English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Sufficient high-quality traffic data are a crucial component of variousIntelligent Transportation System (ITS) applications and research related tocongestion prediction, speed prediction, incident detection, and other trafficoperation tasks. Nonetheless, missing traffic data are a common issue in sensordata which is inevitable due to several reasons, such as malfunctioning, poormaintenance or calibration, and intermittent communications. Such missing dataissues often make data analysis and decision-making complicated andchallenging. In this study, we have developed a generative adversarial network(GAN) based traffic sensor data imputation framework (TSDIGAN) to efficientlyreconstruct the missing data by generating realistic synthetic data. In recentyears, GANs have shown impressive success in image data generation. However,generating traffic data by taking advantage of GAN based modeling is achallenging task, since traffic data have strong time dependency. To addressthis problem, we propose a novel time-dependent encoding method called theGramian Angular Summation Field (GASF) that converts the problem of traffictime-series data generation into that of image generation. We have evaluatedand tested our proposed model using the benchmark dataset provided by CaltransPerformance Management Systems (PeMS). This study shows that the proposed modelcan significantly improve the traffic data imputation accuracy in terms of MeanAbsolute Error (MAE) and Root Mean Squared Error (RMSE) compared tostate-of-the-art models on the benchmark dataset. Further, the model achievesreasonably high accuracy in imputation tasks even under a very high missingdata rate ($>$ 50\%), which shows the robustness and efficiency of the proposedmodel.

Deep convolutional generative adversarial networks for traffic data imputation encoding time series as images