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

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.

Download Full-text

Traffic Incident Duration Estimation Based on a Dual-Learning Bayesian Network Model

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/0361198118796938 ◽

2018 ◽

Vol 2672 (45) ◽

pp. 196-209 ◽

Cited By ~ 1

Author(s):

Haozhe Cong ◽

Cong Chen ◽

Pei-Sung Lin ◽

Guohui Zhang ◽

John Milton ◽

...

Keyword(s):

Bayesian Network ◽

Expert Knowledge ◽

Transportation Systems ◽

Practical Significance ◽

Incident Management ◽

Highway Traffic ◽

Traffic Incidents ◽

Traffic Incident ◽

Incident Duration ◽

Traffic Incident Management

Highway traffic incidents induce a significant loss of life, economy, and productivity through injuries and fatalities, extended travel time and delay, and excessive energy consumption and air pollution. Traffic emergency management during incident conditions is the core element of active traffic management, and it is of practical significance to accurately understand the duration time distribution for typical traffic incident types and the factors that influence incident duration. This study proposes a dual-learning Bayesian network (BN) model to estimate traffic incident duration and to examine the influence of heterogeneous factors on the length of duration based on expert knowledge of traffic incident management and highway incident data collected in Zhejiang Province, China. Fifteen variables related to three aspects of traffic incidents, including incident information, incident consequences, and rescue resources, were included in the analysis. The trained BN model achieves favorable performance in several areas, including classification accuracy, the receiver operating characteristic (ROC) curve, and the area under curve (AUC) value. A classification matrix, and significant variables and their heterogeneous influences are identified accordingly. The research findings from this study provide beneficial reference to the understanding of decision-making in traffic incident response and process, active traffic incident management, and intelligent transportation systems.

Download Full-text

A Hybrid Method for Traffic Incident Duration Prediction Using BOA-Optimized Random Forest Combined with Neighborhood Components Analysis

Journal of Advanced Transportation ◽

10.1155/2019/4202735 ◽

2019 ◽

Vol 2019 ◽

pp. 1-11 ◽

Cited By ~ 8

Author(s):

Qiang Shang ◽

Derong Tan ◽

Song Gao ◽

Linlin Feng

Keyword(s):

Random Forest ◽

Confusion Matrix ◽

Prediction Method ◽

Bayesian Optimization ◽

Incident Management ◽

Bayesian Optimization Algorithm ◽

Traffic Incident ◽

Incident Duration ◽

Components Analysis ◽

Duration Prediction

Predicting traffic incident duration is important for effective and real-time traffic incident management (TIM), which helps to minimize traffic congestion, environmental pollution, and secondary incident related to this incident. Traffic incident duration prediction methods often use more input variables to obtain better prediction results. However, the problems that available variables are limited at the beginning of an incident and how to select significant variables are ignored to some extent. In this paper, a novel prediction method named NCA-BOA-RF is proposed using the Neighborhood Components Analysis (NCA) and the Bayesian Optimization Algorithm (BOA)-optimized Random Forest (RF) model. Firstly, the NCA is applied to select feature variables for traffic incident duration. Then, RF model is trained based on the training set constructed using feature variables, and the BOA is employed to optimize the RF parameters. Finally, confusion matrix is introduced to measure the optimized RF model performance and compare with other methods. In addition, the performance is also tested in the absence of some feature variables. The results demonstrate that the proposed method not only has high accuracy, but also exhibits excellent reliability and robustness.

Download Full-text

A Study on Freeway Traffic Incident Duration and Improvement Countermeasures

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.411-414.2752 ◽

2013 ◽

Vol 411-414 ◽

pp. 2752-2757

Author(s):

Jing Ru Gao

Keyword(s):

Incident Management ◽

Key Factors ◽

Traffic Incidents ◽

Freeway Traffic ◽

Emergency Rescue ◽

Traffic Incident ◽

Incident Duration ◽

Clearing Time ◽

Discovery Time ◽

Traffic Incident Management

Reducing the duration of freeway traffic incident plays a significant role in improving the efficiency of freeway transportation. The duration of freeway traffic incidents is composed of four stages: the discovery time, response time, clearing time and the recovery time. Through analyzing the key factors influencing different duration stations, this article studies how factors including incident severity, aid resource allocation and emergency rescue preplan influence the duration, and pointedly propose countermeasures to reduce freeway traffic incidents duration. The conclusion of this article provides reference for improving the efficiency in freeway traffic incident management. Key words: traffic incident; duration; factor analysis; improve countermeasures

Download Full-text

Incident Duration Modeling Using Flexible Parametric Hazard-Based Models

Computational Intelligence and Neuroscience ◽

10.1155/2014/723427 ◽

2014 ◽

Vol 2014 ◽

pp. 1-10 ◽

Cited By ~ 8

Author(s):

Ruimin Li ◽

Pan Shang

Keyword(s):

Failure Time ◽

Economic Losses ◽

Incident Management ◽

Accelerated Failure Time ◽

Traffic Incidents ◽

Traffic Incident ◽

Duration Time ◽

Incident Duration ◽

Traffic Incident Management ◽

Log Normal

Assessing and prioritizing the duration time and effects of traffic incidents on major roads present significant challenges for road network managers. This study examines the effect of numerous factors associated with various types of incidents on their duration and proposes an incident duration prediction model. Several parametric accelerated failure time hazard-based models were examined, including Weibull, log-logistic, log-normal, and generalized gamma, as well as all models with gamma heterogeneity and flexible parametric hazard-based models with freedom ranging from one to ten, by analyzing a traffic incident dataset obtained from the Incident Reporting and Dispatching System in Beijing in 2008. Results show that different factors significantly affect different incident time phases, whose best distributions were diverse. Given the best hazard-based models of each incident time phase, the prediction result can be reasonable for most incidents. The results of this study can aid traffic incident management agencies not only in implementing strategies that would reduce incident duration, and thus reduce congestion, secondary incidents, and the associated human and economic losses, but also in effectively predicting incident duration time.

