Temporal knowledge graph completion(TKGC),which merges temporal information into traditional static knowledge graph completion(SKGC),has garnered increasing attention recently.Among numerous emerging approaches,transl...Temporal knowledge graph completion(TKGC),which merges temporal information into traditional static knowledge graph completion(SKGC),has garnered increasing attention recently.Among numerous emerging approaches,translation-based embedding models constitute a prominent approach in TKGC research.However,existing translation-based methods typically incorporate timestamps into entities or relations,rather than utilizing them independently.This practice fails to fully exploit the rich semantics inherent in temporal information,thereby weakening the expressive capability of models.To address this limitation,we propose embedding timestamps,like entities and relations,in one or more dedicated semantic spaces.After projecting all embeddings into a shared space,we use the relation-timestamp pair instead of the conventional relation embedding as the translation vector between head and tail entities.Our method elevates timestamps to the same representational significance as entities and relations.Based on this strategy,we introduce two novel translation-based embedding models:TE-TransR and TE-TransT.With the independent representation of timestamps,our method not only enhances capabilities in link prediction but also facilitates a relatively underexplored task,namely time prediction.To further bolster the precision and reliability of time prediction,we introduce a granular,time unit-based timestamp setting and a relation-specific evaluation protocol.Extensive experiments demonstrate that our models achieve strong performance on link prediction benchmarks,with TE-TransR outperforming existing baselines in the time prediction task.展开更多
Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising campaigns.Conventional methods use deep neural networks to make predictions ba...Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising campaigns.Conventional methods use deep neural networks to make predictions based on features related to user topic interests and social preferences.However,these models frequently fail to account for the difculties arising from limited training data and model size,which restrict their capacity to learn and capture the intricate patterns within microblogging data.To overcome this limitation,we introduce a novel model Adapt pre-trained Large Language model for Reposting Prediction(ALL-RP),which incorporates two key steps:(1)extracting features from post content and social interactions using a large language model with extensive parameters and trained on a vast corpus,and(2)performing semantic and temporal adaptation to transfer the large language model’s knowledge of natural language,vision,and graph structures to reposting prediction tasks.Specifcally,the temporal adapter in the ALL-RP model captures multi-dimensional temporal information from evolving patterns of user topic interests and social preferences,thereby providing a more realistic refection of user attributes.Additionally,to enhance the robustness of feature modeling,we introduce a variant of the temporal adapter that implements multiple temporal adaptations in parallel while maintaining structural simplicity.Experimental results on real-world datasets demonstrate that the ALL-RP model surpasses state-of-the-art models in predicting both individual user reposting behavior and group sharing behavior,with performance gains of 2.81%and 4.29%,respectively.展开更多
Background Lip reading uses lip images for visual speech recognition.Deep-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of shor...Background Lip reading uses lip images for visual speech recognition.Deep-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of short-term temporal dependencies of lip-shape variations between adjacent frames,which leaves space for further improvement in feature extraction.Methods This article presents a spatiotemporal feature fusion network(STDNet)that compensates for the deficiencies of current lip-reading approaches in short-term temporal dependency modeling.Specifically,to distinguish more similar and intricate content,STDNet adds a temporal feature extraction branch based on a 3D-CNN,which enhances the learning of dynamic lip movements in adjacent frames while not affecting spatial feature extraction.In particular,we designed a local–temporal block,which aggregates interframe differences,strengthening the relationship between various local lip regions through multiscale convolution.We incorporated the squeeze-and-excitation mechanism into the Global-Temporal Block,which processes a single frame as an independent unitto learn temporal variations across the entire lip region more effectively.Furthermore,attention pooling was introduced to highlight meaningful frames containing key semantic information for the target word.Results Experimental results demonstrated STDNet's superior performance on the LRW and LRW-1000,achieving word-level recognition accuracies of 90.2% and 53.56%,respectively.Extensive ablation experiments verified the rationality and effectiveness of its modules.Conclusions The proposed model effectively addresses short-term temporal dependency limitations in lip reading,and improves the temporal robustness of the model against variable-length sequences.These advancements validate the importance of explicit short-term dynamics modeling for practical lip-reading systems.展开更多
Accurate ultra-short-term photovoltaic(PV)power forecasting is crucial for mitigating variations caused by PV power generation and ensuring the stable and efficient operation of power grids.To capture intricate tempor...Accurate ultra-short-term photovoltaic(PV)power forecasting is crucial for mitigating variations caused by PV power generation and ensuring the stable and efficient operation of power grids.To capture intricate temporal relationships and enhance the precision of multi-step time forecast,this paper introduces an innovative approach for ultra-short-term photovoltaic(PV)power prediction,leveraging an enhanced Temporal Convolutional Neural Network(TCN)architecture and feature modeling.First,this study introduces a method employing the Spearman coefficient for meteorological feature filtration.Integrated with three-dimensional PV panel modeling,key factors influencing PV power generation are identified and prioritized.Second,the analysis of the correlation coefficient between astronomical features and PV power prediction demonstrates the theoretical substantiation for the practicality and essentiality of incorporating astronomical features.Third,an enhanced TCN model is introduced,augmenting the original TCN structure with a projection head layer to enhance its capacity for learning and expressing nonlinear features.Meanwhile,a new rolling timing network mechanism is constructed to guarantee the segmentation prediction of future long-time output sequences.Multiple experiments demonstrate the superior performance of the proposed forecasting method compared to existing models.The accuracy of PV power prediction in the next 4 hours,devoid of meteorological conditions,increases by 20.5%.Furthermore,incorporating shortwave radiation for predictions over 4 hours,2 hours,and 1 hour enhances accuracy by 11.1%,9.1%,and 8.8%,respectively.展开更多
