您好,欢迎访问北京市农林科学院 机构知识库!

Rapid identification of the geographical origins of crops using laser-induced breakdown spectroscopy combined with transfer learning

文献类型: 外文期刊

作者: Lin, Peng 1 ; Wen, Xuelin 2 ; Ma, Shixiang 2 ; Liu, Xinchao 1 ; Xiao, Renhang 1 ; Gu, Yifan 1 ; Chen, Guanghai 1 ; Han, Yuxing 3 ; Dong, Daming 2 ;

作者机构: 1.South China Agr Univ, Coll Artificial Intelligence, Coll Elect Engn, 486 Wushan Rd, Guangzhou 510642, Peoples R China

2.Minist Agr & Rural Affairs, Key Lab Agr Sensors, Beijing 100097, Peoples R China

3.Tsinghua Univ, Shenzhen Int Grad Sch, RIOS Lab, Shenzhen 518055, Peoples R China

4.Huazhong Univ Sci & Technol, Wuhan Natl Lab Optoelect WNLO, Wuhan 430074, Hubei, Peoples R China

5.Beijing Acad Agr & Forestry Sci, Res Ctr Intelligent Equipment, Beijing 100097, Peoples R China

关键词: Laser-induced breakdown spectroscopy; Transfer learning; Origins classification; Crops

期刊名称:SPECTROCHIMICA ACTA PART B-ATOMIC SPECTROSCOPY ( 影响因子:3.3; 五年影响因子:3.1 )

ISSN: 0584-8547

年卷期: 2023 年 206 卷

页码:

收录情况: SCI

摘要: Identification of the geographical origins of crops using deep learning-assisted laser-induced breakdown spectroscopy (LIBS) can quickly realize food traceability and guarantee the interests of consumers. However, this technique is not suitable for practical application when the number of training samples is limited and has poor transferability. In this study, a transfer learning-assisted LIBS method was developed to identify the geographical origins of crops, which achieved a maximum accuracy of 93.81% among six different transfer combinations. To further improve the identification accuracy, Deep Adaptation Networks (DAN) was applied for the first time and demonstrated improved performance on five cases. Finally, feature visualization confirmed that the LIBS information could be transferred to other crops. Our results show that transfer learning-assisted LIBS can enhance crop traceability in cases with limited numbers of samples. The study provided new idea to identify geographical origin under sample-limited conditions.

  • 相关文献
作者其他论文 更多>>