Roadway Segments Research Articles

Malignant mixes: The overlap of motor vehicle crashes and crime in Stockholm, Sweden

Places that concentrate both motor vehicle crashes and crime in Stockholm, Sweden were examined for common socio-economic, land use, and neighborhood characteristics. Using vehicle crash (N = 3,700) and non-traffic crime (N = 605,052) data from 2016 to 2018, hot spots of these two sets of events and their overlap were identified. Crash hot spots captured 14% of the crashes in only 0.5% of Stockholm’s area while crime hot spots captured 27% of the recorded offences in less than 1% of the area. There was overlap in these hot spots for 7% of the crashes and 10% of the crimes. To model predictors, the events were allocated to roadway segments (N = 5511) and tested using a Poisson-Gamma-CAR spatial regression model. Both crashes and crimes exhibit a clear center-periphery pattern that varies over time and by type of crashes and crimes.Crashes tended to occur on roadways with higher average daily traffic (ADT) while crimes tend to occur on roadways with lower ADT with around half occurring on residential streets. Both types of incidents tended to be higher in lower income neighborhoods. Land uses common to both types of harm were the location of underground stations, ATM machines, and alcohol-serving businesses. These are places where people and cars converge at particular times. The effect of these events on police, emergency, and medical services is discussed.

Modeling and simulation of dynamic lane reversal using a cell transmission model

In recent years, large-scale testing has begun for connected and autonomous driving, making it possible to implement the concept of Dynamic Lane Reversal (DLR), which can quickly shift lane directions to reflect instantaneous flow dynamics. DLR is to make full use of road space and avoid waste of road capacity, and potentially alleviate congestion. However, the impact and feasibility of DLR remain unclear. In order to investigate the effectiveness, the feasibility, and the applicability of DLR, we utilize a direction-changeable, lane-based cell transmission model to find an optimal DLR scheme for a roadway segment with stochastic traffic flow in both directions. A proxy model is also designed to realize DLR in VISSIM. A regression analysis was carried out to find the impacts of directional flow rate and the number of lanes on delay reductions due to DLR. Results indicate that implementing DLR can reduce the total queuing delay considerably compared to traditional reversible lane strategies. We found that DLR achieved superior performance on segments with more lanes and when the flows from each direction were close to one another. A zigzag frontier of the delay reduction was discovered. Findings from this research shed light on the feasibility and effectiveness of DLR on various types of road segments.

Estimation of crash type frequencies on individual collector roadway segments

Individual collision types have different underlying causes and thus the relationships between roadway/traffic characteristics and crash frequency are likely to differ across unique collision types. One way these different influences have been studied is by developing separate statistical models for each collision type. While this is the most straightforward approach, developing collision-specific models can be very tedious and can produce unreliable estimates for collision types that are less frequently observed. Moreover, ignoring correlations between different collision types may result in biased and inefficient parameter estimation. To overcome these limitations, researchers have adopted a multivariate approach that explicitly accounts for the correlation among individual collision types. As an alternative to multivariate approach, two-stage approaches have been proposed in which one model is estimated to predict total crash frequency and its prediction is combined with another model, used to predict the proportions of different collision types. More efficient one-stage joint models, in which both the frequency and proportion models are estimated simultaneously and predictions are provided more directly, have also been proposed for macro-level analysis. This study investigates the performance of this joint model paradigm in analyzing unique collision type frequencies on individual road segments. For this, a joint negative binomial-multinomial fractional split (NB-MFS) model is used. Moreover, this study also proposes the use of a multinomial logit (MNL) model to estimate the proportion of different collision types. As total crash frequency NB model and MNL model utilize different datasets, a two-stage estimation process is required, which leads to the two-stage NB-MNL model proposed here. The performance of proposed model is compared with that of collision-specific NB models, multivariate negative binomial (MVNB) model, and NB-MFS model in predicting crash frequency by collision type on two-way two-lane urban-suburban collector roadway segments in Pennsylvania. The goodness of fit statistics show that the NB-MNL model performs better than collision-specific NB models, MVNB model and joint NB-MFS model and is thus a promising approach in predicting crash frequency by collision type.

