Side-scan sonar(SSS)is now a prevalent instrument for large-scale seafloor topography measurements,deployable on an autonomous underwater vehicle(AUV)to execute fully automated underwater acoustic scanning imaging alo...Side-scan sonar(SSS)is now a prevalent instrument for large-scale seafloor topography measurements,deployable on an autonomous underwater vehicle(AUV)to execute fully automated underwater acoustic scanning imaging along a predetermined trajectory.However,SSS images often suffer from speckle noise caused by mutual interference between echoes,and limited AUV computational resources further hinder noise suppression.Existing approaches for SSS image processing and speckle noise reduction rely heavily on complex network structures and fail to combine the benefits of deep learning and domain knowledge.To address the problem,Rep DNet,a novel and effective despeckling convolutional neural network is proposed.Rep DNet introduces two re-parameterized blocks:the Pixel Smoothing Block(PSB)and Edge Enhancement Block(EEB),preserving edge information while attenuating speckle noise.During training,PSB and EEB manifest as double-layered multi-branch structures,integrating first-order and secondorder derivatives and smoothing functions.During inference,the branches are re-parameterized into a 3×3 convolution,enabling efficient inference without sacrificing accuracy.Rep DNet comprises three computational operations:3×3 convolution,element-wise summation and Rectified Linear Unit activation.Evaluations on benchmark datasets,a real SSS dataset and Data collected at Lake Mulan aestablish Rep DNet as a well-balanced network,meeting the AUV computational constraints in terms of performance and latency.展开更多
Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain limitations.Conversely,deep learning techniques have gained promine...Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain limitations.Conversely,deep learning techniques have gained prominence as a central focus of research in the field of fault diagnosis by strong fault feature extraction ability and end-to-end fault diagnosis efficiency.Recently,utilizing the respective advantages of convolution neural network(CNN)and Transformer in local and global feature extraction,research on cooperating the two have demonstrated promise in the field of fault diagnosis.However,the cross-channel convolution mechanism in CNN and the self-attention calculations in Transformer contribute to excessive complexity in the cooperative model.This complexity results in high computational costs and limited industrial applicability.To tackle the above challenges,this paper proposes a lightweight CNN-Transformer named as SEFormer for rotating machinery fault diagnosis.First,a separable multiscale depthwise convolution block is designed to extract and integrate multiscale feature information from different channel dimensions of vibration signals.Then,an efficient self-attention block is developed to capture critical fine-grained features of the signal from a global perspective.Finally,experimental results on the planetary gearbox dataset and themotor roller bearing dataset prove that the proposed framework can balance the advantages of robustness,generalization and lightweight compared to recent state-of-the-art fault diagnosis models based on CNN and Transformer.This study presents a feasible strategy for developing a lightweight rotating machinery fault diagnosis framework aimed at economical deployment.展开更多
In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accurac...In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.展开更多
The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to u...The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.展开更多
Micro-expressions(ME)recognition is a complex task that requires advanced techniques to extract informative features fromfacial expressions.Numerous deep neural networks(DNNs)with convolutional structures have been pr...Micro-expressions(ME)recognition is a complex task that requires advanced techniques to extract informative features fromfacial expressions.Numerous deep neural networks(DNNs)with convolutional structures have been proposed.However,unlike DNNs,shallow convolutional neural networks often outperform deeper models in mitigating overfitting,particularly with small datasets.Still,many of these methods rely on a single feature for recognition,resulting in an insufficient ability to extract highly effective features.To address this limitation,in this paper,an Improved Dual-stream Shallow Convolutional Neural Network based on an Extreme Gradient Boosting Algorithm(IDSSCNN-XgBoost)is introduced for ME Recognition.The proposed method utilizes a dual-stream architecture where motion vectors(temporal features)are extracted using Optical Flow TV-L1 and amplify subtle changes(spatial features)via EulerianVideoMagnification(EVM).These features are processed by IDSSCNN,with an attention mechanism applied to refine the extracted effective features.The outputs are then fused,concatenated,and classified using the XgBoost algorithm.This comprehensive approach significantly improves recognition accuracy by leveraging the strengths of both temporal and spatial information,supported by the robust classification power of XgBoost.The proposed method is evaluated on three publicly available ME databases named Chinese Academy of Sciences Micro-expression Database(CASMEII),Spontaneous Micro-Expression Database(SMICHS),and Spontaneous Actions and Micro-Movements(SAMM).Experimental results indicate that the proposed model can achieve outstanding results compared to recent models.The accuracy results are 79.01%,69.22%,and 68.99%on CASMEII,SMIC-HS,and SAMM,and the F1-score are 75.47%,68.91%,and 63.84%,respectively.The proposed method has the advantage of operational efficiency and less computational time.展开更多
The hazard produced by natural phenomena on infrastructure and urban populations has been widely studied in the last 50 years. Researchers have recognised that the real danger posed by these phenomena depends on their...The hazard produced by natural phenomena on infrastructure and urban populations has been widely studied in the last 50 years. Researchers have recognised that the real danger posed by these phenomena depends on their extreme values. Most researchers focus on the extremes of natural phenomena considered in isolation, one variable at a time. However, what is relevant in hazard studies is coincident extremes of several climatic variables, i.e., the presence of compound extremes. The peak value of these extremes seldom coincides, but off-peak values located in the tail of the distributions are often concurrent and can lead to catastrophic events. What is essential in hazard studies is to calculate the probabilistic distribution of the extremes of coincident climatic variables. The presence of correlations between these variables complicates the problem. This paper presents a computationally efficient and robust mathematical methodology to solve the problem. The procedure is based on the convolution of the distributions of the climatic variables. Once the probabilistic distribution of the compound variables is found, it is possible to calculate the curves of the return period, which is the indicator of importance in hazard and risk studies. This compound Return Period is computed using the Statistics of Extreme Values. To illustrate the problem, the case of a cyclone landing close to a low-gradient coastal city is discussed, and its probability of flooding and recurrence period is calculated. We show that the failure to correctly model the correlation between variables can result in overestimating the Return Period curve, consequently increasing mitigation costs.展开更多
