Showing papers in "Transportation Research Record in 2010"

Bikesharing in Europe, the Americas, and Asia: Past, Present, and Future

Abstract: Growing concerns about global motorization and climate change have led to increasing interest in sustainable transportation alternatives such as bikesharing (the shared use of a bicycle fleet). Since 1965, bikesharing has grown across the globe on five continents: Europe, North America, South America, Asia, and Australia. Today, approximately 100 bikesharing programsareoperatinginanestimated125cities, with more than 139,300 bicycles. Bikesharing's evolution is categorized into three generations: (a) white bikes (or free bike systems), (b) coin-deposit systems, and (c) information technology-based systems. In this paper, a fourth generation is proposed: demand-responsive, multimodal systems. A range of existing bikesharing businessmodels(e.g., advertising)andlessons learned are discussed, including (a) bicycle theft and vandalism, (b) bicycle redistribution, (c) information systems (e.g., real-time information), (d) insurance and liability concerns, and (e) prelaunch considerations. Although limited in num...

Impact of Carsharing on Household Vehicle Holdings: Results from North American Shared-Use Vehicle Survey

Abstract: Carsharing has grown considerably in North America during the past decade and has flourished in metropolitan regions across the United States and Canada. The new transportation landscape offers urban residents an alternative to automobility, one without car ownership. As carsharing has expanded, there has been a growing demand to understand its environmental effects. This paper presents the results of a North American carsharing member survey (N = 6,281). A before-and-after analytical design is established with a focus on carsharing's effects on household vehicle holdings and the aggregate vehicle population. The results show that carsharing members reduce their vehicle holdings to a degree that is statistically significant. The average number of vehicles per household of the sample drops from 0.47 to 0.24. Most of this shift constitutes onecar households becoming carless. The average fuel economy of carsharing vehicles used most often by respondents is 10 mi/gal more efficient than the average vehicle sh...

County-Level Crash Risk Analysis in Florida: Bayesian Spatial Modeling

Abstract: An increasing research effort has been made on spatially disaggregated safety analysis models to meet the needs of region-level safety inspection and recently emerging transportation safety planning techniques. However, without explicitly differentiating exposure variables and risk factors, most existing studies alternate the use of crash frequency, crash rate, and crash risk to interpret model coefficients. This procedure may have resulted in the inconsistent findings in relevant studies. This study proposes a Bayesian spatial model to account for county-level variations of crash risk in Florida by explicitly controlling for exposure variables of daily vehicle miles traveled and population. A conditional autoregressive prior is specified to accommodate for the spatial autocorrelations of adjacent counties. The results show no significant difference in safety effects of risk factors on all crashes and severe crashes. Counties with higher traffic intensity and population density and a higher level of urban...

Near Crashes as Crash Surrogate for Naturalistic Driving Studies

Abstract: Naturalistic driving is an innovative method for investigating driver behavior and traffic safety. However, as the number of crashes observed in naturalistic driving studies is typically small, crash surrogates are needed. A study evaluated the use of near crashes as a surrogate measure for assessment of the safety impact of driver behaviors and other risk factors. Two metrics, the precision and bias of risk estimation, were used to assess whether near crashes could be combined with crashes. The principles and exact conditions for improved precision and unbiased estimation were proposed and applied to data from the 100-Car Naturalistic Driving Study. The analyses indicated that a positive relationship exists between the frequencies of contributing factors for crashes and for near crashes. The study also indicated that analyses based on combined crash and near-crash data consistently underestimate the risk of contributing factors compared to use of crash data alone. At the same time, the precision of the estimation will increase. This consistent pattern allows investigators to identify true high-risk behaviors while qualitatively assessing potential bias. In summary, the study concluded that the use of near crashes as a crash surrogate provides definite benefit when naturalistic studies are not large enough to generate sufficient numbers of crashes for statistical analysis.

Data Collection of Freeway Travel Time Ground Truth with Bluetooth Sensors

Abstract: Accurate travel time information is essential to the effective management of traffic conditions. Traditionally, floating car data have been used as the primary source of ground truth for measuring the quality of real-time travel time provided by traffic surveillance systems. This paper introduces Bluetooth sensors as a new and effective means of data collection of freeway ground truth travel time. The concept of vehicle identification using Bluetooth signatures for travel time estimation along a section of freeway is explained. Issues related to error analysis, filtering of raw matched data, and accuracy of the resulting ground truth compared with floating car are discussed. Data from loop detectors on several freeway segments are used to approximate and report the average sampling rate of Bluetooth sensors. Results show that the new technology is a promising method for collecting high-quality travel time data that can be used as ground truth for evaluating other sources of travel time and other intellige...

