Study of the similarity and recognition between volatiles of brown rice plant hoppers and rice stem based on the electronic nose

文献类型： 外文期刊

第一作者： Xu, Sai

作者： Xu, Sai;Zhou, Zhiyan;Tian, Luhong;Lu, Huazhong;Luo, Xiwen;Lan, Yubin;Xu, Sai;Zhou, Zhiyan;Tian, Luhong;Lu, Huazhong;Luo, Xiwen;Lan, Yubin;Zhou, Zhiyan;Tian, Luhong;Luo, Xiwen;Lan, Yubin;Xu, Sai;Lu, Huazhong

作者机构：

关键词： Rice plant; Brown rice plan hopper; Similarity; Recognition; Electronic nose

期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：5.565； 五年影响因子：5.494 ）

ISSN： 0168-1699

年卷期： 2018 年 152 卷

页码：

收录情况： SCI

摘要： The volatiles of Brown rice plant hopper (BRPH) itself is an important evidence for BRPH electronic nose detection. However, during infestation, BRPH always sucks the juice from the rice stem, therefore, a study on the similarity between BRPH's volatiles and undamaged rice stem volatiles might help determine whether the volatile contents of BRPH would be influenced by the sucking of the rice stem juice. If so, recognizing BRPH from rice stem should be a crucial step to reduce the misjudgment of BRPH occurrence prediction by using electronic nose, which has not been reported until now. This paper used an electronic nose (PEN3) sample of the volatile of U3IN (under the 3th-instar nymphs), O3IN (over the 3th-instar nymphs) and healthy rice stem. Hierarchical clustering analysis (HCA), Loading analysis (Loadings), principal component analysis (PCA), k-nearest neighbor (KNN), probabilistic neural network (PNN), and support vector machine (SVM) were used for data analysis. HCA, Loadings, and PCA results proved that certain similarities exist between volatiles of rice stem and BRPH, Loadings and PCA results also indicated the volatile similarity between O31N and rice stem is stronger than the volatile similarity between U3IN and rice stem. To reduce the redundant information and improve computation efficiency, according to Loadings and PCA results, sensor R5 of electronic nose has been be removed, then, the fist four principle components has been kept as the feature values. KNN, PNN and SVM all can recognize rice stem, O3IN, and U3IN effectively, however, KNN and PNN are more fit to solve the problem of rice stem and BRHP recognition than SVM. This experiment results proved that certain similarities exist between volatiles of rice stem and BRPH, also figured out the feasible way to recognize rice stem and BRPH, which could provide a reference for further research of BRPH prediction.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序