Rockburst is a phenomenon in which free surfaces are formed during excavation,which subsequently causes the sudden release of energy in the construction of mines and tunnels.Light rockburst only peels off rock slices ...Rockburst is a phenomenon in which free surfaces are formed during excavation,which subsequently causes the sudden release of energy in the construction of mines and tunnels.Light rockburst only peels off rock slices without ejection,while severe rockburst causes casualties and property loss.The frequency and degree of rockburst damage increases with the excavation depth.Moreover,rockburst is the leading engineering geological hazard in the excavation process,and thus the prediction of its intensity grade is of great significance to the development of geotechnical engineering.Therefore,the prediction of rockburst intensity grade is one problem that needs to be solved urgently.By comprehensively considering the occurrence mechanism of rockburst,this paper selects the stress index(σθ/σc),brittleness index(σ_(c)/σ_(t)),and rock elastic energy index(Wet)as the rockburst evaluation indexes through the Spearman coefficient method.This overcomes the low accuracy problem of a single evaluation index prediction method.Following this,the BGD-MSR-DNN rockburst intensity grade prediction model based on batch gradient descent and a multi-scale residual deep neural network is proposed.The batch gradient descent(BGD)module is used to replace the gradient descent algorithm,which effectively improves the efficiency of the network and reduces the model training time.Moreover,the multi-scale residual(MSR)module solves the problem of network degradation when there are too many hidden layers of the deep neural network(DNN),thus improving the model prediction accuracy.The experimental results reveal the BGDMSR-DNN model accuracy to reach 97.1%,outperforming other comparable models.Finally,actual projects such as Qinling Tunnel and Daxiangling Tunnel,reached an accuracy of 100%.The model can be applied in mines and tunnel engineering to realize the accurate and rapid prediction of rockburst intensity grade.展开更多
The detection of ash content in coal slime flotation tailings using deep learning can be hindered by various factors such as foam,impurities,and changing lighting conditions that disrupt the collection of tailings ima...The detection of ash content in coal slime flotation tailings using deep learning can be hindered by various factors such as foam,impurities,and changing lighting conditions that disrupt the collection of tailings images.To address this challenge,we present a method for ash content detection in coal slime flotation tailings.This method utilizes chromatographic filter paper sampling and a multi-scale residual network,which we refer to as MRCN.Initially,tailings are sampled using chromatographic filter paper to obtain static tailings images,effectively isolating interference factors at the flotation site.Subsequently,the MRCN,consisting of a multi-scale residual network,is employed to extract image features and compute ash content.Within the MRCN structure,tailings images undergo convolution operations through two parallel branches that utilize convolution kernels of different sizes,enabling the extraction of image features at various scales and capturing a more comprehensive representation of the ash content information.Furthermore,a channel attention mechanism is integrated to enhance the performance of the model.The combination of the multi-scale residual structure and the channel attention mechanism within MRCN results in robust capabilities for image feature extraction and ash content detection.Comparative experiments demonstrate that this proposed approach,based on chromatographic filter paper sampling and the multi-scale residual network,exhibits significantly superior performance in the detection of ash content in coal slime flotation tailings.展开更多
Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address ...Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.展开更多
In the burgeoning field of anomaly detection within attributed networks,traditional methodologies often encounter the intricacies of network complexity,particularly in capturing nonlinearity and sparsity.This study in...In the burgeoning field of anomaly detection within attributed networks,traditional methodologies often encounter the intricacies of network complexity,particularly in capturing nonlinearity and sparsity.This study introduces an innovative approach that synergizes the strengths of graph convolutional networks with advanced deep residual learning and a unique residual-based attention mechanism,thereby creating a more nuanced and efficient method for anomaly detection in complex networks.The heart of our model lies in the integration of graph convolutional networks that capture complex structural relationships within the network data.This is further bolstered by deep residual learning,which is employed to model intricate nonlinear connections directly from input data.A pivotal innovation in our approach is the incorporation of a residual-based attention mech-anism.This mechanism dynamically adjusts the importance of nodes based on their residual information,thereby significantly enhancing the sensitivity of the model to subtle anomalies.Furthermore,we introduce a novel hypersphere mapping technique in the latent space to distinctly separate normal and anomalous data.This mapping is the key to our model’s ability to pinpoint anomalies with greater precision.An extensive experimental setup was used to validate the efficacy of the proposed model.Using attributed social network datasets,we demonstrate that our model not only competes with but also surpasses existing state-of-the-art methods in anomaly detection.The results show the exceptional capability of our model to handle the multifaceted nature of real-world networks.展开更多