Aspect-oriented sentiment analysis is a meticulous sentiment analysis task that aims to analyse the sentiment polarity of specific aspects. Most of the current research builds graph convolutional networks based on dep...Aspect-oriented sentiment analysis is a meticulous sentiment analysis task that aims to analyse the sentiment polarity of specific aspects. Most of the current research builds graph convolutional networks based on dependent syntactic trees, which improves the classification performance of the models to some extent. However, the technical limitations of dependent syntactic trees can introduce considerable noise into the model. Meanwhile, it is difficult for a single graph convolutional network to aggregate both semantic and syntactic structural information of nodes, which affects the final sentence classification. To cope with the above problems, this paper proposes a bi-channel graph convolutional network model. The model introduces a phrase structure tree and transforms it into a hierarchical phrase matrix. The adjacency matrix of the dependent syntactic tree and the hierarchical phrase matrix are combined as the initial matrix of the graph convolutional network to enhance the syntactic information. The semantic information feature representations of the sentences are obtained by the graph convolutional network with a multi-head attention mechanism and fused to achieve complementary learning of dual-channel features. Experimental results show that the model performs well and improves the accuracy of sentiment classification on three public benchmark datasets, namely Rest14, Lap14 and Twitter.展开更多
The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has signifi...The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has significantly advanced the analysis of ocular disease images,there is a need for a probabilistic model to generate the distributions of potential outcomes and thusmake decisions related to uncertainty quantification.Therefore,this study implements a Bayesian Convolutional Neural Networks(BCNN)model for predicting cataracts by assigning probability values to the predictions.It prepares convolutional neural network(CNN)and BCNN models.The proposed BCNN model is CNN-based in which reparameterization is in the first and last layers of the CNN model.This study then trains them on a dataset of cataract images filtered from the ocular disease fundus images fromKaggle.The deep CNN model has an accuracy of 95%,while the BCNN model has an accuracy of 93.75% along with information on uncertainty estimation of cataracts and normal eye conditions.When compared with other methods,the proposed work reveals that it can be a promising solution for cataract prediction with uncertainty estimation.展开更多
The wheat above-ground biomass(AGB)is an important index that shows the life activity of vegetation,which is of great significance for wheat growth monitoring and yield prediction.Traditional biomass estimation method...The wheat above-ground biomass(AGB)is an important index that shows the life activity of vegetation,which is of great significance for wheat growth monitoring and yield prediction.Traditional biomass estimation methods specifically include sample surveys and harvesting statistics.Although these methods have high estimation accuracy,they are time-consuming,destructive,and difficult to implement to monitor the biomass at a large scale.The main objective of this study is to optimize the traditional remote sensing methods to estimate the wheat AGBbased on improved convolutional features(CFs).Low-cost unmanned aerial vehicles(UAV)were used as the main data acquisition equipment.This study acquired image data acquired by RGB camera(RGB)and multi-spectral(MS)image data of the wheat population canopy for two wheat varieties and five key growth stages.Then,field measurements were conducted to obtain the actual wheat biomass data for validation.Based on the remote sensing indices(RSIs),structural features(SFs),and CFs,this study proposed a new feature named AUR-50(multi-source combination based on convolutional feature optimization)to estimate the wheat AGB.The results show that AUR-50 could estimate the wheat AGB more accurately than RSIs and SFs,and the average R^(2) exceeded 0.77.In the overwintering period,AUR-50_(MS)(multi-source combination with convolutional feature optimization using multispectral imagery)had the highest estimation accuracy(R^(2) of 0.88).In addition,AUR-50 reduced the effect of the vegetation index saturation on the biomass estimation accuracy by adding CFs,where the highest R^(2) was 0.69 at the flowering stage.The results of this study provide an effective method to evaluate the AGB in wheat with high throughput and a research reference for the phenotypic parameters of other crops.展开更多
Instance segmentation is crucial in various domains,such as autonomous driving and robotics.However,there is scope for improvement in the detection speed of instance-segmentation algorithms for edge devices.Therefore,...Instance segmentation is crucial in various domains,such as autonomous driving and robotics.However,there is scope for improvement in the detection speed of instance-segmentation algorithms for edge devices.Therefore,it is essential to enhance detection speed while maintaining high accuracy.In this study,we propose you only look once-layer fusion(YOLO-LF),a lightweight instance segmentation method specifically designed to optimize the speed of instance segmentation for autonomous driving applications.Based on the You Only Look Once version 8 nano(YOLOv8n)framework,we introduce a lightweight convolutional module and design a lightweight layer aggrega-tion module called Reparameterization convolution and Partial convolution Efficient Layer Aggregation Networks(RPELAN).This module effectively reduces the impact of redundant information generated by traditional convolutional stacking on the network size and detection speed while enhancing the capability to process feature information.We experimentally verified that our generalized one-stage detection network lightweight method based on Grouped Spatial Convolution(GSconv)enhances the detection speed while maintaining accuracy across various state-of-the-art(SOTA)networks.Our experiments conducted on the publicly available Cityscapes dataset demonstrated that YOLO-LF maintained the same accuracy as yolov8n(mAP@0.537.9%),the model volume decreased by 14.3%from 3.259 to=2.804 M,and the Frames Per Second(FPS)increased by 14.48%from 57.47 to 65.79 compared with YOLOv8n,thereby demonstrating its potential for real-time instance segmentation on edge devices.展开更多
In the PSP(Pressure-Sensitive Paint),image deblurring is essential due to factors such as prolonged camera exposure times and highmodel velocities,which can lead to significant image blurring.Conventional deblurring m...In the PSP(Pressure-Sensitive Paint),image deblurring is essential due to factors such as prolonged camera exposure times and highmodel velocities,which can lead to significant image blurring.Conventional deblurring methods applied to PSP images often suffer from limited accuracy and require extensive computational resources.To address these issues,this study proposes a deep learning-based approach tailored for PSP image deblurring.Considering that PSP applications primarily involve the accurate pressure measurements of complex geometries,the images captured under such conditions exhibit distinctive non-uniform motion blur,presenting challenges for standard deep learning models utilizing convolutional or attention-based techniques.In this paper,we introduce a novel deblurring architecture featuring multiple DAAM(Deformable Ack Attention Module).These modules provide enhanced flexibility for end-to-end deblurring,leveraging irregular convolution operations for efficient feature extraction while employing attention mechanisms interpreted as multiple 1×1 convolutions,subsequently reassembled to enhance performance.Furthermore,we incorporate a RSC(Residual Shortcut Convolution)module for initial feature processing,aimed at reducing redundant computations and improving the learning capacity for representative shallow features.To preserve critical spatial information during upsampling and downsampling,we replace conventional convolutions with wt(Haar wavelet downsampling)and dysample(Upsampling by Dynamic Sampling).This modification significantly enhances high-precision image reconstruction.By integrating these advanced modules within an encoder-decoder framework,we present the DFDNet(Deformable Fusion Deblurring Network)for image blur removal,providing robust technical support for subsequent PSP data analysis.Experimental evaluations on the FY dataset demonstrate the superior performance of our model,achieving competitive results on the GOPRO and HIDE datasets.展开更多
