Accurate large-scale ocean environment modeling is challenged by multi-scale dynamics,sparse sampling,and measurement noise.This paper presents a fast spatiotemporal(ST)modeling and robust target diagnosis for large-s...Accurate large-scale ocean environment modeling is challenged by multi-scale dynamics,sparse sampling,and measurement noise.This paper presents a fast spatiotemporal(ST)modeling and robust target diagnosis for large-scale ocean environments.First,the four-dimensional field is factorized via a Karhunen-Loève(KL)expansion into orthonormal spatial modes and their temporal features.The spatial modes are further regularized by smooth parametric functions,while the temporal features follow a compact nonlinear evolution,enabling efficient ST fusion for reconstruction.Building on the denoised field,the diagnosis module applies depth-wise Savitzky-Golay smoothing,prominence-based peak search on the vertical temperature gradient,and a half-maximum rule to estimate thermocline depth and thickness.Experiments on a Pacific Ocean dataset demonstrate favorable efficiency,stability,and interpretability.The proposed method achieves a root mean square error 0.1945℃in temperature reconstruction tests,while delivering reliable thermocline localization and thickness estimation suitable for online deployment.展开更多
This paper focuses on the distributed parameter modeling of the zinc electrowinning process(ZEWP)to reveal the spatiotemporal distribution of concentration of zinc ions(CZI)and sulfuric acid(CSA)in the electrolyte.Con...This paper focuses on the distributed parameter modeling of the zinc electrowinning process(ZEWP)to reveal the spatiotemporal distribution of concentration of zinc ions(CZI)and sulfuric acid(CSA)in the electrolyte.Considering the inverse diffusion of such ions in the electrolyte,the dynamic distribution of ions is described by the axial dispersion model.A parameter estimation strategy based on orthogonal approximation has been proposed to estimate the unknown parameters in the process model.Different industrial data sets are used to test the effectiveness of the spatiotemporal distribution model and the proposed parameter estimation approach.The results demonstrate that the analytical model can effectively capture the trends of the electrolysis reaction in time and thus has the potential to implement further optimization and control in the ZEWP.展开更多
The spatiotemporal distribution and relationship between nominal catch-per-unit-ef fort(CPUE) and environment for the jumbo flying squid( Dosidicus gigas) were examined in of fshore Peruvian waters during 2009–2013. ...The spatiotemporal distribution and relationship between nominal catch-per-unit-ef fort(CPUE) and environment for the jumbo flying squid( Dosidicus gigas) were examined in of fshore Peruvian waters during 2009–2013. Three typical oceanographic factors aff ecting the squid habitat were investigated in this research, including sea surface temperature(SST), sea surface salinity(SSS) and sea surface height(SSH). We studied the CPUE-environment relationships for D. gigas using a spatially-lagged version of spatial autoregressive(SAR) model and a generalized additive model(GAM), with the latter for auxiliary and comparative purposes. The annual fishery centroids were distributed broadly in an area bounded by 79.5°–82.7°W and 11.9°–17.1°S, while the monthly fishery centroids were spatially close and lay in a smaller area bounded by 81.0°–81.2°W and 14.3°–15.4°S. Our results show that the preferred environmental ranges for D. gigas offshore Peru were 20.9°–21.9°C for SST, 35.16–35.32 for SSS and 27.2–31.5 cm for SSH in the areas bounded by 78°–80°W/82–84°W and 15°–18°S. Monthly spatial distributions during October to December were predicted using the calibrated GAM and SAR models and general similarities were found between the observed and predicted patterns for the nominal CPUE of D. gigas. The overall accuracies for the hotspots generated by the SAR model were much higher than those produced by the GAM model for all three months. Our results contribute to a better understanding of the spatiotemporal distributions of D. gigas off shore Peru, and off er a new SAR modeling method for advancing fishery science.展开更多
By modeling the spatiotemporal data of the power grid, it is possible to better understand its operational status, identify potential issues and risks, and take timely measures to adjust and optimize the system. Compa...By modeling the spatiotemporal data of the power grid, it is possible to better understand its operational status, identify potential issues and risks, and take timely measures to adjust and optimize the system. Compared to the bus-branch model, the node-breaker model provides higher granularity in describing grid components and can dynamically reflect changes in equipment status, thus improving the efficiency of grid dispatching and operation. This paper proposes a spatiotemporal data modeling method based on a graph database. It elaborates on constructing graph nodes, graph ontology models, and graph entity models from grid dispatch data, describing the construction of the spatiotemporal node-breaker graph model and the transformation to the bus-branch model. Subsequently, by integrating spatiotemporal data attributes into the pre-built static grid graph model, a spatiotemporal evolving graph of the power grid is constructed. Furthermore, the concept of the “Power Grid One Graph” and its requirements in modern power systems are elucidated. Leveraging the constructed spatiotemporal node-breaker graph model and graph computing technology, the paper explores the feasibility of grid situational awareness. Finally, typical applications in an operational provincial grid are showcased, and potential scenarios of the proposed spatiotemporal graph model are discussed.展开更多
Oceanic dissolved oxygen(DO)in the ocean has an indispensable role on supporting biological respiration,maintaining ecological balance and promoting nutrient cycling.According to existing research,the total DO has dec...Oceanic dissolved oxygen(DO)in the ocean has an indispensable role on supporting biological respiration,maintaining ecological balance and promoting nutrient cycling.According to existing research,the total DO has declined by 2%of the total over the past 50 a,and the tropical Pacific Ocean occupied the largest oxygen minimum zone(OMZ)areas.However,the sparse observation data is limited to understanding the dynamic variation and trend of ocean using traditional interpolation methods.In this study,we applied different machine learning algorithms to fit regression models between measured DO,ocean reanalysis physical variables,and spatiotemporal variables.We demonstrate that extreme gradient boosting(XGBoost)model has the best performance,hereby reconstructing a four-dimensional DO dataset of the tropical Pacific Ocean from 1920 to 2023.The results reveal that XGBoost significantly improves the reconstruction performance in the tropical Pacific Ocean,with a 35.3%reduction in root mean-squared error and a 39.5%decrease in mean absolute error.Additionally,we compare the results with three Coupled Model Intercomparison Project Phase 6(CMIP6)models data to confirm the high accuracy of the 4-dimensional reconstruction.Overall,the OMZ mainly dominates the eastern tropical Pacific Ocean,with a slow expansion.This study used XGBoost to efficiently reconstructing 4-dimensional DO enhancing the understanding of the hypoxic expansion in the tropical Pacific Ocean and we foresee that this approach would be extended to reconstruct more ocean elements.展开更多
Accurate predictions and representations of plant growth patterns in simulated and controlled environments are important for addressing various challenges in plant phenomics research.This review explores various works...Accurate predictions and representations of plant growth patterns in simulated and controlled environments are important for addressing various challenges in plant phenomics research.This review explores various works on state-of-the-art predictive pattern recognition techniques,focusing on the spatiotemporal modeling of plant traits and the integration of dynamic environmental interactions.We provide a comprehensive examination of deterministic,probabilistic,and generative modeling approaches,emphasizing their applications in high-throughput phenotyping and simulation-based plant growth forecasting.Key topics include regressions and neural network-based representation models for the task of forecasting,limitations of existing experiment-based deterministic approaches,and the need for dynamic frameworks that incorporate uncertainty and evolving environmental feedback.This review surveys advances in 2D and 3D structured data representations through functional-structural plant models and conditional generative models.We offer a perspective on opportunities for future works,emphasizing the integration of domain-specific knowledge to data-driven methods,improvements to available datasets,and the implementation of these techniques toward real-world applications.展开更多
