Ultrasonic guided wave is an attractive monitoring technique for large-scale structures but is vulnerable to changes in environmental and operational conditions(EOC),which are inevitable in the normal inspection of ci...Ultrasonic guided wave is an attractive monitoring technique for large-scale structures but is vulnerable to changes in environmental and operational conditions(EOC),which are inevitable in the normal inspection of civil and mechanical structures.This paper thus presents a robust guided wave-based method for damage detection and localization under complex environmental conditions by singular value decomposition-based feature extraction and one-dimensional convolutional neural network(1D-CNN).After singular value decomposition-based feature extraction processing,a temporal robust damage index(TRDI)is extracted,and the effect of EOCs is well removed.Hence,even for the signals with a very large temperature-varying range and low signal-to-noise ratios(SNRs),the final damage detection and localization accuracy retain perfect 100%.Verifications are conducted on two different experimental datasets.The first dataset consists of guided wave signals collected from a thin aluminum plate with artificial noises,and the second is a publicly available experimental dataset of guided wave signals acquired on a composite plate with a temperature ranging from 20℃to 60℃.It is demonstrated that the proposed method can detect and localize the damage accurately and rapidly,showing great potential for application in complex and unknown EOC.展开更多
In order to directly construct the mapping between multiple state parameters and remaining useful life(RUL),and reduce the interference of random error on prediction accuracy,a RUL prediction model of aeroengine based...In order to directly construct the mapping between multiple state parameters and remaining useful life(RUL),and reduce the interference of random error on prediction accuracy,a RUL prediction model of aeroengine based on principal component analysis(PCA)and one-dimensional convolution neural network(1D-CNN)is proposed in this paper.Firstly,multiple state parameters corresponding to massive cycles of aeroengine are collected and brought into PCA for dimensionality reduction,and principal components are extracted for further time series prediction.Secondly,the 1D-CNN model is constructed to directly study the mapping between principal components and RUL.Multiple convolution and pooling operations are applied for deep feature extraction,and the end-to-end RUL prediction of aeroengine can be realized.Experimental results show that the most effective principal component from the multiple state parameters can be obtained by PCA,and the long time series of multiple state parameters can be directly mapped to RUL by 1D-CNN,so as to improve the efficiency and accuracy of RUL prediction.Compared with other traditional models,the proposed method also has lower prediction error and better robustness.展开更多
Severe ground-level ozone(O_(3))pollution over major Chinese cities has become one of the most challenging problems,which have deleterious effects on human health and the sustainability of society.This study explored ...Severe ground-level ozone(O_(3))pollution over major Chinese cities has become one of the most challenging problems,which have deleterious effects on human health and the sustainability of society.This study explored the spatiotemporal distribution characteristics of ground-level O_(3) and its precursors based on conventional pollutant and meteorological monitoring data in Zhejiang Province from 2016 to 2021.Then,a high-performance convolutional neural network(CNN)model was established by expanding the moment and the concentration variations to general factors.Finally,the response mechanism of O_(3) to the variation with crucial influencing factors is explored by controlling variables and interpolating target variables.The results indicated that the annual average MDA8-90th concentrations in Zhejiang Province are higher in the northern and lower in the southern.When the wind direction(WD)ranges from east to southwest and the wind speed(WS)ranges between 2 and 3 m/sec,higher O_(3) concentration prone to occur.At different temperatures(T),the O_(3) concentration showed a trend of first increasing and subsequently decreasing with increasing NO_(2) concentration,peaks at the NO_(2) concentration around 0.02mg/m^(3).The sensitivity of NO_(2) to O_(3) formation is not easily affected by temperature,barometric pressure and dew point temperature.Additionally,there is a minimum IRNO_(2) at each temperature when the NO_(2) concentration is 0.03 mg/m^(3),and this minimum IRNO_(2) decreases with increasing temperature.The study explores the response mechanism of O_(3) with the change of driving variables,which can provide a scientific foundation and methodological support for the targeted management of O_(3) pollution.展开更多
The isolated fracture-vug systems controlled by small-scale strike-slip faults within ultra-deep carbonate rocks of the Tarim Basin exhibit significant exploration potential.The study employs a novel training set inco...The isolated fracture-vug systems controlled by small-scale strike-slip faults within ultra-deep carbonate rocks of the Tarim Basin exhibit significant exploration potential.The study employs a novel training set incorporating innovative fault labels to train a U-Net-structured CNN model,enabling effective identification of small-scale strike-slip faults through seismic data interpretation.Based on the CNN faults,we analyze the distribution patterns of small-scale strike-slip faults.The small-scale strike-slip faults can be categorized into NNW-trending and NE-trending groups with strike lengths ranging 200–5000 m.The development intensity of small-scale strike-slip faults in the Lower Yingshan Member notably exceeds that in the Upper Member.The Lower and Upper Yingshan members are two distinct mechanical layers with contrasting brittleness characteristics,separated by a low-brittleness layer.The superior brittleness of the Lower Yingshan Member enhances the development intensity of small-scale strike-slip faults compared to the upper member,while the low-brittleness layer exerts restrictive effects on vertical fault propagation.Fracture-vug systems formed by interactions of two or more small-scale strike-slip faults demonstrate larger sizes than those controlled by individual faults.All fracture-vug system sizes show positive correlations with the vertical extents of associated small-scale strike-slip faults,particularly intersection and approaching fracture-vug systems exhibit accelerated size increases proportional to the vertical extents.展开更多
The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to u...The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.展开更多
Micro-expressions(ME)recognition is a complex task that requires advanced techniques to extract informative features fromfacial expressions.Numerous deep neural networks(DNNs)with convolutional structures have been pr...Micro-expressions(ME)recognition is a complex task that requires advanced techniques to extract informative features fromfacial expressions.Numerous deep neural networks(DNNs)with convolutional structures have been proposed.However,unlike DNNs,shallow convolutional neural networks often outperform deeper models in mitigating overfitting,particularly with small datasets.Still,many of these methods rely on a single feature for recognition,resulting in an insufficient ability to extract highly effective features.To address this limitation,in this paper,an Improved Dual-stream Shallow Convolutional Neural Network based on an Extreme Gradient Boosting Algorithm(IDSSCNN-XgBoost)is introduced for ME Recognition.The proposed method utilizes a dual-stream architecture where motion vectors(temporal features)are extracted using Optical Flow TV-L1 and amplify subtle changes(spatial features)via EulerianVideoMagnification(EVM).These features are processed by IDSSCNN,with an attention mechanism applied to refine the extracted effective features.The outputs are then fused,concatenated,and classified using the XgBoost algorithm.This comprehensive approach significantly improves recognition accuracy by leveraging the strengths of both temporal and spatial information,supported by the robust classification power of XgBoost.The proposed method is evaluated on three publicly available ME databases named Chinese Academy of Sciences Micro-expression Database(CASMEII),Spontaneous Micro-Expression Database(SMICHS),and Spontaneous Actions and Micro-Movements(SAMM).Experimental results indicate that the proposed model can achieve outstanding results compared to recent models.The accuracy results are 79.01%,69.22%,and 68.99%on CASMEII,SMIC-HS,and SAMM,and the F1-score are 75.47%,68.91%,and 63.84%,respectively.The proposed method has the advantage of operational efficiency and less computational time.展开更多
