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

Quantitative determination of acid value in palm oil during thermal oxidation using Raman spectroscopy combined with deep learning models

Accurate monitoring of acid value (AV) is critical for edible oil quality control, yet traditional chemometric methods often face limitations in handling complex spectral data. This study combines Raman spectroscopy with deep learning, including Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Transformer, to explore their potential in improving the accuracy and efficiency of AV quantification during the thermal oxidation of palm oil. The results showed that all three deep learning models outperformed traditional chemometric methods in predictive accuracy. The CNN-LSTM model achieved the best performance, with a predicted coefficient of determination (Rp2) of 0.9978, a mean square error of prediction (RMSEP) of 0.0015, and a residual predictive deviation (RPD) of 21.21. This method demonstrates the effectiveness of Raman spectroscopy-driven deep learning for precise AV monitoring and holds promise for further validation with more diverse indicator datasets, providing a novel technical reference for edible oil quality control.

Detection of camellia oil adulteration based on near-infrared spectroscopy and smartphone combined with deep learning and multimodal fusion

Camellia oil (CO) is known for its nutritional value and health benefits, but its high price makes it susceptible to adulteration. This study developed a binary adulteration system for CO in response to the adulteration of rapeseed oil (RO) into CO that been observed in the market. A total of 243 oil samples adulterated with various concentrations of RO were prepared. The spectral information of the adulterated oil samples was obtained using near-infrared (NIR) spectroscopy. Additionally, visual data obtained from smartphone-captured images and videos were analysed. Deep-learning models trained on video data reached the highest accuracy of 96.30 %. To improve detection accuracy, a multimodal approach was adopted by combing spectral and visual data. Generally, this study presented a novel method for detecting the authenticity of CO in real time, providing technical support to address increasingly serious food safety concerns and laying the foundation for future rapid online detection using smartphones.

Quantitative analysis of β-carotene and unsaturated fatty acids in blended olive oil via Raman spectroscopy combined with model prediction

Blended vegetable oil is considered to be a valuable product in the market owing to favourable taste and nutritional composition. The quantification of its contents has notable implications for protecting food safety and consumer interests. Thus, a rapid and non-destructive method is needed to analyse the composition of blended oil. This study established an analytical method combining Raman spectroscopy and prediction models to determine the content of olive oil in a mixture. Competitive adaptive reweighted sampling was employed to select feature bands attributed to β-carotene and unsaturated fatty acids. Various models were used to calculate the mixture proportion, and the importance of characteristic peak intensity affecting the prediction was evaluated via grey relational analysis. The random forest model exhibited superior performance in quantitative analysis, with RMSE and R2 of 0.0447 and 0.9799, respectively. Overall, this approach was proven to effectively identify blended olive oils, exemplifying its potential in food authentication.

Rapid detection and quantitative analysis of thiram in fruits using a shape-adaptable flexible SERS substrate combined with deep learning

Ensuring food safety necessitates rapid identification of pesticide residues on fruits. Herein, we developed a shape-adaptable flexible surface-enhanced Raman scattering (SERS) substrate, combined with a deep learning algorithm, to quickly detect and quantitatively analyze thiram on fruit surfaces. This SERS substrate was fabricated by depositing silver nanoparticles (Ag NPs) onto a thin, corrugated polydimethylsiloxane (PDMS) film. This innovative design improves physical flexibility, ensuring conformal contact with curved surfaces while achieving high sensitivity, reproducibility, and mechanical robustness. The corrugated Ag NPs@PDMS thin film was able to directly detect thiram at concentrations as low as 10-7 M on tomato and blueberry peels, exhibiting consistent SERS activity with small interference from the fruit's shape. Furthermore, we developed a one-dimensional convolutional neural network (1D CNN) model, trained using a dataset of SERS signals from thiram, for quantitative analysis. The developed model achieved high prediction accuracy, with a coefficient of determination (R2) of 0.9905 and a root mean square error (RMSE) of 0.1364. The integration of our flexible SERS substrate, which adapts well to irregular surfaces, with the 1D CNN algorithm for quantitative analysis, holds great potential for rapid thiram detection in fruits.

