Showing papers by "Yunpeng Wang published in 2016"

A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting

Abstract: The k-nearest neighbor (KNN) model is an effective statistical model applied in short-term traffic forecasting that can provide reliable data to guide travelers. This study proposes an improved KNN model to enhance forecasting accuracy based on spatiotemporal correlation and to achieve multistep forecasting. The physical distances among road segments are replaced with equivalent distances, which are defined by the static and dynamic data collected from real road networks. The traffic state of a road segment is described by a spatiotemporal state matrix instead of only a time series as in the original KNN model. The nearest neighbors are selected according to the Gaussian weighted Euclidean distance, which adjusts the influences of time and space factors on spatiotemporal state matrices. The forecasting accuracies of the improved KNN and of four other models are compared, and experimental results indicate that the improved KNN model is more appropriate for short-term traffic multistep forecasting than the other models are. This study also discusses the application of the improved KNN model in a time-varying traffic state.

Joint analysis of the spatial impacts of built environment on car ownership and travel mode choice

Abstract: Concerns over transportation energy consumption and emissions have prompted more studies into the impacts of built environment on driving-related behavior, especially on car ownership and travel mode choice. This study contributes to examine the impacts of the built environment on commuter’s driving behavior at both spatial zone and individual levels. The aim of this study is threefold. First, a multilevel integrated multinomial logit (MNL) and structural equation model (SEM) approach was employed to jointly explore the impacts of the built environment on car ownership and travel mode choice. Second, the spatial context in which individuals make the travel decisions was accommodated, and spatial heterogeneities of car ownership and travel mode choice across traffic analysis zones (TAZs) were recognized. Third, the indirect effects of the built environment on travel mode choice through the mediating variable car ownership were calculated, in other words, the intermediary nature of car ownership was considered. Using the Washington metropolitan area as the study case, the built environment measures were calculated for each TAZ, and the commuting trips were drawn from the household travel survey in this area. To estimate the model parameters, the robust maximum likelihood (MLR) method was used. Meanwhile, a comparison among different model structures was conducted. The model results suggest that application of the multilevel integrated MNL and SEM approach obtains significant improvements over other models. This study give transportation planners a better understanding on how the built environment influences car ownership and commuting mode choice, and consequently develop effective and targeted countermeasures.

A Hybrid Vehicle Detection Method Based on Viola-Jones and HOG + SVM from UAV Images

Abstract: A new hybrid vehicle detection scheme which integrates the Viola-Jones (V-J) and linear SVM classifier with HOG feature (HOG + SVM) methods is proposed for vehicle detection from low-altitude unmanned aerial vehicle (UAV) images. As both V-J and HOG + SVM are sensitive to on-road vehicles’ in-plane rotation, the proposed scheme first adopts a roadway orientation adjustment method, which rotates each UAV image to align the roads with the horizontal direction so the original V-J or HOG + SVM method can be directly applied to achieve fast detection and high accuracy. To address the issue of descending detection speed for V-J and HOG + SVM, the proposed scheme further develops an adaptive switching strategy which sophistically integrates V-J and HOG + SVM methods based on their different descending trends of detection speed to improve detection efficiency. A comprehensive evaluation shows that the switching strategy, combined with the road orientation adjustment method, can significantly improve the efficiency and effectiveness of the vehicle detection from UAV images. The results also show that the proposed vehicle detection method is competitive compared with other existing vehicle detection methods. Furthermore, since the proposed vehicle detection method can be performed on videos captured from moving UAV platforms without the need of image registration or additional road database, it has great potentials of field applications. Future research will be focusing on expanding the current method for detecting other transportation modes such as buses, trucks, motors, bicycles, and pedestrians.

Pedestrian Detection and Tracking from Low-Resolution Unmanned Aerial Vehicle Thermal Imagery