The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and hist...The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and historical context,DL offers a powerful complement by enhancing the speed,objectivity,and precision of the classification process.This research explores the significance of image data augmentation techniques in optimizing the performance of convolutional neural networks(CNNs)for geological image analysis,particularly in the classification of igneous,metamorphic,and sedimentary rock types from rock thin section(RTS)images.This study primarily focuses on classic image augmentation techniques and evaluates their impact on model accuracy and precision.Results demonstrate that augmentation techniques like Equalize significantly enhance the model's classification capabilities,achieving an F1-Score of 0.9869 for igneous rocks,0.9884 for metamorphic rocks,and 0.9929 for sedimentary rocks,representing improvements compared to the baseline original results.Moreover,the weighted average F1-Score across all classes and techniques is 0.9886,indicating an enhancement.Conversely,methods like Distort lead to decreased accuracy and F1-Score,with an F1-Score of 0.949 for igneous rocks,0.954 for metamorphic rocks,and 0.9416 for sedimentary rocks,exacerbating the performance compared to the baseline.The study underscores the practicality of image data augmentation in geological image classification and advocates for the adoption of DL methods in this domain for automation and improved results.The findings of this study can benefit various fields,including remote sensing,mineral exploration,and environmental monitoring,by enhancing the accuracy of geological image analysis both for scientific research and industrial applications.展开更多
Human disturbance activities is one of the main reasons for inducing geohazards.Ecological impact assessment metrics of roads are inconsistent criteria and multiple.From the perspective of visual observation,the envir...Human disturbance activities is one of the main reasons for inducing geohazards.Ecological impact assessment metrics of roads are inconsistent criteria and multiple.From the perspective of visual observation,the environment damage can be shown through detecting the uncovered area of vegetation in the images along road.To realize this,an end-to-end environment damage detection model based on convolutional neural network is proposed.A 50-layer residual network is used to extract feature map.The initial parameters are optimized by transfer learning.An example is shown by this method.The dataset including cliff and landslide damage are collected by us along road in Shennongjia national forest park.Results show 0.4703 average precision(AP)rating for cliff damage and 0.4809 average precision(AP)rating for landslide damage.Compared with YOLOv3,our model shows a better accuracy in cliff and landslide detection although a certain amount of speed is sacrificed.展开更多
During its growth stage,the plant is exposed to various diseases.Detection and early detection of crop diseases is amajor challenge in the horticulture industry.Crop infections can harmtotal crop yield and reduce farm...During its growth stage,the plant is exposed to various diseases.Detection and early detection of crop diseases is amajor challenge in the horticulture industry.Crop infections can harmtotal crop yield and reduce farmers’income if not identified early.Today’s approved method involves a professional plant pathologist to diagnose the disease by visual inspection of the afflicted plant leaves.This is an excellent use case for Community Assessment and Treatment Services(CATS)due to the lengthy manual disease diagnosis process and the accuracy of identification is directly proportional to the skills of pathologists.An alternative to conventional Machine Learning(ML)methods,which require manual identification of parameters for exact results,is to develop a prototype that can be classified without pre-processing.To automatically diagnose tomato leaf disease,this research proposes a hybrid model using the Convolutional Auto-Encoders(CAE)network and the CNN-based deep learning architecture of DenseNet.To date,none of the modern systems described in this paper have a combined model based on DenseNet,CAE,and ConvolutionalNeuralNetwork(CNN)todiagnose the ailments of tomato leaves automatically.Themodelswere trained on a dataset obtained from the Plant Village repository.The dataset consisted of 9920 tomato leaves,and the model-tomodel accuracy ratio was 98.35%.Unlike other approaches discussed in this paper,this hybrid strategy requires fewer training components.Therefore,the training time to classify plant diseases with the trained algorithm,as well as the training time to automatically detect the ailments of tomato leaves,is significantly reduced.展开更多
With the vigorous development of China's transportation industry,the mileage of high-grade highways based on semi rigid base layers has been increasing year by year.However,the commonly used material for semi rigi...With the vigorous development of China's transportation industry,the mileage of high-grade highways based on semi rigid base layers has been increasing year by year.However,the commonly used material for semi rigid base layers,cement stabilized crushed stone mixture(hereinafter referred to as water stabilized mixture),often experiences segregation during mixing,transportation,and paving.Separation of water stabilized mixture can greatly reduce the service life of roads and cause damage to people's property,the traditional separation detection method that relies on manual experience has problems of low detection efficiency and low recognition accuracy.In order to solve these problems and assist in the modernization of road construction,this article proposes a separation recognition method for water stabilized mixtures based on deep learning.Firstly,a database of segregation diseases of water stabilized mixture was built.Secondly,the control tests were set up by standard fine-tuning and feature extraction,and four different optimizers were set up respectively.By comparing accuracy,loss,precision,recall and F1-score at the end of the pre-trained network,the overall recognition effect of ResNet-101 as the network model was better.Thirdly,the ResNet-101 model was optimized by SpotTune,replacing cross entropy loss with focus loss,adding PReLU to the pre-trained network and a BN layer to the top layer of the pre-trained network,and using 1×1.Convolutional replacement of the fully connected layer.Finally,build a web side water stabilized mixture segregation recognition platform,and its stability was verified in practical engineering.展开更多
Prediction of the age of each individual is possible using the changing pattern of DNA methylation with age.In this paper an age prediction approach to work out multivariate regression problems using DNA methylation d...Prediction of the age of each individual is possible using the changing pattern of DNA methylation with age.In this paper an age prediction approach to work out multivariate regression problems using DNA methylation data is developed.In this research study a convolutional neural network(CNN)-based model optimised by the genetic algorithm(GA)is addressed.This paper contributes to enhancing age prediction as a regression problem using a union of two CNNs and exchanging knowledge be-tween them.This specifically re-starts the training process from a possibly higher-quality point in different iterations and,consequently,causes potentially yeilds better results at each iteration.The method proposed,which is called cooperative deep neural network(Co-DeepNet),is tested on two types of age prediction problems.Sixteen datasets containing 1899 healthy blood samples and nine datasets containing 2395 diseased blood samples are employed to examine the method's efficiency.As a result,the mean absolute deviation(MAD)is 1.49 and 3.61 years for training and testing data,respectively,when the healthy data is tested.The diseased blood data show MAD results of 3.81 and 5.43 years for training and testing data,respectively.The results of the Co-DeepNet are compared with six other methods proposed in previous studies and a single CNN using four prediction accuracy measurements(R^(2),MAD,MSE and RMSE).The effectiveness of the Co-DeepNet and superiority of its results is proved through the statistical analysis.展开更多
