Hyperspectral technique combined with deep learning algorithm for detection of compound heavy metals in lettuce

•Vis-NIR HSI was used to detect compound heavy metals content in lettuce leaves.•WT-SCAE is proposed to obtain the deep spectral features.•Deep learning has a great potential for the identification of compound heavy metals content. The aim of this research was to develop a deep learning method which...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Food chemistry Ročník 321; s. 126503
Hlavní autoři: Zhou, Xin, Sun, Jun, Tian, Yan, Lu, Bing, Hang, Yingying, Chen, Quansheng
Médium: Journal Article
Jazyk:angličtina
Vydáno: England Elsevier Ltd 15.08.2020
Témata:
cadmium
Cadmium - analysis
Compound heavy metals
Deep learning
heavy metals
hyperspectral imagery
Lactuca - chemistry
Lactuca sativa
lead
Lead - analysis
Least-Squares Analysis
leaves
Lettuce
Nondestructive testing
Plant Leaves - chemistry
prediction
Stack convolution auto encoder
Support Vector Machine
support vector machines
wavelet
Wavelet Analysis
Wavelet transform
Deep learning
Lettuce
Wavelet transform
Compound heavy metals
Nondestructive testing
Stack convolution auto encoder
ISSN:0308-8146, 1873-7072, 1873-7072
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Vis-NIR HSI was used to detect compound heavy metals content in lettuce leaves.•WT-SCAE is proposed to obtain the deep spectral features.•Deep learning has a great potential for the identification of compound heavy metals content. The aim of this research was to develop a deep learning method which involved wavelet transform (WT) and stack convolution auto encoder (SCAE) for extracting compound heavy metals detection deep features of lettuce leaves. WT was used to decompose the visible-near infrared (400.68–1001.61 nm) hyperspectral image of lettuce sample in the multi-scale transform to acquire the optimal wavelet decomposition layers of cadmium (Cd) and lead (Pb) content prediction, and then using SCAE to perform deep feature learning on spectral data under optimal wavelet decomposition layer. Support vector machine regression (SVR) models established by the deep features obtained by WT-SCAE achieved reasonable performance with coefficient of determination for prediction (Rp2) of 0.9319, root mean square error for prediction (RMSEP) of 0.04988 mg/kg and the relative percent different (RPD) of 3.187 for Cd content, and with Rp2 of 0.9418, RMSEP of 0.04123 mg/kg and RPD of 3.214 for Pb content. The results of this study confirmed the great potential for detecting compound heavy metals by the combination of hyperspectral technique and deep learning algorithm.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0308-8146
1873-7072
1873-7072
DOI:10.1016/j.foodchem.2020.126503