Verification of usRAP Risk Assessments for Run-Off and Head-On Crashes Using Field Data

The United States Road Assessment Program (usRAP) provides a systemic approach to estimate the risk of severe injury and fatal crashes along roadway segments based on the expected safety performance of roadway and roadside characteristics, together with a general estimation of traffic volume. Detailed crash data are not needed for safety assessments, providing advantages over more traditional crash-driven approaches. However, experiences with usRAP are limited to the United States and to date, the program has a growing but limited number of participating states. Verification of the adequacy of usRAP assessments is therefore of significant value, not only to identify strengths and limitations of the methodology within the U.S. context, but also to potentially expand the set of tools available to agencies. This paper presents a verification of usRAP risk assessments for run-off-road and head-on crashes using over 7,000 mi of coded segments and five years of crash data collected in Utah. Comparisons between risk estimations from usRAP and actual crash rates provided insights into the expected and observed effects of roadside objects and their distances from the lanes traveled, type of median present, and horizontal curves. A spatial correlation test also confirmed the agreement between usRAP risk assessments and crash data, providing additional promising indications of the suitability of this systemic methodology for safety applications.

Examining the impacts of crash data aggregation on SPF estimation

The American Association of State Highway and Transportation Officials’ Highway Safety Manual (HSM) includes a collection of safety performance functions (SPFs) or statistical models to estimate the expected crash frequency of roadway segments, intersections, and interchanges. These models are applied in several steps of the safety management process, including to screen the road network for opportunities to improve safety and to evaluate the performance of safety countermeasure deployments. The SPFs in the HSM are generally estimated using negative binomial regression modeling. In some instances, they are estimated using annual crash frequency and site-specific (e.g., traffic volume) data, while in other instances they are estimated using aggregate crash frequency and site-specific data. This paper explores the differences that result from estimating SPFs using aggregate versus disaggregate data using the same methods as those used to estimate the SPFs in the HSM. A synthetic dataset was first used to conduct these comparisons – these data were generated in a manner that is consistent with the properties of the negative binomial distribution. Then, an observational dataset from Pennsylvania was used to compare the SPFs from both aggregate and disaggregate data. The results show that SPFs estimated using the panel (disaggregate) data and aggregated data provide similar model coefficients, although some differences may sometimes arise. However, the overdispersion parameter obtained using each dataset can differ significantly. These differences result in systematic biases in calculations of expected crash frequency when Empirical Bayes adjustments are applied, which – as the paper demonstrates – could lead to different outcomes in a network screening exercise. Overall, these results reveal that aggregating crash data might result in biased SPF outputs and lead to inconsistent Empirical Bayes adjustments.

Characteristics of Crashes Caused by Distracted Driving on Rural and Suburban Roadways in Jordan

The objective of this study was to identify the most salient driver faults that cause crashes on some Jordanian rural and suburban roadway segments, to examine crashes with distracted driving as the driver’s fault, and to investigate the differences between crashes caused by distracted driving. Data for more than 10,200 crashes on nine roadway segments (five rural and four suburban) were accessed from the relevant government agency, but only n = 2472 were used for analysis after controlling for crashes specified as being caused by drivers’ distracted driving. IBM SPSS version 22 was used to perform descriptive analysis and independent samples’ t-tests. The results revealed that distracted driving was the second most common driver fault to cause crashes and the second main cause of fatalities and injuries on both rural and suburban roadways. Distracted driving on rural highways appears to be more fatal, whereas it caused more crashes with severe injuries on suburban roads. The variables at junction, road grade, number of lanes, weather condition, crash type, and number of vehicles involved were found to be statistically significant but with a small effect size. The following categories showed high percentages of distracted driving crashes on rural and suburban roadways: males, drivers 25–39 years old, non-holidays, weekdays, tangent sections, two-way divided roads, not at junction, level roads, two-lane roads, clear weather, dry surface, daylight, and automobile vehicles showed high percentages of distracted driving crashes on rural and suburban roadways. Differences between crashes on rural and suburban roadways caused by distracted driving were found to be small.

