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
Currently,deep convolutional neural networks have made great progress in the field of semantic segmentation.Because of the fixed convolution kernel geometry,standard convolution neural networks have been limited the a...Currently,deep convolutional neural networks have made great progress in the field of semantic segmentation.Because of the fixed convolution kernel geometry,standard convolution neural networks have been limited the ability to simulate geometric transformations.Therefore,a deformable convolution is introduced to enhance the adaptability of convolutional networks to spatial transformation.Considering that the deep convolutional neural networks cannot adequately segment the local objects at the output layer due to using the pooling layers in neural network architecture.To overcome this shortcoming,the rough prediction segmentation results of the neural network output layer will be processed by fully connected conditional random fields to improve the ability of image segmentation.The proposed method can easily be trained by end-to-end using standard backpropagation algorithms.Finally,the proposed method is tested on the ISPRS dataset.The results show that the proposed method can effectively overcome the influence of the complex structure of the segmentation object and obtain state-of-the-art accuracy on the ISPRS Vaihingen 2D semantic labeling dataset.展开更多
In the textile industry,the presence of defects on the surface of fabric is an essential factor in determining fabric quality.Therefore,identifying fabric defects forms a crucial part of the fabric production process....In the textile industry,the presence of defects on the surface of fabric is an essential factor in determining fabric quality.Therefore,identifying fabric defects forms a crucial part of the fabric production process.Traditional fabric defect detection algorithms can only detect specific materials and specific fabric defect types;in addition,their detection efficiency is low,and their detection results are relatively poor.Deep learning-based methods have many advantages in the field of fabric defect detection,however,such methods are less effective in identifying multiscale fabric defects and defects with complex shapes.Therefore,we propose an effective algorithm,namely multilayer feature extraction combined with deformable convolution(MFDC),for fabric defect detection.In MFDC,multi-layer feature extraction is used to fuse the underlying location features with high-level classification features through a horizontally connected top-down architecture to improve the detection of multi-scale fabric defects.On this basis,a deformable convolution is added to solve the problem of the algorithm’s weak detection ability of irregularly shaped fabric defects.In this approach,Roi Align and Cascade-RCNN are integrated to enhance the adaptability of the algorithm in materials with complex patterned backgrounds.The experimental results show that the MFDC algorithm can achieve good detection results for both multi-scale fabric defects and defects with complex shapes,at the expense of a small increase in detection time.展开更多
Electrocardiogram (ECG) analysis is critical for detecting arrhythmias, but traditional methods struggle with large-scale Electrocardiogram data and rare arrhythmia events in imbalanced datasets. These methods fail to...Electrocardiogram (ECG) analysis is critical for detecting arrhythmias, but traditional methods struggle with large-scale Electrocardiogram data and rare arrhythmia events in imbalanced datasets. These methods fail to perform multi-perspective learning of temporal signals and Electrocardiogram images, nor can they fully extract the latent information within the data, falling short of the accuracy required by clinicians. Therefore, this paper proposes an innovative hybrid multimodal spatiotemporal neural network to address these challenges. The model employs a multimodal data augmentation framework integrating visual and signal-based features to enhance the classification performance of rare arrhythmias in imbalanced datasets. Additionally, the spatiotemporal fusion module incorporates a spatiotemporal graph convolutional network to jointly model temporal and spatial features, uncovering complex dependencies within the Electrocardiogram data and improving the model’s ability to represent complex patterns. In experiments conducted on the MIT-BIH arrhythmia dataset, the model achieved 99.95% accuracy, 99.80% recall, and a 99.78% F1 score. The model was further validated for generalization using the clinical INCART arrhythmia dataset, and the results demonstrated its effectiveness in terms of both generalization and robustness.展开更多
Traffic flow prediction is a crucial element of intelligent transportation systems.However,accu-rate traffic flow prediction is quite challenging because of its highly nonlinear,complex,and dynam-ic characteristics.To...Traffic flow prediction is a crucial element of intelligent transportation systems.However,accu-rate traffic flow prediction is quite challenging because of its highly nonlinear,complex,and dynam-ic characteristics.To address the difficulties in simultaneously capturing local and global dynamic spatiotemporal correlations in traffic flow,as well as the high time complexity of existing models,a multi-head flow attention-based local-global dynamic hypergraph convolution(MFA-LGDHC)pre-diction model is proposed.which consists of multi-head flow attention(MHFA)mechanism,graph convolution network(GCN),and local-global dynamic hypergraph convolution(LGHC).MHFA is utilized to extract the time dependency of traffic flow and reduce the time complexity of the model.GCN is employed to catch the spatial dependency of traffic flow.LGHC utilizes down-sampling con-volution and isometric convolution to capture the local and global spatial dependencies of traffic flow.And dynamic hypergraph convolution is used to model the dynamic higher-order relationships of the traffic road network.Experimental results indicate that the MFA-LGDHC model outperforms current popular baseline models and exhibits good prediction performance.展开更多