The ubiquitous spatiotemporal information extracted from Internet texts limits its application in spatiotemporal association and analysis due to its unstructured nature and uncertainty.This study uses ST-Voxel modelin...The ubiquitous spatiotemporal information extracted from Internet texts limits its application in spatiotemporal association and analysis due to its unstructured nature and uncertainty.This study uses ST-Voxel modeling to solve the problem of structured modeling and the association of ubiquitous spatiotemporal information in natural language texts.It provides a new solution for associating ubiquitous spatiotemporal information on the Internet and discovering public opinion.The main contributions of this paper include:(1)It proposes a convolved method for ST-Voxel,which solves the voxel modeling problem of unstructured and uncertain spatiotemporal objects and spatiotemporal relation in natural language texts.Experiments show that this method can effectively model 5 types of spatiotemporal objects and 16 types of uncertain spatiotemporal relation founded in texts;(2)It realizes the unknown event discovery based on voxelized spatiotemporal information association.Experiments show that this method can effectively solve the aggregation of ubiquitous spatiotemporal information in multi-natural language texts,which is conducive to discovering spatiotemporal events.The selection of convolution parameters in voxel modeling is also discussed.A parameter selection method for balancing the discovery capability and discovery accuracy of spatiotemporal events is given.展开更多
As urban carbon neutrality initiatives accelerate,green spaces in cities are playing an increasingly critical role as natural carbon sinks in mitigating greenhouse gas emissions.However,conventional carbon estimation ...As urban carbon neutrality initiatives accelerate,green spaces in cities are playing an increasingly critical role as natural carbon sinks in mitigating greenhouse gas emissions.However,conventional carbon estimation approaches struggle with spatial fragmentation and temporal variability in urban green areas,resulting in limited accuracy and poor adaptability.To address this challenge,this study proposes a deep spatiotemporal modeling framework combining Convolutional Neural Networks(CNN)and Temporal Convolutional Networks(TCN),integrating multi-source remote sensing data from Landsat-8,Sentinel-2,and Moderate Resolution Imaging Spectroradiometer(MODIS)to estimate carbon storage in Guangzhou's green spaces from 2018 to 2023.Experimental results demonstrate that the model achieves robust performance across diverse land types and seasonal conditions,with an overall Root Mean Square Error(RMSE)of 2.71 tC/ha,R^(2)of 0.926,and Structural Similarity Index Measure(SSIM)of 0.841,significantly outperforming traditional statistical and machine learning methods.The study confirms the effectiveness of deep fusion modeling in urban carbon sink estimation and offers a scalable technical pathway to support carbon asset management,green space planning,and low-carbon policy development in complex urban contexts.展开更多
Automated identification and tracking of mesoscale ocean eddies has recently become one research hotspot in physical oceanography. Several methods have been developed and applied to survey the general kinetic and geom...Automated identification and tracking of mesoscale ocean eddies has recently become one research hotspot in physical oceanography. Several methods have been developed and applied to survey the general kinetic and geometric characteristics of the ocean eddies in the South China Sea（SCS）. However, very few studies attempt to examine eddies＇ internal evolution processes. In this study, we reported a hybrid method to trace eddies＇ propagation in the SCS based on their internal structures, which are characterized by eddy centers, footprint borders, and composite borders. Eddy identification and tracking results were represented by a GIS-based spatiotemporal model. Information on instant states, dynamic evolution processes, and events of disappearance, reappearance, split, and mergence is stored in a GIS database. Results were validated by comparing against the ten Dongsha Cyclonic Eddies（DCEs） and the three long-lived anticyclonic eddies（ACEs） in the northern SCS, which were reported in previous literature. Our study confirmed the development of these eddies. Furthermore, we found more DCE-like and ACE-like eddies in these areas from 2005 to 2012 in our database. Spatial distribution analysis of disappearing, reappearing, splitting, and merging activities shows that eddies in the SCS tend to cluster to the northwest of Luzon Island, southwest of Luzon Strait, and around the marginal sea of Vietnam. Kuroshio intrusions and the complex sea floor topography in these areas are the possible factors that lead to these spatial clusters.展开更多
PM2.5 concentration prediction is of great significance to environmental protection and human health.Achieving accurate prediction of PM2.5 concentration has become an important research task.However,PM2.5 pollutants ...PM2.5 concentration prediction is of great significance to environmental protection and human health.Achieving accurate prediction of PM2.5 concentration has become an important research task.However,PM2.5 pollutants can spread in the earth’s atmosphere,causing mutual influence between different cities.To effectively capture the air pollution relationship between cities,this paper proposes a novel spatiotemporal model combining graph attention neural network(GAT)and gated recurrent unit(GRU),named GAT-GRU for PM2.5 concentration prediction.Specifically,GAT is used to learn the spatial dependence of PM2.5 concentration data in different cities,and GRU is to extract the temporal dependence of the long-term data series.The proposed model integrates the learned spatio-temporal dependencies to capture long-term complex spatio-temporal features.Considering that air pollution is related to the meteorological conditions of the city,the knowledge acquired from meteorological data is used in the model to enhance PM2.5 prediction performance.The input of the GAT-GRU model consists of PM2.5 concentration data and meteorological data.In order to verify the effectiveness of the proposed GAT-GRU prediction model,this paper designs experiments on real-world datasets compared with other baselines.Experimental results prove that our model achieves excellent performance in PM2.5 concentration prediction.展开更多
Land cover change has presented clear spatial differences in the New Eurasian Continental Bridge Economic Corridor(NECBEC)region in the 21 st century.A spatiotemporal dynamic probability model and a driving force anal...Land cover change has presented clear spatial differences in the New Eurasian Continental Bridge Economic Corridor(NECBEC)region in the 21 st century.A spatiotemporal dynamic probability model and a driving force analysis model of land cover change were developed to analyze explicitly the dynamics and driving forces of land cover change in the NECBEC region.The results show that the areas of grassland,cropland and built-up land increased by 114.57 million ha,8.41 million ha and 3.96 million ha,and the areas of woodland,other land,and water bodies and wetlands decreased by 74.09 million ha,6.26 million ha,and 46.59 million ha in the NECBEC region between 2001 and 2017,respectively.Woodland and other land were mainly transformed to grassland,and grassland was mainly transformed to woodland and cropland.Built-up land had the largest annual rate of increase and 50%of this originated from cropland.Moreover,since the Belt and Road Initiative(BRI)commenced in 2013,there has been a greater change in the dynamics of land cover change,and the gaps in the socio-economic development level have gradually decreased.The index of socio-economic development was the highest in western Europe,and the lowest in northern Central Asia.The impacts of socio-economic development on cropland and built-up land were greater than those for other land cover types.In general,in the context of rapid socio-economic development,the rate of land cover change in the NECBEC has clearly shown an accelerating trend since 2001,especially after the launch of the BRI in 2013.展开更多
