Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

## Short-term traffic prediction under disruptions using deep learning

• Author(s):
• DOI:

$16.00 (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.

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:

Traffic Information and Control — Recommend this title to your library

## Thank you

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
• 5.2.2.1 Traffic characteristics under disrupted conditions
• 5.2.2.2 Traffic prediction under disrupted conditions
• 5.2.2.3 Summary
• 5.2.3 Review of traffic prediction using deep learning techniques
• 5.2.3.1 Introduction
• 5.2.3.2 Data representation in traffic prediction using deep learning
• 5.2.3.3 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
• 5.3.3.1 Temporal dependencies
• 5.3.3.2 Spatial dependencies
• 5.3.3.3 Attention mechanism
• 5.3.3.4 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
• 5.4.2.1 Traffic speed data preprocessing
• 5.4.2.2 Graph representation
• 5.4.2.3 Baseline methods for comparison
• 5.4.3 Short-term traffic speed prediction under non-incident conditions
• 5.4.3.1 Model setups
• 5.4.3.2 Prediction results under non-incident conditions
• 5.4.4 Short-term traffic data prediction under incidents
• 5.4.4.1 Traffic incident data
• 5.4.4.2 Prediction results during disruptions
• 5.5 Conclusions and future research
• References

Preview this chapter:

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

content/books/10.1049/pbtr026e_ch5
pub_keyword,iet_inspecKeyword,pub_concept
6
6
This is a required field