SAVE-T: Safety Analysis Visualization and Evaluation Tool

Traffic crashes are one of the biggest issues which constitute a threat to lives of the motorists and disrupt operations of the transportation system. To reduce the number of crashes and alleviate their impacts, it is necessary to scrutinize the factors contributing to the risk of traffic crashes. Lately, visual analytics tools become very popular for data exploration and obtaining insights from the data. In this paper, a new web-based data visualization tool called Safety Analysis Visualization and Evaluation Tool (SAVE-T) was introduced. This tool enables users to interactively create queries and visually explore the results. By utilizing an online crash database, it offers various innovative functionalities for analysis and visualization of the crash data such as custom query development module and a subway-like map for easily visualizing the accident on the roadway segments. This tool provides an effective and efficient way to transportation agencies and professionals for traffic safety analyses and visualizations.

Vulnerable road users’ crash hotspot identification on multi-lane arterial roads using estimated exposure and considering context classification

This research develops safety performance functions and identifies the crash hotspots based on estimated vulnerable road users’ exposure at intersections and along the roadway segments. The study utilized big data including Automated Traffic Signal Performance Measures (ATSPM) data, crowdsourced data (Strava), Closed Circuit Television (CCTV) surveillance camera videos, crash data, traffic information, roadway features, land use attributes, and socio-demographic characteristics. It comprises an extensive comparison between a wide array of statistical and machine learning models that were developed to estimate pedestrian and bike exposure. The results indicated that the XGBoost approach was the best to estimate vulnerable road users’ exposure at intersections as well as bike exposure along the roadway segments. Afterwards, the estimated exposure was utilized as input variables to develop crash prediction models that relate different crash types to potential explanatory variables. Negative Binomial approach was followed to develop crash prediction models to be consistent with the Highway Safety Manual. The results show that the exposure variables (i.e., AADT, bike exposure, and the interaction between them) have significant influences on the two types of crashes (i.e., crashes of vulnerable road users at intersections and bike crashes along the segments). Further, the results indicated that the context classification is significantly related to crashes. Based on the developed models, the PSIs were calculated and the hotspots were identified for the two crash types. It was found that hotspots were more likely to be located near the city of Orlando. Coastal roadways were classified as cold categories regarding bike crashes. Further, C4 roadway segments were found to be significantly related to the increase of vulnerable road users’ crashes at intersections and bike crashes along the segments.

Factors Affecting Traffic Accidents Density on Selected Multilane Rural Highways

Estimations of average crash density as a function of traffic elements and characteristics can be used for making good decisions relating to planning, designing, operating, and maintaining roadway networks. This study describes the relationships between total, collision, turnover, and runover accident densities with factors such as hourly traffic flow and average spot speed on multilane rural highways in Iraq. The study is based on data collected from two sources: police stations and traffic surveys. Three highways are selected in Wassit governorate as a case study to cover the studied locations of the accidents. Three highways are selected in Wassit governorate as a case study to cover the studied locations of the accidents. The selection includes Kut–Suwera, Kut–ShekhSaad, and Kut–Hay multilane divided highways located in the south of Iraq. The preliminary presentation of the studied highways was performed using Geographic Information System (GIS) software. Data collection was done to obtain crash numbers and types over five years with their locations, hourly traffic flow, and average spot speed and define roadway segments lengths of crash locations. The cumulative speed distribution curves introduce that the spot speed spectrum for each highway's whole traffic extends over a relatively wide range, indicating a maximum speed of 180 kph and a minimum speed of 30 kph. Multiple linear regression analysis is applied to the data using SPSS software to attain the relationships between the dependent variables and the independent variables to identify elements strongly correlated with crash densities. Four regression models are developed which verify good and strong statistical relationships between crash densities with the studied factors. The results show that traffic volume and driving speed have a significant impact on the crash densities. It means that there is a positive correlation between the single factors and crash occurrence. The higher volumes and the faster the driving speed, the more likely it is to crash. As the hourly traffic flow of automobile grows, the need for safe traffic facilities also extended. Doi: 10.28991/cej-2021-03091719 Full Text: PDF

Quantifying and comparing the effects of key risk factors on various types of roadway segment crashes with LightGBM and SHAP