Breast Cancer(BC)remains a leadingmalignancy among women,resulting in highmortality rates.Early and accurate detection is crucial for improving patient outcomes.Traditional diagnostic tools,while effective,have limita...Breast Cancer(BC)remains a leadingmalignancy among women,resulting in highmortality rates.Early and accurate detection is crucial for improving patient outcomes.Traditional diagnostic tools,while effective,have limitations that reduce their accessibility and accuracy.This study investigates the use ofConvolutionalNeuralNetworks(CNNs)to enhance the diagnostic process of BC histopathology.Utilizing the BreakHis dataset,which contains thousands of histopathological images,we developed a CNN model designed to improve the speed and accuracy of image analysis.Our CNN architecture was designed with multiple convolutional layers,max-pooling layers,and a fully connected network optimized for feature extraction and classification.Hyperparameter tuning was conducted to identify the optimal learning rate,batch size,and number of epochs,ensuring robust model performance.The dataset was divided into training(80%),validation(10%),and testing(10%)subsets,with performance evaluated using accuracy,precision,recall,and F1-score metrics.Our CNN model achieved a magnification-independent accuracy of 97.72%,with specific accuracies of 97.50%at 40×,97.61%at 100×,99.06%at 200×,and 97.25%at 400×magnification levels.These results demonstrate the model’s superior performance relative to existing methods.The integration of CNNs in diagnostic workflows can potentially reduce pathologist workload,minimize interpretation errors,and increase the availability of diagnostic testing,thereby improving BC management and patient survival rates.This study highlights the effectiveness of deep learning in automating BC histopathological classification and underscores the potential for AI-driven diagnostic solutions to improve patient care.展开更多
Photonic computing has emerged as a promising technology for the ever-increasing computational demands of machine learning and artificial intelligence.Due to the advantages in computing speed,integrated photonic chips...Photonic computing has emerged as a promising technology for the ever-increasing computational demands of machine learning and artificial intelligence.Due to the advantages in computing speed,integrated photonic chips have attracted wide research attention on performing convolutional neural network algorithm.Programmable photonic chips are vital for achieving practical applications of photonic computing.Herein,a programmable photonic chip based on ultrafast laser-induced phase change is fabricated for photonic computing.Through designing the ultrafast laser pulses,the Sb film integrated into photonic waveguides can be reversibly switched between crystalline and amorphous phase,resulting in a large contrast in refractive index and extinction coefficient.As a consequence,the light transmission of waveguides can be switched between write and erase states.To determine the phase change time,the transient laser-induced phase change dynamics of Sb film are revealed at atomic scale,and the time-resolved transient reflectivity is measured.Based on the integrated photonic chip,photonic convolutional neural networks are built to implement machine learning algorithm,and images recognition task is achieved.This work paves a route for fabricating programmable photonic chips by designed ultrafast laser,which will facilitate the application of photonic computing in artificial intelligence.展开更多
Developing an accurate and efficient comprehensive water quality prediction model and its assessment method is crucial for the prevention and control of water pollution.Deep learning(DL),as one of the most promising t...Developing an accurate and efficient comprehensive water quality prediction model and its assessment method is crucial for the prevention and control of water pollution.Deep learning(DL),as one of the most promising technologies today,plays a crucial role in the effective assessment of water body health,which is essential for water resource management.This study models using both the original dataset and a dataset augmented with Generative Adversarial Networks(GAN).It integrates optimization algorithms(OA)with Convolutional Neural Networks(CNN)to propose a comprehensive water quality model evaluation method aiming at identifying the optimal models for different pollutants.Specifically,after preprocessing the spectral dataset,data augmentation was conducted to obtain two datasets.Then,six new models were developed on these datasets using particle swarm optimization(PSO),genetic algorithm(GA),and simulated annealing(SA)combined with CNN to simulate and forecast the concentrations of three water pollutants:Chemical Oxygen Demand(COD),Total Nitrogen(TN),and Total Phosphorus(TP).Finally,seven model evaluation methods,including uncertainty analysis,were used to evaluate the constructed models and select the optimal models for the three pollutants.The evaluation results indicate that the GPSCNN model performed best in predicting COD and TP concentrations,while the GGACNN model excelled in TN concentration prediction.Compared to existing technologies,the proposed models and evaluation methods provide a more comprehensive and rapid approach to water body prediction and assessment,offering new insights and methods for water pollution prevention and control.展开更多
Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attentio...Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attention, challenges remain, especially when dealing with diverse data types. In this study, we introduce a novel data imputation method based on a modified convolutional neural network, specifically, a Deep Residual-Convolutional Neural Network (DRes-CNN) architecture designed to handle missing values across various datasets. Our approach demonstrates substantial improvements over existing imputation techniques by leveraging residual connections and optimized convolutional layers to capture complex data patterns. We evaluated the model on publicly available datasets, including Medical Information Mart for Intensive Care (MIMIC-III and MIMIC-IV), which contain critical care patient data, and the Beijing Multi-Site Air Quality dataset, which measures environmental air quality. The proposed DRes-CNN method achieved a root mean square error (RMSE) of 0.00006, highlighting its high accuracy and robustness. We also compared with Low Light-Convolutional Neural Network (LL-CNN) and U-Net methods, which had RMSE values of 0.00075 and 0.00073, respectively. This represented an improvement of approximately 92% over LL-CNN and 91% over U-Net. The results showed that this DRes-CNN-based imputation method outperforms current state-of-the-art models. These results established DRes-CNN as a reliable solution for addressing missing data.展开更多
The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spect...The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spectrometer(ANIS)at the China Spallation Neutron Source(CSNS).The Yolov3 and MNIST models were implemented on the XILINX28-nm system-on-chip(So C).Meanwhile,the Yolov3 and ResNet50 models were deployed on the XILINX 16-nm Fin FET Ultra Scale+MPSoC.The atmospheric neutron SEEs on the tested CNN systems were comprehensively evaluated from six aspects,including chip type,network architecture,deployment methods,inference time,datasets,and the position of the anchor boxes.The various types of SEE soft errors,SEE cross-sections,and their distribution were analyzed to explore the radiation sensitivities and rules of 28-nm and 16-nm SoC.The current research can provide the technology support of radiation-resistant design of CNN system for developing and applying high-reliability,long-lifespan domestic artificial intelligence chips.展开更多