A comparative study on rapid qualitative and quantitative determination of olive oil adulteration

Authenticity of olive oil is a significant concern for producers, consumers, and policymakers. To help address this issue, a rapid, efficient, and accurate flow injection mass spectrometric (FIMS) fingerprinting approach, combined with SVM and PLS classification and regression models, was proposed for the identification and quantitative analysis of olive oil adulteration. Based on the comprehensive comparative analysis, SVM outperformed those of PLS-DA, achieving higher values for accuracy, sensitivity, and specificity, as well as positive predictive and negative predictive values, in identifying adulterated olive oil samples. Furthermore, compared with PLSR model, the SVR model demonstrated superior performance in determining the content of adulterated olive oil, with a higher coefficient of determination and lower Root Mean Square Error. In conclusion, FIMS fingerprinting technology in combination with SVM can be effectively implemented for rapid, reliable, and accurate identification and quantification of olive oil adulteration.

Adulteration detection of multi-species vegetable oils in camellia oil using Raman spectroscopy: Comparison of chemometrics and deep learning methods

Oil adulteration is a global challenge in the production of high value-added natural oils. Raman spectroscopy combined with mathematical modeling can be used for adulteration detection of camellia oil (CAO). In this study, the advantages of traditional chemometrics and deep learning methods in identifying and quantifying adulterated CAO were compared from a statistical perspective, and no significant difference were founded in the identification of CAO at different levels of adulteration. The recognition rate of pure and adulterated CAO was 100 %, but there were misclassifications among different adulterated CAOs. The deep learning models outperformed chemometrics methods in quantitative prediction of adulteration level, with RP2, RMSEP, and RPD of the optimal ConvLSTM model achieved 0.999, 0.9 % and 31.5, respectively. The classifiers and models developed in this study based on deep learning have wide applicability and reliability, and provide a fast and accurate method for adulteration detection in CAO.

Fast dentification of overlapping fluorescence spectra of oil species based on LDA and two-dimensional convolutional neural network

Although most petroleum oil species can be identified by their fluorescence spectra, overlapping fluorescence spectra make identification difficult. This study aims to address the issue that fluorescence spectroscopy is ineffective in identifying overlapping oil species. In this study, an equivalent model of overlapping oil species with fluorescence spectra was established. The linear discriminant analysis (LDA)-assisted machine learning (ML) algorithms K nearest neighbor (KNN), decision tree (DT), and random forest (RF) improved the identification of fluorescent spectrally overlapping oil species for diesel-lubricant oils. The identification accuracies of two-dimensional convolutional neural network (2DCNN), LDA combined with the ML algorithms effectively all 100 %. Furthermore, Partial Least Squares Regression (PLSR) algorithm, Support Vector Regression (SVR) algorithm, DT regression algorithm, and RF regression algorithm were also used to identify the lubricant concentration in diesel-lubricant oils. The coefficient of determination of the DT was 1, and the root-mean-square error was 0, which identified the concentration of lubricant oils in them accurately and without error.

A novel method for quantitative determination of multiple substances using Raman spectroscopy combined with CWT

The identification of mixed solutions is a challenging and important subject in chemical analysis. In this paper, we propose a novel workflow that enables rapid qualitative and quantitative detection of mixed solutions. We use a methanol-ethanol mixed solution as an example to demonstrate the superiority of this workflow. The workflow includes the following steps: (1) converting Raman spectra into Raman images through CWT; (2) using MobileNetV3 as the backbone network, improved multi-label and multi-channel synchronization enables simultaneous prediction of multiple mixture concentrations; and (3) using transfer learning and multi-stage training strategies for training to achieve accurate quantitative analysis. We compare six traditional machine learning algorithms and two deep learning models to evaluate the performance of our new method. The experimental results show that our model has achieved good prediction results when predicting the concentration of methanol and ethanol, and the coefficient of determination R2 is greater than 0.999. At different concentrations, both MAPE and RSD outperform other models, which demonstrates that our workflow has outstanding analytical capabilities. Importantly, we have solved the problem that current quantitative analysis algorithms for Raman spectroscopy are almost unable to accurately predict the concentration of multiple substances simultaneously. In conclusion, it is foreseeable that this non-destructive, automated, and highly accurate workflow can further advance Raman spectroscopy.