This paper presents CW-HRNet,a high-resolution,lightweight crack segmentation network designed to address challenges in complex scenes with slender,deformable,and blurred crack structures.The model incorporates two ke...This paper presents CW-HRNet,a high-resolution,lightweight crack segmentation network designed to address challenges in complex scenes with slender,deformable,and blurred crack structures.The model incorporates two key modules:Constrained Deformable Convolution(CDC),which stabilizes geometric alignment by applying a tanh limiter and learnable scaling factor to the predicted offsets,and the Wavelet Frequency Enhancement Module(WFEM),which decomposes features using Haar wavelets to preserve low-frequency structures while enhancing high-frequency boundaries and textures.Evaluations on the CrackSeg9k benchmark demonstrate CW-HRNet’s superior performance,achieving 82.39%mIoU with only 7.49M parameters and 10.34 GFLOPs,outperforming HrSegNet-B48 by 1.83% in segmentation accuracy with minimal complexity overhead.The model also shows strong cross-dataset generalization,achieving 60.01%mIoU and 66.22%F1 on Asphalt3k without fine-tuning.These results highlight CW-HRNet’s favorable accuracyefficiency trade-off for real-world crack segmentation tasks.展开更多
Accurate vehicle detection is essential for autonomous driving,traffic monitoring,and intelligent transportation systems.This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module,Convolutional B...Accurate vehicle detection is essential for autonomous driving,traffic monitoring,and intelligent transportation systems.This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module,Convolutional Block Attention Module(CBAM),and Deformable Convolutional Networks v2(DCNv2).The Ghost Module streamlines feature generation to reduce redundancy,CBAM applies channel and spatial attention to improve feature focus,and DCNv2 enables adaptability to geometric variations in vehicle shapes.These components work together to improve both accuracy and computational efficiency.Evaluated on the KITTI dataset,the proposed model achieves 95.4%mAP@0.5—an 8.97% gain over standard YOLOv8n—along with 96.2% precision,93.7% recall,and a 94.93%F1-score.Comparative analysis with seven state-of-the-art detectors demonstrates consistent superiority in key performance metrics.An ablation study is also conducted to quantify the individual and combined contributions of GhostModule,CBAM,and DCNv2,highlighting their effectiveness in improving detection performance.By addressing feature redundancy,attention refinement,and spatial adaptability,the proposed model offers a robust and scalable solution for vehicle detection across diverse traffic scenarios.展开更多
In this paper,an improved spatio-temporal alignment measurement method is presented to address the inertial matching measurement of hull deformation under the coexistence of time delay and large misalignment angle.Lar...In this paper,an improved spatio-temporal alignment measurement method is presented to address the inertial matching measurement of hull deformation under the coexistence of time delay and large misalignment angle.Large misalignment angle and time delay often occur simultaneously and bring great challenges to the accurate measurement of hull deformation in space and time.The proposed method utilizes coarse alignment with large misalignment angle and time delay estimation of inertial measurement unit modeling to establish a brand-new spatiotemporal aligned hull deformation measurement model.In addition,two-step loop control is designed to ensure the accurate description of dynamic deformation angle and static deformation angle by the time-space alignment method of hull deformation.The experiments illustrate that the proposed method can effectively measure the hull deformation angle when time delay and large misalignment angle coexist.展开更多
Although the Convolutional Neural Network(CNN)has shown great potential for land cover classification,the frequently used single-scale convolution kernel limits the scope of informa-tion extraction.Therefore,we propos...Although the Convolutional Neural Network(CNN)has shown great potential for land cover classification,the frequently used single-scale convolution kernel limits the scope of informa-tion extraction.Therefore,we propose a Multi-Scale Fully Convolutional Network(MSFCN)with a multi-scale convolutional kernel as well as a Channel Attention Block(CAB)and a Global Pooling Module(GPM)in this paper to exploit discriminative representations from two-dimensional(2D)satellite images.Meanwhile,to explore the ability of the proposed MSFCN for spatio-temporal images,we expand our MSFCN to three-dimension using three-dimensional(3D)CNN,capable of harnessing each land cover category’s time series interac-tion from the reshaped spatio-temporal remote sensing images.To verify the effectiveness of the proposed MSFCN,we conduct experiments on two spatial datasets and two spatio-temporal datasets.The proposed MSFCN achieves 60.366%on the WHDLD dataset and 75.127%on the GID dataset in terms of mIoU index while the figures for two spatio-temporal datasets are 87.753%and 77.156%.Extensive comparative experiments and abla-tion studies demonstrate the effectiveness of the proposed MSFCN.展开更多
