Real-Time Crash Risk Prediction using Long Short-Term Memory Recurrent Neural Network

Abstract

With the help of traffic detectors widely deployed along arterial roads and intersections, real-time traffic data are collected and updated in a very short time period, which makes it possible to conduct real-time analysis at signalized intersections. Among them, real-time crash risk prediction is one of the most promising and challenging research topics. This study attempts to predict real-time crash risk by considering time series dependency with the employment of a long short-term memory recurrent neural network (LSTM-RNN) algorithm. Also, the synthetic minority over-sampling technique (SMOTE) was utilized in this study to generate a balanced training dataset for algorithm training. In comparison, a conditional logistic model was developed based on matched case control design. Both models were evaluated based on the real-world unbalanced test dataset rather than an artificially balanced dataset. The comparison results indicate that the LSTM-RNN with SMOTE outperforms the conditional logistic model. The methods and findings of this study attempt to verify the feasibility of real-time crash risk prediction by using LSTM-RNN with over-sampled dataset (SMOTE).

Prediction of Pedestrian Crossing Intentions at Intersections Based on Long Short-Term Memory Recurrent Neural Network

“…In transportation fields, LSTM neural networks were used to predict vehicle travel time or traffic speed on highway links as well as urban arterials (21)(22)(23). They were also used for driving behavior classification and real-time crash risk prediction (24)(25)(26). Through these implementations, LSTM models proved their good performances on sequential traffic data.…”

Bluetooth Verisi Kullanarak Kentsel Arterlerde Seyahat Süresinin Değerlendirilmesi

“…BT-based traffic data has been frequently used in traffic analysis due to the higher sampling rate and low cost [12]. While some studies focused on the reliability of travel times for freeways or urban arterials [3][4][5][6][7][8][9][10], some other studies focused on the estimation of origindestination matrix [2,[13][14][15], freeway performance evaluation [10,[16][17], traffic safety analysis [18], delay estimation for signalized intersections [19][20][21]. Since the focus of this study is to examine the reliability of TT data, it is useful to present the TT related studies in this section.…”

Crash Prediction on Expressway Incorporating Traffic Flow Continuity Parameters Based on Machine Learning Approach

“…Typical statistical methods found in related studies mainly include matched case-control logistic regression [4,10,16,18], aggregate log linear model [5], and Bayesian statistics [3,9,14,19]. Algorithms based on neural networks [31,32], fuzzy logic method [20], classification trees [33], machine learning [6,9,34], and deep learning [8,[35][36][37] are encompassed in modern methods. Regarding the intercorrelation problem of traffic variables, statistical approaches usually delete the intercorrelated variables during modelling process [14].…”