Urban expansion in semi-arid regions poses critical challenges for sustainable land management,ecological resilience,and heritage conservation.Jaipur,India-a United Nations Educational,Scientific and Cultural Organiza...Urban expansion in semi-arid regions poses critical challenges for sustainable land management,ecological resilience,and heritage conservation.Jaipur,India-a United Nations Educational,Scientific and Cultural Organization(UNESCO)World Heritage City located in a semi-arid environment-faces rapid urbanization that threatens agricultural productivity,fragile ecosystems,and cultural assets.This study quantifies past and projects future land use/land cover(LULC)dynamics in Jaipur to support evidence-based planning.Using theDynamicWorld dataset,we generated annual 10-m LULC maps from 2016 to 2025 within the municipal boundary.Temporal change detection was conducted through empirical transition probability analysis,and future scenarios for 2026-2030 were simulated with a Markov chain model coupled with a neighbour-aware cellular automata(CA-Markov)allocation to capture spatial diffusion and terrain constraints.Validation on a 2025 hold-out achieved an Overall Accuracy of 0.79,Cohen’sκof 0.15,and a figure of Merit of 0.073 for built-up gains,confirming credible localization of urban growth.Results reveal that the built-up area expanded from 340.57 km^(2) in 2016 to 387.25 km^(2) in 2025(+13.71%)and is projected to rise by+44.96%by 2030.Over 2016-2025,cropland declined by−40.83%,shrub/scrub by−27.71%,tree cover by−4.12%,and flooded vegetation by−41.28%,while bare ground(+3.14%),grass(−4.22%),and water(~+0.18%)showed minimal change.Forecasts for 2016-2030 indicate severe contractions in crops(−98.40%),shrub/scrub(−93.10%),trees(−80.44%),grass(−95.36%),water(−99.53%),bare ground(−99.51%),and flooded vegetation(−99.80%).These findings highlight an accelerating transformation of Jaipur’s peri-urban landscape,with built-up expansion occurring at the expense of nearly all productive and ecological land classes.The study demonstrates that CA-Markov-based LULC forecasting provides a reproducible and transparent framework for high-frequency monitoring and offers actionable insights for sustainable urban management in heritage cities under rapid growth pressure.展开更多
In order to find the completeness threshold which offers a practical method of making bounded model checking complete, the over-approximation for the complete threshold is presented. First, a linear logic of knowledge...In order to find the completeness threshold which offers a practical method of making bounded model checking complete, the over-approximation for the complete threshold is presented. First, a linear logic of knowledge is introduced into the past tense operator, and then a new temporal epistemic logic LTLKP is obtained, so that LTLKP can naturally and precisely describe the system＇s reliability. Secondly, a set of prior algorithms are designed to calculate the maximal reachable depth and the length of the longest of loop free paths in the structure based on the graph structure theory. Finally, some theorems are proposed to show how to approximate the complete threshold with the diameter and recurrence diameter. The proposed work resolves the completeness threshold problem so that the completeness of bounded model checking can be guaranteed.展开更多
With a focus on the difficulty of quantitatively describing the degree of nonuniformity of temporal and spatial distributions of water resources, quantitative research was carried out on the temporal and spatial distr...With a focus on the difficulty of quantitatively describing the degree of nonuniformity of temporal and spatial distributions of water resources, quantitative research was carried out on the temporal and spatial distribution characteristics of water resources in Guangdong Province from 1956 to 2000 based on a cloud model. The spatial variation of the temporal distribution characteristics and the temporal variation of the spatial distribution characteristics were both analyzed. In addition, the relationships between the numerical characteristics of the cloud model of temporal and spatial distributions of water resources and precipitation were also studied. The results show that, using a cloud model, it is possible to intuitively describe the temporal and spatial distribution characteristics of water resources in cloud images. Water resources in Guangdong Province and their temporal and spatial distribution characteristics are differentiated by their geographic locations. Downstream and coastal areas have a larger amount of water resources with greater uniformity and stronger stability in terms of temporal distribution. Regions with more precipitation possess larger amounts of water resources, and years with more precipitation show greater nonuniformity in the spatial distribution of water resources. The correlation between the nonuniformity of the temporal distribution and local precipitation is small, and no correlation is found between the stability of the nonuniformity of the temporal and spatial distributions of water resources and precipitation. The amount of water resources in Guangdong Province shows an increasing trend from 1956 to 2000, the nonuniformity of the spatial distribution of water resources declines, and the stability of the nonuniformity of the spatial distribution of water resources is enhanced.展开更多
Model checking based on linear temporal logic reduces the false negative rate of misuse detection.However,linear temporal logic formulae cannot be used to describe concurrent attacks and piecewise attacks.So there is ...Model checking based on linear temporal logic reduces the false negative rate of misuse detection.However,linear temporal logic formulae cannot be used to describe concurrent attacks and piecewise attacks.So there is still a high rate of false negatives in detecting these complex attack patterns.To solve this problem,we use interval temporal logic formulae to describe concurrent attacks and piecewise attacks.On this basis,we formalize a novel algorithm for intrusion detection based on model checking interval temporal logic.Compared with the method based on model checking linear temporal logic,the new algorithm can find unknown succinct attacks.The simulation results show that the new method can effectively reduce the false negative rate of concurrent attacks and piecewise attacks.展开更多
There are mainly four kinds of models to record and deal with historical information.By taking them as reference,the spatio-temporal model based on event semantics is proposed.In this model,according to the way for de...There are mainly four kinds of models to record and deal with historical information.By taking them as reference,the spatio-temporal model based on event semantics is proposed.In this model,according to the way for describing an event,all the information are divided into five domains.This paper describes the model by using the land parcel change in the cadastral information system,and expounds the model by using five tables corresponding to the five domains.With the aid of this model,seven examples are given on historical query,trace back and recurrence.This model can be implemented either in the extended relational database or in the object-oriented database.展开更多
