Showing papers on "Traffic count published in 2019"

Optimization of traffic count locations for estimation of travel demands with covariance between origin-destination flows

Abstract: Vehicular traffic between different Origin-Destination (OD) pairs for a typical hourly period may statistically correlate with each other. The covariance mainly generated from the daily variation of travel patterns, network topology, and trip chaining activities of household members can be particularly high during the morning peak hour. With the increasing attention on the OD demand variance and covariance in stochastic road networks, a new criterion is proposed in this paper for measuring the estimation accuracy of OD demand covariance. The mathematical properties of this proposed criterion are analyzed to better understand the relationship between the estimation errors of mean and covariance of OD demands. This paper aims to investigate how to optimize the traffic count locations for minimizing the weighted maximum deviation of estimated mean and covariance of OD demands from the “true” values. To consider the effects of stochastic OD demands on the traffic count location problem in the proposed model, link choice proportions are regarded as stochastic variables and updated by an adapted traffic flow simulator in this study. Both the weighted-sum approach and bi-objective approach are examined with the adaption of the firefly algorithm (FA) to solve the single-objective and bi-objective problems. Numerical examples are presented to demonstrate the effects, with and without considering the covariance of the OD demands for the optimization of traffic count locations.

Spatial and Temporal Analyses for Estimation of Origin-Destination Demands by Time of Day over Year

Abstract: This paper proposes a two-stage model for the estimation of origin-destination (OD) demands by the time of day over the year with the use of offline traffic data from the real-time travel information system. In the first stage, a travel time recursive function is proposed to use the offline travel speed data for the investigation of the spatial and temporal relationships between time-dependent OD demands and traffic counts. As such, it is not required to carry out the time-consuming dynamic traffic assignment (DTA) process which is frequently used in the conventional time-dependent OD estimation models. Using the results in the first stage together with the available traffic count data, a least-squares method is adopted to formulate the time-dependent OD demand estimation problem as a quadratic programming model in the second stage. A solution algorithm is adapted for solving the proposed model. Then, the proposed method is easy for implementation in practice. Particularly, when the traffic accident occurs in the network, the estimated time-dependent OD demands can be helpful for understanding the complex travel behavior (e.g., departure time choice) under uncertainty condition. The numerical examples are presented to illustrate the applications of the proposed model.

Traffic control approach based on multi-source data fusion

Abstract: A multi-source data-driven traffic control approach is developed to alleviate traffic overload at bottleneck road segments. In the proposed approach, the high-penetration feature of mobile-phone signalling data and the real-time feature of taxi global-positioning-system data are combined to simulate traffic flows in the road network of Shenzhen, a major city of southern China. The road intersections for implementing traffic control schemes are selected by locating the major vehicle sources of the bottleneck road segments, and a genetic algorithm was used to solve the dynamic traffic control schemes. Two important bottleneck road segments in Shenzhen were used as case studies to test the effectiveness of the proposed approach. The authors also propose a method to calibrate the simulated traffic flows when traffic count data are available in the future.

Applicability of an automatic pneumatic–tube–based traffic counting device for collecting data under mixed traffic

Abstract: Traffic volume and composition data can be collected using several techniques such as manual, camera video recordings and automatic traffic count devices installed across the road pavement. An automatic traffic count device is often used for long hours of traffic data collection exercises. In view that the accuracy of the data is an important aspect of data analysis, this paper discusses the applicability of an automatic traffic count device to be used for traffic volume and composition data collections based on Malaysian vehicle classification system, i.e. where traffic is characterised by various types of vehicles or mixed traffic. The automatic traffic count (ATC) used in the study was the pneumatic tube-based equipment known as Metrocount@5600. The data used for validating the ATC was obtained using a video recording technique. The data was collected at four different sites to ensure the result of the analysis is reliable. A video camera and ATC were installed at each of the sites considered in the study. Traffic volumes and compositions from video recordings were extracted manually based on five classes of vehicles, i.e. cars and small vans, medium trucks and lorries with two axles, large trucks and lorries with three and more axles, buses and motorcycles. The ATC was set to classify vehicle types using one of the equipment's default setting, i.e. 13 classes (Scheme F). The data retrieved from the ATC was reorganised based on the vehicle classifications used in the data collected using the video recording technique. Twenty datasets of vehicles composition from four sites were used in the analysis. The result of the statistical analysis showed that there is no significant different in traffic volumes and compositions obtained using both techniques. The finding implies that an automatic pneumatic-tube-based traffic counting device such as MetroCount@5600 with scheme F can be used as an alternative technique to collect traffic volumes and compositions data based on five standard classes of vehicles classification system.