Microwave detection technique combined with deep learning algorithm facilitates quantitative analysis of heavy metal Pb residues in edible oils

The heavy metal content in edible oils is intricately associated with their suitability for human consumption. In this study, standard soybean oil was used as a sample to quantify the specified concentration of heavy metals using microwave sensing technique. In addition, an attention-based deep residual neural network model was developed as an alternative to traditional modeling methods for predicting heavy metals in edible oils. In the process of microwave data processing, this work continued to discuss the impact of depth on convolutional neural networks. The results demonstrated that the proposed attention-based residual network model outperforms all other deep learning models in all metrics. The performance of this model was characterized by a coefficient of determination (R2) of 0.9605, a relative prediction deviation (RPD) of 5.0479, and a root mean square error (RMSE) of 3.1654 mg/kg. The research findings indicate that the combination of microwave detection technology and chemometrics holds significant potential for assessing heavy metal levels in edible oils.

Quantitative analysis of the quality constituents of Lonicera japonica Thunberg based on Raman spectroscopy

Quantitative analysis of the quality constituents of Lonicera japonica (Jinyinhua [JYH]) using a feasible method provides important information on its evaluation and applications. Limitations of sample pretreatment, experimental site, and analysis time should be considered when identifying new methods. In response to these considerations, Raman spectroscopy combined with deep learning was used to establish a quantitative analysis model to determine the quality of JYH. Chlorogenic acid and total flavonoids were identified as analysis targets via network pharmacology. High performance liquid chromatograph and ultraviolet spectroscopy were used to construct standard curves for quantitative analysis. Raman spectra of JYH extracts (1200) were collected. Subsequently, models were built using partial least squares regression, Support Vector Machine, Back Propagation Neural Network, and One-dimensional Convolutional Neural Network (1D-CNN). Among these, the 1D-CNN model showed superior prediction capability and had higher accuracy (R2 = 0.971), and lower root mean square error, indicating its suitability for rapid quantitative analysis.

Serum analysis based on SERS combined with 2D convolutional neural network and Gramian angular field for breast cancer screening

Breast cancer is a significant cause of death among women worldwide. It is crucial to quickly and accurately diagnose breast cancer in order to reduce mortality rates. While traditional diagnostic techniques for medical imaging and pathology samples have been commonly used in breast cancer screening, they still have certain limitations. Surface-enhanced Raman spectroscopy (SERS) is a fast, highly sensitive and user-friendly method that is often combined with deep learning techniques like convolutional neural networks. This combination helps identify unique molecular spectral features, also known as "fingerprint", in biological samples such as serum. Ultimately, this approach is able to accurately screen for cancer. The Gramian angular field (GAF) algorithm can convert one-dimensional (1D) time series into two-dimensional (2D) images. These images can be used for data visualization, pattern recognition and machine learning tasks. In this study, 640 serum SERS from breast cancer patients and healthy volunteers were converted into 2D spectral images by Gramian angular field (GAF) technique. These images were then used to train and test a two-dimensional convolutional neural network-GAF (2D-CNN-GAF) model for breast cancer classification. We compared the performance of the 2D-CNN-GAF model with other methods, including one-dimensional convolutional neural network (1D-CNN), support vector machine (SVM), K-nearest neighbor (KNN) and principal component analysis-linear discriminant analysis (PCA-LDA), using various evaluation metrics such as accuracy, precision, sensitivity, F1-score, receiver operating characteristic (ROC) curve and area under curve (AUC) value. The results showed that the 2D-CNN model outperformed the traditional models, achieving an AUC value of 0.9884, an accuracy of 98.13%, sensitivity of 98.65% and specificity of 97.67% for breast cancer classification. In this study, we used conventional nano-silver sol as the SERS-enhanced substrate and a portable laser Raman spectrometer to obtain the serum SERS data. The 2D-CNN-GAF model demonstrated accurate and automatic classification of breast cancer patients and healthy volunteers. The method does not require augmentation and preprocessing of spectral data, simplifying the processing steps of spectral data. This method has great potential for accurate breast cancer screening and also provides a useful reference in more types of cancer classification and automatic screening.