Precision steel balls are critical components in precision bearings.Surface defects on the steel balls will significantly reduce their useful life and cause linear or rotational transmission errors.Human visual inspec...Precision steel balls are critical components in precision bearings.Surface defects on the steel balls will significantly reduce their useful life and cause linear or rotational transmission errors.Human visual inspection of precision steel balls demands significant labor work.Besides,human inspection cannot maintain consistent quality assurance.To address these limitations and reduce inspection time,a convolutional neural network(CNN)based optical inspection system has been developed that automatically detects steel ball defects using a novel designated vertical mechanism.During image detection processing,two key challenges were addressed and resolved.They are the reflection caused by the coaxial light onto the ball center and the image deformation appearing at the edge of the steel balls.The special vertical rotating mechanism utilizing a spinning rod along with a spiral track was developed to enable successful and reliable full steel ball surface inspection during the rod rotation.The combination of the spinning rod and the spiral rotating component effectively rotates the steel ball to facilitate capturing complete surface images.Geometric calculations demonstrate that the steel balls can be completely inspected through specific rotation degrees,with the surface fully captured in 12 photo shots.These images are then analyzed by a CNN to determine surface quality defects.This study presents a new inspection method that enables the entire examination of steel ball surfaces.The successful development of this innovative automated optical inspection system with CNN represents a significant advancement in inspection quality control for precision steel balls.展开更多
Background:Convolutional neural networks(CNN)have achieved remarkable success in medical image analysis.However,unlike some general-domain tasks where model accuracy is paramount,medical applications demand both accur...Background:Convolutional neural networks(CNN)have achieved remarkable success in medical image analysis.However,unlike some general-domain tasks where model accuracy is paramount,medical applications demand both accuracy and explainability due to the high stakes affecting patients'lives.Based on model explanations,clinicians can evaluate the diagnostic decisions suggested by CNN.Nevertheless,prior explainable artificial intelligence methods treat medical image tasks akin to general vision tasks,following end-to-end paradigms to generate explanations and frequently overlooking crucial clinical domain knowledge.Methods:We propose a plug-and-play module that explicitly integrates anatomic boundary information into the explanation process for CNN-based thoracopathy classifiers.To generate the anatomic boundary of the lung parenchyma,we utilize a lung segmentation model developed on external public datasets and deploy it on the unseen target dataset to constrain model ex-planations within the lung parenchyma for the clinical task of thoracopathy classification.Results:Assessed by the intersection over union and dice similarity coefficient between model-extracted explanations and expert-annotated lesion areas,our method consistently outperformed the baseline devoid of clinical domain knowledge in 71 out of 72 scenarios,encompassing 3 CNN architectures(VGG-11,ResNet-18,and AlexNet),2 classification settings(binary and multi-label),3 explanation methods(Saliency Map,Grad-CAM,and Integrated Gradients),and 4 co-occurred thoracic diseases(Atelectasis,Fracture,Mass,and Pneumothorax).Conclusions:We underscore the effectiveness of leveraging radiology knowledge in improving model explanations for CNN and envisage that it could inspire future efforts to integrate clinical domain knowledge into medical image analysis.展开更多
Traditional meteorological downscaling methods face limitations due to the complex distribution of meteorological variables,which can lead to unstable forecasting results,especially in extreme scenarios.To overcome th...Traditional meteorological downscaling methods face limitations due to the complex distribution of meteorological variables,which can lead to unstable forecasting results,especially in extreme scenarios.To overcome this issue,we propose a convolutional graph neural network(CGNN)model,which we enhance with multilayer feature fusion and a squeeze-and-excitation block.Additionally,we introduce a spatially balanced mean squared error(SBMSE)loss function to address the imbalanced distribution and spatial variability of meteorological variables.The CGNN is capable of extracting essential spatial features and aggregating them from a global perspective,thereby improving the accuracy of prediction and enhancing the model's generalization ability.Based on the experimental results,CGNN has certain advantages in terms of bias distribution,exhibiting a smaller variance.When it comes to precipitation,both UNet and AE also demonstrate relatively small biases.As for temperature,AE and CNNdense perform outstandingly during the winter.The time correlation coefficients show an improvement of at least 10%at daily and monthly scales for both temperature and precipitation.Furthermore,the SBMSE loss function displays an advantage over existing loss functions in predicting the98th percentile and identifying areas where extreme events occur.However,the SBMSE tends to overestimate the distribution of extreme precipitation,which may be due to the theoretical assumptions about the posterior distribution of data that partially limit the effectiveness of the loss function.In future work,we will further optimize the SBMSE to improve prediction accuracy.展开更多
The converter steelmaking process represents a pivotal aspect of steel metallurgical production,with the characteristics of the flame at the furnace mouth serving as an indirect indicator of the internal smelting stag...The converter steelmaking process represents a pivotal aspect of steel metallurgical production,with the characteristics of the flame at the furnace mouth serving as an indirect indicator of the internal smelting stage.Effectively identifying and predicting the smelt-ing stage poses a significant challenge within industrial production.Traditional image-based methodologies,which rely on a single static flame image as input,demonstrate low recognition accuracy and inadequately extract the dynamic changes in smelting stage.To address this issue,the present study introduces an innovative recognition model that preprocesses flame video sequences from the furnace mouth and then employs a convolutional recurrent neural network(CRNN)to extract spatiotemporal features and derive recognition outputs.Ad-ditionally,we adopt feature layer visualization techniques to verify the model’s effectiveness and further enhance model performance by integrating the Bayesian optimization algorithm.The results indicate that the ResNet18 with convolutional block attention module(CBAM)in the convolutional layer demonstrates superior image feature extraction capabilities,achieving an accuracy of 90.70%and an area under the curve of 98.05%.The constructed Bayesian optimization-CRNN(BO-CRNN)model exhibits a significant improvement in comprehensive performance,with an accuracy of 97.01%and an area under the curve of 99.85%.Furthermore,statistics on the model’s average recognition time,computational complexity,and parameter quantity(Average recognition time:5.49 ms,floating-point opera-tions per second:18260.21 M(1 M=1×10^(6)),parameters:11.58 M)demonstrate superior performance.Through extensive repeated ex-periments on real-world datasets,the proposed CRNN model is capable of rapidly and accurately identifying smelting stages,offering a novel approach for converter smelting endpoint control.展开更多
基金Supported by National Natural Science Foundation of China(Grant Nos.52272433 and 11874110)Jiangsu Provincial Key R&D Program(Grant No.BE2021084)Technical Support Special Project of State Administration for Market Regulation(Grant No.2022YJ11).