Photonic computing has emerged as a promising technology for the ever-increasing computational demands of machine learning and artificial intelligence.Due to the advantages in computing speed,integrated photonic chips...Photonic computing has emerged as a promising technology for the ever-increasing computational demands of machine learning and artificial intelligence.Due to the advantages in computing speed,integrated photonic chips have attracted wide research attention on performing convolutional neural network algorithm.Programmable photonic chips are vital for achieving practical applications of photonic computing.Herein,a programmable photonic chip based on ultrafast laser-induced phase change is fabricated for photonic computing.Through designing the ultrafast laser pulses,the Sb film integrated into photonic waveguides can be reversibly switched between crystalline and amorphous phase,resulting in a large contrast in refractive index and extinction coefficient.As a consequence,the light transmission of waveguides can be switched between write and erase states.To determine the phase change time,the transient laser-induced phase change dynamics of Sb film are revealed at atomic scale,and the time-resolved transient reflectivity is measured.Based on the integrated photonic chip,photonic convolutional neural networks are built to implement machine learning algorithm,and images recognition task is achieved.This work paves a route for fabricating programmable photonic chips by designed ultrafast laser,which will facilitate the application of photonic computing in artificial intelligence.展开更多
Abnormal network traffic, as a frequent security risk, requires a series of techniques to categorize and detect it. Existing network traffic anomaly detection still faces challenges: the inability to fully extract loc...Abnormal network traffic, as a frequent security risk, requires a series of techniques to categorize and detect it. Existing network traffic anomaly detection still faces challenges: the inability to fully extract local and global features, as well as the lack of effective mechanisms to capture complex interactions between features;Additionally, when increasing the receptive field to obtain deeper feature representations, the reliance on increasing network depth leads to a significant increase in computational resource consumption, affecting the efficiency and performance of detection. Based on these issues, firstly, this paper proposes a network traffic anomaly detection model based on parallel dilated convolution and residual learning (Res-PDC). To better explore the interactive relationships between features, the traffic samples are converted into two-dimensional matrix. A module combining parallel dilated convolutions and residual learning (res-pdc) was designed to extract local and global features of traffic at different scales. By utilizing res-pdc modules with different dilation rates, we can effectively capture spatial features at different scales and explore feature dependencies spanning wider regions without increasing computational resources. Secondly, to focus and integrate the information in different feature subspaces, further enhance and extract the interactions among the features, multi-head attention is added to Res-PDC, resulting in the final model: multi-head attention enhanced parallel dilated convolution and residual learning (MHA-Res-PDC) for network traffic anomaly detection. Finally, comparisons with other machine learning and deep learning algorithms are conducted on the NSL-KDD and CIC-IDS-2018 datasets. The experimental results demonstrate that the proposed method in this paper can effectively improve the detection performance.展开更多
Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attentio...Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attention, challenges remain, especially when dealing with diverse data types. In this study, we introduce a novel data imputation method based on a modified convolutional neural network, specifically, a Deep Residual-Convolutional Neural Network (DRes-CNN) architecture designed to handle missing values across various datasets. Our approach demonstrates substantial improvements over existing imputation techniques by leveraging residual connections and optimized convolutional layers to capture complex data patterns. We evaluated the model on publicly available datasets, including Medical Information Mart for Intensive Care (MIMIC-III and MIMIC-IV), which contain critical care patient data, and the Beijing Multi-Site Air Quality dataset, which measures environmental air quality. The proposed DRes-CNN method achieved a root mean square error (RMSE) of 0.00006, highlighting its high accuracy and robustness. We also compared with Low Light-Convolutional Neural Network (LL-CNN) and U-Net methods, which had RMSE values of 0.00075 and 0.00073, respectively. This represented an improvement of approximately 92% over LL-CNN and 91% over U-Net. The results showed that this DRes-CNN-based imputation method outperforms current state-of-the-art models. These results established DRes-CNN as a reliable solution for addressing missing data.展开更多
Recommendation systems(RSs)are crucial in personalizing user experiences in digital environments by suggesting relevant content or items.Collaborative filtering(CF)is a widely used personalization technique that lever...Recommendation systems(RSs)are crucial in personalizing user experiences in digital environments by suggesting relevant content or items.Collaborative filtering(CF)is a widely used personalization technique that leverages user-item interactions to generate recommendations.However,it struggles with challenges like the cold-start problem,scalability issues,and data sparsity.To address these limitations,we develop a Graph Convolutional Networks(GCNs)model that captures the complex network of interactions between users and items,identifying subtle patterns that traditional methods may overlook.We integrate this GCNs model into a federated learning(FL)framework,enabling themodel to learn fromdecentralized datasets.This not only significantly enhances user privacy—a significant improvement over conventionalmodels but also reassures users about the safety of their data.Additionally,by securely incorporating demographic information,our approach further personalizes recommendations and mitigates the coldstart issue without compromising user data.We validate our RSs model using the openMovieLens dataset and evaluate its performance across six key metrics:Precision,Recall,Area Under the Receiver Operating Characteristic Curve(ROC-AUC),F1 Score,Normalized Discounted Cumulative Gain(NDCG),and Mean Reciprocal Rank(MRR).The experimental results demonstrate significant enhancements in recommendation quality,underscoring that combining GCNs with CF in a federated setting provides a transformative solution for advanced recommendation systems.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
