Traffic Operation Data Research Articles

Graph convolutional LSTM algorithm for real-time crash prediction on mountainous freeways

Accurate real-time traffic crash prediction is crucial for proactive traffic safety management. Currently, the majority of real-time models forecast crashes every 5 min to support different intelligent transportation systems. However, these intervals might be too short for practical use in manually implementing proactive traffic safety measures such as deploying traffic law enforcement and emergency rescue resources. Therefore, this study develops hourly crash prediction models to provide network operators with sufficient time to take measures in advance. A section of a mountainous freeway in Guizhou province is divided into homogeneous segments, with crash data, traffic operations data, and meteorological data being collected hourly. As the result is an imbalanced dataset of crash and non-crash instances, the training dataset is resampled using synthetic minority over-sampling technique (SMOTE) to address the issue. To fully capture the complex spatiotemporal relationships in the data and achieve high crash prediction accuracy, a graph convolutional network-long short-term memory (GCN-LSTM) model is constructed for the first time, combining a graph convolutional network (GCN) and long short-term memory (LSTM) neural network. For comparison purposes, LSTM, Extreme Gradient Boosting (XGBoost), and logistic regression (LR) models are developed. The results show that the GCN-LSTM model outperforms other models in hourly traffic crash prediction, and the optimal prediction performance is achieved with the crash-to-non-crash ratio of 1:4. The GCN-LSTM method is found to effectively capture the complex spatiotemporal relationships in prediction data and to handle imbalanced traffic crash data.

A data-based framework for automatic road network generation of multi-modal transport micro-simulation

<abstract> <p>In microscopic traffic simulation, the fidelity of the road network model has a significant impact on the difference between the simulation and the actual urban traffic state. Accurately matching data on the simulated road network and the surroundings has become a central concern in traffic simulation research. This study provides a multi-source data-based framework for automatic road network generation (ARNG) to address the issue of manual procedures in the creation of the simulated road network and surroundings. First, the proposed method of fusion and matching of diverse road network data is used to acquire the basic road network information, and the combining of the features of different road network data can enhance the authenticity of the basic road network. Second, a multi-modal simulation road network is developed based on multi-modal traffic operation data to serve as the simulation operation's foundational environment. To address the requirements of the dynamic evolution of the simulated road network, an editor for the dynamic road network is built based on spatial closest neighbor matching. The case study illustrates the process of building the simulated road network and environment in the old city zone of Suzhou. Real-world examples demonstrate that the data-based ARNG approach provided in this study is highly automatic and scalable.</p> </abstract>

The Limited Responses of Provincial Expressway Network Operation Quality to the Impact of COVID-19: Taking Shaanxi Province as an Example

Recent research indicates that the coronavirus disease 2019 (COVID-19) pandemic has impacted road traffic operation quality. From the perspective of service level, safety level, and operation orderliness, this study attempts to analyze the limited responses of the operation quality of the provincial expressway network (PEN) to the impact of COVID-19. The traffic operation data of the PEN in Shaanxi Province were collected for three consecutive years (from 2019 to 2021) before and after the COVID-19 outbreak, including weekly average daily traffic, weekly traffic interruption times, weekly traffic control time, weekly traffic accidents, weekly traffic injuries, and weekly traffic deaths. Through descriptive statistics and dynamic analysis, we studied the limited responses of the safety and service levels of the PEN to the impact of COVID-19. An evaluation model of operation orderliness of the PEN was established by using dissipative structure theory and entropy theory. Results show that in 2020, the service level, safety level, and operation orderliness of the PEN dropped to their lowest. With the gradual control of pandemic, its negative impacts on the service level and operation orderliness of the PEN gradually decreased but did not recover to the pre-pandemic level. In terms of the safety level, the number of traffic accidents, traffic injuries, and traffic deaths decreased, whereas the traffic accident rate and accident casualty rate remained high. In summary, the operation quality of the PEN in Shaanxi Province has had a limited response to the impact of COVID-19.