Travel time forecasting and dynamic origin-destination estimation for freeways based on bluetooth traffic monitoring

Abstract: Traditional technologies, such as inductive loop detectors, do not usually produce measurements of the quality required by real-time applications. Therefore, one wonders what could be expected from newer information and communication technologies, such as automatic vehicle location, license plate recognition, and detection of mobile devices. The main objectives of this paper are to explore the quality of the data produced by Bluetooth detection of mobile devices that equip vehicles for travel time forecasting and its use in estimating time-dependent origin-destination matrices. Ad hoc procedures based on Kalman filtering have been designed and implemented successfully, and the numerical results of the computational experiments are presented and discussed.

Vehicle Routing Problem for Emissions Minimization

Abstract: Environmental, social, and political pressures to limit the effects associated with greenhouse gas emissions are mounting. Little research has been done on reducing emissions as the primary objective of a routing problem despite the growth in use and impact of commercial vehicles. In the capacitated vehicle routing problem (VRP) with time windows, it is traditionally assumed that carriers minimize the number of vehicles as a primary objective and distance traveled as a secondary objective without violating time windows, route durations, or capacity constraints. New research focuses on a different problem: the minimization of emissions and fuel consumption as the primary or secondary objective. This creates the emissions VRP (EVRP). A formulation and solution approaches for the EVRP are presented. Decision variables and properties are stated and discussed. Results obtained with a proposed EVRP solution approach for different levels of congestion are compared and analyzed.

Large-Scale Automated Analysis of Vehicle Interactions and Collisions

Abstract: Road collisions are a worldwide pandemic that can be addressed through the improvement of existing tools for safety analysis. A refined probabilistic framework is presented for the analysis of road-user interactions. In particular, the identification of potential collision points is used to estimate collision probabilities, and their spatial distribution can be visualized. A probabilistic time to collision is introduced, and interactions are grouped into four categories: head-on, rear-end, side, and parallel. The framework is applied to a large data set of video recordings collected in Kentucky that contains more than 300 severe interactions and collisions. The results demonstrate the usefulness of the approach for studying road-user behavior and mechanisms that may lead to collisions.

Seeding Effect of Nano-CaCO3 on the Hydration of Tricalcium Silicate

Abstract: A previous study indicated that the early hydration and strength development of ordinary portland cement (OPC) delayed by the presence of high volumes of supplementary cementitious materials were compensated for by the accelerating effect of nano-CaCO3. The mechanism responsible for the accelerating effect on the early hydration and strength development was, however, not fully understood. A study aimed at understanding the accelerating mechanism of the addition of nano-CaCO3 on the hydration of tricalcium silicate (C3S) is presented in this paper. A comparison with the addition of micro-CaCO3 was made. The hydration mechanism of C3S with the addition of micro- or nano-CaCO3 was studied by conduction calorimetry, thermogravimetric analysis, and scanning electron microscopy. The conduction calorimetry results indicated that the addition of nano-CaCO3 had an accelerating effect on the hydration of C3S as well as on the hydration of OPC. Furthermore, the induction period of C3S hydration was significantly sho...

Comparative Study of the Effects of Microsilica and Nanosilica in Concrete

Abstract: It is well recognized that the use of mineral admixtures such as silica fume enhances the strength and durability of concrete. This research compares the effects of adding silica fume and nanosilica to concrete and provides a better understanding of the changes in the concrete nanostructure. Nanoindentation with scanning probe microscopy imaging was used to measure the local mechanical properties of cement pastes with 0% and 15% replacement of cement with silica fume. A reduction in the volume fraction of calcium hydroxide in a sample with silica fume provides evidence of pozzolanic reaction. Furthermore, replacing 15% cement by silica fume increased the volume fraction of the high-stiffness calcium silicate hydrate (C-S-H) by a small percentage that was comparable with the decrease in the volume fraction of calcium hydroxide. A parallel study of cement pastes with nanosilica showed that nanosilica significantly improves durability of concrete. This research provides insight into the effects of nanosilica on cement paste nanostructure and explains its effect on durability of concrete. The nanoindentation study showed that the volume fraction of the high-stiffness C-S-H gel increased significantly with addition of nanosilica. Nanoindentation results of cement paste samples with similar percentages of silica fume and nanosilica were compared. Samples with nanosilica had almost twice the amount of high-stiffness C-S-H as the samples with silica fume.