A control valve is one of the most widely used machines in hydraulic systems.However,it often works in harsh environments and failure occurs from time to time.An intelligent and robust control valve fault diagnosis is...A control valve is one of the most widely used machines in hydraulic systems.However,it often works in harsh environments and failure occurs from time to time.An intelligent and robust control valve fault diagnosis is therefore important for operation of the system.In this study,a fault diagnosis based on the mathematical model(MM)imputation and the modified deep residual shrinkage network(MDRSN)is proposed to solve the problem that data-driven models for control valves are susceptible to changing operating conditions and missing data.The multiple fault time-series samples of the control valve at different openings are collected for fault diagnosis to verify the effectiveness of the proposed method.The effects of the proposed method in missing data imputation and fault diagnosis are analyzed.Compared with random and k-nearest neighbor(KNN)imputation,the accuracies of MM-based imputation are improved by 17.87%and 21.18%,in the circumstances of a20.00%data missing rate at valve opening from 10%to 28%.Furthermore,the results show that the proposed MDRSN can maintain high fault diagnosis accuracy with missing data.展开更多
In this paper,we propose an improved deep residual network model to recognize human actions.Action data is composed of channel state information signals,which are continuous fine-grained signals.We replaced the tradit...In this paper,we propose an improved deep residual network model to recognize human actions.Action data is composed of channel state information signals,which are continuous fine-grained signals.We replaced the traditional identity connection with the shrinking thresholdmodule.Themodule automatically adjusts the threshold of the action data signal,and filters out signals that are not related to the principal components.We use the attention mechanism to improve the memory of the network model to the action signal,so as to better recognize the action.To verify the validity of the experiment more accurately,we collected action data in two different environments.The experimental results show that the improved network model is much better than the traditional network in recognition.The accuracy of recognition in complex places can reach 92.85%,among which the recognition rate of raising hands is up to 96%.We combine the improved residual deep network model with channel state information action data,and prove the effectiveness of our model for classification through experimental data.展开更多
Landslides are common natural hazards occurring in most parts of the world and have considerable adverse economic effects. Residual shear strength of clay is one of the most important factors in the determination of s...Landslides are common natural hazards occurring in most parts of the world and have considerable adverse economic effects. Residual shear strength of clay is one of the most important factors in the determination of stability of slopes or landslides. This effect is more pronounced in sensitive clays which show large changes in shear strength from peak to residual states. This study analyses the prediction of the residual strength of clay based on a new prediction model, functional networks（FN） using data available in the literature. The performance of FN was compared with support vector machine（SVM） and artificial neural network（ANN） based on statistical parameters like correlation coefficient（R）, Nash–Sutcliff coefficient of efficiency（E）, absolute average error（AAE）, maximum average error（MAE） and root mean square error（RMSE）. Based on R and E parameters, FN is found to be a better prediction tool than ANN for the given data. However, the R and E values for FN are less than SVM. A prediction equation is presented that can be used by practicing geotechnical engineers. A sensitivity analysis is carried out to ascertain the importance of various inputs in the prediction of the output.展开更多
To solve the problem of difficulty in identifying apple diseases in the natural environment and the low application rate of deep learning recognition networks,a lightweight ResNet(LW-ResNet)model for apple disease rec...To solve the problem of difficulty in identifying apple diseases in the natural environment and the low application rate of deep learning recognition networks,a lightweight ResNet(LW-ResNet)model for apple disease recognition is proposed.Based on the deep residual network(ResNet18),the multi-scale feature extraction layer is constructed by group convolution to realize the compression model and improve the extraction ability of different sizes of lesion features.By improving the identity mapping structure to reduce information loss.By introducing the efficient channel attention module(ECANet)to suppress noise from a complex background.The experimental results show that the average precision,recall and F1-score of the LW-ResNet on the test set are 97.80%,97.92%and 97.85%,respectively.The parameter memory is 2.32 MB,which is 94%less than that of ResNet18.Compared with the classic lightweight networks SqueezeNet and MobileNetV2,LW-ResNet has obvious advantages in recognition performance,speed,parameter memory requirement and time complexity.The proposed model has the advantages of low computational cost,low storage cost,strong real-time performance,high identification accuracy,and strong practicability,which can meet the needs of real-time identification task of apple leaf disease on resource-constrained devices.展开更多
alient object detection aims at identifying the visually interesting object regions that are consistent with human perception. Multispectral remote sensing images provide rich radiometric information in revealing the ...alient object detection aims at identifying the visually interesting object regions that are consistent with human perception. Multispectral remote sensing images provide rich radiometric information in revealing the physical properties of the observed objects, which leads to great potential to perform salient object detection for remote sensing images. Conventional salient object detection methods often employ handcrafted features to predict saliency by evaluating the pixel-wise or superpixel-wise contrast. With the recent use of deep learning framework, in particular, fully convolutional neural networks, there has been profound progress in visual saliency detection. However, this success has not been extended to multispectral remote sensing images, and existing multispectral salient object detection methods are still mainly based on handcrafted features, essentially due to the difficulties in image acquisition and labeling. In this paper, we propose a novel deep residual network based on a top-down model, which is trained in an end-to-end manner to tackle the above issues in multispectral salient object detection. Our model effectively exploits the saliency cues at different levels of the deep residual network. To overcome the limited availability of remote sensing images in training of our deep residual network, we also introduce a new spectral image reconstruction model that can generate multispectral images from RGB images. Our extensive experimental results using both multispectral and RGB salient object detection datasets demonstrate a significant performance improvement of more than 10% improvement compared with the state-of-the-art methods.展开更多
