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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Urban traffic flow prediction using data-driven models can play an importantrole in route planning and preventing congestion on highways. These methodsutilize data collected from traffic recording stations at different timestampsto predict the future status of traffic. Hence, data collection, transmission,storage, and extraction techniques can have a significant impact on theperformance of the traffic flow model. On the other hand, a comprehensivedatabase can provide the opportunity for using complex, yet reliable predictivemodels such as deep learning methods. However, most of these methods havedifficulties in handling missing values and outliers. This study focuses onhybrid deep neural networks to predict traffic flow in the California FreewayPerformance Measurement System (PeMS) with missing values. The proposednetworks are based on a combination of recurrent neural networks (RNNs) toconsider the temporal dependencies in the data recorded in each station andconvolutional neural networks (CNNs) to take the spatial correlations in theadjacent stations into account. Various architecture configurations with seriesand parallel connections are considered based on RNNs and CNNs, and severalprevalent data imputation techniques are used to examine the robustness of thehybrid networks to missing values. A comprehensive analysis performed on twodifferent datasets from PeMS indicates that the proposed series-parallel hybridnetwork with the mean imputation technique achieves the lowest error inpredicting the traffic flow and is robust to missing values up until 21%missing ratio in both complete and incomplete training data scenarios whenapplied to an incomplete test data.

Learning spatiotemporal features from incomplete data for traffic flow prediction using hybrid deep neural networks