文摘Ultrasonic guided wave is an attractive monitoring technique for large-scale structures but is vulnerable to changes in environmental and operational conditions(EOC),which are inevitable in the normal inspection of civil and mechanical structures.This paper thus presents a robust guided wave-based method for damage detection and localization under complex environmental conditions by singular value decomposition-based feature extraction and one-dimensional convolutional neural network(1D-CNN).After singular value decomposition-based feature extraction processing,a temporal robust damage index(TRDI)is extracted,and the effect of EOCs is well removed.Hence,even for the signals with a very large temperature-varying range and low signal-to-noise ratios(SNRs),the final damage detection and localization accuracy retain perfect 100%.Verifications are conducted on two different experimental datasets.The first dataset consists of guided wave signals collected from a thin aluminum plate with artificial noises,and the second is a publicly available experimental dataset of guided wave signals acquired on a composite plate with a temperature ranging from 20℃to 60℃.It is demonstrated that the proposed method can detect and localize the damage accurately and rapidly,showing great potential for application in complex and unknown EOC.
基金supported by Jiangsu Social Science Foundation(No.20GLD008)Science,Technology Projects of Jiangsu Provincial Department of Communications(No.2020Y14)Joint Fund for Civil Aviation Research(No.U1933202)。
文摘In order to directly construct the mapping between multiple state parameters and remaining useful life(RUL),and reduce the interference of random error on prediction accuracy,a RUL prediction model of aeroengine based on principal component analysis(PCA)and one-dimensional convolution neural network(1D-CNN)is proposed in this paper.Firstly,multiple state parameters corresponding to massive cycles of aeroengine are collected and brought into PCA for dimensionality reduction,and principal components are extracted for further time series prediction.Secondly,the 1D-CNN model is constructed to directly study the mapping between principal components and RUL.Multiple convolution and pooling operations are applied for deep feature extraction,and the end-to-end RUL prediction of aeroengine can be realized.Experimental results show that the most effective principal component from the multiple state parameters can be obtained by PCA,and the long time series of multiple state parameters can be directly mapped to RUL by 1D-CNN,so as to improve the efficiency and accuracy of RUL prediction.Compared with other traditional models,the proposed method also has lower prediction error and better robustness.
基金supported by the National Key Research and Development Program of China (Nos.2022YFC3702000 and 2022YFC3703500)the Key R&D Project of Zhejiang Province (No.2022C03146).
文摘Severe ground-level ozone(O_(3))pollution over major Chinese cities has become one of the most challenging problems,which have deleterious effects on human health and the sustainability of society.This study explored the spatiotemporal distribution characteristics of ground-level O_(3) and its precursors based on conventional pollutant and meteorological monitoring data in Zhejiang Province from 2016 to 2021.Then,a high-performance convolutional neural network(CNN)model was established by expanding the moment and the concentration variations to general factors.Finally,the response mechanism of O_(3) to the variation with crucial influencing factors is explored by controlling variables and interpolating target variables.The results indicated that the annual average MDA8-90th concentrations in Zhejiang Province are higher in the northern and lower in the southern.When the wind direction(WD)ranges from east to southwest and the wind speed(WS)ranges between 2 and 3 m/sec,higher O_(3) concentration prone to occur.At different temperatures(T),the O_(3) concentration showed a trend of first increasing and subsequently decreasing with increasing NO_(2) concentration,peaks at the NO_(2) concentration around 0.02mg/m^(3).The sensitivity of NO_(2) to O_(3) formation is not easily affected by temperature,barometric pressure and dew point temperature.Additionally,there is a minimum IRNO_(2) at each temperature when the NO_(2) concentration is 0.03 mg/m^(3),and this minimum IRNO_(2) decreases with increasing temperature.The study explores the response mechanism of O_(3) with the change of driving variables,which can provide a scientific foundation and methodological support for the targeted management of O_(3) pollution.
基金supported by the National Natural Science Foundation of China(No.U21B2062).
文摘The isolated fracture-vug systems controlled by small-scale strike-slip faults within ultra-deep carbonate rocks of the Tarim Basin exhibit significant exploration potential.The study employs a novel training set incorporating innovative fault labels to train a U-Net-structured CNN model,enabling effective identification of small-scale strike-slip faults through seismic data interpretation.Based on the CNN faults,we analyze the distribution patterns of small-scale strike-slip faults.The small-scale strike-slip faults can be categorized into NNW-trending and NE-trending groups with strike lengths ranging 200–5000 m.The development intensity of small-scale strike-slip faults in the Lower Yingshan Member notably exceeds that in the Upper Member.The Lower and Upper Yingshan members are two distinct mechanical layers with contrasting brittleness characteristics,separated by a low-brittleness layer.The superior brittleness of the Lower Yingshan Member enhances the development intensity of small-scale strike-slip faults compared to the upper member,while the low-brittleness layer exerts restrictive effects on vertical fault propagation.Fracture-vug systems formed by interactions of two or more small-scale strike-slip faults demonstrate larger sizes than those controlled by individual faults.All fracture-vug system sizes show positive correlations with the vertical extents of associated small-scale strike-slip faults,particularly intersection and approaching fracture-vug systems exhibit accelerated size increases proportional to the vertical extents.
文摘The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.
基金supported by the Key Research and Development Program of Jiangsu Province under Grant BE2022059-3,CTBC Bank through the Industry-Academia Cooperation Project,as well as by the Ministry of Science and Technology of Taiwan through Grants MOST-108-2218-E-002-055,MOST-109-2223-E-009-002-MY3,MOST-109-2218-E-009-025,and MOST431109-2218-E-002-015.
文摘Micro-expressions(ME)recognition is a complex task that requires advanced techniques to extract informative features fromfacial expressions.Numerous deep neural networks(DNNs)with convolutional structures have been proposed.However,unlike DNNs,shallow convolutional neural networks often outperform deeper models in mitigating overfitting,particularly with small datasets.Still,many of these methods rely on a single feature for recognition,resulting in an insufficient ability to extract highly effective features.To address this limitation,in this paper,an Improved Dual-stream Shallow Convolutional Neural Network based on an Extreme Gradient Boosting Algorithm(IDSSCNN-XgBoost)is introduced for ME Recognition.The proposed method utilizes a dual-stream architecture where motion vectors(temporal features)are extracted using Optical Flow TV-L1 and amplify subtle changes(spatial features)via EulerianVideoMagnification(EVM).These features are processed by IDSSCNN,with an attention mechanism applied to refine the extracted effective features.The outputs are then fused,concatenated,and classified using the XgBoost algorithm.This comprehensive approach significantly improves recognition accuracy by leveraging the strengths of both temporal and spatial information,supported by the robust classification power of XgBoost.The proposed method is evaluated on three publicly available ME databases named Chinese Academy of Sciences Micro-expression Database(CASMEII),Spontaneous Micro-Expression Database(SMICHS),and Spontaneous Actions and Micro-Movements(SAMM).Experimental results indicate that the proposed model can achieve outstanding results compared to recent models.The accuracy results are 79.01%,69.22%,and 68.99%on CASMEII,SMIC-HS,and SAMM,and the F1-score are 75.47%,68.91%,and 63.84%,respectively.The proposed method has the advantage of operational efficiency and less computational time.
