集正确率为95.83%。利用介电特性无损检测技术结合SVM算法,取得了很好的分类效果,为鸡蛋品种鉴别提供了一种新的快速有效的方法。