Abstract: Driven by the prominent thermal signature of humans and following the growing availability of unmanned aerial vehicles (UAVs), more and more research efforts have been focusing on the detection and tracking of pedestrians using thermal infrared images recorded from UAVs. However, pedestrian detection and tracking from the thermal images obtained from UAVs pose many challenges due to the low-resolution of imagery, platform motion, image instability and the relatively small size of the objects. This research tackles these challenges by proposing a pedestrian detection and tracking system. A two-stage blob-based approach is first developed for pedestrian detection. This approach first extracts pedestrian blobs using the regional gradient feature and geometric constraints filtering and then classifies the detected blobs by using a linear Support Vector Machine (SVM) with a hybrid descriptor, which sophisticatedly combines Histogram of Oriented Gradient (HOG) and Discrete Cosine Transform (DCT) features in order to achieve accurate detection. This research further proposes an approach for pedestrian tracking. This approach employs the feature tracker with the update of detected pedestrian location to track pedestrian objects from the registered videos and extracts the motion trajectory data. The proposed detection and tracking approaches have been evaluated by multiple different datasets, and the results illustrate the effectiveness of the proposed methods. This research is expected to significantly benefit many transportation applications, such as the multimodal traffic performance measure, pedestrian behavior study and pedestrian-vehicle crash analysis. Future work will focus on using fused thermal and visual images to further improve the detection efficiency and effectiveness.

A gradient boosting logit model to investigate driver’s stop-or-run behavior at signalized intersections using high-resolution traffic data

Abstract: Driver’s stop-or-run behavior at signalized intersection has become a major concern for the intersection safety. While many studies were undertaken to model and predict drivers’ stop-or-run (SoR) behaviors including Yellow-Light-Running (YLR) and Red-Light-Running (RLR) using traditional statistical regression models, a critical problem for these models is that the relative influences of predictor variables on driver’s SoR behavior could not be evaluated. To address this challenge, this research proposes a new approach which applies a recently developed data mining approach called gradient boosting logit model to handle different types of predictor variables, fit complex nonlinear relationships among variables, and automatically disentangle interaction effects between influential factors using high-resolution traffic and signal event data collected from loop detectors. Particularly, this research will first identify a series of related influential factors including signal timing information, surrounding traffic information, and surrounding drivers’ behaviors using thousands drivers’ decision events including YLR, RLR, and first-to-stop (FSTP) extracted from high-resolution loop detector data from three intersections. Then the research applies the proposed data mining approach to search for the optimal prediction model for each intersection. Furthermore, a comparison was conducted to compare the proposed new method with the traditional statistical regression model. The results show that the gradient boosting logit model has superior performance in terms of prediction accuracy. In contrast to other machine learning methods which usually apply ‘black-box’ procedures, the gradient boosting logit model can identify and rank the relative importance of influential factors on driver’s stop-or-run behavior prediction. This study brings great potential for future practical applications since loops have been widely implemented in many intersections and can collect data in real time. This research is expected to contribute to the improvement of intersection safety significantly.

Headway-based bus bunching prediction using transit smart card data

Abstract: Bus bunching severely deteriorates the quality of transit service with poor on-time performance and excessive waiting time. To mitigate bus bunching, this paper presents a predictive framework to capture the stop-level headway irregularity based on transit smart card data. Historical headway, passenger demands, and travel time are utilized to model the headway fluctuation at the following stops. A Least Squares Support Vector Machine regression is established to detect bus bunching with the predicted headway pattern. An empirical experiment with two bus routes in Beijing is conducted to demonstrate the effectiveness of the proposed approach. The predictive method can successfully identify more than 95% of bus bunching occurrences in comparison with other well-established prediction algorithms. Moreover, the detection accuracy does not significantly deteriorate as the prediction lead time increases. Instead of regularizing the headways at all costs by adopting certain correction actions, the proposed framework can provide timely and accurate information for potential bus bunching prevention and inform passengers when the next bus will arrive. This feature will greatly increase transit ridership and reduce operating costs for transit authorities.

Linear and nonlinear stability analysis of a car-following model considering velocity difference of two adjacent lanes

Abstract: An improved optimal velocity model, which considers the velocity difference of two adjacent lanes, is presented in this paper. Using linear stability theory, the stability criterion of the new model is obtained and the neutral stability curves are plotted. By applying the reductive perturbation method, the nonlinear stability of the proposed model is also investigated and the soliton solution of the modified Korteweg–de Vries equation near the critical point is obtained to characterize the unstable region. All the theoretical analysis and numerical results demonstrate that the proposed model can characterize traffic following behaviors effectively and achieve better stability.

