Recently,the demand for renewable energy has increased due to its environmental and economic needs.Solar panels are the mainstay for dealing with solar energy and converting it into another form of usable energy.Solar...Recently,the demand for renewable energy has increased due to its environmental and economic needs.Solar panels are the mainstay for dealing with solar energy and converting it into another form of usable energy.Solar panels work under suitable climatic conditions that allow the light photons to access the solar cells,as any blocking of sunlight on these cells causes a halt in the panels work and restricts the carry of these photons.Thus,the panels are unable to work under these conditions.A layer of snow forms on the solar panels due to snowfall in areas with low temperatures.Therefore,it causes an insulating layer on solar panels and the inability to produce electrical energy.The detection of snow-covered solar panels is crucial,as it allows us the opportunity to remove snow using some heating techniques more efficiently and restore the photovoltaics system to proper operation.This paper presents five deep learning models,■-16,■-19,ESNET-18,ESNET-50,and ESNET-101,which are used for the recognition and classification of solar panel images.In this paper,two different cases were applied;the first case is performed on the original dataset without trying any kind of preprocessing,and the second case is extreme climate conditions and simulated by generating motion noise.Furthermore,the dataset was replicated using the upsampling technique in order to handle the unbalancing issue.The conducted dataset is divided into three different categories,namely;all_snow,no_snow,and partial snow.The fivemodels are trained,validated,and tested on this dataset under the same conditions 60%training,20%validation,and testing 20%for both cases.The accuracy of the models has been compared and verified to distinguish and classify the processed dataset.The accuracy results in the first case showthat the comparedmodels■-16,■-19,ESNET-18,and ESNET-50 give 0.9592,while ESNET-101 gives 0.9694.In the second case,the models outperformed their counterparts in the first case by evaluating performance,where the accuracy results reached 1.00,0.9545,0.9888,1.00.and 1.00 for■-16,■-19,ESNET-18 and ESNET-50,respectively.Consequently,we conclude that the second case models outperformed their peers.展开更多
With the development of artificial intelligence,artificial neural network(ANN)has been widely used in recent years.In this paper,the method is applied to the prediction of the fluid force exerted on the bluff body whe...With the development of artificial intelligence,artificial neural network(ANN)has been widely used in recent years.In this paper,the method is applied to the prediction of the fluid force exerted on the bluff body when flow passes around.Firstly,back propagation(BP)model and convolutional neural network(CNN)model are introduced;then the mapping relation between the shape of bluff body and the fluid force,which is calculated by computational fluid dynamics(CFD),is established by sample training.Finally,it is used to predict the fluid force of the new shape bluff body.By taking the CFD results as benchmark,CNN model is capable of predicting both the resistance and lift force,while BP model is incompetent to predict lift force.Furthermore,both CNN and BP models have a significant advantage in prediction efficiency,compared by CFD calculation method.展开更多
Alzheimer’s disease(AD)is a chronic and common form of dementia that mainly affects elderly individuals.The disease is dangerous because it causes damage to brain cells and tissues before the symptoms appear,and ther...Alzheimer’s disease(AD)is a chronic and common form of dementia that mainly affects elderly individuals.The disease is dangerous because it causes damage to brain cells and tissues before the symptoms appear,and there is nomedicinal or surgical treatment available yet forAD.ADcauses loss of memory and functionality control in multiple degrees according to AD’s progression level.However,early diagnosis of AD can hinder its progression.Brain imaging tools such as magnetic resonance imaging(MRI),computed tomography(CT)scans,positron emission tomography(PET),etc.can help in medical diagnosis of AD.Recently,computer-aided diagnosis(CAD)such as deep learning applied to brain images obtained with these tools,has been an established strategic methodology that is widely used for clinical assistance in prognosis of AD.In this study,we proposed an intelligent methodology for building a convolutional neural network(CNN)from scratch to detect AD stages from the brain MRI images dataset and to improve patient care.It is worth mentioning that training a deep-learning model requires a large amount of data to produce accurate results and prevent the model from overfitting problems.Therefore,for better understanding of classifiers and to overcome the model overfitting problem,we applied data augmentation to the minority classes in order to increase the number of MRI images in the dataset.All experiments were conducted using Alzheimer’s MRI dataset consisting of brain MRI scanned images.The performance of the proposed model determines detection of the four stages of AD.Experimental results show high performance of the proposed model in that the model achieved a 99.38%accuracy rate,which is the highest so far.Moreover,the proposed model performance in terms of accuracy,precision,sensitivity,specificity,and f-measures is promising when compared to the very recent state-of-the-art domain-specific models existing in the literature.展开更多