Objective:Critically appraise the current state of alternate temporal bone training techniques(virtual reality(VR)simulation,3D-printed models,and mental practice(MP))compared to traditional and cadaver methods.Databa...Objective:Critically appraise the current state of alternate temporal bone training techniques(virtual reality(VR)simulation,3D-printed models,and mental practice(MP))compared to traditional and cadaver methods.Databases Reviewed:PubMed,Cochrane,Web of Science.Methods:Search terms utilized“temporal bone training”,“temporal bone surgical modalities”,and“training modalities temporal bone surgery”with“3D”,“rapid prototyp*”,“stereolithography”,“additive manufact*”,“plaster”,“VR”,“virtual reality”,“animal model”,“animal temporal bone”,and“synthetic”with“AND”for all literature.Exclusion criteria:non-ENT,non-English,and did not compare against alternative/traditional methods.Results:10 studies were included with 322 participants(83.9%ENT residents and 16.1%medical students).Costs include the FDM printer($300),materials($5/3D model),and<$5,000 for freeware simulator hardware.The Welling scale was used in 50%of studies.Alternate methods produced comparable or improved assessment scores to traditional and cadaver methods.Injuries were reported in three VR studies,with two reported significantly lower injury scores in the intervention groups.Time to completion was not significantly different in four VR studies,except for one finding that the time to visualize the incus was significantly lower in the intervention group.Performance after MP was not statistically different.Conclusion:More data are needed to assess whether the alternate methods are comparable to cadaveric dissection in temporal bone training.3D models and VR simulation demonstrate promising potential for novel trainees to acquire the basic skills and produce performance comparable to or significantly better than traditional methods of lectures,textbooks,CT images,and operative videos.展开更多
This article attempts to detail time series characteristics of PM2.5 concentration in Guangzhou(China)from 1 June 2012 to 31 May 2013 based on wavelet analysis tools,and discuss its spatial distribution using geograph...This article attempts to detail time series characteristics of PM2.5 concentration in Guangzhou(China)from 1 June 2012 to 31 May 2013 based on wavelet analysis tools,and discuss its spatial distribution using geographic information system software and a modified land use regression model.In this modified model,an important variable(land use data)is substituted for impervious surface area,which can be obtained conveniently from remote sensing imagery through the linear spectral mixture analysis method.Impervious surface has higher precision than land use data because of its sub-pixel level.Seasonal concentration pattern and day-by-day change feature of PM2.5 in Guangzhou with a micro-perspective are discussed and understood.Results include:(1)the highest concentration of PM2.5 occurs in October and the lowest in July,respectively;(2)average concentration of PM2.5 in winter is higher than in other seasons;and(3)there are two high concentration zones in winter and one zone in spring.展开更多
This paper presents a conceptual data model, the STA-model, for handling spatial, temporal and attribute aspects of objects in GIS. The model is developed on the basis of object-oriented modeling approach. This model ...This paper presents a conceptual data model, the STA-model, for handling spatial, temporal and attribute aspects of objects in GIS. The model is developed on the basis of object-oriented modeling approach. This model includes two major parts: (a) modeling the signal objects by STA-object elements, and (b) modeling relationships between STA-objects. As an example, the STA-model is applied for modeling land cover change data with spatial, temporal and attribute components.展开更多
ISDTM,based on an augmented Allen's interval temporal logic(ITL)and first-order predicate calculus,is a formal temporal model for representing intrusion signatures.It is augmented with some real time extensions wh...ISDTM,based on an augmented Allen's interval temporal logic(ITL)and first-order predicate calculus,is a formal temporal model for representing intrusion signatures.It is augmented with some real time extensions which enhance the expressivity.Intrusion scenarios usually are the set of events and system states,where-the temporal sequence is their basic relation.Intrusion signatures description,therefore,is to represent such temporal relations in a sense.While representing these signatures,ISDTM decomposes the intrusion process into the sequence of events according to their relevant intervals,and then specifies network states in these Intervals.The uncertain intrusion signatures as well as basic temporal modes of events,which consist of the parallel mode,the sequential mode and the hybrid mode,can be succinctly and naturally represented in ISDTM.Mode chart is the visualization of intrusion signatures in ISDTM,which makes the formulas more readable.The intrusion signatures descriptions in ISDTM have advantages of compact construct,concise syntax,scalability and easy implementation.展开更多
Root-cause identification plays a vital role in business decision making by providing effective future directions for the organizations.Aspect extraction and sentiment extraction plays a vital role in identifying the ...Root-cause identification plays a vital role in business decision making by providing effective future directions for the organizations.Aspect extraction and sentiment extraction plays a vital role in identifying the rootcauses.This paper proposes the Ensemble based temporal weighting and pareto ranking(ETP)model for Root-cause identification.Aspect extraction is performed based on rules and is followed by opinion identification using the proposed boosted ensemble model.The obtained aspects are validated and ranked using the proposed aspect weighing scheme.Pareto-rule based aspect selection is performed as the final selection mechanism and the results are presented for business decision making.Experiments were performed with the standard five product benchmark dataset.Performances on all five product reviews indicate the effective performance of the proposed model.Comparisons are performed using three standard state-of-the-art models and effectiveness is measured in terms of F-Measure and Detection rates.The results indicate improved performances exhibited by the proposed model with an increase in F-Measure levels at 1%–15%and detection rates at 4%–24%compared to the state-of-the-art models.展开更多
In this paper,a methodology for Leaf Area Index(LAI) estimating was proposed by assimilating remote sensed data into crop model based on temporal and spatial knowledge.Firstly,sensitive parameters of crop model were c...In this paper,a methodology for Leaf Area Index(LAI) estimating was proposed by assimilating remote sensed data into crop model based on temporal and spatial knowledge.Firstly,sensitive parameters of crop model were calibrated by Shuffled Complex Evolution method developed at the University of Arizona(SCE-UA) optimization method based on phenological information,which is called temporal knowledge.The calibrated crop model will be used as the forecast operator.Then,the Taylor′s mean value theorem was applied to extracting spatial information from the Moderate Resolution Imaging Spectroradiometer(MODIS) multi-scale data,which was used to calibrate the LAI inversion results by A two-layer Canopy Reflectance Model(ACRM) model.The calibrated LAI result was used as the observation operator.Finally,an Ensemble Kalman Filter(EnKF) was used to assimilate MODIS data into crop model.The results showed that the method could significantly improve the estimation accuracy of LAI and the simulated curves of LAI more conform to the crop growth situation closely comparing with MODIS LAI products.The root mean square error(RMSE) of LAI calculated by assimilation is 0.9185 which is reduced by 58.7% compared with that by simulation(0.3795),and before and after assimilation the mean error is reduced by 92.6% which is from 0.3563 to 0.0265.All these experiments indicated that the methodology proposed in this paper is reasonable and accurate for estimating crop LAI.展开更多