Recent developments in computer vision applications have enabled detection of significant visual objects in video streams.Studies quoted in literature have detected objects from video streams using Spatiotemporal Parti...Recent developments in computer vision applications have enabled detection of significant visual objects in video streams.Studies quoted in literature have detected objects from video streams using Spatiotemporal Particle Swarm Optimization(SPSOM)and Incremental Deep Convolution Neural Networks(IDCNN)for detecting multiple objects.However,the study considered opticalflows resulting in assessing motion contrasts.Existing methods have issue with accuracy and error rates in motion contrast detection.Hence,the overall object detection performance is reduced significantly.Thus,consideration of object motions in videos efficiently is a critical issue to be solved.To overcome the above mentioned problems,this research work proposes a method involving ensemble approaches to and detect objects efficiently from video streams.This work uses a system modeled on swarm optimization and ensemble learning called Spatiotemporal Glowworm Swarm Optimization Model(SGSOM)for detecting multiple significant objects.A steady quality in motion contrasts is maintained in this work by using Chebyshev distance matrix.The proposed system achieves global optimization in its multiple object detection by exploiting spatial/temporal cues and local constraints.Its experimental results show that the proposed system scores 4.8%in Mean Absolute Error(MAE)while achieving 86%in accuracy,81.5%in precision,85%in recall and 81.6%in F-measure and thus proving its utility in detecting multiple objects.展开更多
Understanding how hormones and genes interact to coordinate plant growth in a changing environment is a major challenge in plant developmental biology. Auxin, cytokinin, and ethylene are three important hormones that ...Understanding how hormones and genes interact to coordinate plant growth in a changing environment is a major challenge in plant developmental biology. Auxin, cytokinin, and ethylene are three important hormones that regulate many aspects of plant development. This review critically evaluates the crosstalk between the three hormones in Arabidopsis root development. We integrate a variety of experimental data into a crosstalk network, which reveals multiple layers of complexity in auxin, cytokinin, and ethylene crosstalk. In particular, data integration reveals an additional, largely overlooked link between the ethylene and cytokinin pathways, which acts through a phosphorelay mechanism. This proposed link addresses outstanding questions on whether ethylene application promotes or inhibits receptor kinase activity of the ethylene receptors. Elucidating the complexity in auxin, cytokinin, and ethylene crosstalk requires a combined experimental and systems modeling approach. We evaluate important modeling efforts for establishing how crosstalk between auxin, cytokinin, and ethylene regulates patterning in root develop- ment. We discuss how a novel methodology that iteratively combines experiments with systems modeling analysis is essential for elucidating the complexity in crosstalk of auxin, cytokinin, and ethylene in root development. Finally, we discuss the future challenges from a combined experimental and modeling perspective.展开更多
Content-based video copy detection is an active research field due to the need for copyright pro- tection and business intellectual property protection. This paper gives a probabilistic spatiotemporal fusion approach ...Content-based video copy detection is an active research field due to the need for copyright pro- tection and business intellectual property protection. This paper gives a probabilistic spatiotemporal fusion approach for video copy detection. This approach directly estimates the location of the copy segment with a probabilistic graphical model. The spatial and temporal consistency of the video copy is embedded in the local probability function. An effective local descriptor and a two-level descriptor pairing method are used to build a video copy detection system to evaluate the approach. Tests show that it outperforms the popular voting algorithm and the probabilistic fusion framework based on the Hidden Markov Model, improving F-score （F1） by 8%.展开更多
The transmission and prevalence of Hand,Foot and Mouth Disease(HFMD)are affected by a variety of natural and socio-economic environmental factors.This study aims to quantitatively investigate the non-stationary and sp...The transmission and prevalence of Hand,Foot and Mouth Disease(HFMD)are affected by a variety of natural and socio-economic environmental factors.This study aims to quantitatively investigate the non-stationary and spatially varying associations between various environmental factors and HFMD risk.We collected HFMD surveillance cases and a series of relevant environmental data from 2013 to 2021 in Xi'an,Northwest China.By controlling the spatial and temporal mixture effects of HFMD,we constructed a Bayesian spatiotemporal mapping model and characterized the impacts of different driving factors into global linear,non-stationary and spatially varying effects.The results showed that the impact of meteorological conditions on HFMD risk varies in both type and magnitude above certain thresholds(temperature:30°C,precipitation:70 mm,solar radiation:13000 kJ/m^(2),pressure:945 hPa,humidity:69%).Air pollutants(PM_(2.5),PM_(10),NO_(2))showed an inverted U-shaped relationship with the risk of HFMD,while other air pollutants(O_(3),SO_(2))showed nonlinear fluctuations.Moreover,the driving effect of increasing temperature on HFMD was significant in the 3-year period,while the inhibitory effect of increasing precipitation appeared evident in the 5-year period.In addition,the proportion of urban/suburban/rural area had a strong influence on HFMD,indicating that the incidence of HFMD firstly increased and then decreased during the rapid urbanization process.The influence of population density on HFMD was not only limited by spatial location,but also varied between high and low intervals.Higher road density inhibited the risk of HFMD,but higher night light index promoted the occurrence of HFMD.Our findings further demonstrated that both ecological and socioeconomic environmental factors can pose multiple driving effects on increasing the spatiotemporal risk of HFMD,which is of great significance for effectively responding to the changes in HFMD epidemic outbreaks.展开更多
The spatial and spatiotemporal autoregressive conditional heteroscedasticity(STARCH) models receive increasing attention. In this paper, we introduce a spatiotemporal autoregressive(STAR) model with STARCH errors, whi...The spatial and spatiotemporal autoregressive conditional heteroscedasticity(STARCH) models receive increasing attention. In this paper, we introduce a spatiotemporal autoregressive(STAR) model with STARCH errors, which can capture the spatiotemporal dependence in mean and variance simultaneously. The Bayesian estimation and model selection are considered for our model. By Monte Carlo simulations, it is shown that the Bayesian estimator performs better than the corresponding maximum-likelihood estimator, and the Bayesian model selection can select out the true model in most times. Finally, two empirical examples are given to illustrate the superiority of our models in fitting those data.展开更多