Changes in Travel Behavior in Response to Weather Conditions: Do Type of Weather and Trip Purpose Matter?

Abstract: Weather can influence travel demand, traffic flow, and traffic safety. A hypothesis—the type of weather determined the likelihood of a change in travel behavior, and changes in travel behavior because of weather conditions depended on trip purpose—was assayed. A stated adaptation study was conducted in Flanders (the Dutch-speaking region of Belgium). A survey, completed by 586 respondents, was administered both on the Internet and as a traditional paper-and-pencil questionnaire. To ensure optimal correspondence between the survey sample composition and the Flemish population, observations in the sample were weighted. To test the main hypotheses, Pearson chi-square independence tests were performed. Results from both the descriptive analysis and the independence tests confirm that the type of weather matters and that changes in travel behavior in response to these weather conditions are highly dependent on trip purpose. This dependence of behavioral adjustments on trip purpose provides policy makers with a...

Automated Analysis of Pedestrian–Vehicle Conflicts: Context for Before-and-After Studies

Abstract: This paper presents a novel application of automated video analysis for a before-and-after (BA) safety evaluation of a scramble phase treatment. Data availability has been a common challenge to pedestrian studies, especially for proactive safety analysis. The traditional reliance on collision data has many shortcomings because of the quality and quantity of collision records. Qualitative and quantitative issues with road collision data are more pronounced in pedestrian safety studies. In addition, little information on the mechanism of action implicated can be drawn from collision reports. Traffic conflict techniques have been advocated as supplements or alternatives to collision-based safety analysis. Automated conflict analysis has been advocated as a new safety analysis paradigm that empowers the drawbacks of survey-based and observer-based traffic conflict analysis. One of the areas of focus of pedestrian safety that could greatly benefit from vision-based road user tracking is BA evaluation of safety...

Implementation Framework and Development Trajectory of FEATHERS Activity-Based Simulation Platform:

Abstract: To facilitate the development of dynamic activity-based models for transport demand, the FEATHERS framework was developed. This framework suggests a four-stage development trajectory for a smooth transition from the four-step models toward static activity-based models in the short term and dynamic activity-based models in the long term. The development stages discussed in this paper range from an initial static activity-based model without traffic assignment to a dynamic activity-based model that incorporates rescheduling, learning effects, and traffic routing. To illustrate the FEATHERS framework, work that has been done on the development of static and dynamic activity-based models for Flanders (Belgium) and the Netherlands is discussed. First, the data collection is presented. Next, the four-stage activity-based model development trajectory is discussed in detail. The paper concludes with the presentation of the modular FEATHERS framework, which discusses the functionalities of the modules and how they accommodate the requirements imposed on the framework by each of the four stages.

How Far Out of the Way Will We Travel? Built Environment Influences on Route Selection for Bicycle and Car Travel

Abstract: Current travel demand models are calibrated for motorized transportation and do not perform as well for nonmotorized modes. Little evidence exists on how much, and for what reasons, the routes people travel deviate from the shortest-path or least-cost routes generated by transportation models. This paper investigates differences in total distance, road type used, and built environment features for shortest-path routes versus actual routes for utilitarian bicycle trips (n = 50) and car trips (n = 67) in Metro Vancouver, Canada. Bike trips were, on average, 360 m longer than the shortest possible route; car trips were 540 m longer. Regardless of mode, people do not detour far off the shortest route: detour ratios (actual distance/shortest distance) were similar, with three-fourths of trips within 10% of the shortest distance and at least 90% within 25%. Differences in the built environment measures en route suggest why bike commuters chose to detour: the actual routes had significantly more bicycle faciliti...

Getis-Ord Spatial Statistics to Identify Hot Spots by Using Incident Management Data

Abstract: Traditionally, data have been collected to measure and improve the performance of incident management (IM). While these data are less detailed than crash records, they are timelier and contain useful attributes typically not reported in the crash database. This paper proposes the use of Getis-Ord (Gi*) spatial statistics to identify hot spots on freeways from an IM database while selected impact attributes are incorporated into the analysis. The Gi* spatial statistics jointly evaluate the spatial dependency effect of the frequency and attribute values within the framework of the conceptualized spatial relationship. The application of the method was demonstrated through a case study by using the incident database from the Houston, Texas, Transportation Management Center (TranStar). The method successfully identified the clusters of high-impact accidents from more than 30,000 accident records from 2006 to 2008. The accident duration was used as a proxy measure of its impact. The proposed method could be mod...