A new temporal gravity field model called WHU-Grace01s solely recovered from Gravity Recovery and Climate Experiment （GRACE） K-Band Range Rate （KBRR） data based on dynamic integral approach is presented in this pa...A new temporal gravity field model called WHU-Grace01s solely recovered from Gravity Recovery and Climate Experiment （GRACE） K-Band Range Rate （KBRR） data based on dynamic integral approach is presented in this paper. After meticulously preprocessing of the GRACE KBRR data, the root mean square of its post residuals is about 0.2 micrometers per second, and seventy-two monthly temporal solutions truncated to degree and order 60 are computed for the period from January 2003 to December 2008. After applying the combi- nation filter in WHU-Grace01s, the global temporal signals show obvious periodical change rules in the large-scale fiver basins. In terms of the degree variance, our solution is smaller at high degrees, and shows a good consistency at the rest of degrees with the Release 05 models from Center for Space Research （CSR）, GeoForschungsZentrum Potsdam （GFZ） and Jet Pro- pulsion Laboratory 0PL）. Compared with other published models in terms of equivalent water height distribution, our solution is consistent with those published by CSR, GFZ, JPL, Delft institute of Earth Observation and Space system （DEOS）, Tongji University （Tongji）, Institute of Theoretical Geodesy （ITG）, Astronomical Institute in University of Bern （AIUB） and Groupe de Recherche de Geodesie Spatiale （GRGS}, which indicates that the accuracy of WHU-Grace01s has a good consistency with the previously published GRACE solutions.展开更多
Temporal and spatial scales play important roles in fishery ecology,and an inappropriate spatio-temporal scale may result in large errors in modeling fish distribution.The objective of this study is to evaluate the ro...Temporal and spatial scales play important roles in fishery ecology,and an inappropriate spatio-temporal scale may result in large errors in modeling fish distribution.The objective of this study is to evaluate the roles of spatio-temporal scales in habitat suitability modeling,with the western stock of winter-spring cohort of neon flying squid （Ornmastrephes bartramii） in the northwest Pacific Ocean as an example.In this study,the fishery-dependent data from the Chinese Mainland Squid Jigging Technical Group and sea surface temperature （SST） from remote sensing during August to October of 2003-2008 were used.We evaluated the differences in a habitat suitability index model resulting from aggregating data with 36 different spatial scales with a combination of three latitude scales （0.5°,1 ° and 2°）,four longitude scales （0.5°,1°,2° and 4°）,and three temporal scales （week,fortnight,and month）.The coefficients of variation （CV） of the weekly,biweekly and monthly suitability index （SI） were compared to determine which temporal and spatial scales of SI model are more precise.This study shows that the optimal temporal and spatial scales with the lowest CV are month,and 0.5° latitude and 0.5° longitude for O.bartramii in the northwest Pacific Ocean.This suitability index model developed with an optimal scale can be cost-effective in improving forecasting fishing ground and requires no excessive sampling efforts.We suggest that the uncertainty associated with spatial and temporal scales used in data aggregations needs to be considered in habitat suitability modeling.展开更多
Understanding crop patterns and their changes on regional scale is a critical re- quirement for projecting agro-ecosystem dynamics. However, tools and methods for mapping the distribution of crop area and yield are st...Understanding crop patterns and their changes on regional scale is a critical re- quirement for projecting agro-ecosystem dynamics. However, tools and methods for mapping the distribution of crop area and yield are still lacking. Based on the cross-entropy theory, a spatial production allocation model （SPAM） has been developed for presenting spa- tio-temporal dynamics of maize cropping system in Northeast China during 1980-2010. The simulated results indicated that （1） maize sown area expanded northwards to 48~N before 2000, after that the increased sown area mainly occurred in the central and southern parts of Northeast China. Meanwhile, maize also expanded eastwards to 127°E and lower elevation （less than 100 m） as well as higher elevation （mainly distributed between 200 m and 350 m）; （2） maize yield has been greatly promoted for most planted area of Northeast China, espe- cially in the planted zone between 42°N and 48°N, while the yield increase was relatively homogeneous without obvious longitudinal variations for whole region; （3） maize planting density increased gradually to a moderately high level over the investigated period, which reflected the trend of aggregation of maize cultivation driven by market demand.展开更多
In the realm of video understanding,the demand for accurate and contextually rich video captioning has surged with the increasing volume and complexity of multimedia content.This research introduces an innovative solu...In the realm of video understanding,the demand for accurate and contextually rich video captioning has surged with the increasing volume and complexity of multimedia content.This research introduces an innovative solution for video captioning by integrating a Convolutional BiLSTM Convolutional Bidirectional Long Short-Term Memory(BiLSTM)constructed Variational Sequence-to-Sequence(CBVSS)approach.The proposed framework is adept at capturing intricate temporal dependencies within video sequences,enabling a more nuanced and contextually relevant description of dynamic scenes.However,optimizing its parameters for improved performance remains a crucial challenge.In response,in this research Golden Eagle Optimization(GEO)a metaheuristic optimization technique is used to fine-tune the Convolutional BiLSTM variational sequence-to-sequence model parameters.The application of GEO aims to enhancing the CBVSS ability to produce more exact and contextually rich video captions.The proposed attains an overall higher Recall of 59.75%and Precision of 63.78%for both datasets.Additionally,the proposed CBVSS method demonstrated superior performance across both datasets,achieving the highest METEOR(25.67)and CIDER(39.87)scores on the ActivityNet dataset,and further outperforming all compared models on the YouCook2 dataset with METEOR(28.67)and CIDER(43.02),highlighting its effectiveness in generating semantically rich and contextually accurate video captions.展开更多
基金supported by the National Natural Science Foundation of China under Grant No.72293575.
