Weak measurement offers a powerful framework for probing nonclassical features of quantum mechanics,with anomalous weak values serving as operational signatures of contextuality.While the anomalous weak value verifica...Weak measurement offers a powerful framework for probing nonclassical features of quantum mechanics,with anomalous weak values serving as operational signatures of contextuality.While the anomalous weak value verification of quantum contextuality has been predominantly investigated in the single-photon regime and analyzed under approximation condition of infinitesimally small perturbation strength.This study releases the approximation condition and takes into account the impact of perturbation strength on the rigor of the verification.And the investigation on the verification of contextuality is extended to the multi-photon scenarios for observing the influence of the correlation between photons on the verification.Without the limitation of infinitesimally small probability of disturbance,anomalous weak values are identified as necessary for contextuality to emerge,thereby refining the criterion proposed by Pusey[Phys.Rev.Lett.113200401(2014)].In the multi-photon scenarios,the emergence of contextuality also depends strongly on both the photon number and the photon-number distribution state.In particular,contextuality is found to be maximized when the single-photon component dominates and the second-order correlation is lower.These results highlight the critical role of photon statistics in experimental tests of contextuality via anomalous weak values.展开更多
The field of artificial intelligence has advanced significantly in recent years,but achieving a human-like or Artificial General Intelligence(AGI)remains a theoretical challenge.One hypothesis suggests that a key issu...The field of artificial intelligence has advanced significantly in recent years,but achieving a human-like or Artificial General Intelligence(AGI)remains a theoretical challenge.One hypothesis suggests that a key issue is the formalisation of extracting meaning from information.Meaning emerges through a three-stage interpretative process,where the spectrum of possible interpretations is collapsed into a singular outcome by a particular context.However,this approach currently lacks practical grounding.In this research,we developed a model based on contexts,which applies interpretation principles to the visual information to address this gap.The field of computer vision and object recognition has progressed essentially with artificial neural networks,but these models struggle with geometrically transformed images,such as those that are rotated or shifted,limiting their robustness in real-world applications.Various approaches have been proposed to address this problem.Some of them(Hu moments,spatial transformers,capsule networks,attention and memory mechanisms)share a conceptual connection with the contextual model(CM)discussed in this study.This paper investigates whether CM principles are applicable for interpreting rotated images from the MNIST and Fashion MNIST datasets.The model was implemented in the Rust programming language.It consists of a contextual module and a convolutional neural network(CNN).The CMwas trained on the rotated Mono Icons dataset,which is significantly different from the testing datasets.The CNN module was trained on the original MNIST and Fashion MNIST datasets for interpretation recognition.As a result,the CM was able to recognise the original datasets but encountered rotated images only during testing.The findings show that the model effectively interpreted transformed images by considering them in all available contexts and restoring their original form.This provides a practical foundation for further development of the contextual hypothesis and its relation to theAGI domain.展开更多
Traffic flow prediction constitutes a fundamental component of Intelligent Transportation Systems(ITS),playing a pivotal role in mitigating congestion,enhancing route optimization,and improving the utilization efficie...Traffic flow prediction constitutes a fundamental component of Intelligent Transportation Systems(ITS),playing a pivotal role in mitigating congestion,enhancing route optimization,and improving the utilization efficiency of roadway infrastructure.However,existingmethods struggle in complex traffic scenarios due to static spatio-temporal embedding,restricted multi-scale temporal modeling,and weak representation of local spatial interactions.This study proposes Bi-STAT+,an enhanced bidirectional spatio-temporal attention framework to address existing limitations through three principal contributions:(1)an adaptive spatio-temporal embedding module that dynamically adjusts embeddings to capture complex traffic variations;(2)frequency-domain analysis in the temporal dimension for simultaneous high-frequency details and low-frequency trend extraction;and(3)an agent attention mechanism in the spatial dimension that enhances local feature extraction through dynamic weight allocation.Extensive experiments were performed on four distinct datasets,including two publicly benchmark datasets(PEMS04 and PEMS08)and two private datasets collected from Baotou and Chengdu,China.The results demonstrate that Bi-STAT+consistently outperforms existing methods in terms of MAE,RMSE,and MAPE,while maintaining strong robustness against missing data and noise.Furthermore,the results highlight that prediction accuracy improves significantly with higher sampling rates,providing crucial insights for optimizing real-world deployment scenarios.展开更多
The pseudo-two-dimensional(P2D)model plays an important role in exploring physicochemical mechanisms,predicting the state of health,and improving the fast charge capability for Li-ion batteries(LIBs).However,the fast ...The pseudo-two-dimensional(P2D)model plays an important role in exploring physicochemical mechanisms,predicting the state of health,and improving the fast charge capability for Li-ion batteries(LIBs).However,the fast charge leads to the lithium concentration gradient in the solid and electrolyte phases and the non-uniform electrochemical reaction at the solid/electrolyte interface.In order to decouple charge transfer reactions in LIBs under dynamic conditions,understanding the spatio-temporal resolution of the P2D model is urgently required.Till now,the study of this aspect is still insufficient.This work studies the spatio-temporal resolution for dynamic/static electrochemical impedance spectroscopy(DEIS/SEIS)on multiple scales.In detail,DEIS and SEIS with spatio-temporal resolutions are used to decouple charge transfer reactions in LIBs based on the numerical solution of the P2D model in the frequency domain.The calculated results indicate that decoupling solid diffusion requires a high spatial resolution along the r-direction in particles,decoupling electrolyte diffusion and interfacial transfer reaction requires a high spatial resolution along the x-direction,and decoupling charge transfer reactions in LIBs at an extremely low state of charge(SOC)requires an extremely high temporal resolution along the t-direction.Finally,the optimal range of spatio-temporal resolutions for DEIS/SEIS is derived,and the method to decouple charge transfer reactions with spatio-temporal resolutions is developed.展开更多