Handwritten character recognition(HCR)involves identifying characters in images,documents,and various sources such as forms surveys,questionnaires,and signatures,and transforming them into a machine-readable format fo...Handwritten character recognition(HCR)involves identifying characters in images,documents,and various sources such as forms surveys,questionnaires,and signatures,and transforming them into a machine-readable format for subsequent processing.Successfully recognizing complex and intricately shaped handwritten characters remains a significant obstacle.The use of convolutional neural network(CNN)in recent developments has notably advanced HCR,leveraging the ability to extract discriminative features from extensive sets of raw data.Because of the absence of pre-existing datasets in the Kurdish language,we created a Kurdish handwritten dataset called(KurdSet).The dataset consists of Kurdish characters,digits,texts,and symbols.The dataset consists of 1560 participants and contains 45,240 characters.In this study,we chose characters only from our dataset.We utilized a Kurdish dataset for handwritten character recognition.The study also utilizes various models,including InceptionV3,Xception,DenseNet121,and a customCNNmodel.To show the performance of the KurdSet dataset,we compared it to Arabic handwritten character recognition dataset(AHCD).We applied the models to both datasets to show the performance of our dataset.Additionally,the performance of the models is evaluated using test accuracy,which measures the percentage of correctly classified characters in the evaluation phase.All models performed well in the training phase,DenseNet121 exhibited the highest accuracy among the models,achieving a high accuracy of 99.80%on the Kurdish dataset.And Xception model achieved 98.66%using the Arabic dataset.展开更多
The rapidly escalating sophistication of e-commerce fraud in recent years has led to an increasing reliance on fraud detection methods based on machine learning.However,fraud detection methods based on conventional ma...The rapidly escalating sophistication of e-commerce fraud in recent years has led to an increasing reliance on fraud detection methods based on machine learning.However,fraud detection methods based on conventional machine learning approaches suffer from several problems,including an excessively high number of network parameters,which decreases the efficiency and increases the difficulty of training the network,while simultaneously leading to network overfitting.In addition,the sparsity of positive fraud incidents relative to the overwhelming proportion of negative incidents leads to detection failures in trained networks.The present work addresses these issues by proposing a convolutional neural network(CNN)framework for detecting ecommerce fraud,where network training is conducted using historical market transaction data.The number of network parameters reduces via the local perception field and weight sharing inherent in the CNN framework.In addition,this deep learning framework enables the use of an algorithmiclevel approach to address dataset imbalance by focusing the CNN model on minority data classes.The proposed CNN model is trained and tested using a large public e-commerce service dataset from 2018,and the test results demonstrate that the model provides higher fraud prediction accuracy than existing state-of-the-art methods.展开更多
Porosity,tortuosity,specific surface area(SSA),and permeability are four key parameters of reactive transport modeling in sandstone,which are important for understanding solute transport and geochemical reaction pro-c...Porosity,tortuosity,specific surface area(SSA),and permeability are four key parameters of reactive transport modeling in sandstone,which are important for understanding solute transport and geochemical reaction pro-cesses in sandstone aquifers.These four parameters reflect the characteristics of pore structure of sandstone from different perspectives,and the traditional empirical formulas cannot make accurate predictions of them due to their complexity and heterogeneity.In this paper,eleven types of sandstone CT images were firstly segmented into numerous subsample images,the porosity,tortuosity,SSA,and permeability of the subsamples were calculated,and the dataset was established.The 3D convolutional neural network(CNN)models were subse-quently established and trained to predict the key reactive transport parameters based on subsample CT images of sandstones.The results demonstrated that the 3D CNN model with multiple outputs exhibited excellent prediction ability for the four parameters compared to the traditional empirical formulas.In particular,for the prediction of tortuosity and permeability,the 3D CNN model with multiple outputs even showed slightly better prediction ability than its single-output variant model.Additionally,it demonstrated good generalization per-formance on sandstone CT images not included in the training dataset.The study showed that the 3D CNN model with multiple outputs has the advantages of simplifying operation and saving computational resources,which has the prospect of popularization and application.展开更多