Health monitoring of electro-mechanical actuator(EMA)is critical to ensure the security of airplanes.It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA.The autoenc...Health monitoring of electro-mechanical actuator(EMA)is critical to ensure the security of airplanes.It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA.The autoencoder based on reconstruction loss is a popular model that can carry out anomaly detection with only consideration of normal training data,while it fails to capture spatio-temporal information from multivariate time series signals of multiple monitoring sensors.To mine the spatio-temporal information from multivariate time series signals,this paper proposes an attention graph stacked autoencoder for EMA anomaly detection.Firstly,attention graph con-volution is introduced into autoencoder to convolve temporal information from neighbor features to current features based on different weight attentions.Secondly,stacked autoencoder is applied to mine spatial information from those new aggregated temporal features.Finally,based on the bench-mark reconstruction loss of normal training data,different health thresholds calculated by several statistic indicators can carry out anomaly detection for new testing data.In comparison with tra-ditional stacked autoencoder,the proposed model could obtain higher fault detection rate and lower false alarm rate in EMA anomaly detection experiment.展开更多
Deformable medical image registration plays a vital role in medical image applications,such as placing different temporal images at the same time point or different modality images into the same coordinate system.Vari...Deformable medical image registration plays a vital role in medical image applications,such as placing different temporal images at the same time point or different modality images into the same coordinate system.Various strategies have been developed to satisfy the increasing needs of deformable medical image registration.One popular registration method is estimating the displacement field by computing the optical flow between two images.The motion field(flow field)is computed based on either gray-value or handcrafted descriptors such as the scale-invariant feature transform(SIFT).These methods assume that illumination is constant between images.However,medical images may not always satisfy this assumption.In this study,we propose a metric learning-based motion estimation method called Siamese Flow for deformable medical image registration.We train metric learners using a Siamese network,which produces an image patch descriptor that guarantees a smaller feature distance in two similar anatomical structures and a larger feature distance in two dissimilar anatomical structures.In the proposed registration framework,the flow field is computed based on such features and is close to the real deformation field due to the excellent feature representation ability of the Siamese network.Experimental results demonstrate that the proposed method outperforms the Demons,SIFT Flow,Elastix,and VoxelMorph networks regarding registration accuracy and robustness,particularly with large deformations.展开更多
The intensive application of deep learning in medical image processing has facilitated the advancement of automatic retinal vessel segmentation research.To overcome the limitation that traditional U-shaped vessel segm...The intensive application of deep learning in medical image processing has facilitated the advancement of automatic retinal vessel segmentation research.To overcome the limitation that traditional U-shaped vessel segmentation networks fail to extract features in fundus image sufficiently,we propose a novel network(DSeU-net)based on deformable convolution and squeeze excitation residual module.The deformable convolution is utilized to dynamically adjust the receptive field for the feature extraction of retinal vessel.And the squeeze excitation residual module is used to scale the weights of the low-level features so that the network learns the complex relationships of the different feature layers efficiently.We validate the DSeU-net on three public retinal vessel segmentation datasets including DRIVE,CHASEDB1,and STARE,and the experimental results demonstrate the satisfactory segmentation performance of the network.展开更多
Background Exploring correspondences across multiview images is the basis of various computer vision tasks.However,most existing methods have limited accuracy under challenging conditions.Method To learn more robust a...Background Exploring correspondences across multiview images is the basis of various computer vision tasks.However,most existing methods have limited accuracy under challenging conditions.Method To learn more robust and accurate correspondences,we propose DSD-MatchingNet for local feature matching in this study.First,we develop a deformable feature extraction module to obtain multilevel feature maps,which harvest contextual information from dynamic receptive fields.The dynamic receptive fields provided by the deformable convolution network ensure that our method obtains dense and robust correspondence.Second,we utilize sparse-to-dense matching with symmetry of correspondence to implement accurate pixel-level matching,which enables our method to produce more accurate correspondences.Result Experiments show that our proposed DSD-MatchingNet achieves a better performance on the image matching benchmark,as well as on the visual localization benchmark.Specifically,our method achieved 91.3%mean matching accuracy on the HPatches dataset and 99.3%visual localization recalls on the Aachen Day-Night dataset.展开更多