Sequential and Simultaneous Estimation of Hybrid Discrete Choice Models: Some New Findings

Abstract: The formulation of hybrid discrete choice models, including both observable alternative attributes and latent variables associated with attitudes and perceptions, has become a topic of discussion once more To estimate models integrating both kinds of variables, two methods have been proposed: the sequential approach, in which the latent variables are built before their integration with the traditional explanatory variables in the choice model and the simultaneous approach, in which both processes are done together, albeit with a sophisticated but fairly complex treatment Here both approaches are applied to estimate hybrid choice models by using two data sets: one from the Santiago Panel (an urban mode choice context with many alternatives) and another consisting of synthetic data Differences between both approaches were found as well as similarities not found in earlier studies Even when both approaches result in unbiased estimators, problems arise when valuations are obtained such as the value of tim

Engineered Cementitious Composites: Can Composites Be Accepted as Crack-Free Concrete?

Abstract: Because conventional concrete is brittle and tends to crack easily under mechanical and environmental loads, there are concerns with durability. During the past decade, the effort to modify the brittle nature of ordinary concrete has resulted in high-performance fiber-reinforced cementitious composites (HPFRCCs), which are characterized by tensile strain-hardening after first cracking. Engineered cementitious composites (ECCs), a special type of HPFRCC, represent a new concrete material that offers significant potential to reduce the durability problem of concrete structures. Unlike ordinary concrete and fiber-reinforced concrete materials, ECC strain-hardens after first cracking, as do ductile metals, and it demonstrates a strain capacity 300 to 500 times greater than normal concrete. Even at large imposed deformation, crack widths of ECC remain small, less than 80 μm. Apart from unique tensile properties, the relationship between crack characteristics and durability—including transport properties (perme...

Investigating the Shape of the Macroscopic Fundamental Diagram Using Simulation Data

Abstract: Macroscopic fundamental diagrams (MFDs) exist in large urban networks in which traffic conditions are homogenous. They can be used for estimation of the level of service on road networks, perimeter control, and macroscopic traffic modeling. However, before the MFD concept can be applied, the factors that influence the MFD shape should be identified and their effects investigated. A microscopic simulation model is used to change conditions, that is, to derive MFDs under different conditions and for different types of networks. Results indicate that a relationship indeed exists between production and accumulation for the whole network as well as for parts of the network focused on freeway or urban links. MFD shape is a property not only of the network itself but also of the applied traffic control measures. At the same time, congestion onset and resolution lead to heterogeneous traffic conditions with congestion at specific locations in the network, resulting in loops in congested parts of the MFD. Investig...

Distribution of Carbon Nanofibers and Nanotubes in Cementitious Composites

Abstract: Carbon nanofibers (CNFs) and nanotubes (CNTs) are known to be extremely strong and stiff, and their potential as reinforcement has been of interest to many investigators in the past decade. One of the most important keys for fully harnessing the properties of any type of fiber is to control the distribution in the material matrix. As far as CNFs-CNTs are concerned, the strong attraction among nanoscale fibers due to van der Waals forces makes this task difficult. This study focuses on some of the problems that prevent a uniform distribution of CNFs-CNTs in cement paste and the methods used in the past to enhance dispersion. The first phase of the experimental program investigates the effect of using superplasticizers accompanied by sonication on the dispersion of CNFs in water and paste. The second phase focuses on the problem of cement grain size and limitations that the use of fine grain cement causes. Finally, on the basis of results and past studies, suggestions are made for achieving enhanced dispers...

Travel Time and Transfer Analysis Using Transit Smart Card Data

Abstract: Automatic fare collection systems using smart card technology have become popular because they provide an efficient and cost-saving alternative to the manual fare collection method. In 2004, the City of Seoul, South Korea, introduced a smart card-based transit fare scheme, which was a distance-based, integrated fare collection and calculation system. Over the years, the system was extended twice and now can provide detailed information about public transit use in the region. This information includes each trip's boarding and alighting times and locations, as well as the connected trip chains with transfers. This paper examines possibilities for using such data for transportation planning application. First, a process to generate a travel time map is presented. For this, more than 100 million trip data are used to estimate travel times among stops. It is also demonstrated that transfer data can be readily obtainable because the on- and off-boarding information reside in the data set. Although transfers are...