This study proposes a novel forecasting framework that simultaneously captures the strong periodicity and irregular meteorological fluctuations inherent in solar radiation time series.Existing approaches typically def...This study proposes a novel forecasting framework that simultaneously captures the strong periodicity and irregular meteorological fluctuations inherent in solar radiation time series.Existing approaches typically define inter-regional correlations using either simple correlation coefficients or distance-based measures when applying spatio-temporal graph neural networks(STGNNs).However,such definitions are prone to generating spurious correlations due to the dominance of periodic structures.To address this limitation,we adopt the Elastic-Band Transform(EBT)to decompose solar radiation into periodic and amplitude-modulated components,which are then modeled independently with separate graph neural networks.The periodic component,characterized by strong nationwide correlations,is learned with a relatively simple architecture,whereas the amplitude-modulated component is modeled with more complex STGNNs that capture climatological similarities between regions.The predictions from the two components are subsequently recombined to yield final forecasts that integrate both periodic patterns and aperiodic variability.The proposed framework is validated with multiple STGNN architectures,and experimental results demonstrate improved predictive accuracy and interpretability compared to conventional methods.展开更多
In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The e...In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms,such as UAV-view and satellite-view images.However,images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform,view,and timing.The existing methods predominantly extract features by segmenting feature maps,which overlook the holistic semantic distribution and structural information of objects,resulting in loss of image information.To address these challenges,dilated neighborhood attention Transformer is employed as the feature extraction backbone,and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation(MMHCA)is proposed.In the proposed MMHCA method,the multiscale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels,establishing feature associations of contextual information with global and local information in the image.Subsequently,the multi-feature representations method is utilized to obtain rich discriminative feature information,bolstering the robustness of model in scenarios characterized by positional shifts,varying distances,and scale ambiguities.Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques.showing outstanding results in UAV localization and navigation.展开更多
Due to water conflicts and allocation in the Lancang-Mekong River Basin(LMRB),the spatio-temporal differentiation of total water resources and the natural-human influence need to be clarified.This work investigated LM...Due to water conflicts and allocation in the Lancang-Mekong River Basin(LMRB),the spatio-temporal differentiation of total water resources and the natural-human influence need to be clarified.This work investigated LMRB's terrestrial water storage anomaly(TWSA)and its spatio-temporal dynamics during 2002–2020.Considering the effects of natural factors and human activities,the respective contributions of climate variability and human activities to terrestrial water storage change(TWSC)were separated.Results showed that:(1)LMRB's TWSA decreased by 0.3158 cm/a.(2)TWSA showed a gradual increase in distribution from southwest of MRB to middle LMRB and from northeast of LRB to middle LMRB.TWSA positively changed in Myanmar while slightly changed in Laos and China.It negatively changed in Vietnam,Thailand and Cambodia.(3)TWSA components decreased in a descending order of soil moisture,groundwater and precipitation.(4)Natural factors had a substantial and spatial differentiated influence on TWSA over the LMRB.(5)Climate variability contributed 79%of TWSC in the LMRB while human activities contributed 21%with an increasing impact after 2008.The TWSC of upstream basin countries was found to be controlled by climate variability while Vietnam and Cambodia's TWSC has been controlled by human activities since 2012.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
Objective To investigate the spatiotemporal patterns and socioeconomic factors influencing the incidence of tuberculosis(TB)in the Guangdong Province between 2010 and 2019.Method Spatial and temporal variations in TB ...Objective To investigate the spatiotemporal patterns and socioeconomic factors influencing the incidence of tuberculosis(TB)in the Guangdong Province between 2010 and 2019.Method Spatial and temporal variations in TB incidence were mapped using heat maps and hierarchical clustering.Socioenvironmental influencing factors were evaluated using a Bayesian spatiotemporal conditional autoregressive(ST-CAR)model.Results Annual incidence of TB in Guangdong decreased from 91.85/100,000 in 2010 to 53.06/100,000in 2019.Spatial hotspots were found in northeastern Guangdong,particularly in Heyuan,Shanwei,and Shantou,while Shenzhen,Dongguan,and Foshan had the lowest rates in the Pearl River Delta.The STCAR model showed that the TB risk was lower with higher per capita Gross Domestic Product(GDP)[Relative Risk(RR),0.91;95%Confidence Interval(CI):0.86–0.98],more the ratio of licensed physicians and physician(RR,0.94;95%CI:0.90-0.98),and higher per capita public expenditure(RR,0.94;95%CI:0.90–0.97),with a marginal effect of population density(RR,0.86;95%CI:0.86–1.00).Conclusion The incidence of TB in Guangdong varies spatially and temporally.Areas with poor economic conditions and insufficient healthcare resources are at an increased risk of TB infection.Strategies focusing on equitable health resource distribution and economic development are the key to TB control.展开更多
Based on the contextual adaptation perspective of Verschueren’s Adaptation Theory,this paper explores the Chinese translation strategies of Japanese quotation sentences in the Yang translation of The Courage of One f...Based on the contextual adaptation perspective of Verschueren’s Adaptation Theory,this paper explores the Chinese translation strategies of Japanese quotation sentences in the Yang translation of The Courage of One from the perspectives of communicative context and linguistic context.The study finds that the Chinese translation of Japanese quotation sentences involves various strategies,including retaining direct quotations,converting direct quotations into statements,transforming direct quotations into attributive+noun forms,and alternating between direct and indirect quotations.This research provides a new perspective for the Chinese translation of Japanese quotation sentences and offers theoretical support for translation practices in cross-cultural communication.展开更多