The steel tube arch rib in a large-span concrete-filled steel tube arch bridge has a large span and diameter,which also leads to a larger weld seam scale.Large-scale welding seams will inevitably cause more obvious we...The steel tube arch rib in a large-span concrete-filled steel tube arch bridge has a large span and diameter,which also leads to a larger weld seam scale.Large-scale welding seams will inevitably cause more obvious welding residual stress(WRS).For the purpose of studying the influence of WRS from large-scale welding seam on the mechanical properties of steel tube arch rib during arch rib splicing,test research and numerical simulation analysis on the WRS in arch rib splicing based on the Guangxi Pingnan Third Bridge,which is the world’s largest span concrete-filled steel tube arch bridge,were conducted in this paper,and the distribution pattern of WRS at the arch rib splicing joint was obtained.Subsequently,the WRS was introduced into the mechanical performance analysis of joints and structures to analyze its effects.The findings reveal that the distribution of WRS in the arch rib is greatly influenced by the rib plate,and the axial WRS in the heat-affected zone are primarily tensile,while the circumferential WRS are distributed in an alternating pattern of tensile and compressive stresses along the circumferential direction of the main tube.Under the influence of WRS,the ultimate bearing capacity of the joint is reduced by 29.4%,the initial axial stiffness is reduced by 4.32%,and the vertical deformation of the arch rib structure is increased by 4.7%.展开更多
Industrial ebullated-bed is an important device for promoting the cleaning and upgrading of oil products. The lumped kinetic model is a powerful tool for predicting the product yield of the ebullated-bed residue hydro...Industrial ebullated-bed is an important device for promoting the cleaning and upgrading of oil products. The lumped kinetic model is a powerful tool for predicting the product yield of the ebullated-bed residue hydrogenation (EBRH) unit, However, during the long-term operation of the device, there are phenomena such as low frequency of material property analysis leading to limited operating data and diverse operating modes at the same time scale, which poses a huge challenge to building an accurate product yield prediction model. To address these challenges, a data augmentation-based eleven lumped reaction kinetics mechanism model was constructed. This model combines generative adversarial networks, outlier elimination, and L2 norm data filtering to expand the dataset and utilizes kernel principal component analysis-fuzzy C-means for operating condition partitioning. Based on the hydrogenation reaction mechanism, a single and sub operating condition eleven lumped reaction kinetics model of an ebullated-bed residue hydrogenation unit, comprising 55 reaction paths and 110 parameters, was constructed before and after data augmentation. Compared to the single model before data enhancement, the average absolute error of the sub-models under data enhancement division was reduced by 23%. Thus, these findings can help guide the operation and optimization of the production process.展开更多
Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportati...Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportation,industry,personal life,and other socio-economic fields.The introduction of deep learning has brought new security challenges,like an increment in abnormal traffic,which threatens network security.Insufficient feature extraction leads to less accurate classification results.In abnormal traffic detection,the data of network traffic is high-dimensional and complex.This data not only increases the computational burden of model training but also makes information extraction more difficult.To address these issues,this paper proposes an MD-MRD-ResNeXt model for abnormal network traffic detection.To fully utilize the multi-scale information in network traffic,a Multi-scale Dilated feature extraction(MD)block is introduced.This module can effectively understand and process information at various scales and uses dilated convolution technology to significantly broaden the model’s receptive field.The proposed Max-feature-map Residual with Dual-channel pooling(MRD)block integrates the maximum feature map with the residual block.This module ensures the model focuses on key information,thereby optimizing computational efficiency and reducing unnecessary information redundancy.Experimental results show that compared to the latest methods,the proposed abnormal traffic detection model improves accuracy by about 2%.展开更多
Based on the Residual Oil Hydrodesulfurization Treatment Unit (S-RHT), the n-order reaction kinetic model for residual oil HDS reactions and artificial neural network (ANN) model were developed to determine the sulfur...Based on the Residual Oil Hydrodesulfurization Treatment Unit (S-RHT), the n-order reaction kinetic model for residual oil HDS reactions and artificial neural network (ANN) model were developed to determine the sulfur content of hydrogenated residual oil. The established ANN model covered 4 input variables, 1 output variable and 1 hidden layer with 15 neurons. The comparison between the results of two models was listed. The results showed that the predicted mean relative errors of the two models with three different sample data were less than 5% and both the two models had good predictive precision and extrapolative feature for the HDS process. The mean relative error of 5 sets of testing data of the ANN model was 1.62%—3.23%, all of which were smaller than that of the common mechanism model (3.47%— 4.13%). It showed that the ANN model was better than the mechanism model both in terms of fitting results and fitting difficulty. The models could be easily applied in practice and could also provide a reference for the further research of residual oil HDS process.展开更多
