Kristian Henrickson

Application of finite mixture models for analysing freeway incident clearance time

ABSTRACT A number of approaches have been developed for analysing incident clearance time data and investigating the effects of different explanatory variables on clearance time. Among these methods, hazard-based duration models (i.e. proportional hazard and accelerated failure time (AFT) models) have been extensively used. The finite mixture model is an alternative approach in survival data analysis, and offers greater flexibility in describing different shapes of the hazard function. Additionally, the finite mixture model assumes that the incident clearance time data set contains distinct subpopulations, and it allows the effects of explanatory variables to vary between different subpopulations. In this study, a g-component mixture model is applied to analyse incident clearance time. To demonstrate advantages of the proposed finite mixture model framework, incident clearance time data collected on freeway sections in Seattle, Washington State are analysed. Estimation and prediction results from the proposed mixture model and the AFT model are presented and compared. The results suggest that the proposed mixture model can better describe the survival probability and hazard probability of incident clearance time, and can provide more accurate prediction compared to the AFT model. The mixture model can also provide inferences about the effects of explainable variables on different subpopulations present in incident clearance time data. The additional information obtained from the proposed mixture model can be potentially useful for designing targeted incident management strategies for different incident types. Overall, the findings in this study demonstrate that the mixture modelling approach is a useful and informative method for analysing heterogeneous incident duration data and predicting incident duration on freeways.

Kinect-Based Pedestrian Detection for Crowded Scenes

Pedestrian movement data including volumes, walking speeds, and trajectories are essential in transportation engineering, planning, and research. Although traditional image-based pedestrian detectors provide very rich information, their performance degrades quickly with increased occurrence of occlusion. The three-dimensional sensing capabilities of Microsofts Kinect present a potential cost-effective solution for occlusion-robust pedestrian detection. This article proposes an efficient pedestrian detection approach for crowded scenes by fusing RGB and depth images from the Kinect. More specifically, we first extract the pedestrian contour regions from RGB images using background subtraction. Then, we develop a region clustering algorithm to extract pedestrians from the contour regions using depth information. Finally, a tracking and counting algorithm is designed to acquire pedestrian volumes. The proposed approach was proven effective with an average detection accuracy of 93.1% at 20 frames per second. These results demonstrate the feasibility of using the low-cost Kinect device for real-world pedestrian detection in crowded scenes.

Estimation of Origin and Destination Information from Bluetooth and Wi-Fi Sensing for Transit

Public urban transit offers a convenient, affordable, and sustainable mode of transportation for many. However, limited subsidies and revenue collected from bus fares place restrictions on the number of bus lines that can operate; these restrictions in turn limit the number of individuals who can benefit from public transit. To make well-informed operational decisions for transit planning and operations, understanding the origin and destination patterns of riders is crucial. However, traditional methods of transit data collection are labor-intensive and costly. Although some transit agencies use data from smart card transactions to obtain trip origin information readily, the trip destination information cannot be directly inferred. To aid in transit data acquisition efforts, this study presents a new technique that uses the Bluetooth and wireless fidelity (Wi-Fi) sensing technologies to estimate the origin and destination information for transit lines. Sensors were installed on four buses to collect Bluetooth, Wi-Fi, and GPS location data for a 4-week period. New methods for data processing and reduction were introduced to exclude invalid detections. On the basis of valid samples, the origin and destination information at different bus stops was estimated for a university operated transit line. The developed methods have the potential to be applied for large-scale transit networks.

Flexible and Robust Method for Missing Loop Detector Data Imputation

This study is primarily focused on missing traffic sensor data imputation for the purpose of improving the coverage and accuracy of traffic analysis and performance estimation. Missing data, whether attributable to hardware failure or error detection and removal, are a constant problem in loop and other traffic detector data sets. As the rate of missingness increases, the treatment of missing values quickly becomes the controlling factor in overall data quality. Previously, several imputation approaches have been developed for traffic data. However, few studies aim at handling the traffic data with large blocks of missing values for networkwide implementation. A proven predictive mean matching multiple imputation method is introduced; it was applied to loop detector volume data collected on Interstate 5 in Washington State. With the use of the iterative multiple imputation by chained equations approach, the spatial correlation between nearby detectors was considered for prediction, and the presence of missing data was effectively dealt with in all predictors. The proposed methodology is shown to perform well on a range of missing data patterns, including missing completely at random, missing days, and missing months. After the imputation method was applied to 20-s data and postimputation aggregation was performed, the results in this study suggest that the proposed method can outperform elementary pairwise regression and produce reliable imputation estimates, even when entire days and months are missing from the data set. Thus the predictive mean matching multiple imputation method can be used as an effective approach for imputing missing traffic data in a range of challenging scenarios.

