Quantitative analysis of blended corn-olive oil based on Raman spectroscopy and one-dimensional convolutional neural network

Wu, Xijun; Gao, Shibo; Niu, Yudong; Zhao, Zhijun; Ma, Renqi; Xu, Baoran; Liu, Hailong; Zhang, Yungang

doi:10.1016/j.foodchem.2022.132655

Cited by 31 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, deep learning based models have been widely used in the field of adulteration. − Although high accuracy is always demonstrated, − the underneath mechanism is still unknown. Here, taking the identification of individual vegetable oil and the mixture as an example, the visualization by 1D Grad-CAM clearly displayed why ResNet performed so well.…”

Section: Resultsmentioning

confidence: 99%

1D Gradient-Weighted Class Activation Mapping, Visualizing Decision Process of Convolutional Neural Network-Based Models in Spectroscopy Analysis

Shi

Luo

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

Being characterized by the self-adaption and high accuracy, the deep learning-based models have been widely applied in the 1D spectroscopy-related field. However, the “black-box” operation and “end-to-end” working style of the deep learning normally bring the low interpretability, where a reliable visualization is highly demanded. Although there are some well-developed visualization methods, such as Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM), for the 2D image data, they cannot correctly reflect the weights of the model when being applied to the 1D spectral data, where the importance of position information is not considered. Here, aiming at the visualization of Convolutional Neural Network-based models toward the qualitative and quantitative analysis of 1D spectroscopy, we developed a novel visualization algorithm (1D Grad-CAM) to more accurately display the decision-making process of the CNN-based models. Different from the classical Grad-CAM, with the removal of the gradient averaging (GAP) and the ReLU operations, a significantly improved correlation between the gradient and the spectral location and a more comprehensive spectral feature capture were realized for 1D Grad-CAM. Furthermore, the introduction of difference (purity or linearity) and feature contribute in the CNN output in 1D Grad-CAM achieved a reliable evaluation of the qualitative accuracy and quantitative precision of CNN-based models. Facing the qualitative and adulteration quantitative analysis of vegetable oils by the combination of Raman spectroscopy and ResNet, the visualization by 1D Grad-CAM well reflected the origin of the high accuracy and precision brought by ResNet. In general, 1D Grad-CAM provides a clear vision about the judgment criterion of CNN and paves the way for CNN to a broad application in the field of 1D spectroscopy.

show abstract

Section: Resultsmentioning

confidence: 99%

1D Gradient-Weighted Class Activation Mapping, Visualizing Decision Process of Convolutional Neural Network-Based Models in Spectroscopy Analysis

Shi

Luo

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

show abstract

“…(2022) applied CNNR and Raman spectroscopy to identify the amount of olive oil in a corn-olive oil blend, with R 2 P = 0.9908 and RMSEP = 0.7183. In addition, one-dimension deep learning regression models based on spectral data are performed well in soluble solid content estimation in cherry tomato ( Xiang et al., 2022 ) and oil content prediction of single maize kernel ( Zhang et al., 2022c ). Hence, the spectral analysis model developed by CNN can be expected to provide a simple, rapid, and accurate analysis of LNC in cotton leaves.…”

Section: Discussionmentioning

confidence: 99%

Visible and near-infrared spectroscopy and deep learning application for the qualitative and quantitative investigation of nitrogen status in cotton leaves

Xiao

Tang

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Leaf nitrogen concentration (LNC) is a critical indicator of crop nutrient status. In this study, the feasibility of using visible and near-infrared spectroscopy combined with deep learning to estimate LNC in cotton leaves was explored. The samples were collected from cotton’s whole growth cycle, and the spectra were from different measurement environments. The random frog (RF), weighted partial least squares regression (WPLS), and saliency map were used for characteristic wavelength selection. Qualitative models (partial least squares discriminant analysis (PLS-DA), support vector machine for classification (SVC), convolutional neural network classification (CNNC) and quantitative models (partial least squares regression (PLSR), support vector machine for regression (SVR), convolutional neural network regression (CNNR)) were established based on the full spectra and characteristic wavelengths. Satisfactory results were obtained by models based on CNN. The classification accuracy of leaves in three different LNC ranges was up to 83.34%, and the root mean square error of prediction (RMSEP) of quantitative prediction models of cotton leaves was as low as 3.36. In addition, the identification of cotton leaves based on the predicted LNC also achieved good results. These results indicated that the nitrogen content of cotton leaves could be effectively detected by deep learning and visible and near-infrared spectroscopy, which has great potential for real-world application.

show abstract

“…For example, Wu, X. J., et al established a 1D-CNN quantitative identification model based on Raman spectra for olive oil. 29 The results showed that the RMSEP of the CNN model was increased from 0.4594 to 0.7183 compared to the PLS model, which demonstrates the lower prediction accuracy of the CNN model. In this paper's case, the scale of training and test dataset is over 200 000.…”

Section: Introductionmentioning

confidence: 93%

A method based on a one-dimensional convolutional neural network for UV-vis spectrometric quantification of nitrate and COD in water under random turbidity disturbance scenario

et al. 2023

View full text Add to dashboard Cite

show abstract

Quantitative analysis of blended corn-olive oil based on Raman spectroscopy and one-dimensional convolutional neural network

Cited by 31 publications

References 20 publications

1D Gradient-Weighted Class Activation Mapping, Visualizing Decision Process of Convolutional Neural Network-Based Models in Spectroscopy Analysis

1D Gradient-Weighted Class Activation Mapping, Visualizing Decision Process of Convolutional Neural Network-Based Models in Spectroscopy Analysis

Visible and near-infrared spectroscopy and deep learning application for the qualitative and quantitative investigation of nitrogen status in cotton leaves

A method based on a one-dimensional convolutional neural network for UV-vis spectrometric quantification of nitrate and COD in water under random turbidity disturbance scenario

Contact Info

Product

Resources

About