文摘Temporal knowledge graph completion(TKGC),which merges temporal information into traditional static knowledge graph completion(SKGC),has garnered increasing attention recently.Among numerous emerging approaches,translation-based embedding models constitute a prominent approach in TKGC research.However,existing translation-based methods typically incorporate timestamps into entities or relations,rather than utilizing them independently.This practice fails to fully exploit the rich semantics inherent in temporal information,thereby weakening the expressive capability of models.To address this limitation,we propose embedding timestamps,like entities and relations,in one or more dedicated semantic spaces.After projecting all embeddings into a shared space,we use the relation-timestamp pair instead of the conventional relation embedding as the translation vector between head and tail entities.Our method elevates timestamps to the same representational significance as entities and relations.Based on this strategy,we introduce two novel translation-based embedding models:TE-TransR and TE-TransT.With the independent representation of timestamps,our method not only enhances capabilities in link prediction but also facilitates a relatively underexplored task,namely time prediction.To further bolster the precision and reliability of time prediction,we introduce a granular,time unit-based timestamp setting and a relation-specific evaluation protocol.Extensive experiments demonstrate that our models achieve strong performance on link prediction benchmarks,with TE-TransR outperforming existing baselines in the time prediction task.
文摘Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising campaigns.Conventional methods use deep neural networks to make predictions based on features related to user topic interests and social preferences.However,these models frequently fail to account for the difculties arising from limited training data and model size,which restrict their capacity to learn and capture the intricate patterns within microblogging data.To overcome this limitation,we introduce a novel model Adapt pre-trained Large Language model for Reposting Prediction(ALL-RP),which incorporates two key steps:(1)extracting features from post content and social interactions using a large language model with extensive parameters and trained on a vast corpus,and(2)performing semantic and temporal adaptation to transfer the large language model’s knowledge of natural language,vision,and graph structures to reposting prediction tasks.Specifcally,the temporal adapter in the ALL-RP model captures multi-dimensional temporal information from evolving patterns of user topic interests and social preferences,thereby providing a more realistic refection of user attributes.Additionally,to enhance the robustness of feature modeling,we introduce a variant of the temporal adapter that implements multiple temporal adaptations in parallel while maintaining structural simplicity.Experimental results on real-world datasets demonstrate that the ALL-RP model surpasses state-of-the-art models in predicting both individual user reposting behavior and group sharing behavior,with performance gains of 2.81%and 4.29%,respectively.
基金Supported by the National Key Research and Development Program of China(2023YFC3306201)the National Natural Science Foundation of China(61772125)the Fundamental Research Funds for the Central Universities(N2317004).
文摘Background Lip reading uses lip images for visual speech recognition.Deep-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of short-term temporal dependencies of lip-shape variations between adjacent frames,which leaves space for further improvement in feature extraction.Methods This article presents a spatiotemporal feature fusion network(STDNet)that compensates for the deficiencies of current lip-reading approaches in short-term temporal dependency modeling.Specifically,to distinguish more similar and intricate content,STDNet adds a temporal feature extraction branch based on a 3D-CNN,which enhances the learning of dynamic lip movements in adjacent frames while not affecting spatial feature extraction.In particular,we designed a local–temporal block,which aggregates interframe differences,strengthening the relationship between various local lip regions through multiscale convolution.We incorporated the squeeze-and-excitation mechanism into the Global-Temporal Block,which processes a single frame as an independent unitto learn temporal variations across the entire lip region more effectively.Furthermore,attention pooling was introduced to highlight meaningful frames containing key semantic information for the target word.Results Experimental results demonstrated STDNet's superior performance on the LRW and LRW-1000,achieving word-level recognition accuracies of 90.2% and 53.56%,respectively.Extensive ablation experiments verified the rationality and effectiveness of its modules.Conclusions The proposed model effectively addresses short-term temporal dependency limitations in lip reading,and improves the temporal robustness of the model against variable-length sequences.These advancements validate the importance of explicit short-term dynamics modeling for practical lip-reading systems.
基金supported by National Key Research and Development Program of China(Key Techniques of Adaptive Grid Integration and Active Synchronization for Extremely High Penetration Distributed Photovoltaic Power Generation,2022YFB2402900).
文摘Accurate ultra-short-term photovoltaic(PV)power forecasting is crucial for mitigating variations caused by PV power generation and ensuring the stable and efficient operation of power grids.To capture intricate temporal relationships and enhance the precision of multi-step time forecast,this paper introduces an innovative approach for ultra-short-term photovoltaic(PV)power prediction,leveraging an enhanced Temporal Convolutional Neural Network(TCN)architecture and feature modeling.First,this study introduces a method employing the Spearman coefficient for meteorological feature filtration.Integrated with three-dimensional PV panel modeling,key factors influencing PV power generation are identified and prioritized.Second,the analysis of the correlation coefficient between astronomical features and PV power prediction demonstrates the theoretical substantiation for the practicality and essentiality of incorporating astronomical features.Third,an enhanced TCN model is introduced,augmenting the original TCN structure with a projection head layer to enhance its capacity for learning and expressing nonlinear features.Meanwhile,a new rolling timing network mechanism is constructed to guarantee the segmentation prediction of future long-time output sequences.Multiple experiments demonstrate the superior performance of the proposed forecasting method compared to existing models.The accuracy of PV power prediction in the next 4 hours,devoid of meteorological conditions,increases by 20.5%.Furthermore,incorporating shortwave radiation for predictions over 4 hours,2 hours,and 1 hour enhances accuracy by 11.1%,9.1%,and 8.8%,respectively.
