Freeway Short-Term Travel Speed Prediction Based on Data Collection Time-Horizons: A Fast Forest Quantile Regression Approach

Short-Term Traffic Speed Forecasting Model for a Parallel Multi-Lane Arterial Road Using GPS-Monitored Data Based on Deep Learning Approach

Traffic speed forecasting in the short term is one of the most critical parts of any intelligent transportation system (ITS). Accurate speed forecasting can support travelers’ route choices, traffic guidance, and traffic control. This study proposes a deep learning approach using long short-term memory (LSTM) network with tuning hyper-parameters to forecast short-term traffic speed on an arterial parallel multi-lane road in a developing country such as Vietnam. The challenge of mishandling the location data of vehicles on small and adjacent multi-lane roads will be addressed in this study. To test the accuracy of the proposed forecasting model, its application is illustrated using historical voyage GPS-monitored data on the Le Hong Phong urban arterial road in Haiphong city of Vietnam. The results indicate that in comparison with other models (e.g., traditional models and convolutional neural network), the best performance in terms of root mean square error (RMSE), mean absolute error (MAE), and median absolute error (MDAE) is obtained by using the proposed model.

Travel Time Prediction and Explanation with Spatio-Temporal Features: A Comparative Study

Travel time information is used as input or auxiliary data for tasks such as dynamic navigation, infrastructure planning, congestion control, and accident detection. Various data-driven Travel Time Prediction (TTP) methods have been proposed in recent years. One of the most challenging tasks in TTP is developing and selecting the most appropriate prediction algorithm. The existing studies that empirically compare different TTP models only use a few models with specific features. Moreover, there is a lack of research on explaining TTPs made by black-box models. Such explanations can help to tune and apply TTP methods successfully. To fill these gaps in the current TTP literature, using three data sets, we compare three types of TTP methods (ensemble tree-based learning, deep neural networks, and hybrid models) and ten different prediction algorithms overall. Furthermore, we apply XAI (Explainable Artificial Intelligence) methods (SHAP and LIME) to understand and interpret models’ predictions. The prediction accuracy and reliability for all models are evaluated and compared. We observed that the ensemble learning methods, i.e., XGBoost and LightGBM, are the best performing models over the three data sets, and XAI methods can adequately explain how various spatial and temporal features influence travel time.

Injury severity prediction of traffic crashes with ensemble machine learning techniques: a comparative study

A better understanding of injury severity risk factors is fundamental to improving crash prediction and effective implementation of appropriate mitigation strategies. Traditional statistical models widely used in this regard have predefined correlation and intrinsic assumptions, which, if flouted, may yield biased predictions. The present study investigates the possibility of using the eXtreme Gradient Boosting (XGBoost) model compared with few traditional machine learning algorithms (logistic regression, random forest, and decision tree) for crash injury severity analysis. The data used in this study was obtained from the traffic safety department, ministry of transport (MOT) at Riyadh, KSA, and contains 13,546 motor vehicle collisions along 15 rural highways reported between January 2017 to December 2019. Empirical results obtained using k-fold (k = 10) for various performance metrics showed that the XGBoost technique outperformed other models in terms of the collective predictive performance as well as injury severity individual class accuracies. XGBoost feature importance analysis indicated that collision type, weather status, road surface conditions, on-site damage type, lighting conditions, and vehicle type are the few sensitive variables in predicting the crash injury severity outcome. Finally, a comparative analysis of XGBoost based on different performance statistics showed that our model outperformed most previous studies.

Exploring the Injury Severity Risk Factors in Fatal Crashes with Neural Network

A better understanding of circumstances contributing to the severity outcome of traffic crashes is an important goal of road safety studies. An in-depth crash injury severity analysis is vital for the proactive implementation of appropriate mitigation strategies. This study proposes an improved feed-forward neural network (FFNN) model for predicting injury severity associated with individual crashes using three years (2017–2019) of crash data collected along 15 rural highways in the Kingdom of Saudi Arabia (KSA). A total of 12,566 crashes were recorded during the study period with a binary injury severity outcome (fatal or non-fatal injury) for the variable to be predicted. FFNN architecture with back-propagation (BP) as a training algorithm, logistic as activation function, and six number of hidden neurons in the hidden layer yielded the best model performance. Results of model prediction for the test data were analyzed using different evaluation metrics such as overall accuracy, sensitivity, and specificity. Prediction results showed the adequacy and robust performance of the proposed method. A detailed sensitivity analysis of the optimized NN was also performed to show the impact and relative influence of different predictor variables on resulting crash injury severity. The sensitivity analysis results indicated that factors such as traffic volume, average travel speeds, weather conditions, on-site damage conditions, road and vehicle type, and involvement of pedestrians are the most sensitive variables. The methods applied in this study could be used in big data analysis of crash data, which can serve as a rapid-useful tool for policymakers to improve highway safety.