The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spect...The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spectrometer(ANIS)at the China Spallation Neutron Source(CSNS).The Yolov3 and MNIST models were implemented on the XILINX28-nm system-on-chip(So C).Meanwhile,the Yolov3 and ResNet50 models were deployed on the XILINX 16-nm Fin FET Ultra Scale+MPSoC.The atmospheric neutron SEEs on the tested CNN systems were comprehensively evaluated from six aspects,including chip type,network architecture,deployment methods,inference time,datasets,and the position of the anchor boxes.The various types of SEE soft errors,SEE cross-sections,and their distribution were analyzed to explore the radiation sensitivities and rules of 28-nm and 16-nm SoC.The current research can provide the technology support of radiation-resistant design of CNN system for developing and applying high-reliability,long-lifespan domestic artificial intelligence chips.展开更多
Precision steel balls are critical components in precision bearings.Surface defects on the steel balls will significantly reduce their useful life and cause linear or rotational transmission errors.Human visual inspec...Precision steel balls are critical components in precision bearings.Surface defects on the steel balls will significantly reduce their useful life and cause linear or rotational transmission errors.Human visual inspection of precision steel balls demands significant labor work.Besides,human inspection cannot maintain consistent quality assurance.To address these limitations and reduce inspection time,a convolutional neural network(CNN)based optical inspection system has been developed that automatically detects steel ball defects using a novel designated vertical mechanism.During image detection processing,two key challenges were addressed and resolved.They are the reflection caused by the coaxial light onto the ball center and the image deformation appearing at the edge of the steel balls.The special vertical rotating mechanism utilizing a spinning rod along with a spiral track was developed to enable successful and reliable full steel ball surface inspection during the rod rotation.The combination of the spinning rod and the spiral rotating component effectively rotates the steel ball to facilitate capturing complete surface images.Geometric calculations demonstrate that the steel balls can be completely inspected through specific rotation degrees,with the surface fully captured in 12 photo shots.These images are then analyzed by a CNN to determine surface quality defects.This study presents a new inspection method that enables the entire examination of steel ball surfaces.The successful development of this innovative automated optical inspection system with CNN represents a significant advancement in inspection quality control for precision steel balls.展开更多
Traditional meteorological downscaling methods face limitations due to the complex distribution of meteorological variables,which can lead to unstable forecasting results,especially in extreme scenarios.To overcome th...Traditional meteorological downscaling methods face limitations due to the complex distribution of meteorological variables,which can lead to unstable forecasting results,especially in extreme scenarios.To overcome this issue,we propose a convolutional graph neural network(CGNN)model,which we enhance with multilayer feature fusion and a squeeze-and-excitation block.Additionally,we introduce a spatially balanced mean squared error(SBMSE)loss function to address the imbalanced distribution and spatial variability of meteorological variables.The CGNN is capable of extracting essential spatial features and aggregating them from a global perspective,thereby improving the accuracy of prediction and enhancing the model's generalization ability.Based on the experimental results,CGNN has certain advantages in terms of bias distribution,exhibiting a smaller variance.When it comes to precipitation,both UNet and AE also demonstrate relatively small biases.As for temperature,AE and CNNdense perform outstandingly during the winter.The time correlation coefficients show an improvement of at least 10%at daily and monthly scales for both temperature and precipitation.Furthermore,the SBMSE loss function displays an advantage over existing loss functions in predicting the98th percentile and identifying areas where extreme events occur.However,the SBMSE tends to overestimate the distribution of extreme precipitation,which may be due to the theoretical assumptions about the posterior distribution of data that partially limit the effectiveness of the loss function.In future work,we will further optimize the SBMSE to improve prediction accuracy.展开更多
Container-based virtualization technology has been more widely used in edge computing environments recently due to its advantages of lighter resource occupation, faster startup capability, and better resource utilizat...Container-based virtualization technology has been more widely used in edge computing environments recently due to its advantages of lighter resource occupation, faster startup capability, and better resource utilization efficiency. To meet the diverse needs of tasks, it usually needs to instantiate multiple network functions in the form of containers interconnect various generated containers to build a Container Cluster(CC). Then CCs will be deployed on edge service nodes with relatively limited resources. However, the increasingly complex and timevarying nature of tasks brings great challenges to optimal placement of CC. This paper regards the charges for various resources occupied by providing services as revenue, the service efficiency and energy consumption as cost, thus formulates a Mixed Integer Programming(MIP) model to describe the optimal placement of CC on edge service nodes. Furthermore, an Actor-Critic based Deep Reinforcement Learning(DRL) incorporating Graph Convolutional Networks(GCN) framework named as RL-GCN is proposed to solve the optimization problem. The framework obtains an optimal placement strategy through self-learning according to the requirements and objectives of the placement of CC. Particularly, through the introduction of GCN, the features of the association relationship between multiple containers in CCs can be effectively extracted to improve the quality of placement.The experiment results show that under different scales of service nodes and task requests, the proposed method can obtain the improved system performance in terms of placement error ratio, time efficiency of solution output and cumulative system revenue compared with other representative baseline methods.展开更多
基金supported by the National Key R&D Program of China(Grant No.2023YFC3010803)the National Nature Science Foundation of China(Grant No.52272424)+1 种基金the Key R&D Program of Hubei Province of China(Grant No.2023BCB123)the Fundamental Research Funds for the Central Universities(Grant No.WUT:2023IVB079)。
文摘Side-scan sonar(SSS)is now a prevalent instrument for large-scale seafloor topography measurements,deployable on an autonomous underwater vehicle(AUV)to execute fully automated underwater acoustic scanning imaging along a predetermined trajectory.However,SSS images often suffer from speckle noise caused by mutual interference between echoes,and limited AUV computational resources further hinder noise suppression.Existing approaches for SSS image processing and speckle noise reduction rely heavily on complex network structures and fail to combine the benefits of deep learning and domain knowledge.To address the problem,Rep DNet,a novel and effective despeckling convolutional neural network is proposed.Rep DNet introduces two re-parameterized blocks:the Pixel Smoothing Block(PSB)and Edge Enhancement Block(EEB),preserving edge information while attenuating speckle noise.During training,PSB and EEB manifest as double-layered multi-branch structures,integrating first-order and secondorder derivatives and smoothing functions.During inference,the branches are re-parameterized into a 3×3 convolution,enabling efficient inference without sacrificing accuracy.Rep DNet comprises three computational operations:3×3 convolution,element-wise summation and Rectified Linear Unit activation.Evaluations on benchmark datasets,a real SSS dataset and Data collected at Lake Mulan aestablish Rep DNet as a well-balanced network,meeting the AUV computational constraints in terms of performance and latency.