Traffic Operation Management Information System Using Extreme Programming Method

The Indonesian National Police (Polri) is a state instrument whose role is to maintain public security and order, enforce the law, and provide protection, protection and service to the community. To support this role, the Police carry out various kinds of police operations. One of them is on the traffic function, namely by carrying out traffic operations. The Traffic Police under the auspices of the Korlantas Polri is a state instrument that is responsible for police functions in the traffic sector. Having a large organization, with 34 Polda and 504 Polres throughout Indonesia, is a challenge for the Polri, especially the Korlantas Polri, in carrying out traffic operations. The challenge faced is that the process of making reports on the results of traffic operations takes a long time, because the activities of reporting, collecting and managing traffic operation data are still carried out in a simple manner. This study aims to build a web-based application that can assist the process of reporting, collecting and managing data from traffic operations, as well as processing it into useful information. This application development applies the Extreme Programming (XP) software development methodology. The choice of the XP method is because XP is one of the methodologies that supports the acceleration of the development of a system with a minimum number of teams. In addition, based on the results of the study, it was found that the implementation of the XP method in application development resulted in software that was in accordance with the requirements.

Urban Road Network Emergency: An Integrative Vulnerability Identification Method

The vulnerability of an urban road network is affected by many factors, such as internal road network layout, network structure strength, and external destructive events, which have great uncertainty and complexity. Thus, there is still no unified and definite vulnerability analysis scheme available to cities. This paper proposes an integrative vulnerability identification method for urban road networks, which mainly relates to the vulnerability connotation and characteristics analysis of urban road networks during emergency, and vulnerability comprehensive evaluation indices design based on urban road network connectivity, traffic efficiency and performance, and an empirical study on a vulnerability identification method of an urban road network. In the empirical case, a real road network and traffic operation data were used from Science and Technology Park of Shenzhen City, China. In the context of one certain emergency scenario, the stated preference survey method and maximum likelihood method are used to solve the road users’ random travel choice behavior parameters; subsequently, based on the traffic equilibrium distribution prediction, the traffic vulnerability identification methods of the road network in this region were verified before and after the emergency. The method presented here not only considers the impact of network topology changes on road network traffic function during emergency but also considers the impact of dynamic changes in road network traffic demand on vulnerability; therefore, it is closer to the actual distribution of urban road network traffic vulnerability.

The Impact of Emergency Parking Bays on Quasi-Eight-Lane Expressway Traffic Operations

Recently, with the discrepancy between increasing traffic demand and limited land resources, more and more expressways are choosing to use hard shoulders to expand into quasi-six-lane or quasi-eight-lane roads. Therefore, more emergency parking bays are used in place of traditional parking belts. However, there are no standards defining clear and unified specifications for the design of parking bays. This paper aimed to investigate the impact of emergency parking bays on expressway traffic operations with various traffic volumes and setting conditions. Based on the Monte Carlo method, VISSIM (Verkehr in Städten Simulation, a microscopic simulation software) simulation experiments were conducted using measured traffic operation data from one expressway in Zhejiang province. The probability of unsafe deceleration, lane-changing maneuvers and delay times were considered as the safety and efficiency indexes in this simulation study. The simulation results indicated that the emergency parking vehicle had an increasing impact on the following vehicle as the traffic volume increased. However, the impact pattern was found to be insensitive to the changing of the bay taper length. For low traffic volume, compared with the arrival vehicle, the departure vehicle had more impact on the traffic operation of the mainline. However, the impact of the arrival vehicle became more remarkable as the traffic volume increased. After parking, the waiting time for merging into the mainline was reduced as the volume decreased or as the bay taper increased. Furthermore, reductions caused by varying bay tapers were more significant under high volume conditions. Finally, this study suggests that parking bays are inapplicable when the occupancy of the road space exceeds 20% (about 3000 veh/h), because they would cause significant impact on the safety and efficiency of the expressway. The results of this paper are useful for the design and implementation of emergency parking bays.

Calibration Method for Microscopic Simulation Model of Urban Expressway Using Internet Traffic Operation Data

To develop a calibration method for microscopic simulation model of urban expressway using internet traffic operation data, a practical calibration process is proposed in this study. In this process, a sensitivity analysis was conducted to detect those parameters that impose the most influence on simulation model. Then the Latin Hypercube Sampling Method is used to generate workable amount of parameter sets for simulation run. The parameter set that produces the least discrepancy between the simulation model and the actual condition would be the calibrated parameter values. To demonstrate the feasibility of the proposed method, an example of the Inner Loop Expressway network in Wuxi City is modelled and calibrated using VISSIM. After calibration, the simulation model can accurately represent real-world condition.