This study examines the effects of rapid land use changes in India,with a specific focus on Sonipat District in Haryana—a region undergoing significant urban expansion.Over the past two decades,rural landscapes in So...This study examines the effects of rapid land use changes in India,with a specific focus on Sonipat District in Haryana—a region undergoing significant urban expansion.Over the past two decades,rural landscapes in Sonipat have undergone notable transformation,as open spaces and agricultural lands are increasingly converted into residential colonies,commercial hubs,and industrial zones.While such changes reflect economic development and urban growth,they also raise critical concerns about sustainability,especially in terms of food security,groundwater depletion,and environmental degradation.The study examines land use changes between 2000 and 2024 using remote sensing techniques and spatial analysis.It further incorporates secondary data and insights from community-level interactions to assess the socio-economic and ecological impacts of this transformation.The findings indicate rising land fragmentation,loss of agricultural livelihoods,pressure on civic infrastructure,and increasing pollution—factors that threaten long-term regional sustainability.The study underscores the urgent need to reconcile urban development with environmental and social sustainability.By offering a detailed case study of Sonipat,this research contributes to the broader discourse on India’s urbanisation pathways.It aims to provide policymakers,planners,and researchers with evidence-based recommendations to manage land transitions more responsibly,promoting urban growth models that ensure ecological integrity,equitable development,and long-term resilience.展开更多
As Deepfake technology continues to evolve,the distinction between real and fake content becomes increasingly blurred.Most existing Deepfake video detectionmethods rely on single-frame facial image features,which limi...As Deepfake technology continues to evolve,the distinction between real and fake content becomes increasingly blurred.Most existing Deepfake video detectionmethods rely on single-frame facial image features,which limits their ability to capture temporal differences between frames.Current methods also exhibit limited generalization capabilities,struggling to detect content generated by unknown forgery algorithms.Moreover,the diversity and complexity of forgery techniques introduced by Artificial Intelligence Generated Content(AIGC)present significant challenges for traditional detection frameworks,whichmust balance high detection accuracy with robust performance.To address these challenges,we propose a novel Deepfake detection framework that combines a two-stream convolutional network with a Vision Transformer(ViT)module to enhance spatio-temporal feature representation.The ViT model extracts spatial features from the forged video,while the 3D convolutional network captures temporal features.The 3D convolution enables cross-frame feature extraction,allowing the model to detect subtle facial changes between frames.The confidence scores from both the ViT and 3D convolution submodels are fused at the decision layer,enabling themodel to effectively handle unknown forgery techniques.Focusing on Deepfake videos and GAN-generated images,the proposed approach is evaluated on two widely used public face forgery datasets.Compared to existing state-of-theartmethods,it achieves higher detection accuracy and better generalization performance,offering a robust solution for deepfake detection in real-world scenarios.展开更多
Sandfly fever is a viral infectious disease transmitted by sand flies that is widely prevalent in tropical and subtropical regions.Previous studies on its infection mechanism,immune response and diagnosis and treatmen...Sandfly fever is a viral infectious disease transmitted by sand flies that is widely prevalent in tropical and subtropical regions.Previous studies on its infection mechanism,immune response and diagnosis and treatment methods were lack of systematic.This study applied spatio-temporal omics technology to comprehensively explain the dynamic changes of immunity in the incubation period,exacerbation period,peak period and recovery period of Sandfl y fever,and integrated with diff erent coping strategies.To provide new research ideas for its overall research.展开更多
Agriculture holds a pivotal position in the economic fabric of every nation,yet concerns about agricultural carbon emission intensity(ACI)have become a major hurdle to achieving global economic sustainability.Focusing...Agriculture holds a pivotal position in the economic fabric of every nation,yet concerns about agricultural carbon emission intensity(ACI)have become a major hurdle to achieving global economic sustainability.Focusing on 31 provincial-level regions in China,this study uses the Exploratory Spatio-temporal Data Analysis(ESTDA)and Panel Quantile Regression(PQR)model to analyze the spatio-temporal interaction characteristics and influencing factors of ACI in China from 2004 to 2023.The findings are as follows:(1)ACI showed an overall downward trend,and the spatial distribution pattern was characterized by“high in the western region and low along the southeastern coast”.Although the overall disparity tended to converge,some high-carbon-intensity regions exhibited extreme trends.ACI displayed clear spatial directionality,with the spatial center shifting steadily toward the northeast.(2)Regions in the northwest,northeast,and central-south parts exhibited strong local spatial structural dynamics,and the local spatial dependence of ACI in each region showed a nonlinear trend.Generally speaking,the spatial association pattern demonstrated a certain degree of inertia in spatial transfer,reflecting strong path dependence or spatial lock-in characteristics.(3)Optimization of industrial structure and improvement in agricultural mechanization will increase ACI,while economic development can effectively reduce it.The impact of urbanization on ACI exhibits a nonlinear pattern.The coordinated development of economic growth and urbanization significantly reduces ACI,with a stronger emission reduction observed in regions with low ACI.The optimization of industrial structure,when combined with urbanization and environmental regulation,contributes to significant emission reductions particularly in high-ACI areas.Similarly,the synergy between agricultural mechanization and urbanization effectively lowers emissions in low-ACI regions,though this effect diminishes in areas with higher ACI.展开更多