文摘Urban expansion in semi-arid regions poses critical challenges for sustainable land management,ecological resilience,and heritage conservation.Jaipur,India-a United Nations Educational,Scientific and Cultural Organization(UNESCO)World Heritage City located in a semi-arid environment-faces rapid urbanization that threatens agricultural productivity,fragile ecosystems,and cultural assets.This study quantifies past and projects future land use/land cover(LULC)dynamics in Jaipur to support evidence-based planning.Using theDynamicWorld dataset,we generated annual 10-m LULC maps from 2016 to 2025 within the municipal boundary.Temporal change detection was conducted through empirical transition probability analysis,and future scenarios for 2026-2030 were simulated with a Markov chain model coupled with a neighbour-aware cellular automata(CA-Markov)allocation to capture spatial diffusion and terrain constraints.Validation on a 2025 hold-out achieved an Overall Accuracy of 0.79,Cohen’sκof 0.15,and a figure of Merit of 0.073 for built-up gains,confirming credible localization of urban growth.Results reveal that the built-up area expanded from 340.57 km^(2) in 2016 to 387.25 km^(2) in 2025(+13.71%)and is projected to rise by+44.96%by 2030.Over 2016-2025,cropland declined by−40.83%,shrub/scrub by−27.71%,tree cover by−4.12%,and flooded vegetation by−41.28%,while bare ground(+3.14%),grass(−4.22%),and water(~+0.18%)showed minimal change.Forecasts for 2016-2030 indicate severe contractions in crops(−98.40%),shrub/scrub(−93.10%),trees(−80.44%),grass(−95.36%),water(−99.53%),bare ground(−99.51%),and flooded vegetation(−99.80%).These findings highlight an accelerating transformation of Jaipur’s peri-urban landscape,with built-up expansion occurring at the expense of nearly all productive and ecological land classes.The study demonstrates that CA-Markov-based LULC forecasting provides a reproducible and transparent framework for high-frequency monitoring and offers actionable insights for sustainable urban management in heritage cities under rapid growth pressure.
基金The National Natural Science Foundation of China (No.10974093)the Scientific Research Foundation for Senior Personnel of Jiangsu University (No.07JDG014)the Natural Science Foundation of Higher Education Institutions of Jiangsu Province (No.08KJD520015)
文摘In order to find the completeness threshold which offers a practical method of making bounded model checking complete, the over-approximation for the complete threshold is presented. First, a linear logic of knowledge is introduced into the past tense operator, and then a new temporal epistemic logic LTLKP is obtained, so that LTLKP can naturally and precisely describe the system＇s reliability. Secondly, a set of prior algorithms are designed to calculate the maximal reachable depth and the length of the longest of loop free paths in the structure based on the graph structure theory. Finally, some theorems are proposed to show how to approximate the complete threshold with the diameter and recurrence diameter. The proposed work resolves the completeness threshold problem so that the completeness of bounded model checking can be guaranteed.
基金supported by the National Science and Technology Major Project of Water Pollution Control and Treatment(Grants No.2014ZX07405002,2012ZX07506007,2012ZX07506006,and 2012ZX07506002)the Natural Science Foundation of the Anhui Higher Education Institutions of China(Grant No.KJ2016A868)the Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘With a focus on the difficulty of quantitatively describing the degree of nonuniformity of temporal and spatial distributions of water resources, quantitative research was carried out on the temporal and spatial distribution characteristics of water resources in Guangdong Province from 1956 to 2000 based on a cloud model. The spatial variation of the temporal distribution characteristics and the temporal variation of the spatial distribution characteristics were both analyzed. In addition, the relationships between the numerical characteristics of the cloud model of temporal and spatial distributions of water resources and precipitation were also studied. The results show that, using a cloud model, it is possible to intuitively describe the temporal and spatial distribution characteristics of water resources in cloud images. Water resources in Guangdong Province and their temporal and spatial distribution characteristics are differentiated by their geographic locations. Downstream and coastal areas have a larger amount of water resources with greater uniformity and stronger stability in terms of temporal distribution. Regions with more precipitation possess larger amounts of water resources, and years with more precipitation show greater nonuniformity in the spatial distribution of water resources. The correlation between the nonuniformity of the temporal distribution and local precipitation is small, and no correlation is found between the stability of the nonuniformity of the temporal and spatial distributions of water resources and precipitation. The amount of water resources in Guangdong Province shows an increasing trend from 1956 to 2000, the nonuniformity of the spatial distribution of water resources declines, and the stability of the nonuniformity of the spatial distribution of water resources is enhanced.
基金supported by National Natural Science Foundation of China under Grant No. 61003079
文摘Model checking based on linear temporal logic reduces the false negative rate of misuse detection.However,linear temporal logic formulae cannot be used to describe concurrent attacks and piecewise attacks.So there is still a high rate of false negatives in detecting these complex attack patterns.To solve this problem,we use interval temporal logic formulae to describe concurrent attacks and piecewise attacks.On this basis,we formalize a novel algorithm for intrusion detection based on model checking interval temporal logic.Compared with the method based on model checking linear temporal logic,the new algorithm can find unknown succinct attacks.The simulation results show that the new method can effectively reduce the false negative rate of concurrent attacks and piecewise attacks.
文摘There are mainly four kinds of models to record and deal with historical information.By taking them as reference,the spatio-temporal model based on event semantics is proposed.In this model,according to the way for describing an event,all the information are divided into five domains.This paper describes the model by using the land parcel change in the cadastral information system,and expounds the model by using five tables corresponding to the five domains.With the aid of this model,seven examples are given on historical query,trace back and recurrence.This model can be implemented either in the extended relational database or in the object-oriented database.