基金supported by the National Natural Science Foundation of China(No.52277055).
文摘Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain limitations.Conversely,deep learning techniques have gained prominence as a central focus of research in the field of fault diagnosis by strong fault feature extraction ability and end-to-end fault diagnosis efficiency.Recently,utilizing the respective advantages of convolution neural network(CNN)and Transformer in local and global feature extraction,research on cooperating the two have demonstrated promise in the field of fault diagnosis.However,the cross-channel convolution mechanism in CNN and the self-attention calculations in Transformer contribute to excessive complexity in the cooperative model.This complexity results in high computational costs and limited industrial applicability.To tackle the above challenges,this paper proposes a lightweight CNN-Transformer named as SEFormer for rotating machinery fault diagnosis.First,a separable multiscale depthwise convolution block is designed to extract and integrate multiscale feature information from different channel dimensions of vibration signals.Then,an efficient self-attention block is developed to capture critical fine-grained features of the signal from a global perspective.Finally,experimental results on the planetary gearbox dataset and themotor roller bearing dataset prove that the proposed framework can balance the advantages of robustness,generalization and lightweight compared to recent state-of-the-art fault diagnosis models based on CNN and Transformer.This study presents a feasible strategy for developing a lightweight rotating machinery fault diagnosis framework aimed at economical deployment.
基金supported by the National Natural Science Foundation of China(62272049,62236006,62172045)the Key Projects of Beijing Union University(ZKZD202301).
文摘In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.
文摘The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.
基金supported by the Key Research and Development Program of Jiangsu Province under Grant BE2022059-3,CTBC Bank through the Industry-Academia Cooperation Project,as well as by the Ministry of Science and Technology of Taiwan through Grants MOST-108-2218-E-002-055,MOST-109-2223-E-009-002-MY3,MOST-109-2218-E-009-025,and MOST431109-2218-E-002-015.
文摘Micro-expressions(ME)recognition is a complex task that requires advanced techniques to extract informative features fromfacial expressions.Numerous deep neural networks(DNNs)with convolutional structures have been proposed.However,unlike DNNs,shallow convolutional neural networks often outperform deeper models in mitigating overfitting,particularly with small datasets.Still,many of these methods rely on a single feature for recognition,resulting in an insufficient ability to extract highly effective features.To address this limitation,in this paper,an Improved Dual-stream Shallow Convolutional Neural Network based on an Extreme Gradient Boosting Algorithm(IDSSCNN-XgBoost)is introduced for ME Recognition.The proposed method utilizes a dual-stream architecture where motion vectors(temporal features)are extracted using Optical Flow TV-L1 and amplify subtle changes(spatial features)via EulerianVideoMagnification(EVM).These features are processed by IDSSCNN,with an attention mechanism applied to refine the extracted effective features.The outputs are then fused,concatenated,and classified using the XgBoost algorithm.This comprehensive approach significantly improves recognition accuracy by leveraging the strengths of both temporal and spatial information,supported by the robust classification power of XgBoost.The proposed method is evaluated on three publicly available ME databases named Chinese Academy of Sciences Micro-expression Database(CASMEII),Spontaneous Micro-Expression Database(SMICHS),and Spontaneous Actions and Micro-Movements(SAMM).Experimental results indicate that the proposed model can achieve outstanding results compared to recent models.The accuracy results are 79.01%,69.22%,and 68.99%on CASMEII,SMIC-HS,and SAMM,and the F1-score are 75.47%,68.91%,and 63.84%,respectively.The proposed method has the advantage of operational efficiency and less computational time.
文摘The hazard produced by natural phenomena on infrastructure and urban populations has been widely studied in the last 50 years. Researchers have recognised that the real danger posed by these phenomena depends on their extreme values. Most researchers focus on the extremes of natural phenomena considered in isolation, one variable at a time. However, what is relevant in hazard studies is coincident extremes of several climatic variables, i.e., the presence of compound extremes. The peak value of these extremes seldom coincides, but off-peak values located in the tail of the distributions are often concurrent and can lead to catastrophic events. What is essential in hazard studies is to calculate the probabilistic distribution of the extremes of coincident climatic variables. The presence of correlations between these variables complicates the problem. This paper presents a computationally efficient and robust mathematical methodology to solve the problem. The procedure is based on the convolution of the distributions of the climatic variables. Once the probabilistic distribution of the compound variables is found, it is possible to calculate the curves of the return period, which is the indicator of importance in hazard and risk studies. This compound Return Period is computed using the Statistics of Extreme Values. To illustrate the problem, the case of a cyclone landing close to a low-gradient coastal city is discussed, and its probability of flooding and recurrence period is calculated. We show that the failure to correctly model the correlation between variables can result in overestimating the Return Period curve, consequently increasing mitigation costs.
文摘Aspect-oriented sentiment analysis is a meticulous sentiment analysis task that aims to analyse the sentiment polarity of specific aspects. Most of the current research builds graph convolutional networks based on dependent syntactic trees, which improves the classification performance of the models to some extent. However, the technical limitations of dependent syntactic trees can introduce considerable noise into the model. Meanwhile, it is difficult for a single graph convolutional network to aggregate both semantic and syntactic structural information of nodes, which affects the final sentence classification. To cope with the above problems, this paper proposes a bi-channel graph convolutional network model. The model introduces a phrase structure tree and transforms it into a hierarchical phrase matrix. The adjacency matrix of the dependent syntactic tree and the hierarchical phrase matrix are combined as the initial matrix of the graph convolutional network to enhance the syntactic information. The semantic information feature representations of the sentences are obtained by the graph convolutional network with a multi-head attention mechanism and fused to achieve complementary learning of dual-channel features. Experimental results show that the model performs well and improves the accuracy of sentiment classification on three public benchmark datasets, namely Rest14, Lap14 and Twitter.