文摘The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and historical context,DL offers a powerful complement by enhancing the speed,objectivity,and precision of the classification process.This research explores the significance of image data augmentation techniques in optimizing the performance of convolutional neural networks(CNNs)for geological image analysis,particularly in the classification of igneous,metamorphic,and sedimentary rock types from rock thin section(RTS)images.This study primarily focuses on classic image augmentation techniques and evaluates their impact on model accuracy and precision.Results demonstrate that augmentation techniques like Equalize significantly enhance the model's classification capabilities,achieving an F1-Score of 0.9869 for igneous rocks,0.9884 for metamorphic rocks,and 0.9929 for sedimentary rocks,representing improvements compared to the baseline original results.Moreover,the weighted average F1-Score across all classes and techniques is 0.9886,indicating an enhancement.Conversely,methods like Distort lead to decreased accuracy and F1-Score,with an F1-Score of 0.949 for igneous rocks,0.954 for metamorphic rocks,and 0.9416 for sedimentary rocks,exacerbating the performance compared to the baseline.The study underscores the practicality of image data augmentation in geological image classification and advocates for the adoption of DL methods in this domain for automation and improved results.The findings of this study can benefit various fields,including remote sensing,mineral exploration,and environmental monitoring,by enhancing the accuracy of geological image analysis both for scientific research and industrial applications.
文摘Human disturbance activities is one of the main reasons for inducing geohazards.Ecological impact assessment metrics of roads are inconsistent criteria and multiple.From the perspective of visual observation,the environment damage can be shown through detecting the uncovered area of vegetation in the images along road.To realize this,an end-to-end environment damage detection model based on convolutional neural network is proposed.A 50-layer residual network is used to extract feature map.The initial parameters are optimized by transfer learning.An example is shown by this method.The dataset including cliff and landslide damage are collected by us along road in Shennongjia national forest park.Results show 0.4703 average precision(AP)rating for cliff damage and 0.4809 average precision(AP)rating for landslide damage.Compared with YOLOv3,our model shows a better accuracy in cliff and landslide detection although a certain amount of speed is sacrificed.
基金funded by UKRI EPSRC Grant EP/W020408/1 Project SPRITE+2:The Security,Privacy,Identity,and Trust Engagement Network plus(phase 2)for this studyfunded by PhD project RS718 on Explainable AI through the UKRI EPSRC Grant-funded Doctoral Training Centre at Swansea University.
文摘During its growth stage,the plant is exposed to various diseases.Detection and early detection of crop diseases is amajor challenge in the horticulture industry.Crop infections can harmtotal crop yield and reduce farmers’income if not identified early.Today’s approved method involves a professional plant pathologist to diagnose the disease by visual inspection of the afflicted plant leaves.This is an excellent use case for Community Assessment and Treatment Services(CATS)due to the lengthy manual disease diagnosis process and the accuracy of identification is directly proportional to the skills of pathologists.An alternative to conventional Machine Learning(ML)methods,which require manual identification of parameters for exact results,is to develop a prototype that can be classified without pre-processing.To automatically diagnose tomato leaf disease,this research proposes a hybrid model using the Convolutional Auto-Encoders(CAE)network and the CNN-based deep learning architecture of DenseNet.To date,none of the modern systems described in this paper have a combined model based on DenseNet,CAE,and ConvolutionalNeuralNetwork(CNN)todiagnose the ailments of tomato leaves automatically.Themodelswere trained on a dataset obtained from the Plant Village repository.The dataset consisted of 9920 tomato leaves,and the model-tomodel accuracy ratio was 98.35%.Unlike other approaches discussed in this paper,this hybrid strategy requires fewer training components.Therefore,the training time to classify plant diseases with the trained algorithm,as well as the training time to automatically detect the ailments of tomato leaves,is significantly reduced.
基金sponsored by the National Natural Science Foundation of China under grant No.52008154,to which the authors are very grateful.
文摘With the vigorous development of China's transportation industry,the mileage of high-grade highways based on semi rigid base layers has been increasing year by year.However,the commonly used material for semi rigid base layers,cement stabilized crushed stone mixture(hereinafter referred to as water stabilized mixture),often experiences segregation during mixing,transportation,and paving.Separation of water stabilized mixture can greatly reduce the service life of roads and cause damage to people's property,the traditional separation detection method that relies on manual experience has problems of low detection efficiency and low recognition accuracy.In order to solve these problems and assist in the modernization of road construction,this article proposes a separation recognition method for water stabilized mixtures based on deep learning.Firstly,a database of segregation diseases of water stabilized mixture was built.Secondly,the control tests were set up by standard fine-tuning and feature extraction,and four different optimizers were set up respectively.By comparing accuracy,loss,precision,recall and F1-score at the end of the pre-trained network,the overall recognition effect of ResNet-101 as the network model was better.Thirdly,the ResNet-101 model was optimized by SpotTune,replacing cross entropy loss with focus loss,adding PReLU to the pre-trained network and a BN layer to the top layer of the pre-trained network,and using 1×1.Convolutional replacement of the fully connected layer.Finally,build a web side water stabilized mixture segregation recognition platform,and its stability was verified in practical engineering.
基金supported by the Universiti Kebangsaan Malaysia(DIP-2016-024).
文摘Prediction of the age of each individual is possible using the changing pattern of DNA methylation with age.In this paper an age prediction approach to work out multivariate regression problems using DNA methylation data is developed.In this research study a convolutional neural network(CNN)-based model optimised by the genetic algorithm(GA)is addressed.This paper contributes to enhancing age prediction as a regression problem using a union of two CNNs and exchanging knowledge be-tween them.This specifically re-starts the training process from a possibly higher-quality point in different iterations and,consequently,causes potentially yeilds better results at each iteration.The method proposed,which is called cooperative deep neural network(Co-DeepNet),is tested on two types of age prediction problems.Sixteen datasets containing 1899 healthy blood samples and nine datasets containing 2395 diseased blood samples are employed to examine the method's efficiency.As a result,the mean absolute deviation(MAD)is 1.49 and 3.61 years for training and testing data,respectively,when the healthy data is tested.The diseased blood data show MAD results of 3.81 and 5.43 years for training and testing data,respectively.The results of the Co-DeepNet are compared with six other methods proposed in previous studies and a single CNN using four prediction accuracy measurements(R^(2),MAD,MSE and RMSE).The effectiveness of the Co-DeepNet and superiority of its results is proved through the statistical analysis.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2024-02-01096).
