Severity prediction of traffic accidents with recurrent neural networks

Sameen, MI; Pradhan, B

Severity prediction of traffic accidents with recurrent neural networks

Sameen, MI Pradhan, B

Permalink

Publication Type:: Journal Article
Citation:: Applied Sciences (Switzerland), 2017, 7 (6)
Issue Date:: 2017-06-08

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published VersionAdobe PDF (2.65 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Sameen, MI	en_US
dc.contributor.author	Pradhan, B https://orcid.org/0000-0001-9863-2054	en_US
dc.date.issued	2017-06-08	en_US
dc.identifier.citation	Applied Sciences (Switzerland), 2017, 7 (6)	en_US
dc.identifier.uri	http://hdl.handle.net/10453/123776
dc.description.abstract	© 2017 by the authors. In this paper, a deep learning model using a Recurrent Neural Network (RNN) was developed and employed to predict the injury severity of traffic accidents based on 1130 accident records that have occurred on the North-South Expressway (NSE), Malaysia over a six-year period from 2009 to 2015. Compared to traditional Neural Networks (NNs), the RNN method is more effective for sequential data, and is expected to capture temporal correlations among the traffic accident records. Several network architectures and configurations were tested through a systematic grid search to determine an optimal network for predicting the injury severity of traffic accidents. The selected network architecture comprised of a Long-Short Term Memory (LSTM) layer, two fully-connected (dense) layers and a Softmax layer. Next, to avoid over-fitting, the dropout technique with a probability of 0.3 was applied. Further, the network was trained with a Stochastic Gradient Descent (SGD) algorithm (learning rate = 0.01) in the Tensorflow framework. A sensitivity analysis of the RNN model was further conducted to determine these factors' impact on injury severity outcomes. Also, the proposed RNN model was compared with Multilayer Perceptron (MLP) and Bayesian Logistic Regression (BLR) models to understand its advantages and limitations. The results of the comparative analyses showed that the RNN model outperformed the MLP and BLR models. The validation accuracy of the RNN model was 71.77%, whereas the MLP and BLR models achieved 65.48% and 58.30% respectively. The findings of this study indicate that the RNN model, in deep learning frameworks, can be a promising tool for predicting the injury severity of traffic accidents.	en_US
dc.relation.ispartof	Applied Sciences (Switzerland)	en_US
dc.relation.isbasedon	10.3390/app7060476	en_US
dc.title	Severity prediction of traffic accidents with recurrent neural networks	en_US
dc.type	Journal Article
utslib.citation.volume	6	en_US
utslib.citation.volume	7	en_US
utslib.for	0301 Analytical Chemistry	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Information, Systems and Modelling
pubs.organisational-group	/University of Technology Sydney/Strength - CAMGIS - Centre for Advanced Modelling and Geospatial lnformation Systems
utslib.copyright.status	open_access
pubs.issue	6	en_US
pubs.publication-status	Published	en_US
pubs.volume	7	en_US

Abstract:

© 2017 by the authors. In this paper, a deep learning model using a Recurrent Neural Network (RNN) was developed and employed to predict the injury severity of traffic accidents based on 1130 accident records that have occurred on the North-South Expressway (NSE), Malaysia over a six-year period from 2009 to 2015. Compared to traditional Neural Networks (NNs), the RNN method is more effective for sequential data, and is expected to capture temporal correlations among the traffic accident records. Several network architectures and configurations were tested through a systematic grid search to determine an optimal network for predicting the injury severity of traffic accidents. The selected network architecture comprised of a Long-Short Term Memory (LSTM) layer, two fully-connected (dense) layers and a Softmax layer. Next, to avoid over-fitting, the dropout technique with a probability of 0.3 was applied. Further, the network was trained with a Stochastic Gradient Descent (SGD) algorithm (learning rate = 0.01) in the Tensorflow framework. A sensitivity analysis of the RNN model was further conducted to determine these factors' impact on injury severity outcomes. Also, the proposed RNN model was compared with Multilayer Perceptron (MLP) and Bayesian Logistic Regression (BLR) models to understand its advantages and limitations. The results of the comparative analyses showed that the RNN model outperformed the MLP and BLR models. The validation accuracy of the RNN model was 71.77%, whereas the MLP and BLR models achieved 65.48% and 58.30% respectively. The findings of this study indicate that the RNN model, in deep learning frameworks, can be a promising tool for predicting the injury severity of traffic accidents.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/123776