Your browser does not support JavaScript!

Short-term traffic prediction under disruptions using deep learning

Short-term traffic prediction under disruptions using deep learning

For access to this article, please select a purchase option:

Buy chapter PDF
(plus tax if applicable)
Buy Knowledge Pack
10 chapters for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
Traffic Information and Control — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

In this chapter, we have proposed a novel graph -based model with TS-TGAT to predict short-term traffic speed under both normal and abnormal traffic fl ow conditions. The novelty of the proposed prediction model is that it can learn both spatial and temporal propagation rules for traffic on a network. Important concepts and improvements are introduced to the model, for example node -level attention weights, multi -head attention and depth -wise separable CNN module to take account of the unique and complex interactions between traffic fl ows and traffic network characteristics. The proposed prediction model was trained and tested using ILDs on a section of the M25 motorway network just before the Dartford Crossing (between Dartford Tunnel and M25 J2 with all slip roads). In order to make the model generic and reusable, the model was trained using generic data (including both normal and abnormal traffic fl ow data) and was tested under mixed conditions and disrupted conditions. A selection of baseline methods was used to benchmark the proposed model performance, including HA, kNN, GBDTs and LSTM, some of which are state-of-the-art methods in the problem of short-term traffic prediction. The results have shown that the proposed TS-TGAT method outperforms other benchmarking methods under both normal and abnormal traffic conditions.

Chapter Contents:

  • 5.1 Introduction
  • 5.2 Literature review
  • 5.2.1 Traffic prediction under normal conditions
  • 5.2.2 Traffic prediction under disrupted conditions
  • Traffic characteristics under disrupted conditions
  • Traffic prediction under disrupted conditions
  • Summary
  • 5.2.3 Review of traffic prediction using deep learning techniques
  • Introduction
  • Data representation in traffic prediction using deep learning
  • Spatio-temporal features in traffic prediction using deep learning
  • 5.2.4 Summary
  • 5.3 Methodology
  • 5.3.1 Traffic network representation on a graph
  • 5.3.2 Problem formulation
  • 5.3.3 Model structure
  • Temporal dependencies
  • Spatial dependencies
  • Attention mechanism
  • Loss function and parameter optimisation
  • 5.3.4 Quantification of prediction accuracy
  • 5.4 Short-term traffic data prediction using real-world data in London
  • 5.4.1 Traffic speed data
  • 5.4.2 Preparation for the prediction model
  • Traffic speed data preprocessing
  • Graph representation
  • Baseline methods for comparison
  • 5.4.3 Short-term traffic speed prediction under non-incident conditions
  • Model setups
  • Prediction results under non-incident conditions
  • 5.4.4 Short-term traffic data prediction under incidents
  • Traffic incident data
  • Prediction results during disruptions
  • 5.5 Conclusions and future research
  • References

Inspec keywords: road traffic control; graph theory; convolutional neural nets; learning (artificial intelligence)

Other keywords: LSTM; GBDT; graph-based model; temporal propagation rules; Dartford crossing; M25 motorway network; spatial propagation rules; normal traffic flow condition; TS-TGAT; M25 J2; node-level attention weights; HA; multihead attention; abnormal traffic flow condition; short-term traffic speed prediction; deep learning; kNN; Dartford Tunnel section; depth-wise separable CNN module

Subjects: Neural computing techniques; Traffic engineering computing; Combinatorial mathematics

Preview this chapter:
Zoom in

Short-term traffic prediction under disruptions using deep learning, Page 1 of 2

| /docserver/preview/fulltext/books/tr/pbtr026e/PBTR026E_ch5-1.gif /docserver/preview/fulltext/books/tr/pbtr026e/PBTR026E_ch5-2.gif

Related content

This is a required field
Please enter a valid email address