基金Saudi Arabia for funding this work through Small Research Group Project under Grant Number RGP.1/316/45.
文摘The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has significantly advanced the analysis of ocular disease images,there is a need for a probabilistic model to generate the distributions of potential outcomes and thusmake decisions related to uncertainty quantification.Therefore,this study implements a Bayesian Convolutional Neural Networks(BCNN)model for predicting cataracts by assigning probability values to the predictions.It prepares convolutional neural network(CNN)and BCNN models.The proposed BCNN model is CNN-based in which reparameterization is in the first and last layers of the CNN model.This study then trains them on a dataset of cataract images filtered from the ocular disease fundus images fromKaggle.The deep CNN model has an accuracy of 95%,while the BCNN model has an accuracy of 93.75% along with information on uncertainty estimation of cataracts and normal eye conditions.When compared with other methods,the proposed work reveals that it can be a promising solution for cataract prediction with uncertainty estimation.
基金supported by the Postgraduate Research&Practice Innovation Program of Jiangsu Province,China(SJCX23_1973)the National Natural Science Foundation of China(32172110,32071945)+7 种基金the Key Research and Development Program(Modern Agriculture)of Jiangsu Province,China(BE2022342-2,BE2020319)the Anhui Province Crop Intelligent Planting and Processing Technology Engineering Research Center Open Project,China(ZHKF04)the National Key Research and Development Program of China(2023YFD2300201,2023YFD1202200)the Special Funds for Scientific and Technological Innovation of Jiangsu Province,China(BE2022425)the Priority Academic Program Development of Jiangsu Higher Education Institutions,China(PAPD)the Central Publicinterest Scientific Institution Basal Research Fund,China(JBYW-AII-2023-08)the Science and Technology Innovation Project of the Chinese Academy of Agricultural Sciences(CAAS-CS-202201)the Special Fund for Independent Innovation of Agriculture Science and Technology in Jiangsu Province,China(CX(22)3112)。
文摘The wheat above-ground biomass(AGB)is an important index that shows the life activity of vegetation,which is of great significance for wheat growth monitoring and yield prediction.Traditional biomass estimation methods specifically include sample surveys and harvesting statistics.Although these methods have high estimation accuracy,they are time-consuming,destructive,and difficult to implement to monitor the biomass at a large scale.The main objective of this study is to optimize the traditional remote sensing methods to estimate the wheat AGBbased on improved convolutional features(CFs).Low-cost unmanned aerial vehicles(UAV)were used as the main data acquisition equipment.This study acquired image data acquired by RGB camera(RGB)and multi-spectral(MS)image data of the wheat population canopy for two wheat varieties and five key growth stages.Then,field measurements were conducted to obtain the actual wheat biomass data for validation.Based on the remote sensing indices(RSIs),structural features(SFs),and CFs,this study proposed a new feature named AUR-50(multi-source combination based on convolutional feature optimization)to estimate the wheat AGB.The results show that AUR-50 could estimate the wheat AGB more accurately than RSIs and SFs,and the average R^(2) exceeded 0.77.In the overwintering period,AUR-50_(MS)(multi-source combination with convolutional feature optimization using multispectral imagery)had the highest estimation accuracy(R^(2) of 0.88).In addition,AUR-50 reduced the effect of the vegetation index saturation on the biomass estimation accuracy by adding CFs,where the highest R^(2) was 0.69 at the flowering stage.The results of this study provide an effective method to evaluate the AGB in wheat with high throughput and a research reference for the phenotypic parameters of other crops.
基金supported by Science and Technology Research Youth Project of Chongqing Municipal Education Commission(No.KJQN202301104)Cooperative Project between universities in Chongqing and Affiliated Institutes of Chinese Academy of Sciences(No.HZ2021011)+1 种基金Chongqing Municipal Science and Technology Commission Technology Innovation and Application Development Special Project(No.2022TIAD-KPX0040)Action Plan for Quality Development of Chongqing University of Technology Graduate Education(Grant No.gzlcx20242014).
文摘Instance segmentation is crucial in various domains,such as autonomous driving and robotics.However,there is scope for improvement in the detection speed of instance-segmentation algorithms for edge devices.Therefore,it is essential to enhance detection speed while maintaining high accuracy.In this study,we propose you only look once-layer fusion(YOLO-LF),a lightweight instance segmentation method specifically designed to optimize the speed of instance segmentation for autonomous driving applications.Based on the You Only Look Once version 8 nano(YOLOv8n)framework,we introduce a lightweight convolutional module and design a lightweight layer aggrega-tion module called Reparameterization convolution and Partial convolution Efficient Layer Aggregation Networks(RPELAN).This module effectively reduces the impact of redundant information generated by traditional convolutional stacking on the network size and detection speed while enhancing the capability to process feature information.We experimentally verified that our generalized one-stage detection network lightweight method based on Grouped Spatial Convolution(GSconv)enhances the detection speed while maintaining accuracy across various state-of-the-art(SOTA)networks.Our experiments conducted on the publicly available Cityscapes dataset demonstrated that YOLO-LF maintained the same accuracy as yolov8n(mAP@0.537.9%),the model volume decreased by 14.3%from 3.259 to=2.804 M,and the Frames Per Second(FPS)increased by 14.48%from 57.47 to 65.79 compared with YOLOv8n,thereby demonstrating its potential for real-time instance segmentation on edge devices.
基金supported by the National Natural Science Foundation of China(No.12202476).