Understanding and quantifying the effects of risk factors on crash frequency is of great importance for developing cost-effective safety countermeasures. In this paper, the effects of key crash contributing factors on total crashes and crashes of different collision types are analyzed separately and compared. A novel Machine Learning (ML) method, Light Gradient Boosting Machine (LightGBM), is introduced to model a Texas dataset consisting of vehicle crashes occurred from 2015 to 2017. Compared with other commonly used ML methods such as eXtreme Gradient Boosting (XGBoost), LightGBM performs significantly better in terms of mean absolute error (MAE) and root mean squared error (RMSE). In addition, the SHapley Additive explanation (SHAP) approach is employed to interpret the LightGBM outputs. Significant risk factors are identified, including speed limits, area type, number of lanes, roadway functional class, shoulder width and shoulder type. With the SHAP method, the importance, total effects, and main and interaction effects of risk factors are quantified. The results suggest that the importance of risk factors vary across collision types. Speed limit is a more important risk factor than right/left shoulder width, lane width, and median width for Rear-End (RE) crashes, while the opposite relationship is found for Run-Off-Road (ROR) crashes. Also, it is found that narrow lanes (8ft to 11ft) increase the risk for all types of crashes (i.e., Total, ROR, and RE) in this study. For road segments with 5 or 6 lanes in both directions combined, a lane width greater than or equal to 12ft may help reduce the risk of all types of crashes. These results have important implications for developing accurate crash modification factors and cost-effective safety countermeasures.

Analytical characterization of multi-state effective discharge rates for bus-only lane conversion scheduling problem

An accurate quantification of traffic flow characteristics with and without bus-only lane is important for determining transit priority strategies. Examinations of real-world vehicle trajectory data, like those from the NGSIM dataset, found that an effective discharge rate may be discounted when merging or lane-changing behaviors are observed. To deal with this, this manuscript analytically derives the effective discharge rate of a roadway segment by considering multi-stage merging behavior and vehicular traffic kinematics near a side entrance, for optimal bus-only lane conversion. The classic fluid-based approximation model by Newell that characterizes the queuing and dissipation process is extended to a multi-state queuing analysis framework. Three effective discharge rate discount factors are explicitly derived, for bus-only lane, general-purpose lane, and mixed-traffic lane, respectively. The derived effective discharge rates are represented by mathematically-simple expressions in a closed-form, and correctly account for the effects of demand inputs, such as arrival rate and the ratio of vehicles of different types, vehicular performance (such as acceleration rate), and traffic flow characteristics (such as backward wave speed and jam density). The bus-only lane conversion scheduling problem is then formulated as an optimization model to minimize total traffic delay. Validation, using NGSIM data, showed that our model reduced the effective discharge rate estimation error significantly on both arterials and freeways. Sensitivity analysis revealed that the optimal bus-only lane scheduling time varied in response to traffic demand and vehicle ratios, and the developed optimization model was always beneficial when compared with the demand-oriented strategy.

Identification of Traffic and Roadway Variables Affecting Safe Motorcycling Along Urban Roads


 
 
 In Malaysia, motorcycles represented 45% of all registered vehicles. Alarmingly, motorcyclists comprise 65% of total road deaths. One major reason being that these vulnerable road users get entangled with other mixed vehicles. It is appreciated that roadway design guidelines are based on the characteristics of drivers/automobiles and not riders/motorcycles. Thus, motorcyclists are expected to occupy the dynamically changing space that is available along the roadway. An effective engineering measure to tackle motorcycle safety problems in mixed traffic conditions would be to segregate the motorcycles exclusively. However, this measure is not appropriate for urban roads. One practical approach to address motorcycling safety along urban roads is to identify the traffic and road environment variables that affects safe motorcycling. This list of variables can be used to check the safe motorcycling status along segments of urban roads. The variables relating to bicyclist's perception on the roadway segments were adopted for the variables affecting motorcycling safety along urban roads. To corroborate the adopted variables factors with the actual perception of motorcyclist, the questionnaires related to the variables affecting safe motorcycling were responded by 137 motorcyclists. The variables were identified to be pavement condition, on-street parking, traffic volume, divided/undivided roadway, left-side kerb clearance, lane width, and travelling speed. To further understand these seven variables from the aspect of motorcyclist perceptions, 14 short clips were presented to 483 motorcyclists who rated each clip based on their perception of safe motorcycling. Results found that the odds of feeling unsafe riding on bad pavement is 61.5 times greater than the odds of riding on good pavement. The odds of unsafe motorcycling along roads with on-street parking is 43.2 times higher than without on- street parking. Overall, it infers that the maintenance of road pavement conditions must be of high priority to the local authorities followed by issues of on-street parking along urban links.
 