In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of ea...In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.展开更多
We propose a novel workflow for fast forward modeling of well logs in axially symmetric 2D models of the nearwellbore environment.The approach integrates the finite element method with deep residual neural networks to...We propose a novel workflow for fast forward modeling of well logs in axially symmetric 2D models of the nearwellbore environment.The approach integrates the finite element method with deep residual neural networks to achieve exceptional computational efficiency and accuracy.The workflow is demonstrated through the modeling of wireline electromagnetic propagation resistivity logs,where the measured responses exhibit a highly nonlinear relationship with formation properties.The motivation for this research is the need for advanced modeling al-gorithms that are fast enough for use in modern quantitative interpretation tools,where thousands of simulations may be required in iterative inversion processes.The proposed algorithm achieves a remarkable enhancement in performance,being up to 3000 times faster than the finite element method alone when utilizing a GPU.While still ensuring high accuracy,this makes it well-suited for practical applications when reliable payzone assessment is needed in complex environmental scenarios.Furthermore,the algorithm’s efficiency positions it as a promising tool for stochastic Bayesian inversion,facilitating reliable uncertainty quantification in subsurface property estimation.展开更多
Hydrologic models generally represent the most dominant processes since they are mere simplifications of physical reality and thus are subject to many significant uncertainties. As such, a coupling strategy is propose...Hydrologic models generally represent the most dominant processes since they are mere simplifications of physical reality and thus are subject to many significant uncertainties. As such, a coupling strategy is proposed. To this end, the coupling of the artificial neural network （ANN） with the Xin＇anjiang conceptual model with a view to enhance the quality of its flow forecast is presented. The approach uses the latest observations and residuals in runoff/discharge forecasts from the Xin＇anjiang model. The two complementary models （Xin＇anjiang ＆ ANN） are used in such a way that residuals of the Xin＇anjiang model are forecasted by a neural network model so that flow forecasts can be improved as new observations come in. For the complementary neural network, the input data were presented in a patterned format to conform to the calibration regime of the Xin＇anjiang conceptual model, using differing variants of the neural network scheme. The results show that there is a substantial improvement in the accuracy of the forecasts when the complementary model was operated on top of the Xin＇anjiang conceptual model as compared with the results of the Xin＇anjiang model alone.展开更多
With the widespread application of deep learning in the field of computer vision,gradually allowing medical image technology to assist doctors in making diagnoses has great practical and research significance.Aiming a...With the widespread application of deep learning in the field of computer vision,gradually allowing medical image technology to assist doctors in making diagnoses has great practical and research significance.Aiming at the shortcomings of the traditional U-Net model in 3D spatial information extraction,model over-fitting,and low degree of semantic information fusion,an improved medical image segmentation model has been used to achieve more accurate segmentation of medical images.In this model,we make full use of the residual network(ResNet)to solve the over-fitting problem.In order to process and aggregate data at different scales,the inception network is used instead of the traditional convolutional layer,and the dilated convolution is used to increase the receptive field.The conditional random field(CRF)can complete the contour refinement work.Compared with the traditional 3D U-Net network,the segmentation accuracy of the improved liver and tumor images increases by 2.89%and 7.66%,respectively.As a part of the image processing process,the method in this paper not only can be used for medical image segmentation,but also can lay the foundation for subsequent image 3D reconstruction work.展开更多
The background pattern of patterned fabrics is complex,which has a great interference in the extraction of defect features.Traditional machine vision algorithms rely on artificially designed features,which are greatly...The background pattern of patterned fabrics is complex,which has a great interference in the extraction of defect features.Traditional machine vision algorithms rely on artificially designed features,which are greatly affected by background patterns and are difficult to effectively extract flaw features.Therefore,a convolutional neural network(CNN)with automatic feature extraction is proposed.On the basis of the two-stage detection model Faster R-CNN,Resnet-50 is used as the backbone network,and the problem of flaws with extreme aspect ratio is solved by improving the initialization algorithm of the prior frame aspect ratio,and the improved multi-scale model is designed to improve detection of small defects.The cascade R-CNN is introduced to improve the accuracy of defect detection,and the online hard example mining(OHEM)algorithm is used to strengthen the learning of hard samples to reduce the interference of complex backgrounds on the defect detection of patterned fabrics,and construct the focal loss as a loss function to reduce the impact of sample imbalance.In order to verify the effectiveness of the improved algorithm,a defect detection comparison experiment was set up.The experimental results show that the accuracy of the defect detection algorithm of patterned fabrics in this paper can reach 95.7%,and it can accurately locate the defect location and meet the actual needs of the factory.展开更多
基金funded by State Key Laboratory for GeoMechanics and Deep Underground Engineering&Institute for Deep Underground Science and Engineering,Grant Number XD2021021BUCEA Post Graduate Innovation Project under Grant,Grant Number PG2023092.