Traffic Operation Data Analysis and Information Processing Based on Data Mining

With the acceleration of urbanization, urban traffic problems are becoming more and more prominent. In the face of massive traffic data, it is difficult to predict traffic condition with effective data analysis methods. In order to deal with traffic data better, this study applied data mining in traffic data analysis and processing, constructed a Hadoop based data analysis system to collect and preprocess data, and analyzed traffic data using parallel distributed calculation based on MapReduce. The improved fuzzy c-means (FCM) algorithm and the random forest algorithm were used. The simulation results showed that the error rate of the improved FCM algorithm is 10% and the accuracy rate of the random forest algorithm is 92.3%, indicating the system had high reliability. Then an experiment was carried out on the main traffic roads in Huadu district of Guangzhou, China. It was found that the method was efficient and accurate and had a good application prospect.

Understanding the emission impacts of high-occupancy vehicle (HOV) to high-occupancy toll (HOT) lane conversions: Experience from Atlanta, Georgia

ABSTRACTConverting a congested high-occupancy vehicle (HOV) lane into a high-occupancy toll (HOT) lane is a viable option for improving travel time reliability for carpools and buses that use the managed lane. However, the emission impacts of HOV-to-HOT conversions are not well understood. The lack of emission impact quantification for HOT conversions creates a policy challenge for agencies making transportation funding choices. The goal of this paper is to evaluate the case study of before-and-after changes in vehicle emissions for the Atlanta, Georgia, I-85 HOV/HOT lane conversion project, implemented in October 2011. The analyses employed the Motor Vehicle Emission Simulator (MOVES) for project-level analysis with monitored changes in vehicle activity data collected by Georgia Tech researchers for the Georgia Department of Transportation (GDOT). During the quarterly field data collection from 2010 to 2012, more than 1.5 million license plates were observed and matched to vehicle class and age information using the vehicle registration database. The study also utilized the 20-sec, lane-specific traffic operations data from the Georgia NaviGAtor intelligent transportation system, as well as a direct feed of HOT lane usage data from the State Road and Tollway Authority (SRTA) managed lane system. As such, the analyses in this paper simultaneously assessed the impacts associated with changes in traffic volumes, on-road operating conditions, and fleet composition before and after the conversion. Both greenhouse gases and criteria pollutants were examined.Implications: A straight before-after analysis showed about 5% decrease in air pollutants and carbon dioxide (CO2). However, when the before-after calendar year of analysis was held constant (to account for the effect of 1 yr of fleet turnover), mass emissions at the analysis site during peak hours increased by as much as 17%, with little change in CO2. Further investigation revealed that a large percentage decrease in criteria pollutants in the straight before-after analysis was associated with a single calendar year change in MOVES. Hence, the Atlanta, Georgia, results suggest that an HOV-to-HOT conversion project may have increased mass emissions on the corridor. The results also showcase the importance of obtaining on-road data for emission impact assessment of HOV-to-HOT conversion projects.

Measuring air traffic complexity based on small samples

Air traffic complexity is an objective metric for evaluating the operational condition of the airspace. It has several applications, such as airspace design and traffic flow management. Therefore, identifying a reliable method to accurately measure traffic complexity is important. Considering that many factors correlate with traffic complexity in complicated nonlinear ways, researchers have proposed several complexity evaluation methods based on machine learning models which were trained with large samples. However, the high cost of sample collection usually results in limited training set. In this paper, an ensemble learning model is proposed for measuring air traffic complexity within a sector based on small samples. To exploit the classification information within each factor, multiple diverse factor subsets (FSSs) are generated under guidance from factor noise and independence analysis. Then, a base complexity evaluator is built corresponding to each FSS. The final complexity evaluation result is obtained by integrating all results from the base evaluators. Experimental studies using real-world air traffic operation data demonstrate the advantages of our model for small-sample-based traffic complexity evaluation over other state-of-the-art methods.

Implications of driving style and road grade for accurate vehicle activity data and emissions estimates

Real-world vehicle operating mode data (2.5 million 1Hz records), collected by instrumenting the vehicles of 82 volunteer drivers with OBD datalogger and GPS while they drove their routine travel routes, were analyzed to quantify vehicle emissions estimate errors due to road grade and driving style in rural, hilly Vermont. Data were collected in winter and summer for MY 1996 and newer passenger cars and trucks only. EPA MOVES2010b was used to estimate running exhaust emissions associated with measured vehicle activity. Changes in vehicle specific power (VSP) and MOVES operating mode (OpMode) due to proper accounting for real-world road grade indicated emission rate errors between 10% and 48%, depending on pollutant, chiefly because grade-related changes in VSP could shift activity by as many as six OpModes, depending on road type. The correct MOVES OpMode assignment was made only 33–55% of the time when road grade was not included in the VSP calculation. Driving style of individual drivers was difficult to assess due to unknown traffic operations data, but the largest differences between individual drivers were observed on rural restricted roads, where traffic conditions and control have minimal impact. The results suggest the importance of (1) measuring and incorporating real-world road grade in order to correctly assign MOVES emission rates; and (2) developing a driving style typology to account for differences in the MOVES emissions estimates due to driver variability.