文摘Breast Cancer(BC)remains a leadingmalignancy among women,resulting in highmortality rates.Early and accurate detection is crucial for improving patient outcomes.Traditional diagnostic tools,while effective,have limitations that reduce their accessibility and accuracy.This study investigates the use ofConvolutionalNeuralNetworks(CNNs)to enhance the diagnostic process of BC histopathology.Utilizing the BreakHis dataset,which contains thousands of histopathological images,we developed a CNN model designed to improve the speed and accuracy of image analysis.Our CNN architecture was designed with multiple convolutional layers,max-pooling layers,and a fully connected network optimized for feature extraction and classification.Hyperparameter tuning was conducted to identify the optimal learning rate,batch size,and number of epochs,ensuring robust model performance.The dataset was divided into training(80%),validation(10%),and testing(10%)subsets,with performance evaluated using accuracy,precision,recall,and F1-score metrics.Our CNN model achieved a magnification-independent accuracy of 97.72%,with specific accuracies of 97.50%at 40×,97.61%at 100×,99.06%at 200×,and 97.25%at 400×magnification levels.These results demonstrate the model’s superior performance relative to existing methods.The integration of CNNs in diagnostic workflows can potentially reduce pathologist workload,minimize interpretation errors,and increase the availability of diagnostic testing,thereby improving BC management and patient survival rates.This study highlights the effectiveness of deep learning in automating BC histopathological classification and underscores the potential for AI-driven diagnostic solutions to improve patient care.
基金supported by the National Key R&D Program of China(2024YFB4609801)the National Natural Science Foundation of China(52075289)the Tsinghua-Jiangyin Innovation Special Fund(TJISF,2023JYTH0104).
文摘Photonic computing has emerged as a promising technology for the ever-increasing computational demands of machine learning and artificial intelligence.Due to the advantages in computing speed,integrated photonic chips have attracted wide research attention on performing convolutional neural network algorithm.Programmable photonic chips are vital for achieving practical applications of photonic computing.Herein,a programmable photonic chip based on ultrafast laser-induced phase change is fabricated for photonic computing.Through designing the ultrafast laser pulses,the Sb film integrated into photonic waveguides can be reversibly switched between crystalline and amorphous phase,resulting in a large contrast in refractive index and extinction coefficient.As a consequence,the light transmission of waveguides can be switched between write and erase states.To determine the phase change time,the transient laser-induced phase change dynamics of Sb film are revealed at atomic scale,and the time-resolved transient reflectivity is measured.Based on the integrated photonic chip,photonic convolutional neural networks are built to implement machine learning algorithm,and images recognition task is achieved.This work paves a route for fabricating programmable photonic chips by designed ultrafast laser,which will facilitate the application of photonic computing in artificial intelligence.
基金Supported by Natural Science Basic Research Plan in Shaanxi Province of China(Program No.2022JM-396)the Strategic Priority Research Program of the Chinese Academy of Sciences,Grant No.XDA23040101+4 种基金Shaanxi Province Key Research and Development Projects(Program No.2023-YBSF-437)Xi'an Shiyou University Graduate Student Innovation Fund Program(Program No.YCX2412041)State Key Laboratory of Air Traffic Management System and Technology(SKLATM202001)Tianjin Education Commission Research Program Project(2020KJ028)Fundamental Research Funds for the Central Universities(3122019132)。
文摘Developing an accurate and efficient comprehensive water quality prediction model and its assessment method is crucial for the prevention and control of water pollution.Deep learning(DL),as one of the most promising technologies today,plays a crucial role in the effective assessment of water body health,which is essential for water resource management.This study models using both the original dataset and a dataset augmented with Generative Adversarial Networks(GAN).It integrates optimization algorithms(OA)with Convolutional Neural Networks(CNN)to propose a comprehensive water quality model evaluation method aiming at identifying the optimal models for different pollutants.Specifically,after preprocessing the spectral dataset,data augmentation was conducted to obtain two datasets.Then,six new models were developed on these datasets using particle swarm optimization(PSO),genetic algorithm(GA),and simulated annealing(SA)combined with CNN to simulate and forecast the concentrations of three water pollutants:Chemical Oxygen Demand(COD),Total Nitrogen(TN),and Total Phosphorus(TP).Finally,seven model evaluation methods,including uncertainty analysis,were used to evaluate the constructed models and select the optimal models for the three pollutants.The evaluation results indicate that the GPSCNN model performed best in predicting COD and TP concentrations,while the GGACNN model excelled in TN concentration prediction.Compared to existing technologies,the proposed models and evaluation methods provide a more comprehensive and rapid approach to water body prediction and assessment,offering new insights and methods for water pollution prevention and control.
基金supported by the Intelligent System Research Group(ISysRG)supported by Universitas Sriwijaya funded by the Competitive Research 2024.
文摘Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attention, challenges remain, especially when dealing with diverse data types. In this study, we introduce a novel data imputation method based on a modified convolutional neural network, specifically, a Deep Residual-Convolutional Neural Network (DRes-CNN) architecture designed to handle missing values across various datasets. Our approach demonstrates substantial improvements over existing imputation techniques by leveraging residual connections and optimized convolutional layers to capture complex data patterns. We evaluated the model on publicly available datasets, including Medical Information Mart for Intensive Care (MIMIC-III and MIMIC-IV), which contain critical care patient data, and the Beijing Multi-Site Air Quality dataset, which measures environmental air quality. The proposed DRes-CNN method achieved a root mean square error (RMSE) of 0.00006, highlighting its high accuracy and robustness. We also compared with Low Light-Convolutional Neural Network (LL-CNN) and U-Net methods, which had RMSE values of 0.00075 and 0.00073, respectively. This represented an improvement of approximately 92% over LL-CNN and 91% over U-Net. The results showed that this DRes-CNN-based imputation method outperforms current state-of-the-art models. These results established DRes-CNN as a reliable solution for addressing missing data.
基金Project supported by the National Natural Science Foundation of China(Grant No.12305303)the Natural Science Foundation of Hunan Province of China(Grant Nos.2023JJ40520,2024JJ2044,and 2021JJ40444)+3 种基金the Science and Technology Innovation Program of Hunan Province,China(Grant No.2020RC3054)the Postgraduate Scientific Research Innovation Project of Hunan Province,China(Grant No.CX20240831)the Natural Science Basic Research Plan in the Shaanxi Province of China(Grant No.2023-JC-QN0015)the Doctoral Research Fund of University of South China(Grant No.200XQD033)。
文摘The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spectrometer(ANIS)at the China Spallation Neutron Source(CSNS).The Yolov3 and MNIST models were implemented on the XILINX28-nm system-on-chip(So C).Meanwhile,the Yolov3 and ResNet50 models were deployed on the XILINX 16-nm Fin FET Ultra Scale+MPSoC.The atmospheric neutron SEEs on the tested CNN systems were comprehensively evaluated from six aspects,including chip type,network architecture,deployment methods,inference time,datasets,and the position of the anchor boxes.The various types of SEE soft errors,SEE cross-sections,and their distribution were analyzed to explore the radiation sensitivities and rules of 28-nm and 16-nm SoC.The current research can provide the technology support of radiation-resistant design of CNN system for developing and applying high-reliability,long-lifespan domestic artificial intelligence chips.