文摘In the PSP(Pressure-Sensitive Paint),image deblurring is essential due to factors such as prolonged camera exposure times and highmodel velocities,which can lead to significant image blurring.Conventional deblurring methods applied to PSP images often suffer from limited accuracy and require extensive computational resources.To address these issues,this study proposes a deep learning-based approach tailored for PSP image deblurring.Considering that PSP applications primarily involve the accurate pressure measurements of complex geometries,the images captured under such conditions exhibit distinctive non-uniform motion blur,presenting challenges for standard deep learning models utilizing convolutional or attention-based techniques.In this paper,we introduce a novel deblurring architecture featuring multiple DAAM(Deformable Ack Attention Module).These modules provide enhanced flexibility for end-to-end deblurring,leveraging irregular convolution operations for efficient feature extraction while employing attention mechanisms interpreted as multiple 1×1 convolutions,subsequently reassembled to enhance performance.Furthermore,we incorporate a RSC(Residual Shortcut Convolution)module for initial feature processing,aimed at reducing redundant computations and improving the learning capacity for representative shallow features.To preserve critical spatial information during upsampling and downsampling,we replace conventional convolutions with wt(Haar wavelet downsampling)and dysample(Upsampling by Dynamic Sampling).This modification significantly enhances high-precision image reconstruction.By integrating these advanced modules within an encoder-decoder framework,we present the DFDNet(Deformable Fusion Deblurring Network)for image blur removal,providing robust technical support for subsequent PSP data analysis.Experimental evaluations on the FY dataset demonstrate the superior performance of our model,achieving competitive results on the GOPRO and HIDE datasets.
基金supported by the National Key R&D Program of China(2024YFB4609801)the National Natural Science Foundation of China(52075289)the Tsinghua-Jiangyin Innovation Special Fund(TJISF,2023JYTH0104).
文摘Photonic computing has emerged as a promising technology for the ever-increasing computational demands of machine learning and artificial intelligence.Due to the advantages in computing speed,integrated photonic chips have attracted wide research attention on performing convolutional neural network algorithm.Programmable photonic chips are vital for achieving practical applications of photonic computing.Herein,a programmable photonic chip based on ultrafast laser-induced phase change is fabricated for photonic computing.Through designing the ultrafast laser pulses,the Sb film integrated into photonic waveguides can be reversibly switched between crystalline and amorphous phase,resulting in a large contrast in refractive index and extinction coefficient.As a consequence,the light transmission of waveguides can be switched between write and erase states.To determine the phase change time,the transient laser-induced phase change dynamics of Sb film are revealed at atomic scale,and the time-resolved transient reflectivity is measured.Based on the integrated photonic chip,photonic convolutional neural networks are built to implement machine learning algorithm,and images recognition task is achieved.This work paves a route for fabricating programmable photonic chips by designed ultrafast laser,which will facilitate the application of photonic computing in artificial intelligence.
基金supported by the Xiamen Science and Technology Subsidy Project(No.2023CXY0318).
文摘Abnormal network traffic, as a frequent security risk, requires a series of techniques to categorize and detect it. Existing network traffic anomaly detection still faces challenges: the inability to fully extract local and global features, as well as the lack of effective mechanisms to capture complex interactions between features;Additionally, when increasing the receptive field to obtain deeper feature representations, the reliance on increasing network depth leads to a significant increase in computational resource consumption, affecting the efficiency and performance of detection. Based on these issues, firstly, this paper proposes a network traffic anomaly detection model based on parallel dilated convolution and residual learning (Res-PDC). To better explore the interactive relationships between features, the traffic samples are converted into two-dimensional matrix. A module combining parallel dilated convolutions and residual learning (res-pdc) was designed to extract local and global features of traffic at different scales. By utilizing res-pdc modules with different dilation rates, we can effectively capture spatial features at different scales and explore feature dependencies spanning wider regions without increasing computational resources. Secondly, to focus and integrate the information in different feature subspaces, further enhance and extract the interactions among the features, multi-head attention is added to Res-PDC, resulting in the final model: multi-head attention enhanced parallel dilated convolution and residual learning (MHA-Res-PDC) for network traffic anomaly detection. Finally, comparisons with other machine learning and deep learning algorithms are conducted on the NSL-KDD and CIC-IDS-2018 datasets. The experimental results demonstrate that the proposed method in this paper can effectively improve the detection performance.
基金supported by the Intelligent System Research Group(ISysRG)supported by Universitas Sriwijaya funded by the Competitive Research 2024.
文摘Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attention, challenges remain, especially when dealing with diverse data types. In this study, we introduce a novel data imputation method based on a modified convolutional neural network, specifically, a Deep Residual-Convolutional Neural Network (DRes-CNN) architecture designed to handle missing values across various datasets. Our approach demonstrates substantial improvements over existing imputation techniques by leveraging residual connections and optimized convolutional layers to capture complex data patterns. We evaluated the model on publicly available datasets, including Medical Information Mart for Intensive Care (MIMIC-III and MIMIC-IV), which contain critical care patient data, and the Beijing Multi-Site Air Quality dataset, which measures environmental air quality. The proposed DRes-CNN method achieved a root mean square error (RMSE) of 0.00006, highlighting its high accuracy and robustness. We also compared with Low Light-Convolutional Neural Network (LL-CNN) and U-Net methods, which had RMSE values of 0.00075 and 0.00073, respectively. This represented an improvement of approximately 92% over LL-CNN and 91% over U-Net. The results showed that this DRes-CNN-based imputation method outperforms current state-of-the-art models. These results established DRes-CNN as a reliable solution for addressing missing data.
基金funded by Soonchunhyang University,Grant Numbers 20241422BK21 FOUR(Fostering Outstanding Universities for Research,Grant Number 5199990914048).
文摘Recommendation systems(RSs)are crucial in personalizing user experiences in digital environments by suggesting relevant content or items.Collaborative filtering(CF)is a widely used personalization technique that leverages user-item interactions to generate recommendations.However,it struggles with challenges like the cold-start problem,scalability issues,and data sparsity.To address these limitations,we develop a Graph Convolutional Networks(GCNs)model that captures the complex network of interactions between users and items,identifying subtle patterns that traditional methods may overlook.We integrate this GCNs model into a federated learning(FL)framework,enabling themodel to learn fromdecentralized datasets.This not only significantly enhances user privacy—a significant improvement over conventionalmodels but also reassures users about the safety of their data.Additionally,by securely incorporating demographic information,our approach further personalizes recommendations and mitigates the coldstart issue without compromising user data.We validate our RSs model using the openMovieLens dataset and evaluate its performance across six key metrics:Precision,Recall,Area Under the Receiver Operating Characteristic Curve(ROC-AUC),F1 Score,Normalized Discounted Cumulative Gain(NDCG),and Mean Reciprocal Rank(MRR).The experimental results demonstrate significant enhancements in recommendation quality,underscoring that combining GCNs with CF in a federated setting provides a transformative solution for advanced recommendation systems.