 

Comparison of motor vehicle-involved e-scooter and bicycle crashes using standardized crash typology

Introduction: The market share of e-scooters in the United States has proliferated in cities: 86 million trips were made on shared e-scooters in 2019, a more than 100% increase compared to 2018. However, the interaction of e-scooters with other road users and infrastructure remains uncertain. Method: This study scrutinized 52 e-scooter and 79 bicycle police-reported crashes in Nashville, Tennessee, from April 2018 to April 2020 from the Tennessee Integrated Traffic Analysis Network (TITAN) database. We used descriptive analysis and a recent prototype version of the Pedestrian and Bicycle Crash Analysis Tool (PBCAT) to classify crashes based on the locations of the crashes relative to roadway segments or intersections, as well as the maneuver of the motor vehicle and e-scooter/bicycle relative to the motor vehicle. Results: Two crash typologies can explain the majority of e-scooter crashes, while bicycle crashes are distributed over several crash typologies. Additionally, 1 in 10 e-scooter- and bicycle-motor vehicle crashes leads to the injury or fatality of the e-scooter rider or bicyclist. Furthermore, we noted statistically significant differences in spatial and temporal distribution, demographics, lighting conditions, and crash distance from home for e-scooter and bicycle crashes. Conclusions: The police crash report provides a comprehensive picture of e-scooter safety complementing existing literature. We found that e-scooter crash characteristics do not fully overlap with features of bicycle crashes. Practical Implications: A generalized engineering, education, and enforcement treatment to reduce and prevent e-scooter and bicycle crashes, injuries, and fatalities might not result in equal outcomes for each mode. More rigorous enforcement could be implemented to deter e-scooters riders under the age of 18 years and e-scooter safety campaigns could target female riders.

A deep learning based traffic crash severity prediction framework

Highway work zones are most vulnerable roadway segments for congestion and traffic collisions. Hence, providing accurate and timely prediction of the severity of traffic collisions at work zones is vital to reduce the response time for emergency units (e.g., medical aid), accordingly improve traffic safety and reduce congestion. In predicting the severity of traffic collisions, previous studies used different statistical and machine learning models with accuracy as the main evaluating factor. However, the performance of these models was generally not good, especially on fatal and injury crashes. Also, looking into the prediction accuracy only is misleading.This paper aims to propose a novel deep learning-based approach with a customized f1-loss function to predict the severity of traffic crashes. Underlying this objective is to compare the results of deep learning models with machine learning model considering two performance indicators, namely precision, and recall. The data used in the analysis include a sample of traffic crashes that occurred at work zones in Louisiana from 2014 to 2018. This dataset includes valuable information (features) related to road, vehicle, and human factors affecting the occurrence and severity of those crashes.The proposed methodology is based on transforming these features/variables into images. Image transformation is conducted using a nonlinear dimensionality reduction technique t-SNE and convex hull algorithm. A CNN based deep learning algorithm with a customized loss function was used to directly optimize the model for precision and recall. The results showed improved performance in predicting the crash severity of fatal and injury crashes using the deep learning approach, which can help to improve traffic safety as well as traffic congestion at work zones and possibly other roadways segments.