With the advent of deep learning,various deep neural network architectures have been proposed to capture the complex spatio-temporal dependencies in traffic data.This paper introduces a novel Deep Bi-directional Adapt...With the advent of deep learning,various deep neural network architectures have been proposed to capture the complex spatio-temporal dependencies in traffic data.This paper introduces a novel Deep Bi-directional Adaptive Gating Graph Convolutional Network(DBAG-GCN)model for spatio-temporal traffic forecasting.The proposed model leverages the power of graph convolutional networks to capture the spatial dependencies in the road network topology and incorporates bi-directional gating mechanisms to control the information flow adaptively.Furthermore,we introduce a multi-scale temporal convolution module to capture multi-scale temporal dynamics and a contextual attention mechanism to integrate external factors such as weather conditions and event information.Extensive experiments on real-world traffic datasets demonstrate the superior performance of DBAG-GCN compared to state-of-the-art baselines,achieving significant improvements in prediction accuracy and computational efficiency.The DBAG-GCN model provides a powerful and flexible framework for spatio-temporal traffic forecasting,paving the way for intelligent transportation management and urban planning.展开更多
Two actual rocks drilled from a typical ultra-deep hydrocarbon reservoir in the Tarim Basin are selected to conduct in-situ stress-loading micro-focus CT scanning experiments.The gray images of rock microstructure at ...Two actual rocks drilled from a typical ultra-deep hydrocarbon reservoir in the Tarim Basin are selected to conduct in-situ stress-loading micro-focus CT scanning experiments.The gray images of rock microstructure at different stress loading stages are obtained.The U-Net fully convolutional neural network is utilized to achieve fine semantic segmentation of rock skeleton,pore space,and microfractures based on CT slice images of deep rocks.The three-dimensional digital rock models of deformed multiscale fractured-porous media at different stress loading stages are thereafter reconstructed,and the equivalent fracture-pore network models are finally extracted to explore the underlying mechanisms of gas-water two-phase flow at the pore-scale.Results indicate that,in the process of insitu stress loading,both the deep rocks have experienced three stages:linear elastic deformation,nonlinear plastic deformation,and shear failure.The micro-mechanical behavior greatly affects the dynamic deformation of rock microstructure and gas-water two-phase flow.In the linear elastic deformation stage,with the increase in in-situ stress,both the deep rocks are gradually compacted,leading to decreases in average pore radius,pore throat ratio,tortuosity,and water-phase relative permeability,while the coordination number nearly remains unchanged.In the plastic deformation stage,the synergistic influence of rock compaction and existence of micro-fractures typically exert a great effect on pore-throat topological properties and gas-water relative permeability.In the shear failure stage,due to the generation and propagation of micro-fractures inside the deep rock,the topological connectivity becomes better,fluid flow paths increase,and flow conductivity is promoted,thus leading to sharp increases in average pore radius and coordination number,rapid decreases in pore throat ratio and tortuosity,as well as remarkable improvement in relative permeability of gas phase and waterphase.展开更多
微表情检测旨在视频中定位幅度微弱、时间短暂的表情区间。其难点在于有效提取面部区域间的动态关联特征和多尺度时序特征,进而精准捕捉面部各区域微小动作之间的关联。针对这些问题,提出了一种融合自适应图注意力和多尺度可变空洞卷积...微表情检测旨在视频中定位幅度微弱、时间短暂的表情区间。其难点在于有效提取面部区域间的动态关联特征和多尺度时序特征,进而精准捕捉面部各区域微小动作之间的关联。针对这些问题,提出了一种融合自适应图注意力和多尺度可变空洞卷积的微表情检测网络(AG-DDNet)。通过引入参数可学习矩阵来实现键值对的特征变换,通过计算面部区域特征向量间的相似度得到动态邻接矩阵,并结合图注意力机制计算区域间权重系数,实现特征的动态融合;采用了多尺度可变空洞卷积模块,通过自适应池化与卷积组合的预测器生成动态感受野,从而实现多尺度的特征提取;引入基于Fisher信息矩阵的自然梯度优化机制,通过Fisher Adam优化器有效捕捉参数空间的几何结构信息,实现学习率的精确自适应调整,从而显著增强了模型对微表情和宏表情的协同检测能力。在微表情检测任务中,该算法与同类代表性算法相比,在CAS(ME)2数据集和SAMM Long Videos数据集上的性能分别提升了54.20%和20.11%。与最新算法相比,两个数据集上的提升幅度分别为38.43%和6.81%,有效证明了该方法在长视频微表情检测任务上的优越性能。展开更多
针对低压交流配电系统中复杂支路串联电弧故障检测困难、易引发电气火灾的挑战,提出了基于马尔可夫变迁场与可变形自引导Transformer(Markov transition field and deformable convolutional self-guided transformer,MTF-DSGT)的检测...针对低压交流配电系统中复杂支路串联电弧故障检测困难、易引发电气火灾的挑战,提出了基于马尔可夫变迁场与可变形自引导Transformer(Markov transition field and deformable convolutional self-guided transformer,MTF-DSGT)的检测方案。利用马尔可夫变迁场将一维电流信号转换为图像,融合可变形卷积网络(deformable convolutional network,DCN)提取局部特征及自引导Transformer捕捉全局信息,以提高故障识别精度。实验结果显示,该方案在复杂支路电路中检测准确率达99.88%,在Jetson Orin Nano平台测试耗时仅7.78 ms。该方案能高效辨识串联电弧故障,具备实时处理能力,适合边缘设备部署。展开更多
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National Key Research and Development Program of China(No.2017YFC0405806)。
文摘Currently,deep convolutional neural networks have made great progress in the field of semantic segmentation.Because of the fixed convolution kernel geometry,standard convolution neural networks have been limited the ability to simulate geometric transformations.Therefore,a deformable convolution is introduced to enhance the adaptability of convolutional networks to spatial transformation.Considering that the deep convolutional neural networks cannot adequately segment the local objects at the output layer due to using the pooling layers in neural network architecture.To overcome this shortcoming,the rough prediction segmentation results of the neural network output layer will be processed by fully connected conditional random fields to improve the ability of image segmentation.The proposed method can easily be trained by end-to-end using standard backpropagation algorithms.Finally,the proposed method is tested on the ISPRS dataset.The results show that the proposed method can effectively overcome the influence of the complex structure of the segmentation object and obtain state-of-the-art accuracy on the ISPRS Vaihingen 2D semantic labeling dataset.