Effect of Street Network Design on Walking and Biking

Abstract: The objective of this research was to investigate whether a relationship existed between street network characteristics and the transportation modes selected in a neighborhood. Factors such as street characteristics, vehicle volumes, activity levels, income levels, and proximity to limited-access highways and the downtown area were controlled for. The results suggested that all three of the fundamental characteristics of a street network—street connectivity, street network density, and street patterns—were statistically significant in affecting the choice to drive, walk, bike, or take transit. Both increased intersection density and additional street connectivity were generally associated with more walking, biking, and transit use. Street patterns with gridded street networks, which tended to have a higher-than-average street connectivity and a much higher street network density, were associated with much more walking and biking. These results suggested that street network patterns were extremely importan...

Synthesis, Characterization, and Mechanical Properties of Red Mud-Based Geopolymers

Abstract: A pilot study investigates the potential of reusing red mud, an abundant industrial waste produced from alumina refining by the Bayer process, by geopolymerization reactions with another solid waste, fly ash, and sodium silicate. Parameters involved in the synthesis, including red mud to fly ash ratio (values of 80/20, 50/50, and 20/80), presence of sand filler, curing duration (up to 28 days), and sodium silicate solution to solid mixture (consisting of red mud and fly ash) ratio, were examined to understand the extent and degree of geopolymerization. Unconfined compression testing was employed to assess the influence of these synthesis parameters on the mechanical properties of the end products, red mud-based geopolymers. The composition and microstructure were characterized by X-ray diffraction and scanning electron microscopy, respectively, which confirm the geopolymerization reactions. The mechanical properties, including strength, stiffness, and failure strain, were analyzed against the chemical com...

Heuristic Ramp-Metering Coordination Strategy Implemented at Monash Freeway, Australia

Abstract: A new traffic-responsive feedback control strategy, heuristic ramp-metering coordination (HERO) that coordinates local ramp-metering actions in freeway networks is presented. The proposed coordination scheme is simple and reactive [i.e., based on readily available real-time measurements without the need for real-time model calculations or external disturbance (e.g., demand) prediction]. HERO employs an extended version of the feedback regulator ALINEA at the local level. The new strategy overcomes the problem of uncertain freeway capacity by targeting the critical occupancy for maximum throughput. HERO out-performs uncoordinated local ramp metering and approaches the efficiency of sophisticated optimal control schemes. HERO has been implemented by VicRoads, the road authority for the state of Victoria, Australia, at six consecutive inbound on-ramps on the Monash Freeway in Melbourne, Australia. This pilot project is part of the Monash-CityLink-West Gate (MCW) upgrade. The obtained results show a significa...

Real-Time Measurement of Travel Time Delay in Work Zones and Evaluation Metrics Using Bluetooth Probe Tracking:

Abstract: This paper describes the collection and use of 1.4 million travel time records that were collected over a 12-week period in 2009 to evaluate and communicate quantifiable travel mobility metrics for a rural interstate highway work zone along I-65 in northwestern Indiana. The effort involved the automated collection and processing of Bluetooth probe data from multiple field collection sites, communicating travel delay times to the motoring public, assessing driver diversion rates, and developing proposed metrics for a state transportation agency to evaluate work zone mobility performance. Collected travel time profiles were compared with traditionally measured hourly flows in both incident and nonincident conditions. Through the 12-week period over which work zone performance was measured, the work zone had 422 h of congested conditions in which travel time delay was greater than 10 min. Despite the display of real-time delay measurements to the motoring public through portable dynamic message signs, a negl...

Evaluation of Arterial Signal Coordination: Methodologies for Visualizing High-Resolution Event Data and Measuring Travel Time

Abstract: Signal offsets are a signal-timing parameter that has a substantial impact on arterial travel times. The traditional technique is to optimize offsets with an offline software package, implement the settings, and then possibly observe field operations. It is not uncommon for a traffic engineer to fine-tune the settings by observing the arrivals of platoons at an intersection and making adjustments to the offset from this qualitative visual analysis. This paper discusses two tools to assist the engineer in managing arterial offsets. First, it introduces the Purdue coordination diagram (PCD) as a means of visualizing a large amount of controller and detector event data to allow investigation of the time-varying arrival patterns of coordinated movements. The second technique is arterial travel time measurement by vehicle reidentification via address matching by Bluetooth media access control. This technique is used to evaluate existing offsets and assess the impact of implemented offset changes. These tools a...