文摘Objective:Critically appraise the current state of alternate temporal bone training techniques(virtual reality(VR)simulation,3D-printed models,and mental practice(MP))compared to traditional and cadaver methods.Databases Reviewed:PubMed,Cochrane,Web of Science.Methods:Search terms utilized“temporal bone training”,“temporal bone surgical modalities”,and“training modalities temporal bone surgery”with“3D”,“rapid prototyp*”,“stereolithography”,“additive manufact*”,“plaster”,“VR”,“virtual reality”,“animal model”,“animal temporal bone”,and“synthetic”with“AND”for all literature.Exclusion criteria:non-ENT,non-English,and did not compare against alternative/traditional methods.Results:10 studies were included with 322 participants(83.9%ENT residents and 16.1%medical students).Costs include the FDM printer($300),materials($5/3D model),and<$5,000 for freeware simulator hardware.The Welling scale was used in 50%of studies.Alternate methods produced comparable or improved assessment scores to traditional and cadaver methods.Injuries were reported in three VR studies,with two reported significantly lower injury scores in the intervention groups.Time to completion was not significantly different in four VR studies,except for one finding that the time to visualize the incus was significantly lower in the intervention group.Performance after MP was not statistically different.Conclusion:More data are needed to assess whether the alternate methods are comparable to cadaveric dissection in temporal bone training.3D models and VR simulation demonstrate promising potential for novel trainees to acquire the basic skills and produce performance comparable to or significantly better than traditional methods of lectures,textbooks,CT images,and operative videos.
基金This work is supported by the National Nature Science Foundation of China[grant number:41201432],the National Science Foundation of Tibet[grant number:2016ZR-TU-05]the Foundation for Innovative Research for Young Teachers in Higher Educational Institutions of Tibet[grant number:QCZ2016-07].
文摘This article attempts to detail time series characteristics of PM2.5 concentration in Guangzhou(China)from 1 June 2012 to 31 May 2013 based on wavelet analysis tools,and discuss its spatial distribution using geographic information system software and a modified land use regression model.In this modified model,an important variable(land use data)is substituted for impervious surface area,which can be obtained conveniently from remote sensing imagery through the linear spectral mixture analysis method.Impervious surface has higher precision than land use data because of its sub-pixel level.Seasonal concentration pattern and day-by-day change feature of PM2.5 in Guangzhou with a micro-perspective are discussed and understood.Results include:(1)the highest concentration of PM2.5 occurs in October and the lowest in July,respectively;(2)average concentration of PM2.5 in winter is higher than in other seasons;and(3)there are two high concentration zones in winter and one zone in spring.
文摘This paper presents a conceptual data model, the STA-model, for handling spatial, temporal and attribute aspects of objects in GIS. The model is developed on the basis of object-oriented modeling approach. This model includes two major parts: (a) modeling the signal objects by STA-object elements, and (b) modeling relationships between STA-objects. As an example, the STA-model is applied for modeling land cover change data with spatial, temporal and attribute components.
基金Supported by the National Natural Science Foundation of China(60073074)
文摘ISDTM,based on an augmented Allen's interval temporal logic(ITL)and first-order predicate calculus,is a formal temporal model for representing intrusion signatures.It is augmented with some real time extensions which enhance the expressivity.Intrusion scenarios usually are the set of events and system states,where-the temporal sequence is their basic relation.Intrusion signatures description,therefore,is to represent such temporal relations in a sense.While representing these signatures,ISDTM decomposes the intrusion process into the sequence of events according to their relevant intervals,and then specifies network states in these Intervals.The uncertain intrusion signatures as well as basic temporal modes of events,which consist of the parallel mode,the sequential mode and the hybrid mode,can be succinctly and naturally represented in ISDTM.Mode chart is the visualization of intrusion signatures in ISDTM,which makes the formulas more readable.The intrusion signatures descriptions in ISDTM have advantages of compact construct,concise syntax,scalability and easy implementation.
文摘Root-cause identification plays a vital role in business decision making by providing effective future directions for the organizations.Aspect extraction and sentiment extraction plays a vital role in identifying the rootcauses.This paper proposes the Ensemble based temporal weighting and pareto ranking(ETP)model for Root-cause identification.Aspect extraction is performed based on rules and is followed by opinion identification using the proposed boosted ensemble model.The obtained aspects are validated and ranked using the proposed aspect weighing scheme.Pareto-rule based aspect selection is performed as the final selection mechanism and the results are presented for business decision making.Experiments were performed with the standard five product benchmark dataset.Performances on all five product reviews indicate the effective performance of the proposed model.Comparisons are performed using three standard state-of-the-art models and effectiveness is measured in terms of F-Measure and Detection rates.The results indicate improved performances exhibited by the proposed model with an increase in F-Measure levels at 1%–15%and detection rates at 4%–24%compared to the state-of-the-art models.
基金Under the auspices of Major State Basic Research Development Program of China(No.2007CB714407)National Natural Science Foundation of China(No.40801070)Action Plan for West Development Program of Chinese Academy of Sciences(No.KZCX2-XB2-09)
文摘In this paper,a methodology for Leaf Area Index(LAI) estimating was proposed by assimilating remote sensed data into crop model based on temporal and spatial knowledge.Firstly,sensitive parameters of crop model were calibrated by Shuffled Complex Evolution method developed at the University of Arizona(SCE-UA) optimization method based on phenological information,which is called temporal knowledge.The calibrated crop model will be used as the forecast operator.Then,the Taylor′s mean value theorem was applied to extracting spatial information from the Moderate Resolution Imaging Spectroradiometer(MODIS) multi-scale data,which was used to calibrate the LAI inversion results by A two-layer Canopy Reflectance Model(ACRM) model.The calibrated LAI result was used as the observation operator.Finally,an Ensemble Kalman Filter(EnKF) was used to assimilate MODIS data into crop model.The results showed that the method could significantly improve the estimation accuracy of LAI and the simulated curves of LAI more conform to the crop growth situation closely comparing with MODIS LAI products.The root mean square error(RMSE) of LAI calculated by assimilation is 0.9185 which is reduced by 58.7% compared with that by simulation(0.3795),and before and after assimilation the mean error is reduced by 92.6% which is from 0.3563 to 0.0265.All these experiments indicated that the methodology proposed in this paper is reasonable and accurate for estimating crop LAI.
