Spatio-temporal forecasting is critical in the traffic domain,where accurate predictions are essential for effective urban traffic management,planning,and simulation.Despite the importance of complete historical obser...Spatio-temporal forecasting is critical in the traffic domain,where accurate predictions are essential for effective urban traffic management,planning,and simulation.Despite the importance of complete historical observations,missing values due to sensor failures,data transmission errors,and other issues are common,posing significant challenges to the accuracy and reliability of forecasting models.Existing methods often fail to systematically account for incomplete historical data,especially non-random data missing for extended periods.Fortunately,this study introduces the MissNet,a pre-training enhanced framework for spatio-temporal data forecasting in the presence of missing historical data.MissNet consists of a two-stage process:a pre-training stage where a data masking and recovering task is used to pre-train a backbone,and a finetuning stage where the pre-trained backbone,combined with a specially designed header,predicts future data incorporating spatio-temporal metadata as auxiliary information.Experimental results on real-world datasets demonstrate the effectiveness of MissNet in achieving stable and accurate predictions under various missing data scenarios.展开更多
Holistic understanding of wind behaviour over space,time and height is essential for harvesting wind energy application.This study presents a novel approach for mapping frequent wind profile patterns using multidimens...Holistic understanding of wind behaviour over space,time and height is essential for harvesting wind energy application.This study presents a novel approach for mapping frequent wind profile patterns using multidimensional sequential pattern mining(MDSPM).This study is illustrated with a time series of 24 years of European Centre for Medium-Range Weather Forecasts European Reanalysis-Interim gridded(0.125°×0.125°)wind data for the Netherlands every 6 h and at six height levels.The wind data were first transformed into two spatio-temporal sequence databases(for speed and direction,respectively).Then,the Linear time Closed Itemset Miner Sequence algorithm was used to extract the multidimensional sequential patterns,which were then visualized using a 3D wind rose,a circular histogram and a geographical map.These patterns were further analysed to determine their wind shear coefficients and turbulence intensities as well as their spatial overlap with current areas with wind turbines.Our analysis identified four frequent wind profile patterns.One of them highly suitable to harvest wind energy at a height of 128 m and 68.97%of the geographical area covered by this pattern already contains wind turbines.This study shows that the proposed approach is capable of efficiently extracting meaningful patterns from complex spatio-temporal datasets.展开更多
User-generated social media data tagged with geographic information present messages of dynamic spatiotemporal trajectories. These increasing mobility data provide potential opportunities to enhance the understanding ...User-generated social media data tagged with geographic information present messages of dynamic spatiotemporal trajectories. These increasing mobility data provide potential opportunities to enhance the understanding of human mobility behaviors. Several trajectory data mining approaches have been proposed to benefit from these rich datasets, but fail to incorporate aspatial semantics in mining. This study investigates mining frequent moving sequences of geographic entities with transit time from geo-tagged data. Different from previous analysis of geographic feature only trajectories, this work focuses on extracting patterns with rich context semantics. We extend raw geographic trajectories generated from geo-tagged data with rich context semantic annotations, use regions-of-interest as stops to represent interesting places, enrich them with multiple aspatial semantic annotations, and propose a semantic trajectory pattern mining algorithm that returns basic and multidimensional semantic trajectory patterns. Experimental results demonstrate that semantic trajectory patterns from our method present semantically meaningful patterns and display richer semantic knowledge.展开更多
The discovery of spatio-temporal clusters in complex spatio-temporal data-sets has been a challenging issue in the domain of spatio-temporal data mining and knowledge discovery.In this paper,a novel spatio-temporal cl...The discovery of spatio-temporal clusters in complex spatio-temporal data-sets has been a challenging issue in the domain of spatio-temporal data mining and knowledge discovery.In this paper,a novel spatio-temporal clustering method based on spatio-temporal shared nearest neighbors(STSNN)is proposed to detect spatio-temporal clusters of different sizes,shapes,and densities in spatiotemporal databases with a large amount of noise.The concepts of windowed distance and shared nearest neighbor are utilized to define a novel spatiotemporal density for a spatio-temporal entity with definite mathematical meanings.Then,the density-based clustering strategy is employed to uncover spatio-temporal clusters.The spatio-temporal clustering algorithm developed in this paper is easily implemented and less sensitive to density variation among spatio-temporal entities.Experiments are undertaken on several simulated datasets to demonstrate the effectiveness and advantage of the STSNN algorithm.Also,the real-world applications on two seismic databases show that the STSNN algorithm has the ability to uncover foreshocks and aftershocks effectively.展开更多
Crowd flows prediction is an important problem of urban computing whose goal is to predict the number of incoming and outgoing people of regions in the future.In practice,emergency applications often require less trai...Crowd flows prediction is an important problem of urban computing whose goal is to predict the number of incoming and outgoing people of regions in the future.In practice,emergency applications often require less training time.However,there is a little work on how to obtain good prediction performance with less training time.In this paper,we propose a simplified deep residual network for our problem.By using the simplified deep residual network,we can obtain not only less training time but also competitive prediction performance compared with the existing similar method.Moreover,we adopt the spatio-temporal attention mechanism to further improve the simplified deep residual network with reasonable additional time cost.Based on the real datasets,we construct a series of experiments compared with the existing methods.The experimental results confirm the efficiency of our proposed methods.展开更多
基金supported by National Natural Science Foundation of China under Grant No.52232015by China Postdoctoral Science Foundation under Grant No.2023M743259.