Algorithm for Optimal Arrival and Departure Sequencing and Runway Assignment

This work proposes a framework to compute with computational efficiency, the optimal runway assignment, and sequencing of arrival and departure operations at an airport with any number, layout, and configuration of runways. The runway assignment problem is solved based on the typical demand mix of aircraft and the scheme proposed in this work computes the allocation of arrival and departure operations on each runway, which is then fed into the sequencing algorithm that determines the set of sequences on each runway that minimize the overall makespan. The proposed sequencing algorithm is based on a branch-and-bound technique that minimizes the makespan at a given airport. The lower and upper bounds of the cost of each branch for the best first search in the branch-and-bound algorithm are computed based on the minimum separation standards between arrival and departure operations set by the Federal Aviation Administration. The optimal solution is mathematically proved to lie between these bounds and the algorithm uses these bounds to efficiently find promising branches and discard all others and terminate with at least one sequence with the minimal makespan. The proposed algorithm is analyzed and validated with real traffic operations data at the Denver International Airport and the Hartsfield Jackson Atlanta International Airport.

Assessment of environmental noise due to aircraft operation at the Athens International Airport according to the 2002/49/EC Directive and the new Greek national legislation

Athens International Airport “Eleftherios Venizelos” (A.I.A.) is one of the most modern, functional and safest airports in the world and constitutes the largest hub of air travel in south eastern Europe. Environmental noise from aircraft movements at the airport is a crucial environmental factor of urban environment and quality of life especially in Southern European countries where climatic conditions favour outdoor activities and night life. A.I.A. under the auspices of the Ministry of Environment, Energy and Climate Change, the Hellenic Civil Aviation Authority, and in collaboration with the University of Thessaly has completed a comparative Study on Aircraft Noise – according to the European Directive 49/2002 (ED 2002/49, 2002) – based on both 2006 and 2011 Strategic Noise Maps (SNM) and Noise Action Plans for the EU indicators Lden and Lnight. A full statistical analysis of predicted vs measured noise levels based on the existing A.I.A.’s Noise Monitoring System (NOMOS), is also completed in order to evaluate accuracy of both SNM’s and the relevant comparative data. The comparison analysis for both SNM’s clearly states the efficiency of the introduced Noise Action Plan taking also into account the latest traffic operation data.

Field Data for Evaluating 2010 Highway Capacity Manual Operational Analysis Methodology for Interchange Ramp Terminals

Interchange ramp terminals provide connections between various highway facilities (freeway–arterial, arterial–arterial, freeway–freeway, etc.), so their efficient operation is essential. NCHRP Project 3–60 developed analysis methods for evaluating the operational performance of signalized interchange ramp terminals. Those methods were based primarily on simulated data. Further research used collected field data to evaluate the interchange analysis methodology developed under NCHRP Project 3–60 to identify application limitations and to suggest improvements. Data were collected at eight sites representing various types of interchanges with different geometric and traffic characteristics. Video cameras, mounted on existing poles on the side of the road and on nearby buildings, were used to gather traffic operation data, including demand, lane utilization, and queue length at each site. The research evaluated both individual analytic model components (such as lane utilization factors and internal queue length) and the performance of the interchange (reflected in average queue lengths and control delay). Overall, the models performed well. However, large discrepancies were observed when operating conditions of the interchange were close to capacity. The queue length prediction at the beginning of the upstream arterial or ramp phase was calibrated to modify the effective green time estimation. A new lane utilization model was based on field data for a four- or five-lane external arterial approach where the two leftmost lanes were extensions of the downstream dual left turn lanes. The findings of the work were incorporated into the 2010 Highway Capacity Manual.