Revealing the adulteration of sesame oil products by portable Raman spectrometer and 1D CNN vector regression: A comparative study with chemometrics and colorimetry

Identification and quantification of sesame oil products are crucial due to the existing problems of adulteration with lower-priced oils and false labeling of sesame proportions. In this study, 1D CNN models were established to achieve discrimination of oil types and multiple quantification of adulteration using portable Raman spectrometer. An improved data augmentation method involving discarding transformations that alter peak positions was proposed, and synchronously injecting noise during geometric transformations. Furthermore, a novel neural network structure was introduced incorporating vector regression to accurately predict each component simultaneously. The proposed method has achieved higher accuracy in detecting multi-component adulteration compared with chemometrics (100 % accuracy in classifying different oils; R2 over 0.99 and RMSE within 2 % in predicting unknown adulterated samples). Finally, commercially available sesame oil products were tested and compared with gas chromatography and colorimetric methods, demonstrating the effectiveness of our proposed model in achieving higher detection accuracy at low-concentration adulteration.

Spectral encoder to extract the efficient features of Raman spectra for reliable and precise quantitative analysis

Raman spectroscopy has become a powerful analytical tool highly demanded in many applications such as microorganism sample analysis, food quality control, environmental science, and pharmaceutical analysis, owing to its non-invasiveness, simplicity, rapidity and ease of use. Among them, quantitative research using Raman spectroscopy is a crucial application field of spectral analysis. However, the entire process of quantitative modeling largely relies on the extraction of effective spectral features, particularly for measurements on complex samples or in environments with poor spectral signal quality. In this paper, we propose a method of utilizing a spectral encoder to extract effective spectral features, which can significantly enhance the reliability and precision of quantitative analysis. We built a latent encoded feature regression model; in the process of utilizing the autoencoder for reconstructing the spectrometer output, the latent feature obtained from the intermediate bottleneck layer is extracted. Then, these latent features are fed into a deep regression model for component concentration prediction. Through detailed ablation and comparative experiments, our proposed model demonstrates superior performance to common methods on single-component and multi-component mixture datasets, remarkably improving regression precision while without needing user-selected parameters and eliminating the interference of irrelevant and redundant information. Furthermore, in-depth analysis reveals that latent encoded feature possesses strong nonlinear feature representation capabilities, low computational costs, wide adaptability, and robustness against noise interference. This highlights its effectiveness in spectral regression tasks and indicates its potential in other application fields. Sufficient experimental results show that our proposed method provides a novel and effective feature extraction approach for spectral analysis, which is simple, suitable for various methods, and can meet the measurement needs of different real-world scenarios.

High-precision prediction of blood glucose concentration utilizing Fourier transform Raman spectroscopy and an ensemble machine learning algorithm

Raman spectroscopy has gained popularity in analyzing blood glucose levels due to its non-invasive identification and minimal interference from water. However, the challenge lies in how to accurately predict blood glucose concentrations in human blood using Raman spectroscopy. This paper researches a novel integrated machine learning algorithm called Bagging-ABC-ELM. The optimal input weights and biases of extreme learning machine (ELM) model are obtained by artificial bee colony (ABC) algorithm. The bagging algorithm is used to obtain a better the stability of the model and higher performance than ELM algorithm. The results show that the mean value of coefficient of determination is 0.9928, and root mean square error is 0.1928. Compared to other regression models, the Bagging-ABC-ELM model exhibited superior prediction accuracy, robustness, and generalization capability. The Bagging-ABC-ELM model presents a promising alternative for analyzing blood glucose levels in clinical and research settings.