Background:Malaria remains a significant public health concern in Ghana,with varying risk levels across different geographical areas.Malaria affects millions of people each year and imposes a substantial burden on the...Background:Malaria remains a significant public health concern in Ghana,with varying risk levels across different geographical areas.Malaria affects millions of people each year and imposes a substantial burden on the health care system and population.Accurate risk estimation and mapping are crucial for effectively allocating resources and implementing targeted interventions to identify regions with disease hotspots.This study aimed to identify regions exhibiting elevated malaria risk so that public health interventions can be implemented,and to identify malaria risk predictors that can be controlled as part of public health interventions for malaria control.Methods:The data on laboratory-confirmed malaria cases from 2015 to 2021 were obtained from the Ghana Health Service and Ghana Statistical Service.We studied the spatial and spatiotemporal patterns of the relative risk of malaria using Bayesian spatial and spatiotemporal models.The malaria risk for each region was mapped to visually identify regions with malaria hotspots.Clustering and heterogeneity of disease risks were established using correlated and uncorrelated structures via the conditional autoregressive and Gaussian models,respectively.Parameter estimates from the marginal posterior distribution were estimated within the Integrated Nested Laplace Approximation using the R software.Results:The spatial model indicated an increased risk of malaria in the North East,Bono East,Ahafo,Central,Upper West,Brong Ahafo,Ashanti,and Eastern regions.The spatiotemporal model results highlighted an elevated malaria risk in the North East,Upper West,Upper East,Savannah,Bono East,Central,Bono,and Ahafo regions.Both spatial and spatiotemporal models identified the North East,Upper West,Bono East,Central,and Ahafo Regions as hotspots for malaria risk.Substantial variations in risk were evident across regions(H=104.9,P<0.001).Although climatic and economic factors influenced malaria infection,statistical significance was not established.Conclusions:Malaria risk was clustered and varied among regions in Ghana.There are many regions in Ghana that are hotspots for malaria risk,and climate and economic factors have no significant influence on malaria risk.This study could provide information on malaria transmission patterns in Ghana,and contribute to enhance the effectiveness of malaria control strategies.展开更多
Urban landscape forms can be effective in reducing increasing PM_(2.5) concentrations due to urbanization in China,making it crucially important to accurately quantify the spatiotemporal impact of urban landscape form...Urban landscape forms can be effective in reducing increasing PM_(2.5) concentrations due to urbanization in China,making it crucially important to accurately quantify the spatiotemporal impact of urban landscape forms on PM_(2.5) variations.Three landscape indices and six control variables were selected to assess these impacts in 362 Chinese cities during different time scales from 2001 to 2020,using a spatiotemporal geographically weighted regression model,random forest models and partial dependence plots.The results show that there are spatiotemporal differences in the impacts of landscape indices on PM_(2.5).the proportion of urban green infrastructure(PLAND-UGI)and the fractal dimension of urban green infrastructure(FRACT-UGI)exacerbate PM_(2.5) concentrations in the northwest,the proportion of impervious surfaces(PLAND-Impervious)mitigates air pollution in northwest and southwest China,and shannon’s diversity index(SHDI)has seasonal differences in the northwest.PLAND-UGI is the landscape index with the largest contribution(30%)and interpretable range.The relationship between FRACT and PM_(2.5) was more complex than for other landscape indices.The results of this study contribute to a deeper understanding of the spatial and temporal differences in the impact of urban landscape patterns on PM_(2.5),contributing to clean urban development and sustainable development.展开更多
The research of emotion recognition based on electroencephalogram(EEG)signals often ignores the related information between the brain electrode channels and the contextual emotional information existing in EEG signals...The research of emotion recognition based on electroencephalogram(EEG)signals often ignores the related information between the brain electrode channels and the contextual emotional information existing in EEG signals,which may contain important characteristics related to emotional states.Aiming at the above defects,a spatiotemporal emotion recognition method based on a 3-dimensional(3 D)time-frequency domain feature matrix was proposed.Specifically,the extracted time-frequency domain EEG features are first expressed as a 3 D matrix format according to the actual position of the cerebral cortex.Then,the input 3 D matrix is processed successively by multivariate convolutional neural network(MVCNN)and long short-term memory(LSTM)to classify the emotional state.Spatiotemporal emotion recognition method is evaluated on the DEAP data set,and achieved accuracy of 87.58%and 88.50%on arousal and valence dimensions respectively in binary classification tasks,as well as obtained accuracy of 84.58%in four class classification tasks.The experimental results show that 3 D matrix representation can represent emotional information more reasonably than two-dimensional(2 D).In addition,MVCNN and LSTM can utilize the spatial information of the electrode channels and the temporal context information of the EEG signal respectively.展开更多
Unmanned aerial vehicle(UAV)tracking is a critical task in surveillance,security,and autonomous navigation applications.In this study,we propose graph neural network-tracker(GNN-tracker),a novel GNN-based UAV tracking...Unmanned aerial vehicle(UAV)tracking is a critical task in surveillance,security,and autonomous navigation applications.In this study,we propose graph neural network-tracker(GNN-tracker),a novel GNN-based UAV tracking framework that effectively integrates graph-based spatial-temporal modelling,Transformer-based feature extraction,and multi-sensor fusion to enhance tracking robustness and accuracy.Unlike traditional tracking approaches,GNNtracker dynamically constructs a spatiotemporal graph representation,improving identity consistency and reducing tracking errors under OCC-heavy scenarios.Experimental evaluations on optical,thermal,and fused UAV datasets demonstrate the superiority of GNN-tracker(fused)over state-of-the-art methods.The proposed model achieves multiple object tracking accuracy(MOTA)scores of 91.4%(fused),89.1%(optical),and 86.3%(thermal),surpassing TransT by 8.9%in MOTA and 7.7%in higher order tracking accuracy(HOTA).The HOTA scores of 82.3%(fused),80.1%(optical),and 78.7%(thermal)validate its strong object association capabilities,while its frames per second of 58.9(fused),56.8(optical),and 54.3(thermal)ensures real-time performance.Additionally,ablation studies confirm the essential role of graph-based modelling and multi-sensor fusion,with performance drops of up to 8.9%in MOTA when these components are removed.Thus,GNN-tracker(fused)offers a highly accurate,robust,and efficient UAV tracking solution,effectively addressing real-world challenges across diverse environmental conditions and multiple sensor modalities.展开更多
基金supported by the Research Grants Council of Hong Kong SAR under Grant Nos.14217922,14209623,14209424,and 14200524the Environment and Conservation Fund of Hong Kong SAR Project under Grant No.142/2023。
文摘Accurate large-scale ocean environment modeling is challenged by multi-scale dynamics,sparse sampling,and measurement noise.This paper presents a fast spatiotemporal(ST)modeling and robust target diagnosis for large-scale ocean environments.First,the four-dimensional field is factorized via a Karhunen-Loève(KL)expansion into orthonormal spatial modes and their temporal features.The spatial modes are further regularized by smooth parametric functions,while the temporal features follow a compact nonlinear evolution,enabling efficient ST fusion for reconstruction.Building on the denoised field,the diagnosis module applies depth-wise Savitzky-Golay smoothing,prominence-based peak search on the vertical temperature gradient,and a half-maximum rule to estimate thermocline depth and thickness.Experiments on a Pacific Ocean dataset demonstrate favorable efficiency,stability,and interpretability.The proposed method achieves a root mean square error 0.1945℃in temperature reconstruction tests,while delivering reliable thermocline localization and thickness estimation suitable for online deployment.
