Sufficient high-quality traffic data are a crucial component of various Intelligent Transportation System (ITS) applications and research related to congestion prediction, speed prediction, incident detection, and oth...Sufficient high-quality traffic data are a crucial component of various Intelligent Transportation System (ITS) applications and research related to congestion prediction, speed prediction, incident detection, and other traffic operation tasks. Nonetheless, missing traffic data are a common issue in sensor data which is inevitable due to several reasons, such as malfunctioning, poor maintenance or calibration, and intermittent communications. Such missing data issues often make data analysis and decision-making complicated and challenging. In this study, we have developed a generative adversarial network (GAN) based traffic sensor data imputation framework (TSDIGAN) to efficiently reconstruct the missing data by generating realistic synthetic data. In recent years, GANs have shown impressive success in image data generation. However, generating traffic data by taking advantage of GAN based modeling is a challenging task, since traffic data have strong time dependency. To address this problem, we propose a novel time-dependent encoding method called the Gramian Angular Summation Field (GASF) that converts the problem of traffic time-series data generation into that of image generation. We have evaluated and tested our proposed model using the benchmark dataset provided by Caltrans Performance Management Systems (PeMS). This study shows that the proposed model can significantly improve the traffic data imputation accuracy in terms of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) compared to state-of-the-art models on the benchmark dataset. Further, the model achieves reasonably high accuracy in imputation tasks even under a very high missing data rate (>50%), which shows the robustness and efficiency of the proposed model.展开更多
To fully leverage‘‘smart”transportation infrastructure data-stream investments,the creation of applications that provide real-time meaningful and actionable corridorperformance metrics is needed.However,the presenc...To fully leverage‘‘smart”transportation infrastructure data-stream investments,the creation of applications that provide real-time meaningful and actionable corridorperformance metrics is needed.However,the presence of gaps in data streams can lead to significant application implementation challenges.To demonstrate and help address these challenges,a digital twin smart-corridor application case study is presented with two primary research objectives:(1)explore the characteristics of volume data gaps on the case study corridor,and(2)investigate the feasibility of prioritizing data streams for data imputation to drive the real-time application.For the first objective,a K-means clustering analysis is used to identify similarities and differences among data gap patterns.The clustering analysis successfully identifies eight different data loss patterns.Patterns vary in both continuity and density of data gap occurrences,as well as time-dependent losses in several clusters.For the second objective,a temporal-neighboring interpolation approach for volume data imputation is explored.When investigating the use of temporalneighboring interpolation imputations on the digital twin application,performance is,in part,dependent on the combination of intersection approaches experiencing data loss,demand relative to capacity at individual locations,and the location of the loss along the corridor.The results indicate that these insights could be used to prioritize intersection approaches suitable for data imputation and to identify locations that require a more sensitive imputation methodology or improved maintenance and monitoring.展开更多
文摘Sufficient high-quality traffic data are a crucial component of various Intelligent Transportation System (ITS) applications and research related to congestion prediction, speed prediction, incident detection, and other traffic operation tasks. Nonetheless, missing traffic data are a common issue in sensor data which is inevitable due to several reasons, such as malfunctioning, poor maintenance or calibration, and intermittent communications. Such missing data issues often make data analysis and decision-making complicated and challenging. In this study, we have developed a generative adversarial network (GAN) based traffic sensor data imputation framework (TSDIGAN) to efficiently reconstruct the missing data by generating realistic synthetic data. In recent years, GANs have shown impressive success in image data generation. However, generating traffic data by taking advantage of GAN based modeling is a challenging task, since traffic data have strong time dependency. To address this problem, we propose a novel time-dependent encoding method called the Gramian Angular Summation Field (GASF) that converts the problem of traffic time-series data generation into that of image generation. We have evaluated and tested our proposed model using the benchmark dataset provided by Caltrans Performance Management Systems (PeMS). This study shows that the proposed model can significantly improve the traffic data imputation accuracy in terms of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) compared to state-of-the-art models on the benchmark dataset. Further, the model achieves reasonably high accuracy in imputation tasks even under a very high missing data rate (>50%), which shows the robustness and efficiency of the proposed model.
基金supported in part by the City of Atlanta(CoA)under Research Project FC-9930-Smart Cities Traffic Congestion Mitigation Program and in part by the National Center of Sustainable Transportation(NCST)under NCST Dissertation Fund.
文摘To fully leverage‘‘smart”transportation infrastructure data-stream investments,the creation of applications that provide real-time meaningful and actionable corridorperformance metrics is needed.However,the presence of gaps in data streams can lead to significant application implementation challenges.To demonstrate and help address these challenges,a digital twin smart-corridor application case study is presented with two primary research objectives:(1)explore the characteristics of volume data gaps on the case study corridor,and(2)investigate the feasibility of prioritizing data streams for data imputation to drive the real-time application.For the first objective,a K-means clustering analysis is used to identify similarities and differences among data gap patterns.The clustering analysis successfully identifies eight different data loss patterns.Patterns vary in both continuity and density of data gap occurrences,as well as time-dependent losses in several clusters.For the second objective,a temporal-neighboring interpolation approach for volume data imputation is explored.When investigating the use of temporalneighboring interpolation imputations on the digital twin application,performance is,in part,dependent on the combination of intersection approaches experiencing data loss,demand relative to capacity at individual locations,and the location of the loss along the corridor.The results indicate that these insights could be used to prioritize intersection approaches suitable for data imputation and to identify locations that require a more sensitive imputation methodology or improved maintenance and monitoring.
