Wei Wu

Bio: Wei Wu is an academic researcher. The author has contributed to research in topics: Traffic congestion & Support vector machine. The author has an hindex of 3, co-authored 6 publications receiving 18 citations.

Predicting Freeway Travel Time Using Multiple- Source Heterogeneous Data Integration

Abstract: Freeway travel time is influenced by many factors including traffic volume, adverse weather, accidents, traffic control, and so on. We employ the multiple source data-mining method to analyze freeway travel time. We collected toll data, weather data, traffic accident disposal logs, and other historical data from Freeway G5513 in Hunan Province, China. Using the Support Vector Machine (SVM), we proposed the travel time predicting model founded on these databases. The new SVM model can simulate the nonlinear relationship between travel time and those factors. In order to improve the precision of the SVM model, we applied the Artificial Fish Swarm algorithm to optimize the SVM model parameters, which include the kernel parameter σ, non-sensitive loss function parameter e, and penalty parameter C. We compared the new optimized SVM model with the Back Propagation (BP) neural network and a common SVM model, using the historical data collected from freeway G5513. The results show that the accuracy of the optimized SVM model is 17.27% and 16.44% higher than those of the BP neural network model and the common SVM model, respectively.

Exploring Traffic Congestion on Urban Expressways Considering Drivers' Unreasonable Behavior at Merge/Diverge Sections

Abstract: Mechanism of traffic congestion generation is more than complicated, due to complex geometric road design and complicated driving behavior at urban expressway in China. We employ Cell transmission model (CTM) to simulate traffic flow spatiotemporal evolution process along the expressway, and reveal the characteristics of traffic congestion occurrence and propagation. Here we apply the variable-length-cell CTM to adapt the complicated road geometry and configuration, and propose the merge section CTM considering drivers' mandatory lane-changing and other unreasonable behavior at on-ramp merge section, and propose the diverge section CTM considering queue length end extending expressway mainline to generate dynamic bottleneck at diverge section. In the new improved CTM model, we introduce merge ratio and diverge ratio to describe the effect of driver behavior at merge and diverge section. We conduct simulation on the real urban expressway in China, results show that merge section and diverge section are the original location of expressway traffic congestion generation, on/off-ramp traffic flow has great effect on expressway mainline operation. When on-ramp traffic volume increases by 40%, merge section delay increases by 35%. And when off-ramp capacity increases by 100 veh/hr, diverge section delay decreases about by 10%, which proves the strong interaction between expressway and adjacent road networks . Our results provide the underlying insights of traffic congestion mechanism in urban expressway in China, which can be used to better understand and manage this issue.

Exploring Traffic Congestion on Urban Expressways Considering Drivers’ Unreasonable Behavior at Merge/Diverge Sections in China

Abstract: The mechanisms of traffic congestion generation are more than complicated, due to complex geometric road designs and complicated driving behavior at urban expressways in China. We employ a cell transmission model (CTM) to simulate the traffic flow spatiotemporal evolution process along the expressway, and reveal the characteristics of traffic congestion occurrence and propagation. Here, we apply the variable-length-cell CTM to adapt the complicated road geometry and configuration, and propose the merge section CTM considering drivers’ mandatory lane-changing and other unreasonable behavior at the on-ramp merge section, and propose the diverge section CTM considering queue length end extending the expressway mainline to generate a dynamic bottleneck at the diverge section. In the new improved CTM model, we introduce merge ratio and diverge ratio to describe the effect of driver behavior at the merge and diverge section. We conduct simulations on the real urban expressway in China, with results showing that the merge section and diverge section are the original location of expressway traffic congestion generation, and on/off-ramp traffic flow has a great effect on the expressway mainline operation. When on-ramp traffic volume increases by 40%, the merge section delay increases by 35%, and when off-ramp capacity increases by 100 veh/hr, the diverge section delay decreases about by 10%, which proves the strong interaction between expressway and adjacent road networks. Our results provide the underlying insights of traffic congestion mechanism in urban expressway in China, which can be used to better understand and manage this issue.

Predicting Freeway Travelling Time Using Multiple-Source Data

Abstract: Freeway travelling time is affected by many factors including traffic volume, adverse weather, accident, traffic control and so on. We employ the multiple source data-mining method to analyze freeway travelling time. We collected toll data, weather data, traffic accident disposal logs and other historical data of freeway G5513 in Hunan province, China. Using Support Vector Machine (SVM), we proposed the travelling time model based on these databases. The new SVM model can simulate the nonlinear relationship between travelling time and those factors. In order to improve the precision of the SVM model, we applied Artificial Fish Swarm algorithm to optimize the SVM model parameters, which include the kernel parameter σ, non-sensitive loss function parameter ε, and penalty parameter C. We compared the new optimized SVM model with Back Propagation (BP) neural network and common SVM model, using the historical data collected from freeway G5513. The results show that the accuracy of the optimized SVM model is 17.27% and 16.44% higher than those of the BP neural network model and the common SVM model respectively.

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

Abstract: Short-term traffic speed prediction is vital for proactive traffic control, and is one of the integral components of an intelligent transportation system (ITS). Accurate prediction of short-term travel speed has numerous applications for traffic monitoring, route planning, as well as helping to relieve traffic congestion. Previous studies have attempted to approach this problem using statistical and conventional artificial intelligence (AI) methods without accounting for influence of data collection time-horizons. However, statistical methods have received widespread criticism concerning prediction accuracy performance, while traditional AI approaches have too shallow architecture to capture non-linear stochastics variations in traffic flow. Hence, this study aims to explore prediction of short-term traffic speed at multiple time-ahead intervals using data collected from loop detectors. A fast forest quantile regression (FFQR) via hyperparameters optimization was introduced for predicting short-term traffic speed prediction. FFQR is an ensemble machine learning model that combines several regression trees to improve speed prediction accuracy. The accuracy of short-term traffic speed prediction was compared using the FFQR model at different data collection time-horizons. Prediction results demonstrated the adequacy and robustness of the proposed approach under different scenarios. It was concluded that prediction performance of FFQR was significantly enhanced and robust, particularly at time intervals larger than 5 min. The findings also revealed that speed prediction error (in terms of quantiles loss) ranged between 0.58 and 1.18.