文摘Rockburst is a phenomenon in which free surfaces are formed during excavation,which subsequently causes the sudden release of energy in the construction of mines and tunnels.Light rockburst only peels off rock slices without ejection,while severe rockburst causes casualties and property loss.The frequency and degree of rockburst damage increases with the excavation depth.Moreover,rockburst is the leading engineering geological hazard in the excavation process,and thus the prediction of its intensity grade is of great significance to the development of geotechnical engineering.Therefore,the prediction of rockburst intensity grade is one problem that needs to be solved urgently.By comprehensively considering the occurrence mechanism of rockburst,this paper selects the stress index(σθ/σc),brittleness index(σ_(c)/σ_(t)),and rock elastic energy index(Wet)as the rockburst evaluation indexes through the Spearman coefficient method.This overcomes the low accuracy problem of a single evaluation index prediction method.Following this,the BGD-MSR-DNN rockburst intensity grade prediction model based on batch gradient descent and a multi-scale residual deep neural network is proposed.The batch gradient descent(BGD)module is used to replace the gradient descent algorithm,which effectively improves the efficiency of the network and reduces the model training time.Moreover,the multi-scale residual(MSR)module solves the problem of network degradation when there are too many hidden layers of the deep neural network(DNN),thus improving the model prediction accuracy.The experimental results reveal the BGDMSR-DNN model accuracy to reach 97.1%,outperforming other comparable models.Finally,actual projects such as Qinling Tunnel and Daxiangling Tunnel,reached an accuracy of 100%.The model can be applied in mines and tunnel engineering to realize the accurate and rapid prediction of rockburst intensity grade.
基金This work was supported by National Natural Science Foundation of China:Grant No.62106048.
文摘The detection of ash content in coal slime flotation tailings using deep learning can be hindered by various factors such as foam,impurities,and changing lighting conditions that disrupt the collection of tailings images.To address this challenge,we present a method for ash content detection in coal slime flotation tailings.This method utilizes chromatographic filter paper sampling and a multi-scale residual network,which we refer to as MRCN.Initially,tailings are sampled using chromatographic filter paper to obtain static tailings images,effectively isolating interference factors at the flotation site.Subsequently,the MRCN,consisting of a multi-scale residual network,is employed to extract image features and compute ash content.Within the MRCN structure,tailings images undergo convolution operations through two parallel branches that utilize convolution kernels of different sizes,enabling the extraction of image features at various scales and capturing a more comprehensive representation of the ash content information.Furthermore,a channel attention mechanism is integrated to enhance the performance of the model.The combination of the multi-scale residual structure and the channel attention mechanism within MRCN results in robust capabilities for image feature extraction and ash content detection.Comparative experiments demonstrate that this proposed approach,based on chromatographic filter paper sampling and the multi-scale residual network,exhibits significantly superior performance in the detection of ash content in coal slime flotation tailings.
基金supported by the National Natural Science Foundation of China(Grant Nos.62472149,62376089,62202147)Hubei Provincial Science and Technology Plan Project(2023BCB04100).
文摘Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.
文摘In the burgeoning field of anomaly detection within attributed networks,traditional methodologies often encounter the intricacies of network complexity,particularly in capturing nonlinearity and sparsity.This study introduces an innovative approach that synergizes the strengths of graph convolutional networks with advanced deep residual learning and a unique residual-based attention mechanism,thereby creating a more nuanced and efficient method for anomaly detection in complex networks.The heart of our model lies in the integration of graph convolutional networks that capture complex structural relationships within the network data.This is further bolstered by deep residual learning,which is employed to model intricate nonlinear connections directly from input data.A pivotal innovation in our approach is the incorporation of a residual-based attention mech-anism.This mechanism dynamically adjusts the importance of nodes based on their residual information,thereby significantly enhancing the sensitivity of the model to subtle anomalies.Furthermore,we introduce a novel hypersphere mapping technique in the latent space to distinctly separate normal and anomalous data.This mapping is the key to our model’s ability to pinpoint anomalies with greater precision.An extensive experimental setup was used to validate the efficacy of the proposed model.Using attributed social network datasets,we demonstrate that our model not only competes with but also surpasses existing state-of-the-art methods in anomaly detection.The results show the exceptional capability of our model to handle the multifaceted nature of real-world networks.