文摘Precision steel balls are critical components in precision bearings.Surface defects on the steel balls will significantly reduce their useful life and cause linear or rotational transmission errors.Human visual inspection of precision steel balls demands significant labor work.Besides,human inspection cannot maintain consistent quality assurance.To address these limitations and reduce inspection time,a convolutional neural network(CNN)based optical inspection system has been developed that automatically detects steel ball defects using a novel designated vertical mechanism.During image detection processing,two key challenges were addressed and resolved.They are the reflection caused by the coaxial light onto the ball center and the image deformation appearing at the edge of the steel balls.The special vertical rotating mechanism utilizing a spinning rod along with a spiral track was developed to enable successful and reliable full steel ball surface inspection during the rod rotation.The combination of the spinning rod and the spiral rotating component effectively rotates the steel ball to facilitate capturing complete surface images.Geometric calculations demonstrate that the steel balls can be completely inspected through specific rotation degrees,with the surface fully captured in 12 photo shots.These images are then analyzed by a CNN to determine surface quality defects.This study presents a new inspection method that enables the entire examination of steel ball surfaces.The successful development of this innovative automated optical inspection system with CNN represents a significant advancement in inspection quality control for precision steel balls.
文摘Background:Convolutional neural networks(CNN)have achieved remarkable success in medical image analysis.However,unlike some general-domain tasks where model accuracy is paramount,medical applications demand both accuracy and explainability due to the high stakes affecting patients'lives.Based on model explanations,clinicians can evaluate the diagnostic decisions suggested by CNN.Nevertheless,prior explainable artificial intelligence methods treat medical image tasks akin to general vision tasks,following end-to-end paradigms to generate explanations and frequently overlooking crucial clinical domain knowledge.Methods:We propose a plug-and-play module that explicitly integrates anatomic boundary information into the explanation process for CNN-based thoracopathy classifiers.To generate the anatomic boundary of the lung parenchyma,we utilize a lung segmentation model developed on external public datasets and deploy it on the unseen target dataset to constrain model ex-planations within the lung parenchyma for the clinical task of thoracopathy classification.Results:Assessed by the intersection over union and dice similarity coefficient between model-extracted explanations and expert-annotated lesion areas,our method consistently outperformed the baseline devoid of clinical domain knowledge in 71 out of 72 scenarios,encompassing 3 CNN architectures(VGG-11,ResNet-18,and AlexNet),2 classification settings(binary and multi-label),3 explanation methods(Saliency Map,Grad-CAM,and Integrated Gradients),and 4 co-occurred thoracic diseases(Atelectasis,Fracture,Mass,and Pneumothorax).Conclusions:We underscore the effectiveness of leveraging radiology knowledge in improving model explanations for CNN and envisage that it could inspire future efforts to integrate clinical domain knowledge into medical image analysis.
基金partially funded by the National Natural Science Foundation of China(U2142205)the Guangdong Major Project of Basic and Applied Basic Research(2020B0301030004)+1 种基金the Special Fund for Forecasters of China Meteorological Administration(CMAYBY2020-094)the Graduate Student Research and Innovation Program of Central South University(2023ZZTS0347)。
文摘Traditional meteorological downscaling methods face limitations due to the complex distribution of meteorological variables,which can lead to unstable forecasting results,especially in extreme scenarios.To overcome this issue,we propose a convolutional graph neural network(CGNN)model,which we enhance with multilayer feature fusion and a squeeze-and-excitation block.Additionally,we introduce a spatially balanced mean squared error(SBMSE)loss function to address the imbalanced distribution and spatial variability of meteorological variables.The CGNN is capable of extracting essential spatial features and aggregating them from a global perspective,thereby improving the accuracy of prediction and enhancing the model's generalization ability.Based on the experimental results,CGNN has certain advantages in terms of bias distribution,exhibiting a smaller variance.When it comes to precipitation,both UNet and AE also demonstrate relatively small biases.As for temperature,AE and CNNdense perform outstandingly during the winter.The time correlation coefficients show an improvement of at least 10%at daily and monthly scales for both temperature and precipitation.Furthermore,the SBMSE loss function displays an advantage over existing loss functions in predicting the98th percentile and identifying areas where extreme events occur.However,the SBMSE tends to overestimate the distribution of extreme precipitation,which may be due to the theoretical assumptions about the posterior distribution of data that partially limit the effectiveness of the loss function.In future work,we will further optimize the SBMSE to improve prediction accuracy.
基金financially supported by the National Natural Science Foundation of China(No.52374320).
文摘The converter steelmaking process represents a pivotal aspect of steel metallurgical production,with the characteristics of the flame at the furnace mouth serving as an indirect indicator of the internal smelting stage.Effectively identifying and predicting the smelt-ing stage poses a significant challenge within industrial production.Traditional image-based methodologies,which rely on a single static flame image as input,demonstrate low recognition accuracy and inadequately extract the dynamic changes in smelting stage.To address this issue,the present study introduces an innovative recognition model that preprocesses flame video sequences from the furnace mouth and then employs a convolutional recurrent neural network(CRNN)to extract spatiotemporal features and derive recognition outputs.Ad-ditionally,we adopt feature layer visualization techniques to verify the model’s effectiveness and further enhance model performance by integrating the Bayesian optimization algorithm.The results indicate that the ResNet18 with convolutional block attention module(CBAM)in the convolutional layer demonstrates superior image feature extraction capabilities,achieving an accuracy of 90.70%and an area under the curve of 98.05%.The constructed Bayesian optimization-CRNN(BO-CRNN)model exhibits a significant improvement in comprehensive performance,with an accuracy of 97.01%and an area under the curve of 99.85%.Furthermore,statistics on the model’s average recognition time,computational complexity,and parameter quantity(Average recognition time:5.49 ms,floating-point opera-tions per second:18260.21 M(1 M=1×10^(6)),parameters:11.58 M)demonstrate superior performance.Through extensive repeated ex-periments on real-world datasets,the proposed CRNN model is capable of rapidly and accurately identifying smelting stages,offering a novel approach for converter smelting endpoint control.