Real-Time Traffic Monitoring System Using Spark

Abstract: Objective: Predict the total traffic count of streaming data in various routes to reduce traffic congestion and informing public about current traffic condition by displaying it in dashboard. Analysis: Real-time traffic monitoring can be made with the help of sensor connected devices, it generates huge volume and high speed data, Apache Kafka and Spark streaming engine is used for Processing these data. Findings: In existing system Traffic is predicted by deploying sensors in traffic signal lane and Apache hadoop used for processing data, it is batch processing system takes more time to process the data. In Proposed system total count of traffic predicted by using connected vehicles and Apache spark is used for processing live streaming data, by using spring boot total count of traffic is displayed in dashboard. Improvement: Real-time traffic prediction is done with live streaming data, Apache spark process data in-memory and dashboard updated for every five seconds

Investigation on road damage due to vehicle overloading of high volume Ipoh state road

Abstract: Traffic load was a major factor in thickness design due to the main function of pavement which was to resist traffic load. Although efforts to repair the road damage had been done continuously, the recovering effects were almost meaningless if the road was continuously receiving overloading from vehicles. Issues of road damage due to vehicle overloading had been addressed by most agencies in developing countries. However, there were no available study to address this issue on Perak state road. Therefore, this research aimed to determine the current traffic composition, the percentage of overloading vehicle, the Equivalence Factor (E.F.), the adequacy of existing pavement thickness and the reduction of pavement service life due to overloading of the road by referred to AASHTO and Arahan Teknik (Jalan) 5/85. The selected study area was at Jalan Tuanku Abdul Rahman, Ipoh (also known as Jalan Kuala Kangsar). Data were employed which acquired from traffic count survey, axle load survey, coring test and dynamic cone penetrometer test. Review on current traffic count data showed that vehicles with 2-axle contributes more than 60% of the overall daily traffic while percentage of overloading vehicle revealed that more than 50% of vehicles contributed from 4-axle, 5-axle and 6-axle exceeded the maximum permissible gross vehicle weight (PGVW). The analysis on the E.F. showed that primary and secondary directions gained E.F. value of 4 and 3 times higher than the 3.0 E.F. design value which were 12.4 and 9.2 respectively. This also denoted that additional overlay pavement thickness was required about 70mm and 50mm for primary and secondary direction respectively to ensure the target design life was achieved. This study also discovered the road pavement experienced 7 and 6 years of reduction of service life for both directions respectively.

Automated Scenario Generation for Meeting Human-In-The-Loop Simulation Requirements

Abstract: A two-step automated Multi-Aircraft Control System traffic scenario generation process for Human-in-the-Loop evaluations of air traffic management concepts is described. The first step of the two-step process employs the scenario generation capability currently available in NASA's Air Traffic Management Testbed. The second step refines the scenario by filtering flights from the traffic scenario based on route length, cruise speed, cruise altitude, entry time and the desired ratio of internal to external flights. A solution for achieving the desired ratio of internal to external flights, where internal flights are shorter flights and external flights are longer flights based on a distance threshold, is described. Finally, schedulers are described for shaping the hourly arrival traffic count as a function of time in response to airport capacity constraint or for increasing the traffic demand with respect to the available arrival capacity. Results generated for arrival traffic to the four major airports in the New York Metroplex on a busy day using the two-step procedure are discussed. These results show that traffic scenarios for Multi-Aircraft Control System that meet the Human-in-the-Loop and fast-time simulation requirements can be created automatically following the procedures described in the paper. The automated process will improve the accuracy and efficiency by eliminating the tedious manual process for scenario generation.

Traffic Counting and Turning Fraction Estimation using Vehicle-to-UAV Co-operative communication

Abstract: The current roads and supporting infrastructure are often found to be incapable of handling the rapid increase in traffic, leading to congestion and incidents. The availability of accurate and real-time information about the traffic demands may go a long way in designing better traffic control and management systems. Two important quantities of interest for traffic control are the ‘traffic count’ on road segments between junctions and ‘turning fractions’ at the junctions. Together, these two quantities can determine the traffic flow requirements over the road network. The aims of the paper are to investigate the performance of the Vehicle-to-UAV (V2U) communication method for traffic counting and turning fraction estimation using vehicular network simulations and compare with the performance of Bluetooth and loop detectors.

Road Traffic Noise Assessment at Sekolah Kebangsaan Sungai Bakap, Sungai Bakap, Penang, Malaysia

Abstract: This study is intended on the assessment of traffic noise at Sekolah Kebangsaan Sungai Bakap where this study area located near the main road (Jalan Sungai Bakap). The objectives of this study are to determine noise levels during school hours, to identify the source of noise and to establish the noise profiling in the Sekolah Kebangsaan Sungai Bakap environment. With using sound level meter instrument, the noise levels at school were measured where 19 points were selected at school area in order to collect the value of all parameters measured in this study (Leq, Lmax, Lmin, L10, L50, and L90). Each of the noise measurements was taken for 3 minutes in duration and the time taken for all measurements conducted from 8.30 a.m. to 12.00 p.m. Noise mapping performed using ArcMap and My maps website based on the latitude, longitude and also noise parameters. Manually traffic count was conducted to count the number of vehicles on the road. Traffic composition data in this study was categorized into four types, which passenger car and van, motorcycle, medium lorries and heavy lorries. The result showed that the measured noise levels at school area in term of Leq were between the range of 54.8–72.9 dB(A), where it was found that the highest noise level generated was at road zones. From this study, all noise data collected exceeded the Malaysian noise limit. Apart from that, based on the noise mapping it showed that highest noise levels were located in traffic zones area.