Dense Convolutional Neural Network for Identification of Raman Spectra

The rapid development of cloud computing and deep learning makes the intelligent modes of applications widespread in various fields. The identification of Raman spectra can be realized in the cloud, due to its powerful computing, abundant spectral databases and advanced algorithms. Thus, it can reduce the dependence on the performance of the terminal instruments. However, the complexity of the detection environment can cause great interferences, which might significantly decrease the identification accuracies of algorithms. In this paper, a deep learning algorithm based on the Dense network has been proposed to satisfy the realization of this vision. The proposed Dense convolutional neural network has a very deep structure of over 40 layers and plenty of parameters to adjust the weight of different wavebands. In the kernel Dense blocks part of the network, it has a feed-forward fashion of connection for each layer to every other layer. It can alleviate the gradient vanishing or explosion problems, strengthen feature propagations, encourage feature reuses and enhance training efficiency. The network's special architecture mitigates noise interferences and ensures precise identification. The Dense network shows more accuracy and robustness compared to other CNN-based algorithms. We set up a database of 1600 Raman spectra consisting of 32 different types of liquid chemicals. They are detected using different postures as examples of interfered Raman spectra. In the 50 repeated training and testing sets, the Dense network can achieve a weighted accuracy of 99.99%. We have also tested the RRUFF database and the Dense network has a good performance. The proposed approach advances cloud-enabled Raman spectra identification, offering improved accuracy and adaptability for diverse identification tasks.

Label-free detection of trace level zearalenone in corn oil by surface-enhanced Raman spectroscopy (SERS) coupled with deep learning models

Surface-enhanced Raman spectroscopy (SERS) and deep learning models were adopted for detecting zearalenone (ZEN) in corn oil. First, gold nanorods were synthesized as a SERS substrate. Second, the collected SERS spectra were augmented to improve the generalization ability of regression models. Third, five regression models, including partial least squares regression (PLSR), random forest regression (RFR), Gaussian progress regression (GPR), one-dimensional convolutional neural networks (1D CNN), and two-dimensional convolutional neural networks (2D CNN), were developed. The results showed that 1D CNN and 2D CNN models possessed the best prediction performance, i.e., determination of prediction set (R_P²) = 0.9863 and 0.9872, root mean squared error of prediction set (RMSEP) = 0.2267 and 0.2341, ratio of performance to deviation (RPD) = 6.548 and 6.827, limit of detection (LOD) = 6.81 × 10^-4 and 7.24 × 10^-4 μg/mL. Therefore, the proposed method offers an ultrasensitive and effective strategy for detecting ZEN in corn oil.

Investigation of aroma characteristics of seven Chinese commercial sunflower seed oils using a combination of descriptive Analysis, GC-quadrupole-MS, and GC-Orbitrap-MS

The aroma characteristics of seven commercial Chinese sunflower seed oils were investigated in this study using descriptive analysis, headspace solid-phase microextraction coupled with GC-quadrupole-MS (LRMS, low-resolution mass spectrometry), and GC-Orbitrap-MS (HRMS, high-resolution mass spectrometry). GC-Orbitrap-MS quantified 96 compounds, including 18 alcohols, 12 esters, 7 ketones, 20 terpenoids, 11 pyrazines, 6 aldehydes, 6 furans, 6 benzene ring-containing compounds, 3 sulfides, 2 alkanes, and 5 nitrogen-containing compounds. Moreover, 22 compounds including 5 acids, 1 amide, and 16 aldehydes were quantified using GC-Quadrupole-MS. To our knowledge, 23 volatile compounds were reported for the first time in sunflower seed oil. All the seven samples were found to have a 'roasted sunflower seeds' note, 'sunflower seeds aroma' note and 'burnt aroma' note and only five of them had 'fried instant noodles' note, three had 'sweet' note and two had 'puffed food' note. Partial least squares regression was used to screen the candidate key volatiles that caused the aroma differences among these seven samples. It was observed that 'roasted sunflower seeds' note was positively correlated with 1-octen-3-ol, n-heptadehyde and dimethyl sulfone, whereas the 'fried instant noodles' and 'puffed food' demonstrated a positive correlation with pentanal, 3-methylbutanal, hexanal, (E)-2-hexenal and 2-pentylfuran. Our findings provide information to the producers and developers for quality control and improvement of sunflower seed oil.