Phishing attacks remain a pervasive threat in the cybersecurity landscape,necessitating intelligent and scalable detection mechanisms.This paper suggests a deep learning-based method for phishing URL identification us...Phishing attacks remain a pervasive threat in the cybersecurity landscape,necessitating intelligent and scalable detection mechanisms.This paper suggests a deep learning-based method for phishing URL identification using Convolutional Neural Networks(CNNs)on two benchmark datasets:the Phishing and PhishTank datasets.The CNN model eliminates the need for human feature engineering by automatically learning intricate,non-linear patterns from structured information.The Phishing dataset undergoes 5-fold cross-validation to guarantee robustness,and the results are contrasted with those of conventional classifiers like XGBoost and Logistic Regression.According to the results,the CNN routinely beats these baselines in terms of accuracy and F1-score.Notably,on the PhishTank dataset,the CNN achieves exceptional performance with over 99.3%accuracy,underscoring its effectiveness and generalizability.The experimental framework is implemented using TensorFlow in Python and validated on a standard computing setup.The findings reinforce CNN’s suitability for realtime,adaptive phishing detection in dynamic threat environments.展开更多
In this work,we demonstrate aπ-phase-shifted tilted fiber Bragg grating(π-PSTFBG)-based sensor for measuring the refractive index(RI)of NaCl solutions,achieving a real-time and online measurement system by employing...In this work,we demonstrate aπ-phase-shifted tilted fiber Bragg grating(π-PSTFBG)-based sensor for measuring the refractive index(RI)of NaCl solutions,achieving a real-time and online measurement system by employing a densely connected convolutional neural network(D-CNN)model to demodulate the full spectrum.The proposedπ-PSTFBG sensor is prepared by using the advanced fiber grating inscription system based on a two-beam interferometry method,which could introduce deeper features of dip-splitting for all the lossy dips in the spectrum,giving the possibility of fully measuring the change of RI.This enhanced feature gives relatively higher prediction accuracy(R^(2) of 99.67%)using the well-trained D-CNN model compared with the results achieved by pure TFBG or that with a gold coating.As a further demonstration from a practical view,a prototype integrated with the proposed D-CNN algorithm is developed to conduct RI measurement of NaCl solutions in real time using aπ-PSTFBG-based RI sensor.The results show that the proposed real-time demodulation system is capable of measuring RI with an average error of 1.6×10^(-4)RIU in a short response time of<1 s.The demonstrated spectral demodulation approach powered by deep learning shows great potential in real-time analysis for chemical solutions and point-of-care medical testing based on RI changes,especially for the portable requirements.展开更多
The sea surface reconstructed from radar images provides valuable information for marine operations and maritime transport.The standard reconstruction method relies on the three-dimensional fast Fourier transform(3D-F...The sea surface reconstructed from radar images provides valuable information for marine operations and maritime transport.The standard reconstruction method relies on the three-dimensional fast Fourier transform(3D-FFT),which introduces empirical parameters and modulation transfer function(MTF)to correct the modulation effects that may cause errors.In light of the convolutional neural networks’(CNN)success in computer vision tasks,this paper proposes a novel sea surface reconstruction method from marine radar images based on an end-to-end CNN model with the U-Net architecture.Synthetic radar images and sea surface elevation maps were used for training and testing.Compared to the standard reconstruction method,the CNN-based model achieved higher accuracy on the same data set,with an improved correlation coefficient between reconstructed and actual wave fields of up to 0.96-0.97,and a decreased non-dimensional root mean square error(NDRMSE)of around 0.06.The influence of training data on the deep learning model was also studied.Additionally,the impact of the significant wave height and peak period on the CNN model’s accuracy was investigated.It has been demonstrated that the accuracy will fluctuate as the wave steepness increases,but the correlation coefficient remains above 0.90,and the NDRMSE remains less than 0.11.展开更多
The agriculture sector is no exception to the widespread usage of deep learning tools and techniques.In this paper,an automated detection method on the basis of pre-trained Convolutional Neural Network(CNN)models is p...The agriculture sector is no exception to the widespread usage of deep learning tools and techniques.In this paper,an automated detection method on the basis of pre-trained Convolutional Neural Network(CNN)models is proposed to identify and classify paddy crop biotic stresses from the field images.The proposed work also provides the empirical comparison among the leading CNN models with transfer learning from the ImageNet weights namely,Inception-V3,VGG-16,ResNet-50,DenseNet-121 and MobileNet-28.Brown spot,hispa,and leaf blast,three of the most common and destructive paddy crop biotic stresses that occur during the flowering and ripening growth stages are considered for the experimentation.The experimental results reveal that the ResNet-50 model achieves the highest average paddy crop stress classification accuracy of 92.61%outperforming the other considered CNN models.The study explores the feasibility of CNN models for the paddy crop stress identification as well as the applicability of automated methods to non-experts.展开更多