Smart Urban Mobility: When Mobility Systems Meet Smart Data

Abstract: Cities around the world are expanding dramatically, with urban population growth reaching nearly 2.5 billion people in urban areas and road traffic growth exceeding 1.2 billion cars by 2050. The economic contribution of the transport sector represents 5% of the GDP in Europe and costs an average of US $482.05 billion in the United States. These figures indicate the rapid rise of industrial cities and the urgent need to move from traditional cities to smart cities. This article provides a survey of different approaches and technologies such as intelligent transportation systems (ITS) that leverage communication technologies to help maintain road users safe while driving, as well as support autonomous mobility through the optimization of control systems. The role of ITS is strengthened when combined with accurate artificial intelligence models that are built to optimize urban planning, analyze crowd behavior and predict traffic conditions. AI-driven ITS is becoming possible thanks to the existence of a large volume of mobility data generated by billions of users through their use of new technologies and online social media. The optimization of urban planning enhances vehicle routing capabilities and solves traffic congestion problems, as discussed in this paper. From an ecological perspective, we discuss the measures and incentives provided to foster the use of mobility systems. We also underline the role of the political will in promoting open data in the transport sector, considered as an essential ingredient for developing technological solutions necessary for cities to become healthier and more sustainable.

Highway Speed Prediction Using Gated Recurrent Unit Neural Networks

Abstract: Movement analytics and mobility insights play a crucial role in urban planning and transportation management The plethora of mobility data sources, such as GPS trajectories, poses new challenges and opportunities for understanding and predicting movement patterns In this study, we predict highway speed using a gated recurrent unit (GRU) neural network Based on statistical models, previous approaches suffer from the inherited features of traffic data, such as nonlinear problems The proposed method predicts highway speed based on the GRU method after training on digital tachograph data (DTG) The DTG data were recorded in one month, giving approximately 300 million records These data included the velocity and locations of vehicles on the highway Experimental results demonstrate that the GRU-based deep learning approach outperformed the state-of-the-art alternatives, the autoregressive integrated moving average model, and the long short-term neural network (LSTM) model, in terms of prediction accuracy Further, the computational cost of the GRU model was lower than that of the LSTM The proposed method can be applied to traffic prediction and intelligent transportation systems

Smart Urban Mobility: When Mobility Systems Meet Smart Data

Abstract: Cities around the world are expanding dramatically, with urban population growth reaching nearly 2.5 billion people in urban areas and road traffic growth exceeding 1.2 billion cars by 2050. The economic contribution of the transport sector represents 5% of the GDP in Europe and costs an average of US $\$ $ 482.05 billion in the United States. These figures indicate the rapid rise of industrial cities and the urgent need to move from traditional cities to smart cities. This article provides a survey of different approaches and technologies such as intelligent transportation systems (ITS) that leverage communication technologies to help maintain road users safe while driving, as well as support autonomous mobility through the optimization of control systems. The role of ITS is strengthened when combined with accurate artificial intelligence models that are built to optimize urban planning, analyze crowd behavior and predict traffic conditions. AI-driven ITS is becoming possible thanks to the existence of a large volume of mobility data generated by billions of users through their use of new technologies and online social media. The optimization of urban planning enhances vehicle routing capabilities and solves traffic congestion problems, as discussed in this paper. From an ecological perspective, we discuss the measures and incentives provided to foster the use of mobility systems. We also underline the role of the political will in promoting open data in the transport sector, considered as an essential ingredient for developing technological solutions necessary for cities to become healthier and more sustainable.

Devising an Automated Technology to Organize the Railroad Transportation of Containers for Intermodal Deliveries Based on the Theory of Point Processes

Abstract: A significant number of problems and associated additional expenses emerge for operators due to imperfections in the existing technology of operational planning of the functioning of railroad transport as a part of the intermodal transportation system. The source of problems is not only the process of transportation of containers by rail but also the processes that occur immediately before and after it. These processes are uncertain because of their probabilistic nature. Their random nature provokes additional idle time of rolling stock, causes additional operator expenses, and reduces the quality of customer service. However, the direct influence on them is very difficult or economically inexpedient.The study shows that taking into account the probabilistic nature of these processes to reduce their negative impact is most effective precisely at the stage of operational planning of the functioning of railroad enterprises involved in the intermodal transportation process. One should note that it is necessary to take into account random factors of processes of formation and processing of container trains at stations, their movement along sections and transfer to a port simultaneously in order to improve the quality of such planning. However, the arrival of containers at terminal railroad stations requires special attention.It has been proven that the key to the solution to the problem of synchronization of the processes is the formation of automated technology for the organization of the transportation of containers by railroad.We have formalized the technological process of formation and movement of container trains to seaports in the form of a model of stochastic optimization using a mathematical apparatus from the theory of point processes for this purpose. The optimization criterion for this model represents the operating expenses of an operator for the organization of the railroad part of intermodal transportation. The stochastic nature of the model gives a possibility to find the optimal parameters of the operational plan for the organization of container transportation while controlling a level of certainty in the possibility of implementation of the plan taking into account the probabilistic nature of the constituent processes.Based on the developed model, software was created in the MATLAB programming environment and an automated technology for moving container trains was formed. The application of the proposed model in the formation of railroad container transportation technology could reduce operating expenses of a railroad part of intermodal container transportation by at least 10 %