Sloping farmland,particularly in mountainous and hilly areas,constitutes a significant component of regional farmland resources.An investigation into the spatio-temporal pattern of sloping farmland and its influencing...Sloping farmland,particularly in mountainous and hilly areas,constitutes a significant component of regional farmland resources.An investigation into the spatio-temporal pattern of sloping farmland and its influencing factors in China is imperative for the efficient utilization of farmland and the optimization of land space.We used land use transfer matrix,geographically weighted regression model and geographical detector to conduct this study.Results showed that sloping farmland in China firstly decreased and then increased from 2000 to 2020.The proportion of sloping farmland decreased radially outward from Sichuan basin to the surrounding areas.Change rates of sloping farmland with different slopes varied and the slope with 6°-15°underwent the fastest changes.The influencing factors of farmland at various slope degrees were different.For sloping farmland below 15°,land use intensity and elevation had the greatest contribution.For sloping farmland between 15°and 25°,elevation,land use intensity,and population density were the main influencing factors.Sloping farmland above 25°was mostly affected by natural factors.This study can provide scientific basis for rational development and protection of sloping farmland.展开更多
Federated learning(FL)is an intricate and privacy-preserving technique that enables distributed mobile devices to collaboratively train a machine learning model.However,in real-world FL scenarios,the training performa...Federated learning(FL)is an intricate and privacy-preserving technique that enables distributed mobile devices to collaboratively train a machine learning model.However,in real-world FL scenarios,the training performance is affected by a combination of factors such as the mobility of user devices,limited communication and computational resources,thus making the user scheduling problem crucial.To tackle this problem,we jointly consider the user mobility,communication and computational capacities,and develop a stochastic optimization problem to minimize the convergence time.Specifically,we first establish a convergence bound on the training performance based on the heterogeneity of users’data,and then leverage this bound to derive the participation rate for each user.After deriving the user-specific participation rate,we aim to minimize the training latency by optimizing user scheduling under the constraints of the energy consumption and participation rate.Afterward,we transform this optimization problem to the contextual multi-armed bandit framework based on the Lyapunov method and solve it with the submodular reward enhanced linear upper confidence bound(SR-linUCB)algorithm.Experimental results demonstrate the superiority of our proposed algorithm on the training performance and time consumption compared with stateof-the-art algorithms for both independent and identically distributed(IID)and non-IID settings.展开更多
Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decode...Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.展开更多
Electrocardiogram (ECG) analysis is critical for detecting arrhythmias, but traditional methods struggle with large-scale Electrocardiogram data and rare arrhythmia events in imbalanced datasets. These methods fail to...Electrocardiogram (ECG) analysis is critical for detecting arrhythmias, but traditional methods struggle with large-scale Electrocardiogram data and rare arrhythmia events in imbalanced datasets. These methods fail to perform multi-perspective learning of temporal signals and Electrocardiogram images, nor can they fully extract the latent information within the data, falling short of the accuracy required by clinicians. Therefore, this paper proposes an innovative hybrid multimodal spatiotemporal neural network to address these challenges. The model employs a multimodal data augmentation framework integrating visual and signal-based features to enhance the classification performance of rare arrhythmias in imbalanced datasets. Additionally, the spatiotemporal fusion module incorporates a spatiotemporal graph convolutional network to jointly model temporal and spatial features, uncovering complex dependencies within the Electrocardiogram data and improving the model’s ability to represent complex patterns. In experiments conducted on the MIT-BIH arrhythmia dataset, the model achieved 99.95% accuracy, 99.80% recall, and a 99.78% F1 score. The model was further validated for generalization using the clinical INCART arrhythmia dataset, and the results demonstrated its effectiveness in terms of both generalization and robustness.展开更多
The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gaine...The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.展开更多
Exploring the spatial evolution patterns of land use in creative urban tourism complexes provides theoretical and decision-making support to foster creative tourism projects.This study focuses on the Hangzhou Leisure ...Exploring the spatial evolution patterns of land use in creative urban tourism complexes provides theoretical and decision-making support to foster creative tourism projects.This study focuses on the Hangzhou Leisure Expo Garden as a case study,utilizing a land use change index model to analyze the spatial evolution characteristics and dynamic processes of creative urban tourism complexes,as well as to explore their spatial differentiation mechanisms.The analysis indicates that Hangzhou Leisure Expo Garden,initially a derelict industrial area dominated by production and residential land use,has evolved into a creative urban tourism complex with tourism comprehensive service land at its core,going through the pattern evolution processes of“constrained sprawl,”“intensive expansion,”and“random integration.”From the perspective of tourism human-land relationships,the formation of land use evolution patterns in creative urban tourism complexes results from various stakeholders(government,tourism enterprises,residents,tourists,etc.),as humanistic factors,continuously adapting to specific urban spaces,which are considered as geographical elements and have locational advantages and are oriented towards economic and social values.Based on the acquisition of stakeholder interests,the transformation of resource-disadvantaged areas into tourism advantage areas is facilitated,thereby achieving the re-creation of tourism creative space and promoting intensive spatial growth.展开更多
基金Project supported by the National Natural Science Foun-dation of China(Grant Nos.62371199 and 62071186)the Natural Science Foundation of Guangdong Province,China(Grant No.2024A1515012427)+1 种基金the Quantum Science Strate-gic Initiative Project of Guangdong Province,China(Grant No.GDZX2305001)the Key Laboratory Project of Guangdong Province,China(Grant No.2020B1212060066).