文摘Recently,the demand for renewable energy has increased due to its environmental and economic needs.Solar panels are the mainstay for dealing with solar energy and converting it into another form of usable energy.Solar panels work under suitable climatic conditions that allow the light photons to access the solar cells,as any blocking of sunlight on these cells causes a halt in the panels work and restricts the carry of these photons.Thus,the panels are unable to work under these conditions.A layer of snow forms on the solar panels due to snowfall in areas with low temperatures.Therefore,it causes an insulating layer on solar panels and the inability to produce electrical energy.The detection of snow-covered solar panels is crucial,as it allows us the opportunity to remove snow using some heating techniques more efficiently and restore the photovoltaics system to proper operation.This paper presents five deep learning models,■-16,■-19,ESNET-18,ESNET-50,and ESNET-101,which are used for the recognition and classification of solar panel images.In this paper,two different cases were applied;the first case is performed on the original dataset without trying any kind of preprocessing,and the second case is extreme climate conditions and simulated by generating motion noise.Furthermore,the dataset was replicated using the upsampling technique in order to handle the unbalancing issue.The conducted dataset is divided into three different categories,namely;all_snow,no_snow,and partial snow.The fivemodels are trained,validated,and tested on this dataset under the same conditions 60%training,20%validation,and testing 20%for both cases.The accuracy of the models has been compared and verified to distinguish and classify the processed dataset.The accuracy results in the first case showthat the comparedmodels■-16,■-19,ESNET-18,and ESNET-50 give 0.9592,while ESNET-101 gives 0.9694.In the second case,the models outperformed their counterparts in the first case by evaluating performance,where the accuracy results reached 1.00,0.9545,0.9888,1.00.and 1.00 for■-16,■-19,ESNET-18 and ESNET-50,respectively.Consequently,we conclude that the second case models outperformed their peers.
基金the National Natural Science Foundation of China(Nos.51679021 and 51709030)the Fundamental Research Funds for the Central Universities of China(No.3132019115)the Key Scientific Cultivation Research Project of Dalian Maritime University(No.3132019320)。
文摘With the development of artificial intelligence,artificial neural network(ANN)has been widely used in recent years.In this paper,the method is applied to the prediction of the fluid force exerted on the bluff body when flow passes around.Firstly,back propagation(BP)model and convolutional neural network(CNN)model are introduced;then the mapping relation between the shape of bluff body and the fluid force,which is calculated by computational fluid dynamics(CFD),is established by sample training.Finally,it is used to predict the fluid force of the new shape bluff body.By taking the CFD results as benchmark,CNN model is capable of predicting both the resistance and lift force,while BP model is incompetent to predict lift force.Furthermore,both CNN and BP models have a significant advantage in prediction efficiency,compared by CFD calculation method.
文摘Alzheimer’s disease(AD)is a chronic and common form of dementia that mainly affects elderly individuals.The disease is dangerous because it causes damage to brain cells and tissues before the symptoms appear,and there is nomedicinal or surgical treatment available yet forAD.ADcauses loss of memory and functionality control in multiple degrees according to AD’s progression level.However,early diagnosis of AD can hinder its progression.Brain imaging tools such as magnetic resonance imaging(MRI),computed tomography(CT)scans,positron emission tomography(PET),etc.can help in medical diagnosis of AD.Recently,computer-aided diagnosis(CAD)such as deep learning applied to brain images obtained with these tools,has been an established strategic methodology that is widely used for clinical assistance in prognosis of AD.In this study,we proposed an intelligent methodology for building a convolutional neural network(CNN)from scratch to detect AD stages from the brain MRI images dataset and to improve patient care.It is worth mentioning that training a deep-learning model requires a large amount of data to produce accurate results and prevent the model from overfitting problems.Therefore,for better understanding of classifiers and to overcome the model overfitting problem,we applied data augmentation to the minority classes in order to increase the number of MRI images in the dataset.All experiments were conducted using Alzheimer’s MRI dataset consisting of brain MRI scanned images.The performance of the proposed model determines detection of the four stages of AD.Experimental results show high performance of the proposed model in that the model achieved a 99.38%accuracy rate,which is the highest so far.Moreover,the proposed model performance in terms of accuracy,precision,sensitivity,specificity,and f-measures is promising when compared to the very recent state-of-the-art domain-specific models existing in the literature.
