Rapid identification of fish species by laser-induced breakdown spectroscopy and Raman spectroscopy coupled with machine learning methods

doi:10.1016/j.foodchem.2022.134043

CORC > 海洋研究所 > 中国科学院海洋研究所 > 海洋地质与环境重点实验室

	Rapid identification of fish species by laser-induced breakdown spectroscopy and Raman spectroscopy coupled with machine learning methods
	Ren, Lihui 2,4; Tian, Ye 4; Yang, Xiaoying 4; Wang, Qi 2,4; Wang, Leshan 4; Geng, Xin 4; Wang, Kaiqiang 3; Du, Zengfeng 1; Li, Ying 4; Lin, Hong 3
刊名	FOOD CHEMISTRY
	2023-01-30
卷号	400 页码:9
关键词	Fish species identification laser -induced breakdown spectroscopy (LIBS) Raman spectroscopy Machine learning convolutional neural network (CNN) Data fusion
ISSN号	0308-8146
DOI	10.1016/j.foodchem.2022.134043
通讯作者	Tian, Ye(ytian@ouc.edu.cn)
英文摘要	There has been an increasing demand for the rapid verification of fish authenticity and the detection of adul-teration. In this work, we combined LIBS and Raman spectroscopy for the fish species identification for the first time. Two machine learning methods of SVM and CNN are used to establish the classification models based on the LIBS and Raman data obtained from 13 types of fish species. Data fusion strategies including low-level, mid-level and high-level fusions are used for the combination of LIBS and Raman data. It shows that all these data fusion strategies offer a significant improvement in fish classification compared with the individual LIBS or Raman data, and the CNN model works more powerfully than the SVM model. The low-level fusion CNN model provides a best classification accuracy of 98.2%, while the mid-level fusion involved with feature selection improves the computing efficiency and gains the interpretability of CNN.
资助项目	National Key Research and Devel- opment Program of China[2019YFD0901701]
WOS研究方向	Chemistry ; Food Science & Technology ; Nutrition & Dietetics
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000858940600001
内容类型	期刊论文
源URL	[http://ir.qdio.ac.cn/handle/337002/180783]
专题	海洋研究所_海洋地质与环境重点实验室
通讯作者	Tian, Ye
作者单位	1.Chinese Acad Sci, Key Lab Marine Geol & Environm, Qingdao 266071, Peoples R China 2.Chinese Acad Sci, Qingdao Inst BioEnergy & Bioproc Technol, Single Cell Ctr, Qingdao 266101, Peoples R China 3.Ocean Univ China, Food Safety Lab, Qingdao 266003, Peoples R China 4.Ocean Univ China, Coll Phys & Optoelect Engn, Qingdao 266100, Peoples R China
推荐引用方式 GB/T 7714	Ren, Lihui,Tian, Ye,Yang, Xiaoying,et al. Rapid identification of fish species by laser-induced breakdown spectroscopy and Raman spectroscopy coupled with machine learning methods[J]. FOOD CHEMISTRY,2023,400:9.
APA	Ren, Lihui.,Tian, Ye.,Yang, Xiaoying.,Wang, Qi.,Wang, Leshan.,...&Lin, Hong.(2023).Rapid identification of fish species by laser-induced breakdown spectroscopy and Raman spectroscopy coupled with machine learning methods.FOOD CHEMISTRY,400,9.
MLA	Ren, Lihui,et al."Rapid identification of fish species by laser-induced breakdown spectroscopy and Raman spectroscopy coupled with machine learning methods".FOOD CHEMISTRY 400(2023):9.