文摘Weak measurement offers a powerful framework for probing nonclassical features of quantum mechanics,with anomalous weak values serving as operational signatures of contextuality.While the anomalous weak value verification of quantum contextuality has been predominantly investigated in the single-photon regime and analyzed under approximation condition of infinitesimally small perturbation strength.This study releases the approximation condition and takes into account the impact of perturbation strength on the rigor of the verification.And the investigation on the verification of contextuality is extended to the multi-photon scenarios for observing the influence of the correlation between photons on the verification.Without the limitation of infinitesimally small probability of disturbance,anomalous weak values are identified as necessary for contextuality to emerge,thereby refining the criterion proposed by Pusey[Phys.Rev.Lett.113200401(2014)].In the multi-photon scenarios,the emergence of contextuality also depends strongly on both the photon number and the photon-number distribution state.In particular,contextuality is found to be maximized when the single-photon component dominates and the second-order correlation is lower.These results highlight the critical role of photon statistics in experimental tests of contextuality via anomalous weak values.
文摘The field of artificial intelligence has advanced significantly in recent years,but achieving a human-like or Artificial General Intelligence(AGI)remains a theoretical challenge.One hypothesis suggests that a key issue is the formalisation of extracting meaning from information.Meaning emerges through a three-stage interpretative process,where the spectrum of possible interpretations is collapsed into a singular outcome by a particular context.However,this approach currently lacks practical grounding.In this research,we developed a model based on contexts,which applies interpretation principles to the visual information to address this gap.The field of computer vision and object recognition has progressed essentially with artificial neural networks,but these models struggle with geometrically transformed images,such as those that are rotated or shifted,limiting their robustness in real-world applications.Various approaches have been proposed to address this problem.Some of them(Hu moments,spatial transformers,capsule networks,attention and memory mechanisms)share a conceptual connection with the contextual model(CM)discussed in this study.This paper investigates whether CM principles are applicable for interpreting rotated images from the MNIST and Fashion MNIST datasets.The model was implemented in the Rust programming language.It consists of a contextual module and a convolutional neural network(CNN).The CMwas trained on the rotated Mono Icons dataset,which is significantly different from the testing datasets.The CNN module was trained on the original MNIST and Fashion MNIST datasets for interpretation recognition.As a result,the CM was able to recognise the original datasets but encountered rotated images only during testing.The findings show that the model effectively interpreted transformed images by considering them in all available contexts and restoring their original form.This provides a practical foundation for further development of the contextual hypothesis and its relation to theAGI domain.
基金partly supported by the Youth Foundation of the Inner Mongolia Natural Science Foundation[grant number 2024QN06017 and 2025MS06022]the Basic Scientific Research Business Fee Project for Universities in Inner Mongolia[grant numbers 2023XKJX019 and 2023XKJX024]the Central Guidance on Local Science and Technology Development Fund through[grant number 2024ZY0084].
文摘Traffic flow prediction constitutes a fundamental component of Intelligent Transportation Systems(ITS),playing a pivotal role in mitigating congestion,enhancing route optimization,and improving the utilization efficiency of roadway infrastructure.However,existingmethods struggle in complex traffic scenarios due to static spatio-temporal embedding,restricted multi-scale temporal modeling,and weak representation of local spatial interactions.This study proposes Bi-STAT+,an enhanced bidirectional spatio-temporal attention framework to address existing limitations through three principal contributions:(1)an adaptive spatio-temporal embedding module that dynamically adjusts embeddings to capture complex traffic variations;(2)frequency-domain analysis in the temporal dimension for simultaneous high-frequency details and low-frequency trend extraction;and(3)an agent attention mechanism in the spatial dimension that enhances local feature extraction through dynamic weight allocation.Extensive experiments were performed on four distinct datasets,including two publicly benchmark datasets(PEMS04 and PEMS08)and two private datasets collected from Baotou and Chengdu,China.The results demonstrate that Bi-STAT+consistently outperforms existing methods in terms of MAE,RMSE,and MAPE,while maintaining strong robustness against missing data and noise.Furthermore,the results highlight that prediction accuracy improves significantly with higher sampling rates,providing crucial insights for optimizing real-world deployment scenarios.
基金supported by the National Natural Science Foundation of China(Nos.22479092 and 22078190)。
文摘The pseudo-two-dimensional(P2D)model plays an important role in exploring physicochemical mechanisms,predicting the state of health,and improving the fast charge capability for Li-ion batteries(LIBs).However,the fast charge leads to the lithium concentration gradient in the solid and electrolyte phases and the non-uniform electrochemical reaction at the solid/electrolyte interface.In order to decouple charge transfer reactions in LIBs under dynamic conditions,understanding the spatio-temporal resolution of the P2D model is urgently required.Till now,the study of this aspect is still insufficient.This work studies the spatio-temporal resolution for dynamic/static electrochemical impedance spectroscopy(DEIS/SEIS)on multiple scales.In detail,DEIS and SEIS with spatio-temporal resolutions are used to decouple charge transfer reactions in LIBs based on the numerical solution of the P2D model in the frequency domain.The calculated results indicate that decoupling solid diffusion requires a high spatial resolution along the r-direction in particles,decoupling electrolyte diffusion and interfacial transfer reaction requires a high spatial resolution along the x-direction,and decoupling charge transfer reactions in LIBs at an extremely low state of charge(SOC)requires an extremely high temporal resolution along the t-direction.Finally,the optimal range of spatio-temporal resolutions for DEIS/SEIS is derived,and the method to decouple charge transfer reactions with spatio-temporal resolutions is developed.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(RS-2023-00249743).
