您好，欢迎访问北京市农林科学院 机构知识库！
北京市农林科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Deep learning-assisted fluorescence spectroscopy for food quality and safety analysis

文献类型： 外文期刊

作者： Yuan, Yuan 1 ; Ji, Zengtao 2 ; Fan, Yanwei 2 ; Xu, Qian 1 ; Shi, Ce 2 ; Lyu, Jian 6 ; Ertbjerg, Per 6 ;

作者机构： 1.Tarim Univ, Coll Food Sci & Engn, Alar 843301, Peoples R China

2.Beijing Acad Agr & Forestry Sci, Informat Technol Res Ctr, Beijing 100097, Peoples R China

3.Minist Agr & Rural Affairs, Key Lab Cold Chain Logist Technol Agroprod, Beijing 100097, Peoples R China

4.Beijing Acad Agr & Forestry Sci, Natl Engn Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China

5.Key Lab Special Agr Prod Further Proc Southern Xin, Prod & Construction Grp, Alar 843301, Peoples R China

6.Univ Helsinki, Dept Food & Nutr, Helsinki 00014, Finland

关键词： Fluorescence spectroscopy; Limitations of machine learning; Classification and regression; Model optimization; Model performance evaluation; Application

期刊名称：TRENDS IN FOOD SCIENCE & TECHNOLOGY （ 影响因子：15.4； 五年影响因子：18.4 ）

ISSN： 0924-2244

年卷期： 2025 年 156 卷

页码：

收录情况： SCI

摘要： Background: Fluorescence spectroscopy has been widely employed in the quality assessment of food and agricultural products due to its rapid and accurate measurement characteristics. The large amount of fluorescence data or images generated by fluorescence spectroscopy requires more efficient chemometric methods to process and analyze them. However, conventional machine learning models struggle to achieve high-precision predictions when analyzing high-dimensional fluorescence data samples. Deep learning algorithms exhibit powerful automatic learning capabilities in feature extraction and regression modeling of fluorescence spectra. Scope and approach: The complex, abstract and high-dimensional features of fluorescence spectroscopy are firstly demonstrated through the characterization of fluorescent substances in food products. Secondly, this paper highlights various challenges confronting the fluorescence spectrum analysis process and summarizes several deep learning algorithms that can address these solutions, including the convolutional neural network (CNN), long and short-term memory network (LSTM), and auto encoder (AE). Additionally, the application of deep learning models based on fluorescent data in food detection is reviewed in this article according to different testing objectives, including food safety inspections, food quality assessment, adulteration identification, and variety identification. The review also focuses on the future development trend of this technique in food quality and safety detection.
Key findings and conclusions: Deep learning approaches combined with fluorescence spectroscopy exhibits immense potential in food quality detection and food discrimination classification. The selections of representative input parameters, suitable preprocessing methods and optimization methods can effectively tackle the problems of lack of samples and model over-fitting. Owing to the rapid advancement of artificial intelligence, the deep learning-based fluorescence spectroscopy technology is poised to evolve towards high precision, high throughput, automation and cost-effectiveness.

  • 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：北京市农林科学院

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