Abstract
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.
Highlights
Traffic accidents are a primary concern due to many fatalities and economic losses every year worldwide
The results of the comparative analyses showed that the Recurrent Neural Network (RNN) model outperformed the Multilayer Perceptron (MLP) and Bayesian Logistic Regression (BLR) models
The validation accuracy of the RNN model was 71.77%, whereas the MLP and BLR
Summary
Traffic accidents are a primary concern due to many fatalities and economic losses every year worldwide. In Malaysia, recent statistics show that there are nearly 24 deaths per 100,000 people for all road users [1]. Expressways are potential sites of fatal highway accidents in Malaysia. Better accident severity prediction models are critical to enhancing the safety performance of road traffic systems. Driver injury severity can be classified into a few categories such as property damage, possible/evident injury, or disabling injury/fatality [2]. In a deep learning model, an input vector is often mapped into an output vector through a set of nonlinear functions. In the case of accident severity, the input vectors are the characteristics of the accident, such as driver behavior and highway, vehicle and environment characteristics.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have