基金supported by the National Natural Science Foundation of China(No.51875113)the Natural Science Joint Guidance Foundation of the Heilongjiang Province of China(No.LH2019E027)the PhD Student Research and Innovation Fund of the Fundamental Research Funds for the Central Universities(No.XK2070021009),China。
文摘A control valve is one of the most widely used machines in hydraulic systems.However,it often works in harsh environments and failure occurs from time to time.An intelligent and robust control valve fault diagnosis is therefore important for operation of the system.In this study,a fault diagnosis based on the mathematical model(MM)imputation and the modified deep residual shrinkage network(MDRSN)is proposed to solve the problem that data-driven models for control valves are susceptible to changing operating conditions and missing data.The multiple fault time-series samples of the control valve at different openings are collected for fault diagnosis to verify the effectiveness of the proposed method.The effects of the proposed method in missing data imputation and fault diagnosis are analyzed.Compared with random and k-nearest neighbor(KNN)imputation,the accuracies of MM-based imputation are improved by 17.87%and 21.18%,in the circumstances of a20.00%data missing rate at valve opening from 10%to 28%.Furthermore,the results show that the proposed MDRSN can maintain high fault diagnosis accuracy with missing data.
基金This work was supported by Innovation Capability Support Program of Shaanxi(Program No.2018TD-016)Key Research and Development Program of Shaanxi(Program No.2019ZDLSF02-09-02).
文摘In this paper,we propose an improved deep residual network model to recognize human actions.Action data is composed of channel state information signals,which are continuous fine-grained signals.We replaced the traditional identity connection with the shrinking thresholdmodule.Themodule automatically adjusts the threshold of the action data signal,and filters out signals that are not related to the principal components.We use the attention mechanism to improve the memory of the network model to the action signal,so as to better recognize the action.To verify the validity of the experiment more accurately,we collected action data in two different environments.The experimental results show that the improved network model is much better than the traditional network in recognition.The accuracy of recognition in complex places can reach 92.85%,among which the recognition rate of raising hands is up to 96%.We combine the improved residual deep network model with channel state information action data,and prove the effectiveness of our model for classification through experimental data.
文摘Landslides are common natural hazards occurring in most parts of the world and have considerable adverse economic effects. Residual shear strength of clay is one of the most important factors in the determination of stability of slopes or landslides. This effect is more pronounced in sensitive clays which show large changes in shear strength from peak to residual states. This study analyses the prediction of the residual strength of clay based on a new prediction model, functional networks（FN） using data available in the literature. The performance of FN was compared with support vector machine（SVM） and artificial neural network（ANN） based on statistical parameters like correlation coefficient（R）, Nash–Sutcliff coefficient of efficiency（E）, absolute average error（AAE）, maximum average error（MAE） and root mean square error（RMSE）. Based on R and E parameters, FN is found to be a better prediction tool than ANN for the given data. However, the R and E values for FN are less than SVM. A prediction equation is presented that can be used by practicing geotechnical engineers. A sensitivity analysis is carried out to ascertain the importance of various inputs in the prediction of the output.
基金funded by the Science and Technology Development Program of Jilin Province(20190301024NY)the Precision Agriculture and Big Data Engineering Research Center of Jilin Province(2020C005).
文摘To solve the problem of difficulty in identifying apple diseases in the natural environment and the low application rate of deep learning recognition networks,a lightweight ResNet(LW-ResNet)model for apple disease recognition is proposed.Based on the deep residual network(ResNet18),the multi-scale feature extraction layer is constructed by group convolution to realize the compression model and improve the extraction ability of different sizes of lesion features.By improving the identity mapping structure to reduce information loss.By introducing the efficient channel attention module(ECANet)to suppress noise from a complex background.The experimental results show that the average precision,recall and F1-score of the LW-ResNet on the test set are 97.80%,97.92%and 97.85%,respectively.The parameter memory is 2.32 MB,which is 94%less than that of ResNet18.Compared with the classic lightweight networks SqueezeNet and MobileNetV2,LW-ResNet has obvious advantages in recognition performance,speed,parameter memory requirement and time complexity.The proposed model has the advantages of low computational cost,low storage cost,strong real-time performance,high identification accuracy,and strong practicability,which can meet the needs of real-time identification task of apple leaf disease on resource-constrained devices.
基金National 1000 Young Talents Plan of ChinaNational Natural Science Foundation of China(61420106007,61671387,61871325)DECRA of Australica Resenrch Council (DE140100180).
文摘alient object detection aims at identifying the visually interesting object regions that are consistent with human perception. Multispectral remote sensing images provide rich radiometric information in revealing the physical properties of the observed objects, which leads to great potential to perform salient object detection for remote sensing images. Conventional salient object detection methods often employ handcrafted features to predict saliency by evaluating the pixel-wise or superpixel-wise contrast. With the recent use of deep learning framework, in particular, fully convolutional neural networks, there has been profound progress in visual saliency detection. However, this success has not been extended to multispectral remote sensing images, and existing multispectral salient object detection methods are still mainly based on handcrafted features, essentially due to the difficulties in image acquisition and labeling. In this paper, we propose a novel deep residual network based on a top-down model, which is trained in an end-to-end manner to tackle the above issues in multispectral salient object detection. Our model effectively exploits the saliency cues at different levels of the deep residual network. To overcome the limited availability of remote sensing images in training of our deep residual network, we also introduce a new spectral image reconstruction model that can generate multispectral images from RGB images. Our extensive experimental results using both multispectral and RGB salient object detection datasets demonstrate a significant performance improvement of more than 10% improvement compared with the state-of-the-art methods.