文摘This study proposes a novel forecasting framework that simultaneously captures the strong periodicity and irregular meteorological fluctuations inherent in solar radiation time series.Existing approaches typically define inter-regional correlations using either simple correlation coefficients or distance-based measures when applying spatio-temporal graph neural networks(STGNNs).However,such definitions are prone to generating spurious correlations due to the dominance of periodic structures.To address this limitation,we adopt the Elastic-Band Transform(EBT)to decompose solar radiation into periodic and amplitude-modulated components,which are then modeled independently with separate graph neural networks.The periodic component,characterized by strong nationwide correlations,is learned with a relatively simple architecture,whereas the amplitude-modulated component is modeled with more complex STGNNs that capture climatological similarities between regions.The predictions from the two components are subsequently recombined to yield final forecasts that integrate both periodic patterns and aperiodic variability.The proposed framework is validated with multiple STGNN architectures,and experimental results demonstrate improved predictive accuracy and interpretability compared to conventional methods.
基金supported by the National Natural Science Foundation of China(Nos.12072027,62103052,61603346 and 62103379)the Henan Key Laboratory of General Aviation Technology,China(No.ZHKF-230201)+3 种基金the Funding for the Open Research Project of the Rotor Aerodynamics Key Laboratory,China(No.RAL20200101)the Key Research and Development Program of Henan Province,China(Nos.241111222000 and 241111222900)the Key Science and Technology Program of Henan Province,China(No.232102220067)the Scholarship Funding from the China Scholarship Council(No.202206030079).
文摘In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms,such as UAV-view and satellite-view images.However,images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform,view,and timing.The existing methods predominantly extract features by segmenting feature maps,which overlook the holistic semantic distribution and structural information of objects,resulting in loss of image information.To address these challenges,dilated neighborhood attention Transformer is employed as the feature extraction backbone,and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation(MMHCA)is proposed.In the proposed MMHCA method,the multiscale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels,establishing feature associations of contextual information with global and local information in the image.Subsequently,the multi-feature representations method is utilized to obtain rich discriminative feature information,bolstering the robustness of model in scenarios characterized by positional shifts,varying distances,and scale ambiguities.Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques.showing outstanding results in UAV localization and navigation.
基金National Natural Science Foundation of China,No.42161006Yunnan Fundamental Research Projects No.202201AT070094,No.202301BF070001-004+1 种基金Special Project for High-level Talents of Yunnan Province for Young Top Talents,No.C6213001159European Research Council(ERC)Starting-Grant STORIES,No.101040939。
文摘Due to water conflicts and allocation in the Lancang-Mekong River Basin(LMRB),the spatio-temporal differentiation of total water resources and the natural-human influence need to be clarified.This work investigated LMRB's terrestrial water storage anomaly(TWSA)and its spatio-temporal dynamics during 2002–2020.Considering the effects of natural factors and human activities,the respective contributions of climate variability and human activities to terrestrial water storage change(TWSC)were separated.Results showed that:(1)LMRB's TWSA decreased by 0.3158 cm/a.(2)TWSA showed a gradual increase in distribution from southwest of MRB to middle LMRB and from northeast of LRB to middle LMRB.TWSA positively changed in Myanmar while slightly changed in Laos and China.It negatively changed in Vietnam,Thailand and Cambodia.(3)TWSA components decreased in a descending order of soil moisture,groundwater and precipitation.(4)Natural factors had a substantial and spatial differentiated influence on TWSA over the LMRB.(5)Climate variability contributed 79%of TWSC in the LMRB while human activities contributed 21%with an increasing impact after 2008.The TWSC of upstream basin countries was found to be controlled by climate variability while Vietnam and Cambodia's TWSC has been controlled by human activities since 2012.
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 Guangdong Provincial Clinical Research Center for Tuberculosis(No.2020B1111170014)。
文摘Objective To investigate the spatiotemporal patterns and socioeconomic factors influencing the incidence of tuberculosis(TB)in the Guangdong Province between 2010 and 2019.Method Spatial and temporal variations in TB incidence were mapped using heat maps and hierarchical clustering.Socioenvironmental influencing factors were evaluated using a Bayesian spatiotemporal conditional autoregressive(ST-CAR)model.Results Annual incidence of TB in Guangdong decreased from 91.85/100,000 in 2010 to 53.06/100,000in 2019.Spatial hotspots were found in northeastern Guangdong,particularly in Heyuan,Shanwei,and Shantou,while Shenzhen,Dongguan,and Foshan had the lowest rates in the Pearl River Delta.The STCAR model showed that the TB risk was lower with higher per capita Gross Domestic Product(GDP)[Relative Risk(RR),0.91;95%Confidence Interval(CI):0.86–0.98],more the ratio of licensed physicians and physician(RR,0.94;95%CI:0.90-0.98),and higher per capita public expenditure(RR,0.94;95%CI:0.90–0.97),with a marginal effect of population density(RR,0.86;95%CI:0.86–1.00).Conclusion The incidence of TB in Guangdong varies spatially and temporally.Areas with poor economic conditions and insufficient healthcare resources are at an increased risk of TB infection.Strategies focusing on equitable health resource distribution and economic development are the key to TB control.
文摘Based on the contextual adaptation perspective of Verschueren’s Adaptation Theory,this paper explores the Chinese translation strategies of Japanese quotation sentences in the Yang translation of The Courage of One from the perspectives of communicative context and linguistic context.The study finds that the Chinese translation of Japanese quotation sentences involves various strategies,including retaining direct quotations,converting direct quotations into statements,transforming direct quotations into attributive+noun forms,and alternating between direct and indirect quotations.This research provides a new perspective for the Chinese translation of Japanese quotation sentences and offers theoretical support for translation practices in cross-cultural communication.
