Deep learning networks for the recognition and quantitation of surface-enhanced Raman spectroscopy

doi:10.1039/d0an00492h

	Deep learning networks for the recognition and quantitation of surface-enhanced Raman spectroscopy
	Weng, Shizhuang 1; Yuan, Hecai 1; Zhang, Xueyan 1; Li, Pan 2; Zheng, Ling 1; Zhao, Jinling 1; Huang, Linsheng 1
刊名	ANALYST
	2020-07-21
卷号	145
ISSN号	0003-2654
DOI	10.1039/d0an00492h
通讯作者	Weng, Shizhuang(weng_1989@126.com) ; Zheng, Ling()
英文摘要	Surface-enhanced Raman spectroscopy (SERS) based on machine learning methods has been applied in material analysis, biological detection, food safety, and intelligent analysis. However, machine learning methods generally require extra preprocessing or feature engineering, and handling large-scale data using these methods is challenging. In this study, deep learning networks were used as fully connected networks, convolutional neural networks (CNN), fully convolutional networks (FCN), and principal component analysis networks (PCANet) to determine their abilities to recognise drugs in human urine and measure pirimiphos-methyl in wheat extract in the two input forms of a one-dimensional vector or a two-dimensional matrix. The best recognition result for drugs in urine with an accuracy of 98.05% in the prediction set was obtained using CNN with spectra as input in the matrix form. The optimal quantitation for pirimiphos-methyl was obtained using FCN with spectra in the matrix form, and the analysis was accomplished with a determination coefficient of 0.9997 and a root mean square error of 0.1574 in the prediction set. These networks performed better than the common machine learning methods. Overall, the deep learning networks provide feasible alternatives for the recognition and quantitation of SERS.
资助项目	National Natural Science Foundation of China[3170123] ; National Natural Science Foundation of China[31971789] ; National Key Research and Development Program[2016YFD0800904] ; Open Foundation of Laboratory of Quality and Safety Risk Assessment on Agricultural Products (Beijing), Ministry of Agriculture[KFRA201802]
WOS关键词	BASE-LINE ; REGRESSION ; SCATTERING ; SPECTRA
WOS研究方向	Chemistry
语种	英语
出版者	ROYAL SOC CHEMISTRY
WOS记录号	WOS:000548664800009
资助机构	National Natural Science Foundation of China ; National Key Research and Development Program ; Open Foundation of Laboratory of Quality and Safety Risk Assessment on Agricultural Products (Beijing), Ministry of Agriculture
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/102957]
专题	中国科学院合肥物质科学研究院
通讯作者	Weng, Shizhuang; Zheng, Ling
作者单位	1.Anhui Univ, Natl Engn Res Ctr Agroecol Big Data Anal & Applic, Hefei 230601, Peoples R China 2.Chinese Acad Sci, Hefei Inst Phys Sci, Ctr Med Phys & Technol, Hefei 230021, Peoples R China
推荐引用方式 GB/T 7714	Weng, Shizhuang,Yuan, Hecai,Zhang, Xueyan,et al. Deep learning networks for the recognition and quantitation of surface-enhanced Raman spectroscopy[J]. ANALYST,2020,145.
APA	Weng, Shizhuang.,Yuan, Hecai.,Zhang, Xueyan.,Li, Pan.,Zheng, Ling.,...&Huang, Linsheng.(2020).Deep learning networks for the recognition and quantitation of surface-enhanced Raman spectroscopy.ANALYST,145.
MLA	Weng, Shizhuang,et al."Deep learning networks for the recognition and quantitation of surface-enhanced Raman spectroscopy".ANALYST 145(2020).