基金supported in part by the National Science Foundation of China under Grant 62001236in part by the Natural Science Foundation of the Jiangsu Higher Education Institutions of China under Grant 20KJA520003.
文摘In the textile industry,the presence of defects on the surface of fabric is an essential factor in determining fabric quality.Therefore,identifying fabric defects forms a crucial part of the fabric production process.Traditional fabric defect detection algorithms can only detect specific materials and specific fabric defect types;in addition,their detection efficiency is low,and their detection results are relatively poor.Deep learning-based methods have many advantages in the field of fabric defect detection,however,such methods are less effective in identifying multiscale fabric defects and defects with complex shapes.Therefore,we propose an effective algorithm,namely multilayer feature extraction combined with deformable convolution(MFDC),for fabric defect detection.In MFDC,multi-layer feature extraction is used to fuse the underlying location features with high-level classification features through a horizontally connected top-down architecture to improve the detection of multi-scale fabric defects.On this basis,a deformable convolution is added to solve the problem of the algorithm’s weak detection ability of irregularly shaped fabric defects.In this approach,Roi Align and Cascade-RCNN are integrated to enhance the adaptability of the algorithm in materials with complex patterned backgrounds.The experimental results show that the MFDC algorithm can achieve good detection results for both multi-scale fabric defects and defects with complex shapes,at the expense of a small increase in detection time.
基金supported by The Henan Province Science and Technology Research Project(242102211046)the Key Scientific Research Project of Higher Education Institutions in Henan Province(25A520039)+1 种基金theNatural Science Foundation project of Zhongyuan Institute of Technology(K2025YB011)the Zhongyuan University of Technology Graduate Education and Teaching Reform Research Project(JG202424).
文摘Electrocardiogram (ECG) analysis is critical for detecting arrhythmias, but traditional methods struggle with large-scale Electrocardiogram data and rare arrhythmia events in imbalanced datasets. These methods fail to perform multi-perspective learning of temporal signals and Electrocardiogram images, nor can they fully extract the latent information within the data, falling short of the accuracy required by clinicians. Therefore, this paper proposes an innovative hybrid multimodal spatiotemporal neural network to address these challenges. The model employs a multimodal data augmentation framework integrating visual and signal-based features to enhance the classification performance of rare arrhythmias in imbalanced datasets. Additionally, the spatiotemporal fusion module incorporates a spatiotemporal graph convolutional network to jointly model temporal and spatial features, uncovering complex dependencies within the Electrocardiogram data and improving the model’s ability to represent complex patterns. In experiments conducted on the MIT-BIH arrhythmia dataset, the model achieved 99.95% accuracy, 99.80% recall, and a 99.78% F1 score. The model was further validated for generalization using the clinical INCART arrhythmia dataset, and the results demonstrated its effectiveness in terms of both generalization and robustness.
基金Supported by the Key R&D Program of Gansu Province(No.23YFGA0063)the Key Talent Project of Gansu Province(No.2024RCXM57,2024RCXM22)the Major Science and Technology Special Program of Gansu Province(No.25ZYJA037).