Gaussian Model Trees for Traffic Imputation

Abstract: Traffic congestion is one of the most pressing issues for smart cities. Information on traffic flow can be used to reduce congestion by predicting vehicle counts at unmonitored locations so that counter-measures can be applied before congestion appears. To do so pricy sensors must be distributed sparsely in the city and at important roads in the city center to collect road and vehicle information throughout the city in real-time. Then, Machine Learning models can be applied to predict vehicle counts at unmonitored locations. To be fault-tolerant and increase coverage of the traffic predictions to the suburbs, rural regions, or even neighboring villages, these Machine Learning models should not operate at a central traffic control room but rather be distributed across the city. Gaussian Processes (GP) work well in the context of traffic count prediction, but cannot capitalize on the vast amount of data available in an entire city. Furthermore, Gaussian Processes are a global and centralized model, which requires all measurements to be available at a central computation node. Product of Expert (PoE) models have been proposed as a scalable alternative to Gaussian Processes. A PoE model trains multiple, independent GPs on different subsets of the data and weight individual predictions based on each experts uncertainty. These methods work well, but they assume that experts are independent even though they may share data points. Furthermore, PoE models require exhaustive communication bandwidth between the individual experts to form the final prediction. In this paper we propose a hierarchical Product of Expert model, which consist of multiple layers of small, independent and local GP experts. We view Gaussian Process induction as regularized optimization procedure and utilize this view to derive an efficient algorithm which selects independent regions of the data. Then, we train local expert models on these regions, so that each expert is responsible for a given region. The resulting algorithm scales well for large amounts of data and outperforms flat PoE models in terms of communication cost, model size and predictive performance. Last, we discuss how to deploy these local expert models onto small devices.

Urban sensing for anomalous event detection: Distinguishing between legitimate traffic changes and abnormal traffic variability

Abstract: © 2019, Springer Nature Switzerland AG. Sensors deployed in different parts of a city continuously record traffic data, such as vehicle flows and pedestrian counts. We define an unexpected change in the traffic counts as an anomalous local event. Reliable discovery of such events is very important in real-world applications such as real-time crash detection or traffic congestion detection. One of the main challenges to detecting anomalous local events is to distinguish them from legitimate global traffic changes, which happen due to seasonal effects, weather and holidays. Existing anomaly detection techniques often raise many false alarms for these legitimate traffic changes, making such techniques less reliable. To address this issue, we introduce an unsupervised anomaly detection system that represents relationships between different locations in a city. Our method uses training data to estimate the traffic count at each sensor location given the traffic counts at the other locations. The estimation error is then used to calculate the anomaly score at any given time and location in the network. We test our method on two real traffic datasets collected in the city of Melbourne, Australia, for detecting anomalous local events. Empirical results show the greater robustness of our method to legitimate global changes in traffic count than four benchmark anomaly detection methods examined in this paper. Data related to this paper are available at: https://vicroadsopendata-vicroadsmaps.opendata.arcgis.com/datasets/147696bb47544a209e0a5e79e165d1b0_0.

Development and evaluation of an open-source, machine learning-based average annual daily traffic estimation software.

Abstract: Traditionally, Departments of Transportation (DOTs) use the factor-based model to estimate Annual Average Daily Traffic (AADT) from short-term traffic counts. The expansion factors, derived from the permanent traffic count stations, are applied to the short-term counts for AADT estimation. The inherent challenges of the factor-based method (i.e., grouping the count stations, applying proper expansion factors) make the estimated AADT values erroneous. Based on a survey conducted by the authors, 97% of the 39 public transportation agencies use the factor-based AADT estimation model, and these agencies face the aforementioned challenges while using factor-based models to estimate AADT. To derive a more accurate AADT, this paper presents the "estimAADTion" software, which is an open-source software developed based on a machine learning method called support vector regression (SVR) for estimating AADT using 24-hour short-term count data. DOTs conduct short-term counts at different locations periodically. This software has been designed to estimate AADT at a particular location from the short-term counts collected at those locations. In order to estimate AADT from short-term counts, the software uses data from permanent count stations to train the SVR model. The performance of the "estimAADTion" software is validated using the short-term count data from South Carolina. The Mean Absolute Percentage Error (MAPE) of the AADT estimated from the software is 3%, while the factor-based method produces a MAPE value of 6%.

Development and Evaluation of Traffic Count Sensor with Low-Cost Light-Detection and Ranging and Continuous Wavelet Transform: Initial Results:

Abstract: This paper presents a cost-effective, non-intrusive, and easy-to-deploy traffic count data collection method using two-dimensional light-detection and ranging (LiDAR) technology. The proposed metho...