文摘Handwritten character recognition(HCR)involves identifying characters in images,documents,and various sources such as forms surveys,questionnaires,and signatures,and transforming them into a machine-readable format for subsequent processing.Successfully recognizing complex and intricately shaped handwritten characters remains a significant obstacle.The use of convolutional neural network(CNN)in recent developments has notably advanced HCR,leveraging the ability to extract discriminative features from extensive sets of raw data.Because of the absence of pre-existing datasets in the Kurdish language,we created a Kurdish handwritten dataset called(KurdSet).The dataset consists of Kurdish characters,digits,texts,and symbols.The dataset consists of 1560 participants and contains 45,240 characters.In this study,we chose characters only from our dataset.We utilized a Kurdish dataset for handwritten character recognition.The study also utilizes various models,including InceptionV3,Xception,DenseNet121,and a customCNNmodel.To show the performance of the KurdSet dataset,we compared it to Arabic handwritten character recognition dataset(AHCD).We applied the models to both datasets to show the performance of our dataset.Additionally,the performance of the models is evaluated using test accuracy,which measures the percentage of correctly classified characters in the evaluation phase.All models performed well in the training phase,DenseNet121 exhibited the highest accuracy among the models,achieving a high accuracy of 99.80%on the Kurdish dataset.And Xception model achieved 98.66%using the Arabic dataset.
基金supported by the National Natural Science Foundation of China (No.72073041,No.61903131)2020 Hunan Provincial Higher Education Teaching Reform Research Project (Nos.HNJG-2020-1130,HNJG-2020-1124)+1 种基金2020 General Project of Hunan Social Science Fund (No.20B16)Outstanding Youth of Department of Education of Hunan Province (No.20B096)and the China Postdoctoral Science Foundation (No.2020M683715).
文摘The rapidly escalating sophistication of e-commerce fraud in recent years has led to an increasing reliance on fraud detection methods based on machine learning.However,fraud detection methods based on conventional machine learning approaches suffer from several problems,including an excessively high number of network parameters,which decreases the efficiency and increases the difficulty of training the network,while simultaneously leading to network overfitting.In addition,the sparsity of positive fraud incidents relative to the overwhelming proportion of negative incidents leads to detection failures in trained networks.The present work addresses these issues by proposing a convolutional neural network(CNN)framework for detecting ecommerce fraud,where network training is conducted using historical market transaction data.The number of network parameters reduces via the local perception field and weight sharing inherent in the CNN framework.In addition,this deep learning framework enables the use of an algorithmiclevel approach to address dataset imbalance by focusing the CNN model on minority data classes.The proposed CNN model is trained and tested using a large public e-commerce service dataset from 2018,and the test results demonstrate that the model provides higher fraud prediction accuracy than existing state-of-the-art methods.
基金supported by the National Natural Science Foundation of China (12105139 and 42277264)National Key Research and Development Program of China (2021YFC2902104)Education Department of Hunan Province (21B0446).
文摘Porosity,tortuosity,specific surface area(SSA),and permeability are four key parameters of reactive transport modeling in sandstone,which are important for understanding solute transport and geochemical reaction pro-cesses in sandstone aquifers.These four parameters reflect the characteristics of pore structure of sandstone from different perspectives,and the traditional empirical formulas cannot make accurate predictions of them due to their complexity and heterogeneity.In this paper,eleven types of sandstone CT images were firstly segmented into numerous subsample images,the porosity,tortuosity,SSA,and permeability of the subsamples were calculated,and the dataset was established.The 3D convolutional neural network(CNN)models were subse-quently established and trained to predict the key reactive transport parameters based on subsample CT images of sandstones.The results demonstrated that the 3D CNN model with multiple outputs exhibited excellent prediction ability for the four parameters compared to the traditional empirical formulas.In particular,for the prediction of tortuosity and permeability,the 3D CNN model with multiple outputs even showed slightly better prediction ability than its single-output variant model.Additionally,it demonstrated good generalization per-formance on sandstone CT images not included in the training dataset.The study showed that the 3D CNN model with multiple outputs has the advantages of simplifying operation and saving computational resources,which has the prospect of popularization and application.
