An Improved Deep Belief Network Model for Road Safety Analyses

TL;DR

This paper proposes a regularized deep belief network for crash prediction, combining unsupervised and Bayesian neural network training to improve accuracy and reduce manual calibration in road safety analyses.

Contribution

It introduces a novel ML model that enhances crash prediction by integrating deep belief networks with Bayesian fine-tuning, offering a more automated and potentially more accurate alternative to traditional methods.

Findings

The new model outperforms traditional models like NB, KR, and Bayesian NN in crash prediction accuracy.

Demonstrates effectiveness on highway crash data from Ontario, Canada.

Shows reduced need for manual calibration and domain expertise.

Abstract

Crash prediction is a critical component of road safety analyses. A widely adopted approach to crash prediction is application of regression based techniques. The underlying calibration process is often time-consuming, requiring significant domain knowledge and expertise and cannot be easily automated. This paper introduces a new machine learning (ML) based approach as an alternative to the traditional techniques. The proposed ML model is called regularized deep belief network, which is a deep neural network with two training steps: it is first trained using an unsupervised learning algorithm and then fine-tuned by initializing a Bayesian neural network with the trained weights from the first step. The resulting model is expected to have improved prediction power and reduced need for the time-consuming human intervention. In this paper, we attempt to demonstrate the potential of this new model for crash prediction through two case studies including a collision data set from 800 km stretch of Highway 401 and other highways in Ontario, Canada. Our intention is to show the performance of this ML approach in comparison to various traditional models including negative binomial (NB) model, kernel regression (KR), and Bayesian neural network (Bayesian NN). We also attempt to address other related issues such as effect of training data size and training parameters.