基金Project(61673400)supported by the National Natural Science Foundation of ChinaProject(2015cx007)supported by the Innovation-driven Plan in Central South University,China+1 种基金Project(61321003)supported by the Foundation for Innovative Research Groups of the National Natural Science Foundation of ChinaProjects(61590921,61590923)supported by the Major Program of the National Natural Science Foundation of China
文摘This paper focuses on the distributed parameter modeling of the zinc electrowinning process(ZEWP)to reveal the spatiotemporal distribution of concentration of zinc ions(CZI)and sulfuric acid(CSA)in the electrolyte.Considering the inverse diffusion of such ions in the electrolyte,the dynamic distribution of ions is described by the axial dispersion model.A parameter estimation strategy based on orthogonal approximation has been proposed to estimate the unknown parameters in the process model.Different industrial data sets are used to test the effectiveness of the spatiotemporal distribution model and the proposed parameter estimation approach.The results demonstrate that the analytical model can effectively capture the trends of the electrolysis reaction in time and thus has the potential to implement further optimization and control in the ZEWP.
基金Supported by the National Natural Science Foundation of China(Nos.41406146,41476129)the Natural Science Foundation of Shanghai Municipality(No.13ZR1419300)the Shanghai Universities FirstClass Disciplines Project-Fisheries(A)
文摘The spatiotemporal distribution and relationship between nominal catch-per-unit-ef fort(CPUE) and environment for the jumbo flying squid( Dosidicus gigas) were examined in of fshore Peruvian waters during 2009–2013. Three typical oceanographic factors aff ecting the squid habitat were investigated in this research, including sea surface temperature(SST), sea surface salinity(SSS) and sea surface height(SSH). We studied the CPUE-environment relationships for D. gigas using a spatially-lagged version of spatial autoregressive(SAR) model and a generalized additive model(GAM), with the latter for auxiliary and comparative purposes. The annual fishery centroids were distributed broadly in an area bounded by 79.5°–82.7°W and 11.9°–17.1°S, while the monthly fishery centroids were spatially close and lay in a smaller area bounded by 81.0°–81.2°W and 14.3°–15.4°S. Our results show that the preferred environmental ranges for D. gigas offshore Peru were 20.9°–21.9°C for SST, 35.16–35.32 for SSS and 27.2–31.5 cm for SSH in the areas bounded by 78°–80°W/82–84°W and 15°–18°S. Monthly spatial distributions during October to December were predicted using the calibrated GAM and SAR models and general similarities were found between the observed and predicted patterns for the nominal CPUE of D. gigas. The overall accuracies for the hotspots generated by the SAR model were much higher than those produced by the GAM model for all three months. Our results contribute to a better understanding of the spatiotemporal distributions of D. gigas off shore Peru, and off er a new SAR modeling method for advancing fishery science.
基金supported by the Project of China Southern Power Grid Digital Grid Research Institute Co.,Ltd.(210002KK52222026)。
文摘By modeling the spatiotemporal data of the power grid, it is possible to better understand its operational status, identify potential issues and risks, and take timely measures to adjust and optimize the system. Compared to the bus-branch model, the node-breaker model provides higher granularity in describing grid components and can dynamically reflect changes in equipment status, thus improving the efficiency of grid dispatching and operation. This paper proposes a spatiotemporal data modeling method based on a graph database. It elaborates on constructing graph nodes, graph ontology models, and graph entity models from grid dispatch data, describing the construction of the spatiotemporal node-breaker graph model and the transformation to the bus-branch model. Subsequently, by integrating spatiotemporal data attributes into the pre-built static grid graph model, a spatiotemporal evolving graph of the power grid is constructed. Furthermore, the concept of the “Power Grid One Graph” and its requirements in modern power systems are elucidated. Leveraging the constructed spatiotemporal node-breaker graph model and graph computing technology, the paper explores the feasibility of grid situational awareness. Finally, typical applications in an operational provincial grid are showcased, and potential scenarios of the proposed spatiotemporal graph model are discussed.
基金The National Natural Science Foundation of China under contract Nos T2421002, 623B2071,and 42125601the National Key R&D Program of China under contract No. 2023YFF0805300
文摘Oceanic dissolved oxygen(DO)in the ocean has an indispensable role on supporting biological respiration,maintaining ecological balance and promoting nutrient cycling.According to existing research,the total DO has declined by 2%of the total over the past 50 a,and the tropical Pacific Ocean occupied the largest oxygen minimum zone(OMZ)areas.However,the sparse observation data is limited to understanding the dynamic variation and trend of ocean using traditional interpolation methods.In this study,we applied different machine learning algorithms to fit regression models between measured DO,ocean reanalysis physical variables,and spatiotemporal variables.We demonstrate that extreme gradient boosting(XGBoost)model has the best performance,hereby reconstructing a four-dimensional DO dataset of the tropical Pacific Ocean from 1920 to 2023.The results reveal that XGBoost significantly improves the reconstruction performance in the tropical Pacific Ocean,with a 35.3%reduction in root mean-squared error and a 39.5%decrease in mean absolute error.Additionally,we compare the results with three Coupled Model Intercomparison Project Phase 6(CMIP6)models data to confirm the high accuracy of the 4-dimensional reconstruction.Overall,the OMZ mainly dominates the eastern tropical Pacific Ocean,with a slow expansion.This study used XGBoost to efficiently reconstructing 4-dimensional DO enhancing the understanding of the hypoxic expansion in the tropical Pacific Ocean and we foresee that this approach would be extended to reconstruct more ocean elements.