On the Potential Impacts of Smart Traffic Control for Delay, Fuel Energy Consumption, and Emissions: An NSGA-II-Based Optimization Case Study from Dhahran, Saudi Arabia

Intelligent traffic control at urban intersections is vital to ensure efficient and sustainable traffic operations. Urban road intersections are hotspots of congestion and traffic accidents. Poor traffic management at these locations could cause numerous issues, such as longer travel time, low travel speed, long vehicle queues, delays, increased fuel consumption, and environmental emissions, and so forth. Previous studies have shown that the mentioned traffic performance measures or measures of effectiveness (MOEs) could be significantly improved by adopting intelligent traffic control protocols. The majority of studies in this regard have focused on mono or bi-objective optimization with homogenous and lane-based traffic conditions. However, decision-makers often have to deal with multiple conflicting objectives to find an optimal solution under heterogeneous stochastic traffic conditions. Therefore, it is essential to determine the optimum decision plan that offers the least conflict among several objectives. Hence, the current study aimed to develop a multi-objective intelligent traffic control protocol based on the non-dominated sorting genetic algorithm II (NSGA-II) at isolated signalized intersections in the city of Dhahran, Kingdom of Saudi Arabia. The MOEs (optimization objectives) that were considered included average vehicle delay, the total number of vehicle stops, average fuel consumption, and vehicular emissions. NSGA-II simulations were run with different initial populations. The study results showed that the proposed method was effective in optimizing considered performance measures along the optimal Pareto front. MOEs were improved in the range of 16% to 23% compared to existing conditions. To assess the efficacy of the proposed approach, an optimization analysis was performed using a Synchro traffic light simulation and optimization tool. Although the Synchro optimization resulted in a relatively lower signal timing plan than NSGA-II, the proposed algorithm outperformed the Synchro optimization results in terms of percentage reduction in MOE values.

Real-Time Traffic Flow Forecasting via a Novel Method Combining Periodic-Trend Decomposition

Accurate and timely traffic flow forecasting is a critical task of the intelligent transportation system (ITS). The predicted results offer the necessary information to support the decisions of administrators and travelers. To investigate trend and periodic characteristics of traffic flow and develop a more accurate prediction, a novel method combining periodic-trend decomposition (PTD) is proposed in this paper. This hybrid method is based on the principle of “decomposition first and forecasting last”. The well-designed PTD approach can decompose the original traffic flow into three components, including trend, periodicity, and remainder. The periodicity is a strict period function and predicted by cycling, while the trend and remainder are predicted by modelling. To demonstrate the universal applicability of the hybrid method, four prevalent models are separately combined with PTD to establish hybrid models. Traffic volume data are collected from the Minnesota Department of Transportation (Mn/DOT) and used to conduct experiments. Empirical results show that the mean absolute error (MAE), mean absolute percentage error (MAPE), and mean square error (MSE) of hybrid models are averagely reduced by 17%, 17%, and 29% more than individual models, respectively. In addition, the hybrid method is robust for a multi-step prediction. These findings indicate that the proposed method combining PTD is promising for traffic flow forecasting.

Adopting Machine Learning and Spatial Analysis Techniques for Driver Risk Assessment: Insights from a Case Study

Traffic violations usually caused by aggressive driving behavior are often seen as a primary contributor to traffic crashes. Violations are either caused by an unintentional or deliberate act of drivers that jeopardize the lives of fellow drivers, pedestrians, and property. This study is aimed to investigate different traffic violations (overspeeding, wrong-way driving, illegal parking, non-compliance traffic control devices, etc.) using spatial analysis and different machine learning methods. Georeferenced violation data along two expressways (S308 and S219) for the year 2016 was obtained from the traffic police department, in the city of Luzhou, China. Detailed descriptive analysis of the data showed that wrong-way driving was the most common violation type observed. Inverse Distance Weighted (IDW) interpolation in the ArcMap Geographic Information System (GIS) was used to develop violation hotspots zones to guide on efficient use of limited resources during the treatment of high-risk sites. Lastly, a systematic Machine Learning (ML) framework, such as K Nearest Neighbors (KNN) models (using k = 3, 5, 7, 10, and 12), support vector machine (SVM), and CN2 Rule Inducer, was utilized for classification and prediction of each violation type as a function of several explanatory variables. The predictive performance of proposed ML models was examined using different evaluation metrics, such as Area Under the Curve (AUC), F-score, precision, recall, specificity, and run time. The results also showed that the KNN model with k = 7 using manhattan evaluation had an accuracy of 99% and outperformed the SVM and CN2 Rule Inducer. The outcome of this study could provide the practitioners and decision-makers with essential insights for appropriate engineering and traffic control measures to improve the safety of road-users.