基金funded by the Science and Technology Research Program of the Chongqing Municipal Education Commission(grant number KJQN202403002).
文摘The steel tube arch rib in a large-span concrete-filled steel tube arch bridge has a large span and diameter,which also leads to a larger weld seam scale.Large-scale welding seams will inevitably cause more obvious welding residual stress(WRS).For the purpose of studying the influence of WRS from large-scale welding seam on the mechanical properties of steel tube arch rib during arch rib splicing,test research and numerical simulation analysis on the WRS in arch rib splicing based on the Guangxi Pingnan Third Bridge,which is the world’s largest span concrete-filled steel tube arch bridge,were conducted in this paper,and the distribution pattern of WRS at the arch rib splicing joint was obtained.Subsequently,the WRS was introduced into the mechanical performance analysis of joints and structures to analyze its effects.The findings reveal that the distribution of WRS in the arch rib is greatly influenced by the rib plate,and the axial WRS in the heat-affected zone are primarily tensile,while the circumferential WRS are distributed in an alternating pattern of tensile and compressive stresses along the circumferential direction of the main tube.Under the influence of WRS,the ultimate bearing capacity of the joint is reduced by 29.4%,the initial axial stiffness is reduced by 4.32%,and the vertical deformation of the arch rib structure is increased by 4.7%.
基金supported by National Natural Science Foundation of China(Basic Science Center Program:61988101)National Natural Science Foundation of China(62394345,62373155,62173147)the Major Science and Technology Project of Xinjiang(No.2022A01006-4).
文摘Industrial ebullated-bed is an important device for promoting the cleaning and upgrading of oil products. The lumped kinetic model is a powerful tool for predicting the product yield of the ebullated-bed residue hydrogenation (EBRH) unit, However, during the long-term operation of the device, there are phenomena such as low frequency of material property analysis leading to limited operating data and diverse operating modes at the same time scale, which poses a huge challenge to building an accurate product yield prediction model. To address these challenges, a data augmentation-based eleven lumped reaction kinetics mechanism model was constructed. This model combines generative adversarial networks, outlier elimination, and L2 norm data filtering to expand the dataset and utilizes kernel principal component analysis-fuzzy C-means for operating condition partitioning. Based on the hydrogenation reaction mechanism, a single and sub operating condition eleven lumped reaction kinetics model of an ebullated-bed residue hydrogenation unit, comprising 55 reaction paths and 110 parameters, was constructed before and after data augmentation. Compared to the single model before data enhancement, the average absolute error of the sub-models under data enhancement division was reduced by 23%. Thus, these findings can help guide the operation and optimization of the production process.
基金supported by the Key Research and Development Program of Xinjiang Uygur Autonomous Region(No.2022B01008)the National Natural Science Foundation of China(No.62363032)+4 种基金the Natural Science Foundation of Xinjiang Uygur Autonomous Region(No.2023D01C20)the Scientific Research Foundation of Higher Education(No.XJEDU2022P011)National Science and Technology Major Project(No.2022ZD0115803)Tianshan Innovation Team Program of Xinjiang Uygur Autonomous Region(No.2023D14012)the“Heaven Lake Doctor”Project(No.202104120018).
文摘Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportation,industry,personal life,and other socio-economic fields.The introduction of deep learning has brought new security challenges,like an increment in abnormal traffic,which threatens network security.Insufficient feature extraction leads to less accurate classification results.In abnormal traffic detection,the data of network traffic is high-dimensional and complex.This data not only increases the computational burden of model training but also makes information extraction more difficult.To address these issues,this paper proposes an MD-MRD-ResNeXt model for abnormal network traffic detection.To fully utilize the multi-scale information in network traffic,a Multi-scale Dilated feature extraction(MD)block is introduced.This module can effectively understand and process information at various scales and uses dilated convolution technology to significantly broaden the model’s receptive field.The proposed Max-feature-map Residual with Dual-channel pooling(MRD)block integrates the maximum feature map with the residual block.This module ensures the model focuses on key information,thereby optimizing computational efficiency and reducing unnecessary information redundancy.Experimental results show that compared to the latest methods,the proposed abnormal traffic detection model improves accuracy by about 2%.