基金This work was supported by the Natural Sciences and Engineering Research Council of Canada(RGPIN-2021-03266,RGPIN-2021-03410)Gardyn through the Mitacs Accelerate program(IT16220).
文摘Accurate predictions and representations of plant growth patterns in simulated and controlled environments are important for addressing various challenges in plant phenomics research.This review explores various works on state-of-the-art predictive pattern recognition techniques,focusing on the spatiotemporal modeling of plant traits and the integration of dynamic environmental interactions.We provide a comprehensive examination of deterministic,probabilistic,and generative modeling approaches,emphasizing their applications in high-throughput phenotyping and simulation-based plant growth forecasting.Key topics include regressions and neural network-based representation models for the task of forecasting,limitations of existing experiment-based deterministic approaches,and the need for dynamic frameworks that incorporate uncertainty and evolving environmental feedback.This review surveys advances in 2D and 3D structured data representations through functional-structural plant models and conditional generative models.We offer a perspective on opportunities for future works,emphasizing the integration of domain-specific knowledge to data-driven methods,improvements to available datasets,and the implementation of these techniques toward real-world applications.
基金supported by The Excellent Youth Foundation of Henan Municipal Natural Science Foundation(212300410096)Program of Song Shan Laboratory(Included in the Management of Major Science and Technology Program of Henan Province)under Grant number 221100211000-03The National Key R&D Plan of China(2018YFB0505304).
文摘The ubiquitous spatiotemporal information extracted from Internet texts limits its application in spatiotemporal association and analysis due to its unstructured nature and uncertainty.This study uses ST-Voxel modeling to solve the problem of structured modeling and the association of ubiquitous spatiotemporal information in natural language texts.It provides a new solution for associating ubiquitous spatiotemporal information on the Internet and discovering public opinion.The main contributions of this paper include:(1)It proposes a convolved method for ST-Voxel,which solves the voxel modeling problem of unstructured and uncertain spatiotemporal objects and spatiotemporal relation in natural language texts.Experiments show that this method can effectively model 5 types of spatiotemporal objects and 16 types of uncertain spatiotemporal relation founded in texts;(2)It realizes the unknown event discovery based on voxelized spatiotemporal information association.Experiments show that this method can effectively solve the aggregation of ubiquitous spatiotemporal information in multi-natural language texts,which is conducive to discovering spatiotemporal events.The selection of convolution parameters in voxel modeling is also discussed.A parameter selection method for balancing the discovery capability and discovery accuracy of spatiotemporal events is given.
文摘As urban carbon neutrality initiatives accelerate,green spaces in cities are playing an increasingly critical role as natural carbon sinks in mitigating greenhouse gas emissions.However,conventional carbon estimation approaches struggle with spatial fragmentation and temporal variability in urban green areas,resulting in limited accuracy and poor adaptability.To address this challenge,this study proposes a deep spatiotemporal modeling framework combining Convolutional Neural Networks(CNN)and Temporal Convolutional Networks(TCN),integrating multi-source remote sensing data from Landsat-8,Sentinel-2,and Moderate Resolution Imaging Spectroradiometer(MODIS)to estimate carbon storage in Guangzhou's green spaces from 2018 to 2023.Experimental results demonstrate that the model achieves robust performance across diverse land types and seasonal conditions,with an overall Root Mean Square Error(RMSE)of 2.71 tC/ha,R^(2)of 0.926,and Structural Similarity Index Measure(SSIM)of 0.841,significantly outperforming traditional statistical and machine learning methods.The study confirms the effectiveness of deep fusion modeling in urban carbon sink estimation and offers a scalable technical pathway to support carbon asset management,green space planning,and low-carbon policy development in complex urban contexts.
基金The National Science Foundation of China under contract Nos 41071250 and 41371378the Innovation Projects of the State Key Laboratory of Resource and Environment Information System,Chinese Academy of Sciences,under contract No.088RA500TA
文摘Automated identification and tracking of mesoscale ocean eddies has recently become one research hotspot in physical oceanography. Several methods have been developed and applied to survey the general kinetic and geometric characteristics of the ocean eddies in the South China Sea（SCS）. However, very few studies attempt to examine eddies＇ internal evolution processes. In this study, we reported a hybrid method to trace eddies＇ propagation in the SCS based on their internal structures, which are characterized by eddy centers, footprint borders, and composite borders. Eddy identification and tracking results were represented by a GIS-based spatiotemporal model. Information on instant states, dynamic evolution processes, and events of disappearance, reappearance, split, and mergence is stored in a GIS database. Results were validated by comparing against the ten Dongsha Cyclonic Eddies（DCEs） and the three long-lived anticyclonic eddies（ACEs） in the northern SCS, which were reported in previous literature. Our study confirmed the development of these eddies. Furthermore, we found more DCE-like and ACE-like eddies in these areas from 2005 to 2012 in our database. Spatial distribution analysis of disappearing, reappearing, splitting, and merging activities shows that eddies in the SCS tend to cluster to the northwest of Luzon Island, southwest of Luzon Strait, and around the marginal sea of Vietnam. Kuroshio intrusions and the complex sea floor topography in these areas are the possible factors that lead to these spatial clusters.
基金Authors The research project is partially supported by National Natural ScienceFoundation of China under Grant No. 62072015, U19B2039, U1811463National Key R&D Programof China 2018YFB1600903.
文摘PM2.5 concentration prediction is of great significance to environmental protection and human health.Achieving accurate prediction of PM2.5 concentration has become an important research task.However,PM2.5 pollutants can spread in the earth’s atmosphere,causing mutual influence between different cities.To effectively capture the air pollution relationship between cities,this paper proposes a novel spatiotemporal model combining graph attention neural network(GAT)and gated recurrent unit(GRU),named GAT-GRU for PM2.5 concentration prediction.Specifically,GAT is used to learn the spatial dependence of PM2.5 concentration data in different cities,and GRU is to extract the temporal dependence of the long-term data series.The proposed model integrates the learned spatio-temporal dependencies to capture long-term complex spatio-temporal features.Considering that air pollution is related to the meteorological conditions of the city,the knowledge acquired from meteorological data is used in the model to enhance PM2.5 prediction performance.The input of the GAT-GRU model consists of PM2.5 concentration data and meteorological data.In order to verify the effectiveness of the proposed GAT-GRU prediction model,this paper designs experiments on real-world datasets compared with other baselines.Experimental results prove that our model achieves excellent performance in PM2.5 concentration prediction.