Predicting Risky and Aggressive Driving Behavior among Taxi Drivers: Do Spatio-Temporal Attributes Matter?

Risky and aggressive driving maneuvers are considered a significant indicator for traffic accident occurrence as well as they aggravate their severity. Traffic violations caused by such uncivilized driving behavior is a global issue. Studies in existing literature have used statistical analysis methods to explore key contributing factors toward aggressive driving and traffic violations. However, such methods are unable to capture latent correlations among predictor variables, and they also suffer from low prediction accuracies. This study aimed to comprehensively investigate different traffic violations using spatial analysis and machine learning methods in the city of Luzhou, China. Violations committed by taxi drivers are the focus of the current study since they constitute a significant proportion of total violations reported in the city. Georeferenced violation data for the year 2016 was obtained from the traffic police department. Detailed descriptive analysis is presented to summarize key statistics about various violation types. Results revealed that over-speeding was the most prevalent violation type observed in the study area. Frequency-based nearest neighborhood cluster methods in Arc map Geographic Information System (GIS) were used to develop hotspot maps for different violation types that are vital for prioritizing and conducting treatment alternatives efficiently. Finally, different machine learning (ML) methods, including decision tree, AdaBoost with a base estimator decision tree, and stack model, were employed to predict and classify each violation type. The proposed methods were compared based on different evaluation metrics like accuracy, F-1 measure, specificity, and log loss. Prediction results demonstrated the adequacy and robustness of proposed machine learning (ML) methods. However, a detailed comparative analysis showed that the stack model outperformed other models in terms of proposed evaluation metrics.

Intelligent Intersection Control for Delay Optimization: Using Meta-Heuristic Search Algorithms

Traffic signal control is an integral component of an intelligent transportation system (ITS) that play a vital role in alleviating traffic congestion. Poor traffic management and inefficient operations at signalized intersections cause numerous problems as excessive vehicle delays, increased fuel consumption, and vehicular emissions. Operational performance at signalized intersections could be significantly enhanced by optimizing phasing and signal timing plans using intelligent traffic control methods. Previous studies in this regard have mostly focused on lane-based homogenous traffic conditions. However, traffic patterns are usually non-linear and highly stochastic, particularly during rush hours, which limits the adoption of such methods. Hence, this study aims to develop metaheuristic-based methods for intelligent traffic control at isolated signalized intersections, in the city of Dhahran, Saudi Arabia. Genetic algorithm (GA) and differential evolution (DE) were employed to enhance the intersection’s level of service (LOS) by optimizing the signal timings plan. Average vehicle delay through the intersection was selected as the primary performance index and algorithms objective function. The study results indicated that both GA and DE produced a systematic signal timings plan and significantly reduced travel time delay ranging from 15 to 35% compared to existing conditions. Although DE converged much faster to the objective function, GA outperforms DE in terms of solution quality i.e., minimum vehicle delay. To validate the performance of proposed methods, cycle length-delay curves from GA and DE were compared with optimization outputs from TRANSYT 7F, a state-of-the-art traffic signal simulation, and optimization tool. Validation results demonstrated the adequacy and robustness of proposed methods.

Short Term Traffic State Prediction via Hyperparameter Optimization Based Classifiers

Short-term traffic state prediction has become an integral component of an advanced traveler information system (ATIS) in intelligent transportation systems (ITS). Accurate modeling and short-term traffic prediction are quite challenging due to its intricate characteristics, stochastic, and dynamic traffic processes. Existing works in this area follow different modeling approaches that are focused to fit speed, density, or the volume data. However, the accuracy of such modeling approaches has been frequently questioned, thereby traffic state prediction over the short-term from such methods inflicts an overfitting issue. We address this issue to accurately model short-term future traffic state prediction using state-of-the-art models via hyperparameter optimization. To do so, we focused on different machine learning classifiers such as local deep support vector machine (LD-SVM), decision jungles, multi-layers perceptron (MLP), and CN2 rule induction. Moreover, traffic states are evaluated using traffic attributes such as level of service (LOS) horizons and simple if–then rules at different time intervals. Our findings show that hyperparameter optimization via random sweep yielded superior results. The overall prediction performances obtained an average improvement by over 95%, such that the decision jungle and LD-SVM achieved an accuracy of 0.982 and 0.975, respectively. The experimental results show the robustness and superior performances of decision jungles (DJ) over other methods.