Calibration of HDM-4 Models for Estimating the Effect of Pavement Roughness on Fuel Consumption for U. S. Conditions

Abstract: Fuel consumption costs are an essential part of life-cycle cost analysis. These costs are influenced by vehicle technology, pavement condition, roadway geometrics, environment, speed, and other factors. Many models for the effects of pavement condition on fuel consumption were developed on the basis of data generated years ago in other countries for vehicles that vary substantially from those used currently in the United States. Therefore, new information is needed to help in refining and developing models that would better apply to U. S. conditions. The mechanistic model developed as part of the Highway Development and Management software (HDM-4) is recommended after calibration for predicting fuel consumption. The results of the calibration exercise for U. S. conditions, with field data collected as part of the NCHRP Project 1-45, are presented. The calibrated HDM-4 fuel consumption model was able to predict very adequately the fuel consumption of five different vehicle classes under different operating...

Evaluation of Rutting Resistance in Warm-Mix Asphalts Containing Moist Aggregate

Abstract: In recent years, rising energy prices and more stringent environmental regulations have resulted in an interest in warm-mix asphalt (WMA) technologies to decrease the energy consumption and emissions associated with conventional hot-mix asphalt production. In this study, the objective was to conduct a laboratory investigation of rutting resistance in WMA mixtures containing moist aggregates. Rut depth, weight loss, and gyration number of dry and conditioned specimens were measured for all of the mixtures. The experimental design included two aggregate moisture contents (0% and ~0.5% by weight of the dry mass of the aggregate), two lime contents (1% and 2% lime by weight of dry aggregate), three WMA additives (Aspha-min, Sasobit, and Evotherm), and three aggregate sources. Thirty-six mixtures were prepared, and 216 specimens were tested in this study. Test results indicated that the aggregate source significantly affects the rutting resistance regardless of the WMA additive, lime content, and moisture cont...

Comprehensive Field Study of Fuel Use and Emissions of Nonroad Diesel Construction Equipment

Abstract: Limited field data are available for analyses of fuel use and emissions of nonroad diesel construction equipment. This paper summarizes the results of field research that used a portable emissions monitoring system to collect fuel use and emissions data from eight backhoes, six bulldozers, three excavators, four generators, six motor graders, three off-road trucks, one skid-steer loader, three track loaders, and five wheel loaders while they performed various duty cycles. These tests produced approximately 119 h of field data for petroleum diesel and approximately 48 h for B20 biodiesel. Engine attribute data including horsepower, displacement, model year, engine tier, and engine load were collected to determine these factors' influence on fuel use rates and emission rates of nitrogen oxides, hydrocarbons, carbon monoxide, carbon dioxide, and opacity. Mass per time fuel use rates were developed for each item of equipment, as were mass per time and mass per fuel used emission rates for each pollutant. For ...

Dynamic Analysis of Thin Asphalt Pavements by Using Cross-Anisotropic Stress-Dependent Properties for Granular Layer

Abstract: A three-dimensional (3-D) finite element (FE) model was developed to investigate the dynamic responses of thin, flexible pavement under impulsive loading similar to a falling weight deflectometer test. The FE model simulated the hot-mix asphalt (HMA) surface layer as a linear viscoelastic material and considered the cross-anisotropic stress dependent modulus for the unbound base layer. Implicit dynamic analysis was used to consider the effect of inertia on pavement structural responses. Using two thinpavement structures of different HMA layer thicknesses, 76 and 127 mm, the study analyzed the effects of cross-anisotropic stress-dependent aggregate base modulus and dynamic analysis on pavement responses, including surface deflection, tensile strain at the bottom of the HMA layer, deviator stress in the base layer, and compressive strain on top of the subgrade. Results showed that use of the cross-anisotropic stress-dependent modulus for the unbound base layer resulted in greater predicted pavement response...

Gaussian processes for short-term traffic volume forecasting

Abstract: The accurate modeling and forecasting of traffic flow data such as volume and travel time are critical to intelligent transportation systems. Many forecasting models have been developed for this purpose since the 1970s. Recently kernel-based machine learning methods such as support vector machines (SVMs) have gained special attention in traffic flow modeling and other time series analyses because of their outstanding generalization capability and superior nonlinear approximation. In this study, a novel kernel-based machine learning method, the Gaussian processes (GPs) model, was proposed to perform short-term traffic flow forecasting. This GP model was evaluated and compared with SVMs and autoregressive integrated moving average (ARIMA) models based on four sets of traffic volume data collected from three interstate highways in Seattle, Washington. The comparative results showed that the GP and SVM models consistently outperformed the ARIMA model. This study also showed that because the GP model is formul...