Download Full-text

Traffic Incident Duration Prediction Based on K-Nearest Neighbor

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.253-255.1675 ◽

2012 ◽

Vol 253-255 ◽

pp. 1675-1681 ◽

Cited By ~ 3

Author(s):

Yuan Wen ◽

Shu Yan Chen ◽

Qin Yuan Xiong ◽

Ru Bi Han ◽

Shi Yu Chen

Keyword(s):

Nearest Neighbor ◽

Public Works ◽

Incident Management ◽

Bayesian Decision ◽

K Nearest Neighbor ◽

Data Set ◽

K Value ◽

Traffic Incident ◽

Incident Duration ◽

Duration Prediction

Prediction of incident duration is very important in Advanced Intelligent Traffic Incident Management and the accuracy of prediction can provide exact information for travellers. It is widely used in the area of ITS. In this paper, K-Nearest neighbor (KNN) is employed to predict the incident duration, which puts forward a new distance metric and weight determination method. This KNN model is created based on the incident data set collected by DVS-Center for Transport and Navigation, Ministry of Transport, Public Works and Management, the Netherlands. Moreover, a simulation based on Matlab is used for incident duration prediction and optimizing the best k value. Finally, an error analysis is made based on this simulation. As a result, this method (KNN) obtains high accuracy and has a better effect than Bayesian Decision Method-Based Tree Algorithm. So it can be effectively applied to intelligent traffic incident detection and clearance systems.

Download Full-text

Application of nonparametric regression in predicting traffic incident duration

Transport ◽

10.3846/16484142.2015.1004104 ◽

2015 ◽

Vol 33 (1) ◽

pp. 22-31 ◽

Cited By ~ 1

Author(s):

Shi Wang ◽

Ruimin Li ◽

Min Guo

Keyword(s):

Prediction Model ◽

Real Time ◽

Nonparametric Regression ◽

Prediction Algorithm ◽

Incident Management ◽

K Nearest Neighbor ◽

Incident Type ◽

Traffic Incident ◽

Duration Time ◽

Incident Duration

Predicting the duration time of incidents is important for effective real-time Traffic Incident Management (TIM). In the current study, the k-Nearest Neighbor (kNN) algorithm is employed as a nonparametric regression approach to develop a traffic incident duration prediction model. Incident data from 2008 on the third ring expressway mainline in Beijing are collected from the local Incident Reporting and Dispatching System. The incident sites are randomly distributed along the mainline, which is 48.3 km long and has six two-way lanes with a single-lane daily volume of more than 10000 veh. The main incident type used is sideswipe and the average incident duration time is 32.69 min. The most recent one-fourth of the incident records are selected as testing set. Vivatrat method is employed to filter anomalous data for the training set. Incident duration time is set as the dependent variable in Kruskal–Wallis test, and six attributes are identified as the main factors that affect the length of duration time, which are ‘day first shift’, ‘weekday’, ‘incident type’, ‘congestion’, ‘incident grade’ and ‘distance’. Based on the characteristics of duration time distribution, log transformation of original data is tested and proven to improve model performance. Different distance metrics and prediction algorithms are carefully investigated. Results demonstrate that the kNN model has better prediction accuracy using weighted distance metric based on decision tree and weighted prediction algorithm. The developed prediction model is further compared with other models based on the same dataset. Results show that the developed model can obtain reasonable prediction results, except for samples with extremely short or long duration. Such a prediction model can help TIM teams estimate the incident duration and implement real-time incident management strategies.

Download Full-text

Collection, Analysis, and Reporting of Kentucky Traffic Incident Management Performance

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/03611981211001077 ◽

2021 ◽

pp. 036119812110010

Author(s):

Xu Zhang ◽

Reginald R. Souleyrette ◽

Eric Green ◽

Teng Wang ◽

Mei Chen ◽

...

Keyword(s):

Motor Vehicle ◽

Management Strategies ◽

Incident Management ◽

Vehicle Crashes ◽

Clearance Time ◽

Emergency Responders ◽

Traffic Incident ◽

Choropleth Maps ◽

Traffic Incident Management ◽

Secondary Crashes

Traffic incidents remain all too common. They negatively affect the safety of the traveling public and emergency responders and cause significant traffic delays. Congestion associated with incidents can instigate secondary crashes, exacerbating safety risks and economic costs. Traffic incident management (TIM) provides an effective approach for managing highway incidents and reducing their occurrence and impacts. The paper discusses the establishment and methods of calculation for five TIM performance measures that are used by the Kentucky Transportation Cabinet (KYTC) to improve incident response. The measures are: roadway clearance time, incident clearance time, secondary crashes, first responder vehicle crashes, and commercial motor vehicle crashes. Ongoing tracking and analysis of these metrics aid the KYTC in its efforts to comprehensively evaluate its TIM program and make continuous improvements. As part of this effort, a fully interactive TIM dashboard was developed using the Microsoft Power BI platform. Dashboard users can apply various spatial and temporal filters to identify trends at the state, district, county, and agency level. The dashboard also supports dynamic visualizations such as time-series plots and choropleth maps. With the TIM dashboard in place, KYTC personnel, as well as staff at other transportation agencies, can identify the strengths and weaknesses of their incident management strategies and revise practices accordingly.

Download Full-text