文摘Traffic flow prediction is a crucial element of intelligent transportation systems.However,accu-rate traffic flow prediction is quite challenging because of its highly nonlinear,complex,and dynam-ic characteristics.To address the difficulties in simultaneously capturing local and global dynamic spatiotemporal correlations in traffic flow,as well as the high time complexity of existing models,a multi-head flow attention-based local-global dynamic hypergraph convolution(MFA-LGDHC)pre-diction model is proposed.which consists of multi-head flow attention(MHFA)mechanism,graph convolution network(GCN),and local-global dynamic hypergraph convolution(LGHC).MHFA is utilized to extract the time dependency of traffic flow and reduce the time complexity of the model.GCN is employed to catch the spatial dependency of traffic flow.LGHC utilizes down-sampling con-volution and isometric convolution to capture the local and global spatial dependencies of traffic flow.And dynamic hypergraph convolution is used to model the dynamic higher-order relationships of the traffic road network.Experimental results indicate that the MFA-LGDHC model outperforms current popular baseline models and exhibits good prediction performance.
文摘This paper presents CW-HRNet,a high-resolution,lightweight crack segmentation network designed to address challenges in complex scenes with slender,deformable,and blurred crack structures.The model incorporates two key modules:Constrained Deformable Convolution(CDC),which stabilizes geometric alignment by applying a tanh limiter and learnable scaling factor to the predicted offsets,and the Wavelet Frequency Enhancement Module(WFEM),which decomposes features using Haar wavelets to preserve low-frequency structures while enhancing high-frequency boundaries and textures.Evaluations on the CrackSeg9k benchmark demonstrate CW-HRNet’s superior performance,achieving 82.39%mIoU with only 7.49M parameters and 10.34 GFLOPs,outperforming HrSegNet-B48 by 1.83% in segmentation accuracy with minimal complexity overhead.The model also shows strong cross-dataset generalization,achieving 60.01%mIoU and 66.22%F1 on Asphalt3k without fine-tuning.These results highlight CW-HRNet’s favorable accuracyefficiency trade-off for real-world crack segmentation tasks.
文摘Accurate vehicle detection is essential for autonomous driving,traffic monitoring,and intelligent transportation systems.This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module,Convolutional Block Attention Module(CBAM),and Deformable Convolutional Networks v2(DCNv2).The Ghost Module streamlines feature generation to reduce redundancy,CBAM applies channel and spatial attention to improve feature focus,and DCNv2 enables adaptability to geometric variations in vehicle shapes.These components work together to improve both accuracy and computational efficiency.Evaluated on the KITTI dataset,the proposed model achieves 95.4%mAP@0.5—an 8.97% gain over standard YOLOv8n—along with 96.2% precision,93.7% recall,and a 94.93%F1-score.Comparative analysis with seven state-of-the-art detectors demonstrates consistent superiority in key performance metrics.An ablation study is also conducted to quantify the individual and combined contributions of GhostModule,CBAM,and DCNv2,highlighting their effectiveness in improving detection performance.By addressing feature redundancy,attention refinement,and spatial adaptability,the proposed model offers a robust and scalable solution for vehicle detection across diverse traffic scenarios.
基金supported by Beijing Insititute of Technology Research Fund Program for Young Scholars(2020X04104)。
文摘In this paper,an improved spatio-temporal alignment measurement method is presented to address the inertial matching measurement of hull deformation under the coexistence of time delay and large misalignment angle.Large misalignment angle and time delay often occur simultaneously and bring great challenges to the accurate measurement of hull deformation in space and time.The proposed method utilizes coarse alignment with large misalignment angle and time delay estimation of inertial measurement unit modeling to establish a brand-new spatiotemporal aligned hull deformation measurement model.In addition,two-step loop control is designed to ensure the accurate description of dynamic deformation angle and static deformation angle by the time-space alignment method of hull deformation.The experiments illustrate that the proposed method can effectively measure the hull deformation angle when time delay and large misalignment angle coexist.
基金supported by the National Natural Science Foundation of China[grant number 41671452].
文摘Although the Convolutional Neural Network(CNN)has shown great potential for land cover classification,the frequently used single-scale convolution kernel limits the scope of informa-tion extraction.Therefore,we propose a Multi-Scale Fully Convolutional Network(MSFCN)with a multi-scale convolutional kernel as well as a Channel Attention Block(CAB)and a Global Pooling Module(GPM)in this paper to exploit discriminative representations from two-dimensional(2D)satellite images.Meanwhile,to explore the ability of the proposed MSFCN for spatio-temporal images,we expand our MSFCN to three-dimension using three-dimensional(3D)CNN,capable of harnessing each land cover category’s time series interac-tion from the reshaped spatio-temporal remote sensing images.To verify the effectiveness of the proposed MSFCN,we conduct experiments on two spatial datasets and two spatio-temporal datasets.The proposed MSFCN achieves 60.366%on the WHDLD dataset and 75.127%on the GID dataset in terms of mIoU index while the figures for two spatio-temporal datasets are 87.753%and 77.156%.Extensive comparative experiments and abla-tion studies demonstrate the effectiveness of the proposed MSFCN.