Quasi-optimal feedback control for an isolated intersection under oversaturation

Abstract: How to manage signalized intersections under oversaturated conditions is a long-standing problem in traffic science and engineering. However, although research works in this area date back to 1960s, an on-line control strategy with theoretically bounded performance is missing, even for the control of an isolated intersection under oversaturation. This paper makes one step further in this area by proposing a QUEUE-based quasi-optimal feedback control (abbreviated as QUEUE) strategy for an isolated oversaturated intersection. The QUEUE strategy is intuitive, simple, and proved to match the off-line optimum in the case of constant demand. More importantly, the bounds of sub-optimality of the QUEUE strategy can be specified quantitatively in general piece-wise constant demand cases. To better deal with the maximum queue constraints, the oversaturation period is divided into the queuing period and the dissipation period with two different objectives. In the queuing period, the primary objective is to keep the queue length within the maximum value; but for the dissipation period, the primary objective is to eliminate all queues at the earliest time. Interestingly, we found that both control objectives can be realized with the same QUEUE strategy. Numerical examples show that the QUEUE strategy approximates the off-line optimum very well. The average sub-optimality in comparison with the off-line optimum in the challenging conditions with Poisson distributed random demand is below 5%.

Modeling chain collisions in vehicular networks with variable penetration rates

Abstract: The vehicular ad hoc network has great potential in improving traffic safety One of the most important and interesting issues in the research community is the safety evaluation with limited penetration rates of vehicles equipped with inter-vehicular communications In this paper, a stochastic model is proposed for analyzing the vehicle chain collisions It takes into account the influences of different penetration rates, the stochastic nature of inter-vehicular distance distribution, and the different kinematic parameters related to driver and vehicle The usability and accuracy of this model is tested and proved by comparative experiments with Monte Carlo simulations The collision outcomes of a platoon in different penetration rates and traffic scenarios are also analyzed based on this model These results are useful to provide theoretical insights into the safety control of a heterogeneous platoon

A DSRC-Based Vehicular Positioning Enhancement Using a Distributed Multiple-Model Kalman Filter

Abstract: Some inherent shortcomings of the global positioning systems (GPSs), such as limited accuracy and availability, limit the positioning performance of a vehicular location system in urban harsh environments. This motivates the development of cooperative positioning (CP) methods based on emerging vehicle-to-anything communications. In this paper, we present a framework of vehicular positioning enhancement based on dedicated short range communications (DSRC). An interactive multiple model is first used to track the distributed manners of both the vehicle acceleration variations and the switching of the covariances of DSRC physical measurements such as the Doppler frequency shift and the received signal strength indicator, with which a novel CP enhancement method is presented to improve the distributed estimation performance by sharing the motion states and the physical measurements among local vehicles through vehicular DSRC. We have also presented an analysis on the positioning performance, and a closed-formed lower bound, named the modified square position error bound (mSPEB), is derived for bounding the positioning estimation performance of CP systems. Simulation results have been supplemented to compare our proposed method with the stand-alone GPS implementation in terms of the root-mean-square error (RMSE), showing that the obtained positioning enhancement can improve comprehensive positioning performance by the percentage varying between about 35% and about 72% under different traffic intensities and the connected vehicle penetrations. More importantly, the RMSE achieved by our method is shown remarkably closed to the root of the theoretical mSPEB.

An Optimal Schedule for Urban Road Network Repair Based on the Greedy Algorithm

Abstract: The schedule of urban road network recovery caused by rainstorms, snow, and other bad weather conditions, traffic incidents, and other daily events is essential. However, limited studies have been conducted to investigate this problem. We fill this research gap by proposing an optimal schedule for urban road network repair with limited repair resources based on the greedy algorithm. Critical links will be given priority in repair according to the basic concept of the greedy algorithm. In this study, the link whose restoration produces the ratio of the system-wide travel time of the current network to the worst network is the minimum. We define such a link as the critical link for the current network. We will re-evaluate the importance of damaged links after each repair process is completed. That is, the critical link ranking will be changed along with the repair process because of the interaction among links. We repair the most critical link for the specific network state based on the greedy algorithm to obtain the optimal schedule. The algorithm can still quickly obtain an optimal schedule even if the scale of the road network is large because the greedy algorithm can reduce computational complexity. We prove that the problem can obtain the optimal solution using the greedy algorithm in theory. The algorithm is also demonstrated in the Sioux Falls network. The problem discussed in this paper is highly significant in dealing with urban road network restoration.

Short-Term Traffic States Forecasting Considering Spatial–Temporal Impact on an Urban Expressway:

Abstract: Forecasting of short-term traffic states on expressways by adopting spatial–temporal models has gained increasing attention Traffic data from neighboring sites were demonstrated to provide valuable information for predicting traffic states at sites of interest However, when one considers the need to analyze the multivariate nature of traffic states over spatial dimensions, as well as of different models for various times of day, the interaction effects between spatial–temporal patterns require further investigation This study addressed this issue on a segment of Shanghai North–South Expressway Temporal characteristics of traffic volumes and speeds were analyzed by dividing the time of day into ordinal periods with relatively stable states Then, spatial vector autoregressive (VAR) models were constructed at typical analysis periods for volume and speed forecasting by considering different combinations of upstream and downstream impacts The results showed that the impact of downstream traffic conditio

From Cellular Attractor Selection to Adaptive Signal Control for Traffic Networks.

