Dynamic prediction of traffic incident duration on urban expressways: a deep learning approach based on LSTM and MLP

Abstract

Purpose Efficient traffic incident management is needed to alleviate the negative impact of traffic incidents. Accurate and reliable estimation of traffic incident duration is of great importance for traffic incident management. Previous studies have proposed models for traffic incident duration prediction; however, most of these studies focus on the total duration and could not update prediction results in real-time. From a traveler’s perspective, the relevant factor is the residual duration of the impact of the traffic incident. Besides, few (if any) studies have used dynamic traffic flow parameters in the prediction models. This paper aims to propose a framework to fill these gaps. Design/methodology/approach This paper proposes a framework based on the multi-layer perception (MLP) and long short-term memory (LSTM) model. The proposed methodology integrates traffic incident-related factors and real-time traffic flow parameters to predict the residual traffic incident duration. To validate the effectiveness of the framework, traffic incident data and traffic flow data from Shanghai Zhonghuan Expressway are used for modeling training and testing. Findings Results show that the model with 30-min time window and taking both traffic volume and speed as inputs performed best. The area under the curve values exceed 0.85 and the prediction accuracies exceed 0.75. These indicators demonstrated that the model is appropriate for this study context. The model provides new insights into traffic incident duration prediction. Research limitations/implications The incident samples applied by this study might not be enough and the variables are not abundant. The number of injuries and casualties, more detailed description of the incident location and other variables are expected to be used to characterize the traffic incident comprehensively. The framework needs to be further validated through a sufficiently large number of variables and locations. Practical implications The framework can help reduce the impacts of incidents on the safety of efficiency of road traffic once implemented in intelligent transport system and traffic management systems in future practical applications. Originality/value This study uses two artificial neural network methods, MLP and LSTM, to establish a framework aiming at providing accurate and time-efficient information on traffic incident duration in the future for transportation operators and travelers. This study will contribute to the deployment of emergency management and urban traffic navigation planning.

Multivariate time-series blood donation/demand forecasting for resilient supply chain management during COVID-19 pandemic

“…They not only utilized internal information (historical data of traffic state), but also added external information (e.g., weather condition, holiday, the day of week, and the time of day) into the model, to construct more accurate prediction model. Zhu et al (2021) presented a multivariate deep learning technique based on LSTM and multi-layer perceptron (MLP) for the dynamic prediction of traffic incident duration in urban expressways. This method integrates the traffic incident-related factors and real-time traffic flow to predict the traffic incident duration.…”

“…The proposed multivariate LSTM time-series blood donation/demand model not only considers the past values of the donation/demand (internal features), but also takes into account time-series of the new confirmed COVID-19 cases and deaths (external features). Although this idea has been used in other tasks such as traffic prediction systems ( Zhu et al, 2021 , Zhu et al, 2021 ), it has not been used to predict the blood donation/demand values affected by the COVID-19 cases/deaths. By adopting the proposed multivariate time-series model for the blood donation/demand forecasting during the COVID-19 pandemic, a resilient blood supply chain management is achieved, capable of handling uncertain blood supply/demand.…”

HSDDD: A Hybrid Scheme for the Detection of Distracted Driving through Fusion of Deep Learning and Handcrafted Features

“…W. Zhu et al [28] have proposed a framework based on the multi-layer perception (MLP) and long short-term memory (LSTM) model. The proposed methodology contains four parts: data processing, LSTM neural network for incident clearance prediction and MLP network for incident clearance prediction.…”

A Study of Missing Collaborative Data Imputation Models based on Same-City Delivery

“…In the LSTM-GL-ReMF, its temporal regularizer introduces the recurrent neural network LSTM with extremely strong learning performance to discover hidden correlations in the samples. Hochreiter and Schmidhuber proposed the LSTM which could overcome long-term dependencies and determine the best time window automatically [24]. Calculate the hidden layer sequence (6) and output sequence (7) by equations ε to c:…”