文摘Phishing attacks remain a pervasive threat in the cybersecurity landscape,necessitating intelligent and scalable detection mechanisms.This paper suggests a deep learning-based method for phishing URL identification using Convolutional Neural Networks(CNNs)on two benchmark datasets:the Phishing and PhishTank datasets.The CNN model eliminates the need for human feature engineering by automatically learning intricate,non-linear patterns from structured information.The Phishing dataset undergoes 5-fold cross-validation to guarantee robustness,and the results are contrasted with those of conventional classifiers like XGBoost and Logistic Regression.According to the results,the CNN routinely beats these baselines in terms of accuracy and F1-score.Notably,on the PhishTank dataset,the CNN achieves exceptional performance with over 99.3%accuracy,underscoring its effectiveness and generalizability.The experimental framework is implemented using TensorFlow in Python and validated on a standard computing setup.The findings reinforce CNN’s suitability for realtime,adaptive phishing detection in dynamic threat environments.
基金National Natural Science Foundation of China(62275277,U2001601)Guangdong Project(2021QN02X055)+3 种基金Guangdong ST Programme(2024B0101030001)Fundamental Research Funds for the Central Universities,Sun Yat-sen University(23lgbj007)Science and Technology Planning Project of Guangzhou(2024A04J9891)Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)(SML2023SP231)。
文摘In this work,we demonstrate aπ-phase-shifted tilted fiber Bragg grating(π-PSTFBG)-based sensor for measuring the refractive index(RI)of NaCl solutions,achieving a real-time and online measurement system by employing a densely connected convolutional neural network(D-CNN)model to demodulate the full spectrum.The proposedπ-PSTFBG sensor is prepared by using the advanced fiber grating inscription system based on a two-beam interferometry method,which could introduce deeper features of dip-splitting for all the lossy dips in the spectrum,giving the possibility of fully measuring the change of RI.This enhanced feature gives relatively higher prediction accuracy(R^(2) of 99.67%)using the well-trained D-CNN model compared with the results achieved by pure TFBG or that with a gold coating.As a further demonstration from a practical view,a prototype integrated with the proposed D-CNN algorithm is developed to conduct RI measurement of NaCl solutions in real time using aπ-PSTFBG-based RI sensor.The results show that the proposed real-time demodulation system is capable of measuring RI with an average error of 1.6×10^(-4)RIU in a short response time of<1 s.The demonstrated spectral demodulation approach powered by deep learning shows great potential in real-time analysis for chemical solutions and point-of-care medical testing based on RI changes,especially for the portable requirements.
基金the National Natu-ral Science Foundation of China(grant no.51979162 and no.52088102)the Fundamental Research Funds for the Central Universities of Chinathe Oceanic Interdisciplinary Program of Shanghai Jiao Tong University(project number SL2021MS019).
文摘The sea surface reconstructed from radar images provides valuable information for marine operations and maritime transport.The standard reconstruction method relies on the three-dimensional fast Fourier transform(3D-FFT),which introduces empirical parameters and modulation transfer function(MTF)to correct the modulation effects that may cause errors.In light of the convolutional neural networks’(CNN)success in computer vision tasks,this paper proposes a novel sea surface reconstruction method from marine radar images based on an end-to-end CNN model with the U-Net architecture.Synthetic radar images and sea surface elevation maps were used for training and testing.Compared to the standard reconstruction method,the CNN-based model achieved higher accuracy on the same data set,with an improved correlation coefficient between reconstructed and actual wave fields of up to 0.96-0.97,and a decreased non-dimensional root mean square error(NDRMSE)of around 0.06.The influence of training data on the deep learning model was also studied.Additionally,the impact of the significant wave height and peak period on the CNN model’s accuracy was investigated.It has been demonstrated that the accuracy will fluctuate as the wave steepness increases,but the correlation coefficient remains above 0.90,and the NDRMSE remains less than 0.11.
文摘The agriculture sector is no exception to the widespread usage of deep learning tools and techniques.In this paper,an automated detection method on the basis of pre-trained Convolutional Neural Network(CNN)models is proposed to identify and classify paddy crop biotic stresses from the field images.The proposed work also provides the empirical comparison among the leading CNN models with transfer learning from the ImageNet weights namely,Inception-V3,VGG-16,ResNet-50,DenseNet-121 and MobileNet-28.Brown spot,hispa,and leaf blast,three of the most common and destructive paddy crop biotic stresses that occur during the flowering and ripening growth stages are considered for the experimentation.The experimental results reveal that the ResNet-50 model achieves the highest average paddy crop stress classification accuracy of 92.61%outperforming the other considered CNN models.The study explores the feasibility of CNN models for the paddy crop stress identification as well as the applicability of automated methods to non-experts.