文摘This study examines the effects of rapid land use changes in India,with a specific focus on Sonipat District in Haryana—a region undergoing significant urban expansion.Over the past two decades,rural landscapes in Sonipat have undergone notable transformation,as open spaces and agricultural lands are increasingly converted into residential colonies,commercial hubs,and industrial zones.While such changes reflect economic development and urban growth,they also raise critical concerns about sustainability,especially in terms of food security,groundwater depletion,and environmental degradation.The study examines land use changes between 2000 and 2024 using remote sensing techniques and spatial analysis.It further incorporates secondary data and insights from community-level interactions to assess the socio-economic and ecological impacts of this transformation.The findings indicate rising land fragmentation,loss of agricultural livelihoods,pressure on civic infrastructure,and increasing pollution—factors that threaten long-term regional sustainability.The study underscores the urgent need to reconcile urban development with environmental and social sustainability.By offering a detailed case study of Sonipat,this research contributes to the broader discourse on India’s urbanisation pathways.It aims to provide policymakers,planners,and researchers with evidence-based recommendations to manage land transitions more responsibly,promoting urban growth models that ensure ecological integrity,equitable development,and long-term resilience.
基金supported by National Natural Science Foundation of China(Nos.62477026,62177029,61807020)Humanities and Social Sciences Research Program of the Ministry of Education of China(No.23YJAZH047)the Startup Foundation for Introducing Talent of Nanjing University of Posts and Communications under Grant NY222034.
文摘As Deepfake technology continues to evolve,the distinction between real and fake content becomes increasingly blurred.Most existing Deepfake video detectionmethods rely on single-frame facial image features,which limits their ability to capture temporal differences between frames.Current methods also exhibit limited generalization capabilities,struggling to detect content generated by unknown forgery algorithms.Moreover,the diversity and complexity of forgery techniques introduced by Artificial Intelligence Generated Content(AIGC)present significant challenges for traditional detection frameworks,whichmust balance high detection accuracy with robust performance.To address these challenges,we propose a novel Deepfake detection framework that combines a two-stream convolutional network with a Vision Transformer(ViT)module to enhance spatio-temporal feature representation.The ViT model extracts spatial features from the forged video,while the 3D convolutional network captures temporal features.The 3D convolution enables cross-frame feature extraction,allowing the model to detect subtle facial changes between frames.The confidence scores from both the ViT and 3D convolution submodels are fused at the decision layer,enabling themodel to effectively handle unknown forgery techniques.Focusing on Deepfake videos and GAN-generated images,the proposed approach is evaluated on two widely used public face forgery datasets.Compared to existing state-of-theartmethods,it achieves higher detection accuracy and better generalization performance,offering a robust solution for deepfake detection in real-world scenarios.
基金College Students Innovation and Entrepreneurship Training Program(X202511049398)College Students Innovation and Entrepreneurship Training Program(X202511049201)+1 种基金College Students Innovation and Entrepreneurship Training Program(X202511258005S)University-Level Research Funding Program of Hainan Science and Technology Vocational University(HKKY2024-87)。
文摘Sandfly fever is a viral infectious disease transmitted by sand flies that is widely prevalent in tropical and subtropical regions.Previous studies on its infection mechanism,immune response and diagnosis and treatment methods were lack of systematic.This study applied spatio-temporal omics technology to comprehensively explain the dynamic changes of immunity in the incubation period,exacerbation period,peak period and recovery period of Sandfl y fever,and integrated with diff erent coping strategies.To provide new research ideas for its overall research.
基金National Natural Science Foundation of China,No.42230106,No.42171250State Key Laboratory of Earth Surface Processes and Resource Ecology,No.2022-ZD-04。
文摘Agriculture holds a pivotal position in the economic fabric of every nation,yet concerns about agricultural carbon emission intensity(ACI)have become a major hurdle to achieving global economic sustainability.Focusing on 31 provincial-level regions in China,this study uses the Exploratory Spatio-temporal Data Analysis(ESTDA)and Panel Quantile Regression(PQR)model to analyze the spatio-temporal interaction characteristics and influencing factors of ACI in China from 2004 to 2023.The findings are as follows:(1)ACI showed an overall downward trend,and the spatial distribution pattern was characterized by“high in the western region and low along the southeastern coast”.Although the overall disparity tended to converge,some high-carbon-intensity regions exhibited extreme trends.ACI displayed clear spatial directionality,with the spatial center shifting steadily toward the northeast.(2)Regions in the northwest,northeast,and central-south parts exhibited strong local spatial structural dynamics,and the local spatial dependence of ACI in each region showed a nonlinear trend.Generally speaking,the spatial association pattern demonstrated a certain degree of inertia in spatial transfer,reflecting strong path dependence or spatial lock-in characteristics.(3)Optimization of industrial structure and improvement in agricultural mechanization will increase ACI,while economic development can effectively reduce it.The impact of urbanization on ACI exhibits a nonlinear pattern.The coordinated development of economic growth and urbanization significantly reduces ACI,with a stronger emission reduction observed in regions with low ACI.The optimization of industrial structure,when combined with urbanization and environmental regulation,contributes to significant emission reductions particularly in high-ACI areas.Similarly,the synergy between agricultural mechanization and urbanization effectively lowers emissions in low-ACI regions,though this effect diminishes in areas with higher ACI.