Evaluation of Microsimulation Models for Roadway Segments with Different Functional Classifications in Northern Iran

Industrialization, urban development, and population growth in the last decades caused a significant increase in congestion of transportation networks across the world. Increasing congestion of transportation networks and limitations of the traditional methods in analyzing and evaluating the congestion mitigation strategies led many transportation professionals to the use of traffic simulation techniques. Nowadays, traffic simulation is heavily used in a variety of applications, including the design of transportation facilities, traffic flow management, and intelligent transportation systems. The literature review, conducted as a part of this study, shows that many different traffic simulation packages with various features have been developed to date. The present study specifically focuses on a comprehensive comparative analysis of the advanced interactive microscopic simulator for urban and non-urban networks (AIMSUN) and SimTraffic microsimulation models, which have been widely used in the literature and practice. The evaluation of microsimulation models is performed for the four roadway sections with different functional classifications, which are located in the northern part of Iran. The SimTraffic and AIMSUN microsimulation models are compared in terms of the major transportation network performance indicators. The results from the conducted analysis indicate that AIMSUN returned smaller errors for the vehicle flow, travel speed, and total travel distance. On the other hand, SimTraffic provided more accurate values of the travel time. Both microsimulation models were able to effectively identify traffic bottlenecks. Findings from this study will be useful for the researchers and practitioners, who heavily rely on microsimulation models in transportation planning.

Real-Time Vehicle Trajectory Estimation Based on Lane Change Detection using Smartphone Sensors

As technology is moving rapidly toward automation and connectivity, it is of paramount importance to predict vehicle trajectories ahead of time. This not only enhances safety but also ensures mobility in a connected and automated environment. Previous studies have shown that, given the previous trajectory, the future trajectory can be estimated. But this method suffers from considerable drawbacks in the case of intersections as it cannot predict turning movements. It also requires advanced sensors that are not readily available in most vehicles. A smartphone device can also be used in such scenarios, bringing partial automation to vehicles without these sensors. This paper presents an integrated method of estimating vehicle trajectories for both general roadway segments and intersections by using a smartphone. A lane change detection system is taken as an indicator of intersection turning movement estimation and corresponding vehicle trajectories are estimated accordingly. The system can achieve high penetration rates and can be used to replicate onboard units. Sensor readings are taken periodically which are first filtered with a low-pass filter to zero out any high-frequency noise and then fed into a machine learning model to detect lane changes. The model can successfully capture lane changes with smartphone data with high accuracy (95%). Finally, vehicle trajectory is estimated using Chebyshev’s polynomial. This type of estimation system can find applications in collision prediction at intersections between a turning vehicle and a pedestrian on a crosswalk.

Virtual assessment of sight distance limitations using LiDAR technology: Automated obstruction detection and classification

The amount of sight distance available to drivers is an extremely critical design element with significant impacts on the safe operation of highways. If the available sight distance on a roadway is limited, this reduces the ability of drivers to safely carry out certain maneuvers such as stopping or passing. Obstructions to sight distance are often caused by a range of different factors. This includes roadside vegetation overgrowing into the road's right of way and obstructions related to the road's alignment. To ensure that sufficient sight distance is available throughout a road's service life, transportation agencies are required to conduct regular long site visits to identify the existence of any obstructions while identifying the types of those obstructions. Although many studies have attempted quantifying available sight distance in the past, not much work has been done to automatically identify and study the types of obstructions causing sight distance limitations. This information is critical to entities looking to decide on the appropriate construction activity required to alleviate sight distance limitations. To fill in this gap, this paper proposes a fully automated novel method to assess sight distance on highways scanned using mobile LiDAR technology, while also proposing a method for the automated classification of the type of obstruction detected. The algorithm is tested on multiple roadway segments in Alberta, Canada and was successful in identifying limitations in sight distance and classifying obstructions into different types of objects.