Abstract: The management of varying traffic flows essentially depends on signal controls at intersections. However, design an optimal control that considers the dynamic nature of a traffic network and coordinates all intersections simultaneously in a centralized manner is computationally challenging. Inspired by the stable gene expressions of Escherichia coli in response to environmental changes, we explore the robustness and adaptability performance of signalized intersections by incorporating a biological mechanism in their control policies, specifically, the evolution of each intersection is induced by the dynamics governing an adaptive attractor selection in cells. We employ a mathematical model to capture such biological attractor selection and derive a generic, adaptive and distributed control algorithm which is capable of dynamically adapting signal operations for the entire dynamical traffic network. We show that the proposed scheme based on attractor selection can not only promote the balance of traffic loads on each link of the network but also allows the global network to accommodate dynamical traffic demands. Our work demonstrates the potential of bio-inspired intelligence emerging from cells and provides a deep understanding of adaptive attractor selection-based control formation that is useful to support the designs of adaptive optimization and control in other domains.

Comparison of Variability of Individual Vehicle Delay and Average Control Delay at Signalized Intersections

Abstract: Two types of delay variability have been commonly referred to at signalized intersections: arrival-time-dependent individual vehicle delay variability and average control delay variability. The former focuses on the delay experienced by individual vehicles, whereas the latter deals with the average consequence of signal control for the entire traffic flow during a given evaluation period. With a number of methods available for estimation, little research has been conducted to enable a comprehensive comparison of these two variability measures. This issue is addressed by a comparison of these two types of delay variability at isolated, fixed-time controlled intersections based on two analytical models accounting for the stochastic nature of traffic arrivals and overflow queues. The results show that in undersaturated conditions, individual vehicle delay tends to have a wider distribution and a larger variance compared with average control delay. In oversaturated conditions, the shapes of both types of dela...

Unicast Routing Protocol Based on Attractor Selection Model for Vehicular Ad-Hoc Networks

Abstract: As an important member of IOV, vehicular Ad Hoc Networks (VANETs) play a key role for many vehicular applications, which significantly rely on the vehicular routing. However, the frequently changed topology leads to great challenge to the routing protocol. In this work, inspired by the mechanism of cellular adaptive responses in a changing environment, called cellular attractor selection, we propose a novel bio-inspired unicast routing protocol, which can adapt vehicular message forwarding to the changing topology to guarantee the routing efficiency and reliability. The experimental results exhibit the robustness and effectiveness of the proposed method and the significantly improved performance over the conventional routing protocol.

Analysis of Time-Dependent Reliability and Sensitivity of Vehicle Components

Abstract: In this study, a lD Brownian movement formula that considers the uncertainty of initial parameters was derived and a time-dependent model of load and structural parameters established. A model for reliability and its corresponding sensitivity analysis was proposed as well, according to the residual strength distribution calculated based on the S−N characteristics of the material and stress-strength interference theory. This model considers the effects of interaction under uncertain structural parameters and strength as well as the uncertainty of actual use. On this basis, the variation rules of initial parameters, strength, load, reliability, and its sensitivity with time are analyzed; those of reliability, failure rate, and reliability sensitivity with time were calculated when the driving axle of a vehicle was taken as an example.

A V2I-Based Signal Optimization Method and Simulation

Abstract: Traditional signalized intersections use fixed-time control. The duration of a signal is invariant in a period of time. However, traffic volume changes drastically and is nonlinear. With the development of vehicle-to-infrastructure (V2I) communication technology and sensors, original signal control is antiquated. In this paper, how infrastructure obtains vehicle data is introduced. Applications on-board or mobile phone applications (apps) will transmit information such as position, speed, and heading to servers on the roadside. The signal optimization algorithm uses this information to calculate delay and queue length and then allocates phase duration on the basis of these data. A simulation using NETLOGO5 was set up to verify the algorithm. The results indicate that for common crossroads, it works well in unsaturated traffic conditions or with no more than two branches in a saturated condition. As for a T-intersection, this algorithm can reduce delay significantly.