基金National Key R&D Program of China,No.2017YFA0603702,No.2018YFC0507202National Natural Science Foundation of China,No.41971358,No.41930647,No.41977066+1 种基金Strategic Priority Research Program(A)of the Chinese Academy of Sciences,No.XDA20030203Innovation Project of LREIS,No.O88RA600YA。
文摘Land cover change has presented clear spatial differences in the New Eurasian Continental Bridge Economic Corridor(NECBEC)region in the 21 st century.A spatiotemporal dynamic probability model and a driving force analysis model of land cover change were developed to analyze explicitly the dynamics and driving forces of land cover change in the NECBEC region.The results show that the areas of grassland,cropland and built-up land increased by 114.57 million ha,8.41 million ha and 3.96 million ha,and the areas of woodland,other land,and water bodies and wetlands decreased by 74.09 million ha,6.26 million ha,and 46.59 million ha in the NECBEC region between 2001 and 2017,respectively.Woodland and other land were mainly transformed to grassland,and grassland was mainly transformed to woodland and cropland.Built-up land had the largest annual rate of increase and 50%of this originated from cropland.Moreover,since the Belt and Road Initiative(BRI)commenced in 2013,there has been a greater change in the dynamics of land cover change,and the gaps in the socio-economic development level have gradually decreased.The index of socio-economic development was the highest in western Europe,and the lowest in northern Central Asia.The impacts of socio-economic development on cropland and built-up land were greater than those for other land cover types.In general,in the context of rapid socio-economic development,the rate of land cover change in the NECBEC has clearly shown an accelerating trend since 2001,especially after the launch of the BRI in 2013.
文摘Recent developments in computer vision applications have enabled detection of significant visual objects in video streams.Studies quoted in literature have detected objects from video streams using Spatiotemporal Particle Swarm Optimization(SPSOM)and Incremental Deep Convolution Neural Networks(IDCNN)for detecting multiple objects.However,the study considered opticalflows resulting in assessing motion contrasts.Existing methods have issue with accuracy and error rates in motion contrast detection.Hence,the overall object detection performance is reduced significantly.Thus,consideration of object motions in videos efficiently is a critical issue to be solved.To overcome the above mentioned problems,this research work proposes a method involving ensemble approaches to and detect objects efficiently from video streams.This work uses a system modeled on swarm optimization and ensemble learning called Spatiotemporal Glowworm Swarm Optimization Model(SGSOM)for detecting multiple significant objects.A steady quality in motion contrasts is maintained in this work by using Chebyshev distance matrix.The proposed system achieves global optimization in its multiple object detection by exploiting spatial/temporal cues and local constraints.Its experimental results show that the proposed system scores 4.8%in Mean Absolute Error(MAE)while achieving 86%in accuracy,81.5%in precision,85%in recall and 81.6%in F-measure and thus proving its utility in detecting multiple objects.
文摘Understanding how hormones and genes interact to coordinate plant growth in a changing environment is a major challenge in plant developmental biology. Auxin, cytokinin, and ethylene are three important hormones that regulate many aspects of plant development. This review critically evaluates the crosstalk between the three hormones in Arabidopsis root development. We integrate a variety of experimental data into a crosstalk network, which reveals multiple layers of complexity in auxin, cytokinin, and ethylene crosstalk. In particular, data integration reveals an additional, largely overlooked link between the ethylene and cytokinin pathways, which acts through a phosphorelay mechanism. This proposed link addresses outstanding questions on whether ethylene application promotes or inhibits receptor kinase activity of the ethylene receptors. Elucidating the complexity in auxin, cytokinin, and ethylene crosstalk requires a combined experimental and systems modeling approach. We evaluate important modeling efforts for establishing how crosstalk between auxin, cytokinin, and ethylene regulates patterning in root develop- ment. We discuss how a novel methodology that iteratively combines experiments with systems modeling analysis is essential for elucidating the complexity in crosstalk of auxin, cytokinin, and ethylene in root development. Finally, we discuss the future challenges from a combined experimental and modeling perspective.
基金Supported by the National Key Basic Research and Development (863) Program of China (No. 2007CB311003)
文摘Content-based video copy detection is an active research field due to the need for copyright pro- tection and business intellectual property protection. This paper gives a probabilistic spatiotemporal fusion approach for video copy detection. This approach directly estimates the location of the copy segment with a probabilistic graphical model. The spatial and temporal consistency of the video copy is embedded in the local probability function. An effective local descriptor and a two-level descriptor pairing method are used to build a video copy detection system to evaluate the approach. Tests show that it outperforms the popular voting algorithm and the probabilistic fusion framework based on the Hidden Markov Model, improving F-score （F1） by 8%.
基金This work was supported by grants from the National Natural Science Foundation of China(L.S.,grant number:42201448),(K.L.,grant number:82273689)Natural Science Foundation of Hubei Province(L.S.,grant number:2022CFB610).
文摘The transmission and prevalence of Hand,Foot and Mouth Disease(HFMD)are affected by a variety of natural and socio-economic environmental factors.This study aims to quantitatively investigate the non-stationary and spatially varying associations between various environmental factors and HFMD risk.We collected HFMD surveillance cases and a series of relevant environmental data from 2013 to 2021 in Xi'an,Northwest China.By controlling the spatial and temporal mixture effects of HFMD,we constructed a Bayesian spatiotemporal mapping model and characterized the impacts of different driving factors into global linear,non-stationary and spatially varying effects.The results showed that the impact of meteorological conditions on HFMD risk varies in both type and magnitude above certain thresholds(temperature:30°C,precipitation:70 mm,solar radiation:13000 kJ/m^(2),pressure:945 hPa,humidity:69%).Air pollutants(PM_(2.5),PM_(10),NO_(2))showed an inverted U-shaped relationship with the risk of HFMD,while other air pollutants(O_(3),SO_(2))showed nonlinear fluctuations.Moreover,the driving effect of increasing temperature on HFMD was significant in the 3-year period,while the inhibitory effect of increasing precipitation appeared evident in the 5-year period.In addition,the proportion of urban/suburban/rural area had a strong influence on HFMD,indicating that the incidence of HFMD firstly increased and then decreased during the rapid urbanization process.The influence of population density on HFMD was not only limited by spatial location,but also varied between high and low intervals.Higher road density inhibited the risk of HFMD,but higher night light index promoted the occurrence of HFMD.Our findings further demonstrated that both ecological and socioeconomic environmental factors can pose multiple driving effects on increasing the spatiotemporal risk of HFMD,which is of great significance for effectively responding to the changes in HFMD epidemic outbreaks.