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.
基金Project supported by the National Natural Science Foundation of China(Grant No.12305303)the Natural Science Foundation of Hunan Province of China(Grant Nos.2023JJ40520,2024JJ2044,and 2021JJ40444)+3 种基金the Science and Technology Innovation Program of Hunan Province,China(Grant No.2020RC3054)the Postgraduate Scientific Research Innovation Project of Hunan Province,China(Grant No.CX20240831)the Natural Science Basic Research Plan in the Shaanxi Province of China(Grant No.2023-JC-QN0015)the Doctoral Research Fund of University of South China(Grant No.200XQD033)。
文摘The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spectrometer(ANIS)at the China Spallation Neutron Source(CSNS).The Yolov3 and MNIST models were implemented on the XILINX28-nm system-on-chip(So C).Meanwhile,the Yolov3 and ResNet50 models were deployed on the XILINX 16-nm Fin FET Ultra Scale+MPSoC.The atmospheric neutron SEEs on the tested CNN systems were comprehensively evaluated from six aspects,including chip type,network architecture,deployment methods,inference time,datasets,and the position of the anchor boxes.The various types of SEE soft errors,SEE cross-sections,and their distribution were analyzed to explore the radiation sensitivities and rules of 28-nm and 16-nm SoC.The current research can provide the technology support of radiation-resistant design of CNN system for developing and applying high-reliability,long-lifespan domestic artificial intelligence chips.
文摘Precision steel balls are critical components in precision bearings.Surface defects on the steel balls will significantly reduce their useful life and cause linear or rotational transmission errors.Human visual inspection of precision steel balls demands significant labor work.Besides,human inspection cannot maintain consistent quality assurance.To address these limitations and reduce inspection time,a convolutional neural network(CNN)based optical inspection system has been developed that automatically detects steel ball defects using a novel designated vertical mechanism.During image detection processing,two key challenges were addressed and resolved.They are the reflection caused by the coaxial light onto the ball center and the image deformation appearing at the edge of the steel balls.The special vertical rotating mechanism utilizing a spinning rod along with a spiral track was developed to enable successful and reliable full steel ball surface inspection during the rod rotation.The combination of the spinning rod and the spiral rotating component effectively rotates the steel ball to facilitate capturing complete surface images.Geometric calculations demonstrate that the steel balls can be completely inspected through specific rotation degrees,with the surface fully captured in 12 photo shots.These images are then analyzed by a CNN to determine surface quality defects.This study presents a new inspection method that enables the entire examination of steel ball surfaces.The successful development of this innovative automated optical inspection system with CNN represents a significant advancement in inspection quality control for precision steel balls.
基金partially funded by the National Natural Science Foundation of China(U2142205)the Guangdong Major Project of Basic and Applied Basic Research(2020B0301030004)+1 种基金the Special Fund for Forecasters of China Meteorological Administration(CMAYBY2020-094)the Graduate Student Research and Innovation Program of Central South University(2023ZZTS0347)。
文摘Traditional meteorological downscaling methods face limitations due to the complex distribution of meteorological variables,which can lead to unstable forecasting results,especially in extreme scenarios.To overcome this issue,we propose a convolutional graph neural network(CGNN)model,which we enhance with multilayer feature fusion and a squeeze-and-excitation block.Additionally,we introduce a spatially balanced mean squared error(SBMSE)loss function to address the imbalanced distribution and spatial variability of meteorological variables.The CGNN is capable of extracting essential spatial features and aggregating them from a global perspective,thereby improving the accuracy of prediction and enhancing the model's generalization ability.Based on the experimental results,CGNN has certain advantages in terms of bias distribution,exhibiting a smaller variance.When it comes to precipitation,both UNet and AE also demonstrate relatively small biases.As for temperature,AE and CNNdense perform outstandingly during the winter.The time correlation coefficients show an improvement of at least 10%at daily and monthly scales for both temperature and precipitation.Furthermore,the SBMSE loss function displays an advantage over existing loss functions in predicting the98th percentile and identifying areas where extreme events occur.However,the SBMSE tends to overestimate the distribution of extreme precipitation,which may be due to the theoretical assumptions about the posterior distribution of data that partially limit the effectiveness of the loss function.In future work,we will further optimize the SBMSE to improve prediction accuracy.
文摘Container-based virtualization technology has been more widely used in edge computing environments recently due to its advantages of lighter resource occupation, faster startup capability, and better resource utilization efficiency. To meet the diverse needs of tasks, it usually needs to instantiate multiple network functions in the form of containers interconnect various generated containers to build a Container Cluster(CC). Then CCs will be deployed on edge service nodes with relatively limited resources. However, the increasingly complex and timevarying nature of tasks brings great challenges to optimal placement of CC. This paper regards the charges for various resources occupied by providing services as revenue, the service efficiency and energy consumption as cost, thus formulates a Mixed Integer Programming(MIP) model to describe the optimal placement of CC on edge service nodes. Furthermore, an Actor-Critic based Deep Reinforcement Learning(DRL) incorporating Graph Convolutional Networks(GCN) framework named as RL-GCN is proposed to solve the optimization problem. The framework obtains an optimal placement strategy through self-learning according to the requirements and objectives of the placement of CC. Particularly, through the introduction of GCN, the features of the association relationship between multiple containers in CCs can be effectively extracted to improve the quality of placement.The experiment results show that under different scales of service nodes and task requests, the proposed method can obtain the improved system performance in terms of placement error ratio, time efficiency of solution output and cumulative system revenue compared with other representative baseline methods.