基金supported by the National Natural Science Foundation of China (No.52075349)the National Natural Science Foundation of China (No.62303335)+1 种基金the Postdoctoral Researcher Program of China (No.GZC20231779)the Natural Science Foundation of Sichuan Province (No.2022NSFSC1942).
文摘Health monitoring of electro-mechanical actuator(EMA)is critical to ensure the security of airplanes.It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA.The autoencoder based on reconstruction loss is a popular model that can carry out anomaly detection with only consideration of normal training data,while it fails to capture spatio-temporal information from multivariate time series signals of multiple monitoring sensors.To mine the spatio-temporal information from multivariate time series signals,this paper proposes an attention graph stacked autoencoder for EMA anomaly detection.Firstly,attention graph con-volution is introduced into autoencoder to convolve temporal information from neighbor features to current features based on different weight attentions.Secondly,stacked autoencoder is applied to mine spatial information from those new aggregated temporal features.Finally,based on the bench-mark reconstruction loss of normal training data,different health thresholds calculated by several statistic indicators can carry out anomaly detection for new testing data.In comparison with tra-ditional stacked autoencoder,the proposed model could obtain higher fault detection rate and lower false alarm rate in EMA anomaly detection experiment.
基金This study was supported in part by the Sichuan Science and Technology Program(2019YFH0085,2019ZDZX0005,2019YFG0196)in part by the Foundation of Chengdu University of Information Technology(No.KYTZ202008).
文摘Deformable medical image registration plays a vital role in medical image applications,such as placing different temporal images at the same time point or different modality images into the same coordinate system.Various strategies have been developed to satisfy the increasing needs of deformable medical image registration.One popular registration method is estimating the displacement field by computing the optical flow between two images.The motion field(flow field)is computed based on either gray-value or handcrafted descriptors such as the scale-invariant feature transform(SIFT).These methods assume that illumination is constant between images.However,medical images may not always satisfy this assumption.In this study,we propose a metric learning-based motion estimation method called Siamese Flow for deformable medical image registration.We train metric learners using a Siamese network,which produces an image patch descriptor that guarantees a smaller feature distance in two similar anatomical structures and a larger feature distance in two dissimilar anatomical structures.In the proposed registration framework,the flow field is computed based on such features and is close to the real deformation field due to the excellent feature representation ability of the Siamese network.Experimental results demonstrate that the proposed method outperforms the Demons,SIFT Flow,Elastix,and VoxelMorph networks regarding registration accuracy and robustness,particularly with large deformations.
基金Beijing Natural Science Foundation(No.IS23112)Beijing Institute of Technology Research Fund Program for Young Scholars(No.6120220236)。
文摘The intensive application of deep learning in medical image processing has facilitated the advancement of automatic retinal vessel segmentation research.To overcome the limitation that traditional U-shaped vessel segmentation networks fail to extract features in fundus image sufficiently,we propose a novel network(DSeU-net)based on deformable convolution and squeeze excitation residual module.The deformable convolution is utilized to dynamically adjust the receptive field for the feature extraction of retinal vessel.And the squeeze excitation residual module is used to scale the weights of the low-level features so that the network learns the complex relationships of the different feature layers efficiently.We validate the DSeU-net on three public retinal vessel segmentation datasets including DRIVE,CHASEDB1,and STARE,and the experimental results demonstrate the satisfactory segmentation performance of the network.
基金Supported by the National Natural Science Foundation of China under Grants 61872241,62077037 and 62272298in part by Shanghai Municipal Science and Technology Major Project under Grant 2021SHZDZX0102。
文摘Background Exploring correspondences across multiview images is the basis of various computer vision tasks.However,most existing methods have limited accuracy under challenging conditions.Method To learn more robust and accurate correspondences,we propose DSD-MatchingNet for local feature matching in this study.First,we develop a deformable feature extraction module to obtain multilevel feature maps,which harvest contextual information from dynamic receptive fields.The dynamic receptive fields provided by the deformable convolution network ensure that our method obtains dense and robust correspondence.Second,we utilize sparse-to-dense matching with symmetry of correspondence to implement accurate pixel-level matching,which enables our method to produce more accurate correspondences.Result Experiments show that our proposed DSD-MatchingNet achieves a better performance on the image matching benchmark,as well as on the visual localization benchmark.Specifically,our method achieved 91.3%mean matching accuracy on the HPatches dataset and 99.3%visual localization recalls on the Aachen Day-Night dataset.
基金supported by the National Natural Science Foundation of China(Nos.62202247 and 62306073)the National Key Research and Development Program of China(No.2022ZD0115303).