文摘Spatio-temporal forecasting is critical in the traffic domain,where accurate predictions are essential for effective urban traffic management,planning,and simulation.Despite the importance of complete historical observations,missing values due to sensor failures,data transmission errors,and other issues are common,posing significant challenges to the accuracy and reliability of forecasting models.Existing methods often fail to systematically account for incomplete historical data,especially non-random data missing for extended periods.Fortunately,this study introduces the MissNet,a pre-training enhanced framework for spatio-temporal data forecasting in the presence of missing historical data.MissNet consists of a two-stage process:a pre-training stage where a data masking and recovering task is used to pre-train a backbone,and a finetuning stage where the pre-trained backbone,combined with a specially designed header,predicts future data incorporating spatio-temporal metadata as auxiliary information.Experimental results on real-world datasets demonstrate the effectiveness of MissNet in achieving stable and accurate predictions under various missing data scenarios.
基金This work was supported by the Malaysian Ministry of Education(SLAI)and Universiti Teknologi Malaysia(UTM).
文摘Holistic understanding of wind behaviour over space,time and height is essential for harvesting wind energy application.This study presents a novel approach for mapping frequent wind profile patterns using multidimensional sequential pattern mining(MDSPM).This study is illustrated with a time series of 24 years of European Centre for Medium-Range Weather Forecasts European Reanalysis-Interim gridded(0.125°×0.125°)wind data for the Netherlands every 6 h and at six height levels.The wind data were first transformed into two spatio-temporal sequence databases(for speed and direction,respectively).Then,the Linear time Closed Itemset Miner Sequence algorithm was used to extract the multidimensional sequential patterns,which were then visualized using a 3D wind rose,a circular histogram and a geographical map.These patterns were further analysed to determine their wind shear coefficients and turbulence intensities as well as their spatial overlap with current areas with wind turbines.Our analysis identified four frequent wind profile patterns.One of them highly suitable to harvest wind energy at a height of 128 m and 68.97%of the geographical area covered by this pattern already contains wind turbines.This study shows that the proposed approach is capable of efficiently extracting meaningful patterns from complex spatio-temporal datasets.
文摘User-generated social media data tagged with geographic information present messages of dynamic spatiotemporal trajectories. These increasing mobility data provide potential opportunities to enhance the understanding of human mobility behaviors. Several trajectory data mining approaches have been proposed to benefit from these rich datasets, but fail to incorporate aspatial semantics in mining. This study investigates mining frequent moving sequences of geographic entities with transit time from geo-tagged data. Different from previous analysis of geographic feature only trajectories, this work focuses on extracting patterns with rich context semantics. We extend raw geographic trajectories generated from geo-tagged data with rich context semantic annotations, use regions-of-interest as stops to represent interesting places, enrich them with multiple aspatial semantic annotations, and propose a semantic trajectory pattern mining algorithm that returns basic and multidimensional semantic trajectory patterns. Experimental results demonstrate that semantic trajectory patterns from our method present semantically meaningful patterns and display richer semantic knowledge.
基金The work described was supported by the Major State Basic Research Development Program of China(973 Program),No.2012CB719906Program for New Century Excellent Talents in University(NCET),No.NCET-10-0831National Natural Science Foundation of China(NSFC),No.40871180.
文摘The discovery of spatio-temporal clusters in complex spatio-temporal data-sets has been a challenging issue in the domain of spatio-temporal data mining and knowledge discovery.In this paper,a novel spatio-temporal clustering method based on spatio-temporal shared nearest neighbors(STSNN)is proposed to detect spatio-temporal clusters of different sizes,shapes,and densities in spatiotemporal databases with a large amount of noise.The concepts of windowed distance and shared nearest neighbor are utilized to define a novel spatiotemporal density for a spatio-temporal entity with definite mathematical meanings.Then,the density-based clustering strategy is employed to uncover spatio-temporal clusters.The spatio-temporal clustering algorithm developed in this paper is easily implemented and less sensitive to density variation among spatio-temporal entities.Experiments are undertaken on several simulated datasets to demonstrate the effectiveness and advantage of the STSNN algorithm.Also,the real-world applications on two seismic databases show that the STSNN algorithm has the ability to uncover foreshocks and aftershocks effectively.
基金This work was supported by the National Nature Science Foundation of China(NSFC Grant Nos.61572537,U1501252).
文摘Crowd flows prediction is an important problem of urban computing whose goal is to predict the number of incoming and outgoing people of regions in the future.In practice,emergency applications often require less training time.However,there is a little work on how to obtain good prediction performance with less training time.In this paper,we propose a simplified deep residual network for our problem.By using the simplified deep residual network,we can obtain not only less training time but also competitive prediction performance compared with the existing similar method.Moreover,we adopt the spatio-temporal attention mechanism to further improve the simplified deep residual network with reasonable additional time cost.Based on the real datasets,we construct a series of experiments compared with the existing methods.The experimental results confirm the efficiency of our proposed methods.