Crash data and signal coordination: A one-way pair case study

In a coordinated, or synchronized, traffic signal system, drivers become attuned to the timing and pattern of traffic signals. Good signal coordination improves roadway efficiency and reduces delay and emissions, but drivers may speed or engage in other unsafe behavior to stay in the â??platoonâ?? of the traffic flow. Because one-way roads accommodate fewer movements than typical streets, they generally exhibit very efficient signal coordination and may therefore provide the greatest incentives for drivers to engage in unsafe behavior. To better enable analysis of crash trends and distributions, Florida's District 7, which includes the Tampa-St. Petersburg metropolitan area, loaded statewide mainframe crash data into an ESRI/Microsoft Access geodatabase. Using the geodatabase, a cross tabulation was performed showing the distribution of driver-contributing causes among roadway crash rate categories. In addition to addressing an abnormal crash distribution along a specific roadway, this study incorporates aspects of traffic records beyond crash data including traffic volume data, physical conditions, and traffic signal operations data. Review of roadway, crash, and traffic operations data have identified several issues that merit further analysis including: motorist's inability to see traffic signal heads obscured by truck trailers; heavy traffic merges and underutilization of the center lane; and potential signal-timing related red light running crashes.

Field Evaluations of Warning and Regulatory Signs with Enhanced Conspicuity Properties

Researchers examined the impacts of various sign conspicuity enhancements on traffic operations and driver behavior in Texas. Eight types of applications were evaluated: fluorescent yellow chevrons, fluorescent yellow chevron posts, fluorescent yellow curve signs, fluorescent yellow ramp advisory speed signs, fluorescent yellow stop ahead signs, fluorescent red stop signs, flashing red light-emitting diode (LED) stop signs, and a standard red border on speed limit signs. Fourteen sites were used for the evaluations. Traffic operations data collected before and after the sign upgrades included vehicle speeds, edge line encroachments, and stopping compliance. Many statistically significant beneficial results occurred, including the following: fluorescent yellow chevron signs produced a significant reduction in curve speeds and edge line encroachments, both the fluorescent red and LED stop sign treatments reduced the number of vehicles not fully stopping, and the standard red reflectorized border on the speed limit sign produced a significant improvement in speed limit compliance. The data showed no undesirable impacts for the measures of effectiveness for any of the signing treatments. On the basis of the findings, the researchers recommend fluorescent yellow chevrons for full implementation. The other fluorescent yellow signs evaluated in the research are recommended for implementation on an as-needed basis. Microprismatic stop signs and flashing LED stop signs are also recommended for implementation on an as-needed basis. Although found to be effective, the red border speed limit sign currently should be limited to experimental implementation, as permission is required from FHWA to install these signs. The fluorescent red stop sign is not commercially available at this time.

Evaluation of Truck Crashes Using a GIS-Based Crash Referencing and Analysis System

Computerized crash analysis systems in which crash data, roadway inventory data, and traffic operations data can be merged are used in many states and municipalities to identify problem locations and assess the effectiveness of implemented countermeasures. By integrating this traditional system with a geographic information system (GIS), which offers spatial referencing capabilities and graphical displays, a more effective crash analysis program can be realized. In a recent FHWA-sponsored study, a crash referencing and analysis system within a GIS was developed within the Highway Safety Information System (HSIS) of the state of North Carolina for the area of Wake County. The system provides the functions needed to edit both tabular and spatial crash and roadway data as well as to perform crash analyses related to intersections, roadway segments, and special highway features, such as bridges. The second phase of the project was undertaken to illustrate the advantages of a GIS-based crash analysis system. The problem selected was identifying and analyzing locations of high numbers of truck-crashes, both along designated truck corridors and on other roadways within the county. The goal of the study was to determine if there are benefits to using a GIS-based crash referencing system over the traditional databases that contain crash, roadway feature, and operations data files and can be linked by location. Specific objectives for the truck-corridor analysis project included ( a) identifying locations of high numbers of truck crashes using the GIS-based system, and ( b) exploring the applicability of nontraditional databases to this type of analysis.

Geographic Database for Traffic Operations Data

State Transportation Departments nationwide manage huge amounts of information. Examples include geometric plans, sign inventories, maintenance records, engineering studies, and so on. In many cases, no indexing or archiving system is available for storing and retrieving this data. A prototype computer-based model was developed in order to address these indexing needs. The model focuses on engineering report tracking but can be extended to accommodate other types of information. The model is based on a procedure that links signalized intersections and road segments to nonspatial attribute data in a Geographic Information System (GIS) environment. A paper form was developed in order to facilitate the extraction of data from engineering reports. The indexing model also includes a computerized version of the paper form to assist in data entry, and another form for query purposes. The indexing model was applied to 10 years of engineering report data from East Baton Rouge Parish, La.