基金supported by National Natural Science Foundation of China (No.12271206)Natural Science Foundation of Jilin Province (No.20210101143JC)Science and Technology Research Planning Project of Jilin Provincial Department of Education (No.JJKH20231122KJ)。
文摘The spatial and spatiotemporal autoregressive conditional heteroscedasticity(STARCH) models receive increasing attention. In this paper, we introduce a spatiotemporal autoregressive(STAR) model with STARCH errors, which can capture the spatiotemporal dependence in mean and variance simultaneously. The Bayesian estimation and model selection are considered for our model. By Monte Carlo simulations, it is shown that the Bayesian estimator performs better than the corresponding maximum-likelihood estimator, and the Bayesian model selection can select out the true model in most times. Finally, two empirical examples are given to illustrate the superiority of our models in fitting those data.
文摘Background:Malaria remains a significant public health concern in Ghana,with varying risk levels across different geographical areas.Malaria affects millions of people each year and imposes a substantial burden on the health care system and population.Accurate risk estimation and mapping are crucial for effectively allocating resources and implementing targeted interventions to identify regions with disease hotspots.This study aimed to identify regions exhibiting elevated malaria risk so that public health interventions can be implemented,and to identify malaria risk predictors that can be controlled as part of public health interventions for malaria control.Methods:The data on laboratory-confirmed malaria cases from 2015 to 2021 were obtained from the Ghana Health Service and Ghana Statistical Service.We studied the spatial and spatiotemporal patterns of the relative risk of malaria using Bayesian spatial and spatiotemporal models.The malaria risk for each region was mapped to visually identify regions with malaria hotspots.Clustering and heterogeneity of disease risks were established using correlated and uncorrelated structures via the conditional autoregressive and Gaussian models,respectively.Parameter estimates from the marginal posterior distribution were estimated within the Integrated Nested Laplace Approximation using the R software.Results:The spatial model indicated an increased risk of malaria in the North East,Bono East,Ahafo,Central,Upper West,Brong Ahafo,Ashanti,and Eastern regions.The spatiotemporal model results highlighted an elevated malaria risk in the North East,Upper West,Upper East,Savannah,Bono East,Central,Bono,and Ahafo regions.Both spatial and spatiotemporal models identified the North East,Upper West,Bono East,Central,and Ahafo Regions as hotspots for malaria risk.Substantial variations in risk were evident across regions(H=104.9,P<0.001).Although climatic and economic factors influenced malaria infection,statistical significance was not established.Conclusions:Malaria risk was clustered and varied among regions in Ghana.There are many regions in Ghana that are hotspots for malaria risk,and climate and economic factors have no significant influence on malaria risk.This study could provide information on malaria transmission patterns in Ghana,and contribute to enhance the effectiveness of malaria control strategies.
基金funded by the Natural Science Foundation of Hunan Province,China(2023JJ40443)the Outstanding Youth Project of Hunan Provincial Education Department(22B0088 and 22B0055)+1 种基金the Joint Fund for Regional Innovation and Development of the National Natural Science Foundation(U22A20570)the Science and Technology Innovation Program of Hunan Province(2022RC4027),China.
文摘Urban landscape forms can be effective in reducing increasing PM_(2.5) concentrations due to urbanization in China,making it crucially important to accurately quantify the spatiotemporal impact of urban landscape forms on PM_(2.5) variations.Three landscape indices and six control variables were selected to assess these impacts in 362 Chinese cities during different time scales from 2001 to 2020,using a spatiotemporal geographically weighted regression model,random forest models and partial dependence plots.The results show that there are spatiotemporal differences in the impacts of landscape indices on PM_(2.5).the proportion of urban green infrastructure(PLAND-UGI)and the fractal dimension of urban green infrastructure(FRACT-UGI)exacerbate PM_(2.5) concentrations in the northwest,the proportion of impervious surfaces(PLAND-Impervious)mitigates air pollution in northwest and southwest China,and shannon’s diversity index(SHDI)has seasonal differences in the northwest.PLAND-UGI is the landscape index with the largest contribution(30%)and interpretable range.The relationship between FRACT and PM_(2.5) was more complex than for other landscape indices.The results of this study contribute to a deeper understanding of the spatial and temporal differences in the impact of urban landscape patterns on PM_(2.5),contributing to clean urban development and sustainable development.
基金supported by the National Natural Science Foundation of China(61872126)the Key Scientific Research Project Plan of Colleges and Universities in Henan Province(19A520004)。
文摘The research of emotion recognition based on electroencephalogram(EEG)signals often ignores the related information between the brain electrode channels and the contextual emotional information existing in EEG signals,which may contain important characteristics related to emotional states.Aiming at the above defects,a spatiotemporal emotion recognition method based on a 3-dimensional(3 D)time-frequency domain feature matrix was proposed.Specifically,the extracted time-frequency domain EEG features are first expressed as a 3 D matrix format according to the actual position of the cerebral cortex.Then,the input 3 D matrix is processed successively by multivariate convolutional neural network(MVCNN)and long short-term memory(LSTM)to classify the emotional state.Spatiotemporal emotion recognition method is evaluated on the DEAP data set,and achieved accuracy of 87.58%and 88.50%on arousal and valence dimensions respectively in binary classification tasks,as well as obtained accuracy of 84.58%in four class classification tasks.The experimental results show that 3 D matrix representation can represent emotional information more reasonably than two-dimensional(2 D).In addition,MVCNN and LSTM can utilize the spatial information of the electrode channels and the temporal context information of the EEG signal respectively.
文摘Unmanned aerial vehicle(UAV)tracking is a critical task in surveillance,security,and autonomous navigation applications.In this study,we propose graph neural network-tracker(GNN-tracker),a novel GNN-based UAV tracking framework that effectively integrates graph-based spatial-temporal modelling,Transformer-based feature extraction,and multi-sensor fusion to enhance tracking robustness and accuracy.Unlike traditional tracking approaches,GNNtracker dynamically constructs a spatiotemporal graph representation,improving identity consistency and reducing tracking errors under OCC-heavy scenarios.Experimental evaluations on optical,thermal,and fused UAV datasets demonstrate the superiority of GNN-tracker(fused)over state-of-the-art methods.The proposed model achieves multiple object tracking accuracy(MOTA)scores of 91.4%(fused),89.1%(optical),and 86.3%(thermal),surpassing TransT by 8.9%in MOTA and 7.7%in higher order tracking accuracy(HOTA).The HOTA scores of 82.3%(fused),80.1%(optical),and 78.7%(thermal)validate its strong object association capabilities,while its frames per second of 58.9(fused),56.8(optical),and 54.3(thermal)ensures real-time performance.Additionally,ablation studies confirm the essential role of graph-based modelling and multi-sensor fusion,with performance drops of up to 8.9%in MOTA when these components are removed.Thus,GNN-tracker(fused)offers a highly accurate,robust,and efficient UAV tracking solution,effectively addressing real-world challenges across diverse environmental conditions and multiple sensor modalities.