基金supported by the National 973Program of China(2013CB733302)the National Natural Science Foundation of China(41131067,41174020,41374023,41474019)+2 种基金the Open Research Fund Program of the State Key Laboratory of Geodesy and Earth's Dynamics(SKLGED2015-1-3-E)the open fund of State Key Laboratory of Geographic Information Engineering(SKLGIE2013-M-1-3)the open fund of Key Laboratory of Geospace Environment and Geodesy,Ministry of Education(13-02-05)
文摘A new temporal gravity field model called WHU-Grace01s solely recovered from Gravity Recovery and Climate Experiment （GRACE） K-Band Range Rate （KBRR） data based on dynamic integral approach is presented in this paper. After meticulously preprocessing of the GRACE KBRR data, the root mean square of its post residuals is about 0.2 micrometers per second, and seventy-two monthly temporal solutions truncated to degree and order 60 are computed for the period from January 2003 to December 2008. After applying the combi- nation filter in WHU-Grace01s, the global temporal signals show obvious periodical change rules in the large-scale fiver basins. In terms of the degree variance, our solution is smaller at high degrees, and shows a good consistency at the rest of degrees with the Release 05 models from Center for Space Research （CSR）, GeoForschungsZentrum Potsdam （GFZ） and Jet Pro- pulsion Laboratory 0PL）. Compared with other published models in terms of equivalent water height distribution, our solution is consistent with those published by CSR, GFZ, JPL, Delft institute of Earth Observation and Space system （DEOS）, Tongji University （Tongji）, Institute of Theoretical Geodesy （ITG）, Astronomical Institute in University of Bern （AIUB） and Groupe de Recherche de Geodesie Spatiale （GRGS}, which indicates that the accuracy of WHU-Grace01s has a good consistency with the previously published GRACE solutions.
基金funded by National High Technology Research and Development Program of China (863 Program,2012AA092303)Project of Shanghai Science and Technology Innovation (12231203900)+2 种基金Industrialization Program of National Development and Reform Commission (2159999)National Science and Technology Support Program (2013BAD13B01)Shanghai Leading Academic Discipline Project
文摘Temporal and spatial scales play important roles in fishery ecology,and an inappropriate spatio-temporal scale may result in large errors in modeling fish distribution.The objective of this study is to evaluate the roles of spatio-temporal scales in habitat suitability modeling,with the western stock of winter-spring cohort of neon flying squid （Ornmastrephes bartramii） in the northwest Pacific Ocean as an example.In this study,the fishery-dependent data from the Chinese Mainland Squid Jigging Technical Group and sea surface temperature （SST） from remote sensing during August to October of 2003-2008 were used.We evaluated the differences in a habitat suitability index model resulting from aggregating data with 36 different spatial scales with a combination of three latitude scales （0.5°,1 ° and 2°）,four longitude scales （0.5°,1°,2° and 4°）,and three temporal scales （week,fortnight,and month）.The coefficients of variation （CV） of the weekly,biweekly and monthly suitability index （SI） were compared to determine which temporal and spatial scales of SI model are more precise.This study shows that the optimal temporal and spatial scales with the lowest CV are month,and 0.5° latitude and 0.5° longitude for O.bartramii in the northwest Pacific Ocean.This suitability index model developed with an optimal scale can be cost-effective in improving forecasting fishing ground and requires no excessive sampling efforts.We suggest that the uncertainty associated with spatial and temporal scales used in data aggregations needs to be considered in habitat suitability modeling.
基金Foundation： National Natural Science Foundation of China, No.41171328, No.41201184, No.41101537 National Basic Program of China, No.2010CB951502
文摘Understanding crop patterns and their changes on regional scale is a critical re- quirement for projecting agro-ecosystem dynamics. However, tools and methods for mapping the distribution of crop area and yield are still lacking. Based on the cross-entropy theory, a spatial production allocation model （SPAM） has been developed for presenting spa- tio-temporal dynamics of maize cropping system in Northeast China during 1980-2010. The simulated results indicated that （1） maize sown area expanded northwards to 48~N before 2000, after that the increased sown area mainly occurred in the central and southern parts of Northeast China. Meanwhile, maize also expanded eastwards to 127°E and lower elevation （less than 100 m） as well as higher elevation （mainly distributed between 200 m and 350 m）; （2） maize yield has been greatly promoted for most planted area of Northeast China, espe- cially in the planted zone between 42°N and 48°N, while the yield increase was relatively homogeneous without obvious longitudinal variations for whole region; （3） maize planting density increased gradually to a moderately high level over the investigated period, which reflected the trend of aggregation of maize cultivation driven by market demand.
文摘In the realm of video understanding,the demand for accurate and contextually rich video captioning has surged with the increasing volume and complexity of multimedia content.This research introduces an innovative solution for video captioning by integrating a Convolutional BiLSTM Convolutional Bidirectional Long Short-Term Memory(BiLSTM)constructed Variational Sequence-to-Sequence(CBVSS)approach.The proposed framework is adept at capturing intricate temporal dependencies within video sequences,enabling a more nuanced and contextually relevant description of dynamic scenes.However,optimizing its parameters for improved performance remains a crucial challenge.In response,in this research Golden Eagle Optimization(GEO)a metaheuristic optimization technique is used to fine-tune the Convolutional BiLSTM variational sequence-to-sequence model parameters.The application of GEO aims to enhancing the CBVSS ability to produce more exact and contextually rich video captions.The proposed attains an overall higher Recall of 59.75%and Precision of 63.78%for both datasets.Additionally,the proposed CBVSS method demonstrated superior performance across both datasets,achieving the highest METEOR(25.67)and CIDER(39.87)scores on the ActivityNet dataset,and further outperforming all compared models on the YouCook2 dataset with METEOR(28.67)and CIDER(43.02),highlighting its effectiveness in generating semantically rich and contextually accurate video captions.