Online Inspection of Browning in Yali Pears Using Visible-Near Infrared Spectroscopy and Interpretable Spectrogram-Based CNN Modeling

Browning is the most common physiological disease of Yali pears during storage. At the initial stage, browning only occurs in the tissues near the fruit core and cannot be detected from the appearance. The disease, if not identified and removed in time, will seriously undermine the quality and sale of the whole batch of fruit. Therefore, there is an urgent need to explore a method for early diagnosis of the browning in Yali pears. In order to realize the dynamic and online real-time detection of the browning in Yali pears, this paper conducted online discriminant analysis on healthy Yali pears and those with different degrees of browning using visible-near infrared (Vis-NIR) spectroscopy. The experimental results show that the prediction accuracy of the original spectrum combined with a 1D-CNN deep learning model reached 100% for the test sets of browned pears and healthy pears. Features extracted by the 1D-CNN method were converted into images by Gramian angular field (GAF) for PCA visual analysis, showing that deep learning had good performance in extracting features. In conclusion, Vis-NIR spectroscopy combined with the 1D-CNN discriminant model can realize online detection of browning in Yali pears.

Oil content analysis of corn seeds using a hand-held Raman spectrometer and spectral peak decomposition algorithm

Rapid, non-destructive and reliable detection of the oil content of corn seeds is important for development of high-oil corn. However, determination of the oil content is difficult using traditional methods for seed composition analysis. In this study, a hand-held Raman spectrometer was used with a spectral peak decomposition algorithm to determine the oil contents of corn seeds. Mature and waxy Zhengdan 958 corn seeds and mature Jingke 968 corn seeds were analyzed. Raman spectra were obtained in four regions of interest in the embryo of the seed. After analysis of the spectra, a characteristic spectral peak for the oil content was identified. A Gaussian curve fitting spectral peak decomposition algorithm was used to decompose the characteristic spectral peak of oil at 1657 cm^-1. This peak was used to determine the Raman spectral peak intensity for the oil content in the embryo and differences in the oil contents among seeds of varying maturity and different varieties. This method is feasible and effective for detection of corn seed oil.

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

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.

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

This paper proposed a novel spectrometric quantification method for nitrate and COD concentration in water using a double-channel 1-D convolution neural network for relatively long UV-vis absorption spectra data (2600 points). To improve the model's ability to resist turbidity disturbance, a new dataset augmentation method was applied and the absorption spectra of nitrate and COD under different turbidity disturbances were successfully simulated. Compared to the PLSR model, the value of RRMSEP for the CNN model was reduced from 6.1% to 1.4% in nitrate solution and 4.5% to 1.3% in COD solution. Compared to the PLSR model, the regression accuracy of the CNN model was increased from 56% to 93% in nitrate solution and 68% to 91% in COD solution. The test on the actual solution under different turbidity disturbances shows that the 1D-CNN model had a bias rate of less than 2% in both nitrate and COD solutions, while the worst bias rate in the PLSR method was 15%.

A deep learning model designed for Raman spectroscopy with a novel hyperparameter optimization method

Raman spectroscopy is a spectroscopic technique typically used to determine vibrational modes of molecules and is commonly used in chemistry to provide a structural fingerprint by which molecules can be identified. With the help of deep learning, Raman spectroscopy can be analyzed more efficiently and thus provide more accurate molecular information. However, no general neural network is designed for one-dimensional Raman spectral data so far. Furthermore, different combinations of hyperparameters of neural networks lead to results with significant differences, so the optimization of hyperparameters is a crucial issue in deep learning modeling. In this work, we propose a deep learning model designed for Raman spectral data and a hyperparameter optimization method to achieve its best performance, i.e., a method based on the simulated annealing algorithm to optimize the hyperparameters of the model. The proposed model and optimization method have been fully validated in a glioma Raman spectroscopy dataset. Compared with other published methods including linear regression, support vector regression, long short-term memory, VGG and ResNet, the mean squared error is reduced by 0.1557 while the coefficient determination is increased by 0.1195 on average.