Rapid on-site identification of pesticide residues in tea by one-dimensional convolutional neural network coupled with surface-enhanced Raman scattering

Zhu, Junbo; Sharma, Arumugam Selva; Xu, Jing; Xu, Yanhua; Jiao, Tianhui; Ouyang, Qin; Li, Huanhuan; Chen, Quansheng

doi:10.1016/j.saa.2020.118994

Cited by 82 publications

(52 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Areas for improvement may include: 1) enhancing the specificity of the Au substrate, which will ultimately help to reduce matrix effects, the detection of non-targeted compounds and interactions between those analytes which cannot bind as strongly to the substrate; 2) reduce spectral overlapping and interference between multiple residues in a sample, through the use of artificial intelligence (AI) and/or machine learning algorithms e.g. self-modelling mixture analysis (SMA) 47 or convolutional neural networks (CNN) 48 . These will be important steps forward to improve the rapid on-site analysis of multiple contaminants within food and environmental samples.…”

Section: Resultsmentioning

confidence: 99%

Handheld SERS coupled with QuEChERs for the sensitive analysis of multiple pesticides in basmati rice

et al. 2022

View full text Add to dashboard Cite

Pesticides are a safety issue globally and cause serious concerns for the environment, wildlife and human health. The handheld detection of four pesticide residues widely used in Basmati rice production using surface-enhanced Raman spectroscopy (SERS) is reported. Different SERS substrates were synthesised and their plasmonic and Raman scattering properties evaluated. Using this approach, detection limits for pesticide residues were achieved within the range of 5 ppb-75 ppb, in solvent. Various extraction techniques were assessed to recover pesticide residues from spiked Basmati rice. Quick, Easy, Cheap, Effective, Rugged and Safe (QuEChERs) acetate extraction was applied and characteristic spectral data for each pesticide was obtained from the spiked matrix and analysed using handheld-SERS. This approach allowed detection limits within the matrix conditions to be markedly improved, due to the rapid aggregation of nanogold caused by the extraction medium. Thus, detection limits for three out of four pesticides were detectable below the Maximum Residue Limits (MRLs) of 10 ppb in Basmati rice. Furthermore, the multiplexing performance of handheld-SERS was assessed in solvent and matrix conditions. This study highlights the great potential of handheld-SERS for the rapid on-site detection of pesticide residues in rice and other commodities.

show abstract

Section: Resultsmentioning

confidence: 99%

Handheld SERS coupled with QuEChERs for the sensitive analysis of multiple pesticides in basmati rice

et al. 2022

View full text Add to dashboard Cite

show abstract

“…However, by combining SERS with the deep learning method one‐dimensional convolutional neural network (1D CNN), a new analytical method for identifying pesticide residues in tea has been proposed. [ 71 ]…”

Section: Applicationmentioning

confidence: 99%

A review of artificial intelligence methods combined with Raman spectroscopy to identify the composition of substances

Pan

Zhang

Daengngam

et al. 2021

J Raman Spectroscopy

View full text Add to dashboard Cite

In general, most of the substances in nature exist in mixtures, and the noninvasive identification of mixture composition with high speed and accuracy remains a difficult task. However, the development of Raman spectroscopy, machine learning, and deep learning techniques has paved the way for achieving efficient analytical tools capable of identifying mixture components, thus leading to an apparent breakthrough in the identification of mixtures beyond traditional chemical analysis methods. This review summarizes the work of Raman spectroscopy in identifying the composition of substances; reviews the preprocessing process of Raman spectroscopy, artificial intelligence analysis methods, and analysis procedures; and examines the application of artificial intelligence. Finally, the advantages and disadvantages and development prospects of Raman spectroscopy are discussed in detail.

show abstract

“…As a result, DNN can make predictions based on the obtained features and labels. Traditional algorithms can effectively classify Raman spectroscopy with small sample sizes, while DNN seems to be more reliable in big data or complex samples [182].…”

Section: Spectral Acquisition and Processingmentioning

confidence: 99%

Rapid field trace detection of pesticide residue in food based on surface-enhanced Raman spectroscopy

Liang

Wen-wen

et al. 2021

Microchim Acta

View full text Add to dashboard Cite

Surface-enhanced Raman spectroscopy is an alternative detection tool for monitoring food security. However, there is still a lack of a conclusion of SERS detection with respect to pesticides and real sample analysis, and the summary of intelligent algorithms in SERS is also a blank. In this review, a comprehensive report of pesticides detection using SERS technology is given. The SERS detection characteristics of different types of pesticides and the influence of substrate on inspection are discussed and compared by the typical ways of classification. The key points, including the progress in real sample analysis and Raman data processing methods with intelligent algorithm, are highlighted. Lastly, major challenges and future research trends of SERS analysis of pesticide residue are also addressed. SERS has been proven to be a powerful technique for rapid test of residue pesticides in complex food matrices, but there still is a tremendous development space for future research.

show abstract

Rapid on-site identification of pesticide residues in tea by one-dimensional convolutional neural network coupled with surface-enhanced Raman scattering

Cited by 82 publications

References 41 publications

Handheld SERS coupled with QuEChERs for the sensitive analysis of multiple pesticides in basmati rice

Handheld SERS coupled with QuEChERs for the sensitive analysis of multiple pesticides in basmati rice

A review of artificial intelligence methods combined with Raman spectroscopy to identify the composition of substances

Rapid field trace detection of pesticide residue in food based on surface-enhanced Raman spectroscopy

Contact Info

Product

Resources

About