基金supported by the Key Laboratory of Natural Resources Monitoring and Supervision in Southern Hilly Region,Ministry of Natural Resources(NRMSSHR2023Y02)Yunnan Key Laboratory of Plateau Geographic Processes and Environmental Changes,Faculty of Geography,Yunnan Normal University(PGPEC2304)China Scholarship Council。
文摘Sloping farmland,particularly in mountainous and hilly areas,constitutes a significant component of regional farmland resources.An investigation into the spatio-temporal pattern of sloping farmland and its influencing factors in China is imperative for the efficient utilization of farmland and the optimization of land space.We used land use transfer matrix,geographically weighted regression model and geographical detector to conduct this study.Results showed that sloping farmland in China firstly decreased and then increased from 2000 to 2020.The proportion of sloping farmland decreased radially outward from Sichuan basin to the surrounding areas.Change rates of sloping farmland with different slopes varied and the slope with 6°-15°underwent the fastest changes.The influencing factors of farmland at various slope degrees were different.For sloping farmland below 15°,land use intensity and elevation had the greatest contribution.For sloping farmland between 15°and 25°,elevation,land use intensity,and population density were the main influencing factors.Sloping farmland above 25°was mostly affected by natural factors.This study can provide scientific basis for rational development and protection of sloping farmland.
基金supported in part by the Key Technologies R&D Program of Jiangsu under Grants BE2023022 and BE2023022-2National Natural Science Foundation of China under Grants 62471204, 62531015+2 种基金Major Natural Science Foundation of the Higher Education Institutions of Jiangsu Province under Grant 24KJA510003Shanghai Kewei 24DP1500500the Fundamental Research Funds for the Central Universities under Grant 2242025K30025
文摘Federated learning(FL)is an intricate and privacy-preserving technique that enables distributed mobile devices to collaboratively train a machine learning model.However,in real-world FL scenarios,the training performance is affected by a combination of factors such as the mobility of user devices,limited communication and computational resources,thus making the user scheduling problem crucial.To tackle this problem,we jointly consider the user mobility,communication and computational capacities,and develop a stochastic optimization problem to minimize the convergence time.Specifically,we first establish a convergence bound on the training performance based on the heterogeneity of users’data,and then leverage this bound to derive the participation rate for each user.After deriving the user-specific participation rate,we aim to minimize the training latency by optimizing user scheduling under the constraints of the energy consumption and participation rate.Afterward,we transform this optimization problem to the contextual multi-armed bandit framework based on the Lyapunov method and solve it with the submodular reward enhanced linear upper confidence bound(SR-linUCB)algorithm.Experimental results demonstrate the superiority of our proposed algorithm on the training performance and time consumption compared with stateof-the-art algorithms for both independent and identically distributed(IID)and non-IID settings.
基金support for this work was supported by Key Lab of Intelligent and Green Flexographic Printing under Grant ZBKT202301.
文摘Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.
基金supported by The Henan Province Science and Technology Research Project(242102211046)the Key Scientific Research Project of Higher Education Institutions in Henan Province(25A520039)+1 种基金theNatural Science Foundation project of Zhongyuan Institute of Technology(K2025YB011)the Zhongyuan University of Technology Graduate Education and Teaching Reform Research Project(JG202424).
文摘Electrocardiogram (ECG) analysis is critical for detecting arrhythmias, but traditional methods struggle with large-scale Electrocardiogram data and rare arrhythmia events in imbalanced datasets. These methods fail to perform multi-perspective learning of temporal signals and Electrocardiogram images, nor can they fully extract the latent information within the data, falling short of the accuracy required by clinicians. Therefore, this paper proposes an innovative hybrid multimodal spatiotemporal neural network to address these challenges. The model employs a multimodal data augmentation framework integrating visual and signal-based features to enhance the classification performance of rare arrhythmias in imbalanced datasets. Additionally, the spatiotemporal fusion module incorporates a spatiotemporal graph convolutional network to jointly model temporal and spatial features, uncovering complex dependencies within the Electrocardiogram data and improving the model’s ability to represent complex patterns. In experiments conducted on the MIT-BIH arrhythmia dataset, the model achieved 99.95% accuracy, 99.80% recall, and a 99.78% F1 score. The model was further validated for generalization using the clinical INCART arrhythmia dataset, and the results demonstrated its effectiveness in terms of both generalization and robustness.
基金funding from the following sources:National Natural Science Foundation of China(U1904119)Research Programs of Henan Science and Technology Department(232102210054)+3 种基金Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070)Henan Province Key Research and Development Project(231111212000)Aviation Science Foundation(20230001055002)supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).
文摘The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.
文摘Exploring the spatial evolution patterns of land use in creative urban tourism complexes provides theoretical and decision-making support to foster creative tourism projects.This study focuses on the Hangzhou Leisure Expo Garden as a case study,utilizing a land use change index model to analyze the spatial evolution characteristics and dynamic processes of creative urban tourism complexes,as well as to explore their spatial differentiation mechanisms.The analysis indicates that Hangzhou Leisure Expo Garden,initially a derelict industrial area dominated by production and residential land use,has evolved into a creative urban tourism complex with tourism comprehensive service land at its core,going through the pattern evolution processes of“constrained sprawl,”“intensive expansion,”and“random integration.”From the perspective of tourism human-land relationships,the formation of land use evolution patterns in creative urban tourism complexes results from various stakeholders(government,tourism enterprises,residents,tourists,etc.),as humanistic factors,continuously adapting to specific urban spaces,which are considered as geographical elements and have locational advantages and are oriented towards economic and social values.Based on the acquisition of stakeholder interests,the transformation of resource-disadvantaged areas into tourism advantage areas is facilitated,thereby achieving the re-creation of tourism creative space and promoting intensive spatial growth.
