Accurate traffic pattern prediction in largescale networks is of great importance for intelligent system management and automatic resource allocation.System-level mobile traffic forecasting has significant challenges ...Accurate traffic pattern prediction in largescale networks is of great importance for intelligent system management and automatic resource allocation.System-level mobile traffic forecasting has significant challenges due to the tremendous temporal and spatial dynamics introduced by diverse Internet user behaviors and frequent traffic migration.Spatialtemporal graph modeling is an efficient approach for analyzing the spatial relations and temporal trends of mobile traffic in a large system.Previous research may not reflect the optimal dependency by ignoring inter-base station dependency or pre-determining the explicit geological distance as the interrelationship of base stations.To overcome the limitations of graph structure,this study proposes an adaptive graph convolutional network(AGCN)that captures the latent spatial dependency by developing self-adaptive dependency matrices and acquires temporal dependency using recurrent neural networks.Evaluated on two mobile network datasets,the experimental results demonstrate that this method outperforms other baselines and reduces the mean absolute error by 3.7%and 5.6%compared to time-series based approaches.展开更多
A fast image segmentation algorithm based on salient features model and spatial-frequency domain adaptive kernel is proposed to solve the accurate discriminate objects problem of online visual detection in such scenes...A fast image segmentation algorithm based on salient features model and spatial-frequency domain adaptive kernel is proposed to solve the accurate discriminate objects problem of online visual detection in such scenes of variable sample morphological characteristics,low contrast and complex background texture.Firstly,by analyzing the spectral component distribution and spatial contour feature of the image,a salient feature model is established in spatial-frequency domain.Then,the salient object detection method based on Gaussian band-pass filter and the design criterion of adaptive convolution kernel are proposed to extract the salient contour feature of the target in spatial and frequency domain.Finally,the selection and growth rules of seed points are improved by integrating the gray level and contour features of the target,and the target is segmented by seeded region growing.Experiments have been performed on Berkeley Segmentation Data Set,as well as sample images of online detection,to verify the effectiveness of the algorithm.The experimental results show that the Jaccard Similarity Coefficient of the segmentation is more than 90%,which indicates that the proposed algorithm can availably extract the target feature information,suppress the background texture and resist noise interference.Besides,the Hausdorff Distance of the segmentation is less than 10,which infers that the proposed algorithm obtains a high evaluation on the target contour preservation.The experimental results also show that the proposed algorithm significantly improves the operation efficiency while obtaining comparable segmentation performance over other algorithms.展开更多
The targeted design of functional materials often requires the concurrent optimization of multiple interdependent properties.For boron-doped graphene(BDG),both the band gap and work function critically influence perfo...The targeted design of functional materials often requires the concurrent optimization of multiple interdependent properties.For boron-doped graphene(BDG),both the band gap and work function critically influence performance in electronic and catalytic applications,yet existing machine learning(ML)approaches typically focus on single-property prediction and rely on hand-crafted features,limiting their generality.Here we present an adaptive edge-aware graph convolutional neural network with multi-task learning(AEGCNN-MTL)for simultaneous prediction of multiple material properties.On a DFT-computed BDG dataset of 2613 structures,AEGCNN-MTL achieved high accuracy(R2=0.9905 for band gap and 0.9778 for work function),and under identical training budgets,outperformed representative single-task GNN baselines.When transferred to the QM9 benchmark,the framework delivered competitive performance across 12 diverse quantum chemical properties,demonstrating strong generalization capability.These results highlight the potential of AEGCNN-MTL as a scalable and accurate tool for high-throughput,multi-property screening and the data-driven discovery of multifunctional materials.展开更多
Geographic visualization is essential for explaining and describing spatiotemporal geographical processes in flow fields.However,due to multi-scale structures and irregular spatial distribution of vortices in complex ...Geographic visualization is essential for explaining and describing spatiotemporal geographical processes in flow fields.However,due to multi-scale structures and irregular spatial distribution of vortices in complex geographic flow fields,existing two-dimensional visualization methods are susceptible to the effects of data accuracy and sampling resolution,resulting in incomplete and inaccurate vortex information.To address this,we propose an adaptive Line Integral Convolution(LIC)based geographic flow field visualization method by means of rotation distance.Our novel framework of rotation distance and its quantification allows for the effective identification and extraction of vortex features in flow fields effectively.We then improve the LIC algorithm using rotation distance by constructing high-frequency noise from it as input to the convolution,with the integration step size adjusted.This approach allows us to effectively distinguish between vortex and non-vortex fields and adaptively represent the details of vortex features in complex geographic flow fields.Our experimental results show that the proposed method leads to more accurate and effective visualization of the geographic flow fields.展开更多
Digital Twin(DT)is used for lifetime monitoring of the drive train and can be a costly option.This proposal adopts the predictive modelling of wind turbines by digital twins by deep learning strategies.Initially,the d...Digital Twin(DT)is used for lifetime monitoring of the drive train and can be a costly option.This proposal adopts the predictive modelling of wind turbines by digital twins by deep learning strategies.Initially,the data is acquired from publicly available wind turbine datasets.Next,the deep features and statistical features are extracted,and the autoencoder is adapted to get the deep features.Then,the Enhanced Marine Predators Algorithm(EMPA)is to select the optimal weighted fused features,where the EMPA would tune the weights used for fusion and the features selection.Finally,the predictive modelling is done via a newly recommended Adaptive Deep Temporal Convolution Network with an Attention Mechanism(ADTCN-AM).It is tuned for precise outcomes with the help of EMPA for forecasting the wind speed and predicting the generated power.The comparative performance analysis of the recently used wind prediction system model shows better efficient results.展开更多
基金supported by the National Natural Science Foundation of China(61975020,62171053)。
文摘Accurate traffic pattern prediction in largescale networks is of great importance for intelligent system management and automatic resource allocation.System-level mobile traffic forecasting has significant challenges due to the tremendous temporal and spatial dynamics introduced by diverse Internet user behaviors and frequent traffic migration.Spatialtemporal graph modeling is an efficient approach for analyzing the spatial relations and temporal trends of mobile traffic in a large system.Previous research may not reflect the optimal dependency by ignoring inter-base station dependency or pre-determining the explicit geological distance as the interrelationship of base stations.To overcome the limitations of graph structure,this study proposes an adaptive graph convolutional network(AGCN)that captures the latent spatial dependency by developing self-adaptive dependency matrices and acquires temporal dependency using recurrent neural networks.Evaluated on two mobile network datasets,the experimental results demonstrate that this method outperforms other baselines and reduces the mean absolute error by 3.7%and 5.6%compared to time-series based approaches.