Estimating impacts of recurring flooding on roadway networks: a Norfolk, Virginia case study

Climate change and sea level rise have increased the frequency and severity of flooding events in coastal communities. This study quantifies transportation impacts of recurring flooding using crowdsourced traffic and flood incident data. Agency-provided continuous count station traffic volume data at 12 locations is supplemented by crowd-sourced traffic data from location-based apps in Norfolk, Virginia, to assess the impacts of recurrent flooding on traffic flow. A random forest data predictive model utilizing roadway features, traffic flow characteristics, and hydrological data as inputs scales the spatial extent of traffic volume data from 12 to 7736 roadway segments. Modeling results suggest that between January 2017 and August 2018, City of Norfolk reported flood events reduced 24 h citywide vehicle-hours of travel (VHT) by 3%, on average. To examine the temporal and spatial variation of impacts, crowdsourced flood incident reports collected by navigation app Waze between August 2017 and August 2018 were also analyzed. Modeling results at the local scale show that on weekday afternoon and evening periods, flood-impacted areas experience a statistically significant 7% reduction in VHT and 12% reduction in vehicle-miles traveled, on average. These impacts vary across roadway types, with substantial decline in traffic volumes on freeways, while principal arterials experience increased traffic volumes during flood periods. Results suggest that analyzing recurring flooding at the local scale is more prudent as the impact is temporally and spatially heterogeneous. Furthermore, countermeasures to mitigate impacts require a dynamic strategy that can adapt to conditions across various time periods and at specific locations.

Feature Engineering Algorithms for Traffic Dataset

As a result of an increase in the human popula-tion globally, traffic congestion in the urban area is becoming worse, which leads to time-consuming, waste of fuel, and, most importantly, the emission of pollutants. Therefore, there is a need to monitor and estimate traffic density. The emergence of an automatic traffic management system allows us to record and monitor motor vehicles’ movement in a road segment. One of the challenges researchers face is when the historical traffic data is given as an annual average that contains incomplete data. The annual average daily traffic (AADT) is an average number of traffic volumes at the roadway segment in a specific location over a year. An example of AADT data is the one given by Road Traffic Volume Malaysia (RTVM), and this data is incomplete. The RTVM provides an average of daily traffic data and one peak hour. The recorded traffic data is for sixteen hours, and the only hourly data given is one hour, from 8.00 am to 9.00 am. Hence there is a need to estimate hourly traffic volume for the remaining hours. Feature engineering can be used to overcome the issue of incomplete data. This paper proposed feature engineering algorithms that can efficiently estimate hourly traffic volume and generate features from the existing dataset for all traffic census stations in Malaysia using queuing theory. The proposed feature engineering algorithms were able to estimate the hourly traffic volume and generate features for three years in Jalan Kepong census station, Kuala Lumpur, Malaysia. The algorithms were evaluated using the Random Forest model and Decision Tree Models. The result shows that our feature engineering algorithms improve machine learning algorithms’ performance except for the prediction of N􀀀2 using Random Forest, which shows the highest MAE, MSE, and RMSE when traffic data was included for prediction. The algorithm is applied in one of the traffic census stations in Kuala Lumpur, and it can be used for the other stations in Malaysia. Additionally, the algorithm can also be used for any annual average daily traffic data if it includes average hourly data.

Orclsim: A System Architecture for Studying Bicyclist and Pedestrian Physiological Behavior Through Immersive Virtual Environments

Injuries and fatalities for vulnerable road users, especially bicyclists and pedestrians, are on the rise. To better inform design for vulnerable road users, we need to conduct more studies to evaluate how bicyclist and pedestrian behavior and physiological states change in different roadway designs and contextual settings. Previous research highlights the advantages of Immersive Virtual Environment (IVE) in conducting bicyclist and pedestrian studies. These environments do not put participants at risk of getting injured, are low-cost compared to on-road or naturalistic studies and allow researchers to fully control variables of interest. In this paper, we propose a framework ORCLSim, to support human sensing techniques within IVE to evaluate bicyclist and pedestrian physiological and behavioral changes in different contextual settings. To showcase this framework, we present two case studies where we collect and analyze pilot data from five participants' physiological and behavioral responses in an IVE setting, representing real-world roadway segments and traffic conditions. Results from these case studies indicate that physiological data is sensitive to road environment changes and real-time events, especially changes in heart rate and gaze behavior. Additionally, our preliminary data indicates participants may respond differently to various roadway settings (e.g., intersections with or without traffic signal). By analyzing these changes, we can identify how participants' stress levels and cognitive load is impacted by the simulated surrounding environment. The ORCLSim system architecture can be further utilized for future studies in users' behavioral and physiological responses in different virtual reality settings.