Google Earth elevation data extraction and accuracy assessment for transportation applications

Roadway elevation data is critical for a variety of transportation analyses. However, it has been challenging to obtain such data and most roadway GIS databases do not have them. This paper intends to address this need by proposing a method to extract roadway elevation data from Google Earth (GE) for transportation applications. A comprehensive accuracy assessment of the GE-extracted elevation data is conducted for the area of conterminous USA. The GE elevation data was compared with the ground truth data from nationwide GPS benchmarks and roadway monuments from six states in the conterminous USA. This study also compares the GE elevation data with the elevation raster data from the U.S. Geological Survey National Elevation Dataset (USGS NED), which is a widely used data source for extracting roadway elevation. Mean absolute error (MAE) and root mean squared error (RMSE) are used to assess the accuracy and the test results show MAE, RMSE and standard deviation of GE roadway elevation error are 1.32 meters, 2.27 meters and 2.27 meters, respectively. Finally, the proposed extraction method was implemented and validated for the following three scenarios: (1) extracting roadway elevation differentiating by directions, (2) multi-layered roadway recognition in freeway segment and (3) slope segmentation and grade calculation in freeway segment. The methodology validation results indicate that the proposed extraction method can locate the extracting route accurately, recognize multi-layered roadway section, and segment the extracted route by grade automatically. Overall, it is found that the high accuracy elevation data available from GE provide a reliable data source for various transportation applications.

A Two-Stage Algorithm for Origin-Destination Matrices Estimation Considering Dynamic Dispersion Parameter for Route Choice

This paper proposes a two-stage algorithm to simultaneously estimate origin-destination (OD) matrix, link choice proportion, and dispersion parameter using partial traffic counts in a congested network. A non-linear optimization model is developed which incorporates a dynamic dispersion parameter, followed by a two-stage algorithm in which Generalized Least Squares (GLS) estimation and a Stochastic User Equilibrium (SUE) assignment model are iteratively applied until the convergence is reached. To evaluate the performance of the algorithm, the proposed approach is implemented in a hypothetical network using input data with high error, and tested under a range of variation coefficients. The root mean squared error (RMSE) of the estimated OD demand and link flows are used to evaluate the model estimation results. The results indicate that the estimated dispersion parameter theta is insensitive to the choice of variation coefficients. The proposed approach is shown to outperform two established OD estimation methods and produce parameter estimates that are close to the ground truth. In addition, the proposed approach is applied to an empirical network in Seattle, WA to validate the robustness and practicality of this methodology. In summary, this study proposes and evaluates an innovative computational approach to accurately estimate OD matrices using link-level traffic flow data, and provides useful insight for optimal parameter selection in modeling travelers’ route choice behavior.

Vehicle traffic delay prediction in ferry terminal based on Bayesian multiple models combination method

ABSTRACT This paper presents a new class of models for predicting vehicle traffic delay in ferry terminals. Ferry service plays an important role in many cities adjacent to navigable bodies of water. Transportation agencies, port authorities, and drivers can benefit from a reliable method for ferry traffic delay prediction, which can support improved ferry service scheduling, land-based transit and ferry coordination, and proactive trip planning. In this study, vehicle traffic delay within a ferry terminal is considered to be comprised of both periodic and dynamic components. Frequency analysis is applied to confirm the presence of a consistent periodic trend. A combination method is adopted to fit the dynamic component, which assembles artificial neural network, support vector machine, and ARIMA model in a Bayesian framework. The results presented indicate that, by aggregating the output of multiple models, this model ensemble approach can lead to greater predictive accuracy in modelling ferry traffic delay.

Dynamic Lane Assignment Approach for Freeway Weaving Segment Operation

This paper proposes a dynamic lane assignment (DLA) approach for one-sided freeway weaving segments. The approach divides the weaving segment into weaving lanes and nonweaving lanes to reduce the disturbance between weaving and nonweaving traffic streams. The proposed DLA strategy is optimized by nonlinear integer programming under various on-ramp traffic volumes and weaving volume ratios. The applicability of DLA is tested with numerical experiments under different weave types, traffic flow rates, weaving volume ratios, and segment lengths. A VISSIM microsimulation model was developed and used to evaluate the performance of the proposed strategy. Test results drawn from the numerical experiments and simulation indicate that the proposed DLA approach is applicable when the main-line weaving volume ratio is relatively low and it can increase the capacity and decrease the traffic delay for the weaving and upstream segments.

Application of the Empirical Bayes Method with the Finite Mixture Model for Identifying Accident-Prone Spots

Hotspot identification (HSID) is an important component of the highway safety management process. A number of methods have been proposed to identify hotspots. Among these methods, previous studies have indicated that the empirical Bayes (EB) method can outperform other methods for identifying hotspots, since the EB method combines the historical crash records of the site and expected number of crashes obtained from a safety performance function (SPF) for similar sites. However, the SPFs are usually developed based on a large number of sites, which may contain heterogeneity in traffic characteristic. As a result, the hotspot identification accuracy of EB methods can possibly be affected by SPFs, when heterogeneity is present in crash data. Thus, it is necessary to consider the heterogeneity and homogeneity of roadway segments when using EB methods. To address this problem, this paper proposed three different classification-based EB methods to identify hotspots. Rural highway crash data collected in Texas were analyzed and classified into different groups using the proposed methods. Based on the modeling results for Texas crash dataset, it is found that one proposed classification-based EB method performs better than the standard EB method as well as other HSID methods.