您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

A self-built electronic nose system for monitoring damage caused by different rice planthopper species

文献类型： 外文期刊

作者： Li, Tingting 1 ; Luo, Ju 1 ; Wang, Aiying 1 ; Yang, Baojun 1 ; Wang, Cilin 1 ; Liu, Shuhua 1 ; Yang, Guiying 1 ;

作者机构： 1.China Natl Rice Res Inst, State Key Lab Rice Biol & Breeding, Hangzhou 311400, Peoples R China

关键词： Rice planthoppers; Volatile organic compounds; Electronic nose; MOS sensor array; Two-stage feature selection

期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：8.9； 五年影响因子：9.3 ）

ISSN： 0168-1699

年卷期： 2025 年 236 卷

页码：

收录情况： SCI

摘要： Rice is one of the world's major food crops, and rice planthoppers are among the most important migratory pests affecting rice production. Timely and accurate monitoring rice planthoppers, especially different species, is crucial for the precise application of pesticides and delaying the development of pesticide resistance. In this study, we investigated specific volatile organic compounds (VOCs) induced by different rice planthopper species using Gas Chromatography-Mass Spectrometry (GC-MS). Based on VOC analysis, we designed a Metal-Oxide Semiconductor (MOS) sensor array and developed a novel electronic nose (E-nose) system. A two-stage feature selection process was applied, followed by multi-model evaluation to enhance classification accuracy. Results indicated that a total of 105 VOCs were identified, including 46 key VOCs categorized into eight distinct groups based on their chemical characteristics. An array of eight MOS sensors was selected based on these eight VOC groups. The feature selection process, incorporating Boruta followed by Support Vector Machine-Recursive Feature Elimination (SVM-RFE), successfully identified 17 key features. Finally, multi-model evaluation optimized with Bayesian techniques revealed that the Support Vector Machine (SVM) model outperformed the other models, achieving an accuracy of 95.45%. This research provides a novel approach for pest detection in rice, integrating VOC-based detection with a high-performance E-nose system. The findings contribute to the early monitoring of different rice planthoppers, the development of rice planthopper management strategies, and enhancing sustainable rice production practices.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台