文摘Based on the Residual Oil Hydrodesulfurization Treatment Unit (S-RHT), the n-order reaction kinetic model for residual oil HDS reactions and artificial neural network (ANN) model were developed to determine the sulfur content of hydrogenated residual oil. The established ANN model covered 4 input variables, 1 output variable and 1 hidden layer with 15 neurons. The comparison between the results of two models was listed. The results showed that the predicted mean relative errors of the two models with three different sample data were less than 5% and both the two models had good predictive precision and extrapolative feature for the HDS process. The mean relative error of 5 sets of testing data of the ANN model was 1.62%—3.23%, all of which were smaller than that of the common mechanism model (3.47%— 4.13%). It showed that the ANN model was better than the mechanism model both in terms of fitting results and fitting difficulty. The models could be easily applied in practice and could also provide a reference for the further research of residual oil HDS process.
文摘In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.
基金financially supported by the Russian federal research project No.FWZZ-2022-0026“Innovative aspects of electro-dynamics in problems of exploration and oilfield geophysics”.
文摘We propose a novel workflow for fast forward modeling of well logs in axially symmetric 2D models of the nearwellbore environment.The approach integrates the finite element method with deep residual neural networks to achieve exceptional computational efficiency and accuracy.The workflow is demonstrated through the modeling of wireline electromagnetic propagation resistivity logs,where the measured responses exhibit a highly nonlinear relationship with formation properties.The motivation for this research is the need for advanced modeling al-gorithms that are fast enough for use in modern quantitative interpretation tools,where thousands of simulations may be required in iterative inversion processes.The proposed algorithm achieves a remarkable enhancement in performance,being up to 3000 times faster than the finite element method alone when utilizing a GPU.While still ensuring high accuracy,this makes it well-suited for practical applications when reliable payzone assessment is needed in complex environmental scenarios.Furthermore,the algorithm’s efficiency positions it as a promising tool for stochastic Bayesian inversion,facilitating reliable uncertainty quantification in subsurface property estimation.
文摘Hydrologic models generally represent the most dominant processes since they are mere simplifications of physical reality and thus are subject to many significant uncertainties. As such, a coupling strategy is proposed. To this end, the coupling of the artificial neural network （ANN） with the Xin＇anjiang conceptual model with a view to enhance the quality of its flow forecast is presented. The approach uses the latest observations and residuals in runoff/discharge forecasts from the Xin＇anjiang model. The two complementary models （Xin＇anjiang ＆ ANN） are used in such a way that residuals of the Xin＇anjiang model are forecasted by a neural network model so that flow forecasts can be improved as new observations come in. For the complementary neural network, the input data were presented in a patterned format to conform to the calibration regime of the Xin＇anjiang conceptual model, using differing variants of the neural network scheme. The results show that there is a substantial improvement in the accuracy of the forecasts when the complementary model was operated on top of the Xin＇anjiang conceptual model as compared with the results of the Xin＇anjiang model alone.
文摘With the widespread application of deep learning in the field of computer vision,gradually allowing medical image technology to assist doctors in making diagnoses has great practical and research significance.Aiming at the shortcomings of the traditional U-Net model in 3D spatial information extraction,model over-fitting,and low degree of semantic information fusion,an improved medical image segmentation model has been used to achieve more accurate segmentation of medical images.In this model,we make full use of the residual network(ResNet)to solve the over-fitting problem.In order to process and aggregate data at different scales,the inception network is used instead of the traditional convolutional layer,and the dilated convolution is used to increase the receptive field.The conditional random field(CRF)can complete the contour refinement work.Compared with the traditional 3D U-Net network,the segmentation accuracy of the improved liver and tumor images increases by 2.89%and 7.66%,respectively.As a part of the image processing process,the method in this paper not only can be used for medical image segmentation,but also can lay the foundation for subsequent image 3D reconstruction work.
基金National Key Research and Development Project,China(No.2018YFB1308800)。
文摘The background pattern of patterned fabrics is complex,which has a great interference in the extraction of defect features.Traditional machine vision algorithms rely on artificially designed features,which are greatly affected by background patterns and are difficult to effectively extract flaw features.Therefore,a convolutional neural network(CNN)with automatic feature extraction is proposed.On the basis of the two-stage detection model Faster R-CNN,Resnet-50 is used as the backbone network,and the problem of flaws with extreme aspect ratio is solved by improving the initialization algorithm of the prior frame aspect ratio,and the improved multi-scale model is designed to improve detection of small defects.The cascade R-CNN is introduced to improve the accuracy of defect detection,and the online hard example mining(OHEM)algorithm is used to strengthen the learning of hard samples to reduce the interference of complex backgrounds on the defect detection of patterned fabrics,and construct the focal loss as a loss function to reduce the impact of sample imbalance.In order to verify the effectiveness of the improved algorithm,a defect detection comparison experiment was set up.The experimental results show that the accuracy of the defect detection algorithm of patterned fabrics in this paper can reach 95.7%,and it can accurately locate the defect location and meet the actual needs of the factory.