文摘With the advent of deep learning,various deep neural network architectures have been proposed to capture the complex spatio-temporal dependencies in traffic data.This paper introduces a novel Deep Bi-directional Adaptive Gating Graph Convolutional Network(DBAG-GCN)model for spatio-temporal traffic forecasting.The proposed model leverages the power of graph convolutional networks to capture the spatial dependencies in the road network topology and incorporates bi-directional gating mechanisms to control the information flow adaptively.Furthermore,we introduce a multi-scale temporal convolution module to capture multi-scale temporal dynamics and a contextual attention mechanism to integrate external factors such as weather conditions and event information.Extensive experiments on real-world traffic datasets demonstrate the superior performance of DBAG-GCN compared to state-of-the-art baselines,achieving significant improvements in prediction accuracy and computational efficiency.The DBAG-GCN model provides a powerful and flexible framework for spatio-temporal traffic forecasting,paving the way for intelligent transportation management and urban planning.
基金supported by the National Natural Science Foundation of China(No.52174043)the Beijing Natural Science Foundation(No.3242019)+1 种基金the CNPC Innovation Foundation(No.2022DQ02-0208)the State Key Laboratory of Deep Oil and Gas(No.SKLD0G2024-KFZD-06).
文摘Two actual rocks drilled from a typical ultra-deep hydrocarbon reservoir in the Tarim Basin are selected to conduct in-situ stress-loading micro-focus CT scanning experiments.The gray images of rock microstructure at different stress loading stages are obtained.The U-Net fully convolutional neural network is utilized to achieve fine semantic segmentation of rock skeleton,pore space,and microfractures based on CT slice images of deep rocks.The three-dimensional digital rock models of deformed multiscale fractured-porous media at different stress loading stages are thereafter reconstructed,and the equivalent fracture-pore network models are finally extracted to explore the underlying mechanisms of gas-water two-phase flow at the pore-scale.Results indicate that,in the process of insitu stress loading,both the deep rocks have experienced three stages:linear elastic deformation,nonlinear plastic deformation,and shear failure.The micro-mechanical behavior greatly affects the dynamic deformation of rock microstructure and gas-water two-phase flow.In the linear elastic deformation stage,with the increase in in-situ stress,both the deep rocks are gradually compacted,leading to decreases in average pore radius,pore throat ratio,tortuosity,and water-phase relative permeability,while the coordination number nearly remains unchanged.In the plastic deformation stage,the synergistic influence of rock compaction and existence of micro-fractures typically exert a great effect on pore-throat topological properties and gas-water relative permeability.In the shear failure stage,due to the generation and propagation of micro-fractures inside the deep rock,the topological connectivity becomes better,fluid flow paths increase,and flow conductivity is promoted,thus leading to sharp increases in average pore radius and coordination number,rapid decreases in pore throat ratio and tortuosity,as well as remarkable improvement in relative permeability of gas phase and waterphase.
文摘微表情检测旨在视频中定位幅度微弱、时间短暂的表情区间。其难点在于有效提取面部区域间的动态关联特征和多尺度时序特征,进而精准捕捉面部各区域微小动作之间的关联。针对这些问题,提出了一种融合自适应图注意力和多尺度可变空洞卷积的微表情检测网络(AG-DDNet)。通过引入参数可学习矩阵来实现键值对的特征变换,通过计算面部区域特征向量间的相似度得到动态邻接矩阵,并结合图注意力机制计算区域间权重系数,实现特征的动态融合;采用了多尺度可变空洞卷积模块,通过自适应池化与卷积组合的预测器生成动态感受野,从而实现多尺度的特征提取;引入基于Fisher信息矩阵的自然梯度优化机制,通过Fisher Adam优化器有效捕捉参数空间的几何结构信息,实现学习率的精确自适应调整,从而显著增强了模型对微表情和宏表情的协同检测能力。在微表情检测任务中,该算法与同类代表性算法相比,在CAS(ME)2数据集和SAMM Long Videos数据集上的性能分别提升了54.20%和20.11%。与最新算法相比,两个数据集上的提升幅度分别为38.43%和6.81%,有效证明了该方法在长视频微表情检测任务上的优越性能。
文摘针对低压交流配电系统中复杂支路串联电弧故障检测困难、易引发电气火灾的挑战,提出了基于马尔可夫变迁场与可变形自引导Transformer(Markov transition field and deformable convolutional self-guided transformer,MTF-DSGT)的检测方案。利用马尔可夫变迁场将一维电流信号转换为图像,融合可变形卷积网络(deformable convolutional network,DCN)提取局部特征及自引导Transformer捕捉全局信息,以提高故障识别精度。实验结果显示,该方案在复杂支路电路中检测准确率达99.88%,在Jetson Orin Nano平台测试耗时仅7.78 ms。该方案能高效辨识串联电弧故障,具备实时处理能力,适合边缘设备部署。
