Nondestructive detection of cadmium content in oilseed rape leaves under different silicon environments using deep transfer learning and Vis-NIR hyperspectral imaging

In this paper, a transfer stack denoising autoencoder (T-SDAE) algorithm is proposed to implement the migration of cadmium (Cd) prediction depth characteristic model of oilseed rape leaves in different silicon environments. Stacked denoising autoencoder (SDAE) algorithm was used to reduce dimensiona...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Food chemistry Ročník 479; s. 143799
Hlavní autori: Zhou, Xin, Liu, Yang, Zhao, Chunjiang, Sun, Jun, Shi, Lei, Cong, Sunli
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: England Elsevier Ltd 01.07.2025
Predmet:
Algorithms
Brassica napus
Brassica napus - chemistry
cadmium
Cadmium - analysis
Cadmium；hyperspectral imaging
Deep Learning
food chemistry
Hyperspectral Imaging - methods
Plant Leaves - chemistry
prediction
silicon
Silicon - analysis
Silicon environment
Spectroscopy, Near-Infrared - methods
Stacked denoising autoencoder
Transfer learning
Deep learning
Silicon environment
Stacked denoising autoencoder
Transfer learning
Cadmium；hyperspectral imaging
ISSN:0308-8146, 1873-7072, 1873-7072
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this paper, a transfer stack denoising autoencoder (T-SDAE) algorithm is proposed to implement the migration of cadmium (Cd) prediction depth characteristic model of oilseed rape leaves in different silicon environments. Stacked denoising autoencoder (SDAE) algorithm was used to reduce dimensionality, and the most effective SDAE deep learning network was transferred to create the T-SDAE model. The results showed that SVR model using SDAE to extract depth features had the best prediction effect on Cd content in silicon-free, low-silicon and higher-silicon environments. Moreover, the coefficient of determination of prediction set (Rp2) were 0.9127, 0.9829 and 0.9606, respectively. Specifically, the Rp2 value of the T-SDAE-SVR optimal prediction set under different silicon environments is 0.9273, RMSEP is 0.01465 mg/kg, and RPD is 3.237. By integrating hyperspectral imaging technology with a deep transfer learning algorithm, accurate detection of various Cd contents in oilseed rape leaves is feasible under different silicon environments. [Display omitted] •HSI used to detect Cd content in oilseed rape leaves in different silicon environments.•T-SDAE model proposed for deep learning model transfer.•Both low and higher silicon concentrations reduce crop heavy metal absorption.•DTL method effectively predicts Cd content in different silicon environments.
Bibliografia: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.2025.143799