基金supported by National Natural Science Foundation of China[grant numbers 61573233]Natural Science Foundation of Guangdong,China[grant numbers 2021A1515010661]+1 种基金Special projects in key fields of colleges and universities in Guangdong Province[grant numbers 2020ZDZX2005]Innovation Team Project of University in Guangdong Province[grant numbers 2015KCXTD018].
文摘A fast image segmentation algorithm based on salient features model and spatial-frequency domain adaptive kernel is proposed to solve the accurate discriminate objects problem of online visual detection in such scenes of variable sample morphological characteristics,low contrast and complex background texture.Firstly,by analyzing the spectral component distribution and spatial contour feature of the image,a salient feature model is established in spatial-frequency domain.Then,the salient object detection method based on Gaussian band-pass filter and the design criterion of adaptive convolution kernel are proposed to extract the salient contour feature of the target in spatial and frequency domain.Finally,the selection and growth rules of seed points are improved by integrating the gray level and contour features of the target,and the target is segmented by seeded region growing.Experiments have been performed on Berkeley Segmentation Data Set,as well as sample images of online detection,to verify the effectiveness of the algorithm.The experimental results show that the Jaccard Similarity Coefficient of the segmentation is more than 90%,which indicates that the proposed algorithm can availably extract the target feature information,suppress the background texture and resist noise interference.Besides,the Hausdorff Distance of the segmentation is less than 10,which infers that the proposed algorithm obtains a high evaluation on the target contour preservation.The experimental results also show that the proposed algorithm significantly improves the operation efficiency while obtaining comparable segmentation performance over other algorithms.
基金supported by the key project of science and technology research program of Chongqing Education Commission of China(KJZD-K202501109)the National Natural Science Foundation of China(U22A20434)Scientific research foundation of Ministry of Industry and Information Technology of the People's Republic of China(TC220A04A-43).
文摘The targeted design of functional materials often requires the concurrent optimization of multiple interdependent properties.For boron-doped graphene(BDG),both the band gap and work function critically influence performance in electronic and catalytic applications,yet existing machine learning(ML)approaches typically focus on single-property prediction and rely on hand-crafted features,limiting their generality.Here we present an adaptive edge-aware graph convolutional neural network with multi-task learning(AEGCNN-MTL)for simultaneous prediction of multiple material properties.On a DFT-computed BDG dataset of 2613 structures,AEGCNN-MTL achieved high accuracy(R2=0.9905 for band gap and 0.9778 for work function),and under identical training budgets,outperformed representative single-task GNN baselines.When transferred to the QM9 benchmark,the framework delivered competitive performance across 12 diverse quantum chemical properties,demonstrating strong generalization capability.These results highlight the potential of AEGCNN-MTL as a scalable and accurate tool for high-throughput,multi-property screening and the data-driven discovery of multifunctional materials.
文摘Geographic visualization is essential for explaining and describing spatiotemporal geographical processes in flow fields.However,due to multi-scale structures and irregular spatial distribution of vortices in complex geographic flow fields,existing two-dimensional visualization methods are susceptible to the effects of data accuracy and sampling resolution,resulting in incomplete and inaccurate vortex information.To address this,we propose an adaptive Line Integral Convolution(LIC)based geographic flow field visualization method by means of rotation distance.Our novel framework of rotation distance and its quantification allows for the effective identification and extraction of vortex features in flow fields effectively.We then improve the LIC algorithm using rotation distance by constructing high-frequency noise from it as input to the convolution,with the integration step size adjusted.This approach allows us to effectively distinguish between vortex and non-vortex fields and adaptively represent the details of vortex features in complex geographic flow fields.Our experimental results show that the proposed method leads to more accurate and effective visualization of the geographic flow fields.
文摘Digital Twin(DT)is used for lifetime monitoring of the drive train and can be a costly option.This proposal adopts the predictive modelling of wind turbines by digital twins by deep learning strategies.Initially,the data is acquired from publicly available wind turbine datasets.Next,the deep features and statistical features are extracted,and the autoencoder is adapted to get the deep features.Then,the Enhanced Marine Predators Algorithm(EMPA)is to select the optimal weighted fused features,where the EMPA would tune the weights used for fusion and the features selection.Finally,the predictive modelling is done via a newly recommended Adaptive Deep Temporal Convolution Network with an Attention Mechanism(ADTCN-AM).It is tuned for precise outcomes with the help of EMPA for forecasting the wind speed and predicting the generated power.The comparative performance analysis of the recently used wind prediction system model shows better efficient results.
