Urban Traffic Speed Research Articles

Missing traffic data imputation and pattern discovery with a Bayesian augmented tensor factorization model

Spatiotemporal traffic data, which represent multidimensional time series on considering different spatial locations, are ubiquitous in real-world transportation systems. However, the inevitable missing data problem makes data-driven intelligent transportation systems suffer from an incorrect response. Therefore, imputing missing values is of great importance but challenging as it is not easy to capture spatiotemporal traffic patterns, including explicit and latent features. In this study, we propose an augmented tensor factorization model by incorporating generic forms of domain knowledge from transportation systems. Specifically, we present a fully Bayesian framework for automatically learning parameters of this model using variational Bayes (VB). Relying on the publicly available urban traffic speed data set collected in Guangzhou, China, experiments on two types of missing data scenarios (i.e., random and non-random) demonstrate that the proposed Bayesian augmented tensor factorization (BATF) model achieves best imputation accuracies and outperforms the state-of-the-art baselines (e.g., Bayesian tensor factorization models). Besides, we discover interpretable patterns from the experimentally learned global parameter, biases, and latent factors that indeed conform to the dynamic of traffic states.

A Novel Spatio-Temporal Model for City-Scale Traffic Speed Prediction

City-scale traffic speed prediction provides significant data foundation for the intelligent transportation system, which enriches commuters with up-to-date information about traffic condition. However, predicting on-road vehicle speed accurately is challenging, as the speed of the vehicle on the urban road is affected by various types of factors. These factors can be categorized into three main aspects, which are temporal, spatial, and other latent information. In this paper, we propose a novel spatio-temporal model named L-U-Net based on U-Net as well as long short-term memory architecture and develop an effective speed prediction model, which is capable of forecasting city-scale traffic conditions. It is worth noting that our model can avoid the high complexity and uncertainty of subjective features extraction and can be easily extended to solve other spatio-temporal prediction problems such as flow prediction. The experimental results demonstrate that the prediction model we proposed can forecast urban traffic speed effectively.

EFFECTS OF THE RAINSTORM ON URBAN ROAD TRAFFIC SPEED — A CASE STUDY OF SHENZHEN, CHINA

Abstract. The adverse weather may significantly impact urban traffic speed and travel time. Understanding the influence of the rainstorm to urban traffic speed is of great importance for traffic management under stormy weather. This study aims to investigate the impact of rainfall intensity on traffic speed in the Shenzhen (China) during the period 1 July 2015–31 August 2016. The analysis was carried out for five 1-h periods on weekdays during the morning periods (6:00 AM–11:00 AM). Taxi-enabled GPS tracking data obtained from Shenzhen city are used in the analysis. There are several findings in this study. Firstly, nearly half of the roads are significantly affected by the rainstorm. Secondly, the proportion of positive correlated roads is about 35 %, but there still are some roads with uncorrelated traffic speed variation rates (SVR) and rainfall intensities. Thirdly, the impact of the rainstorm on traffic speed is not homogeneous but with obvious spatial difference. This research provides useful information that can be used in traffic management on a city-wide scale under stormy weather.

Monitoring Noise Pollution in Urban Area Through SUNET System

Modelling the sound pressure levels of traffic noise at any location in an urban area requires a series of steps in order to collect, collat and report data, in accordance with the European Community legislation (Directive 2002/49/EC of the European Parliament and of the Council of 25 June 2002). The present paper presents a model performed through SUNET (System for Urban Noise and Eco-Traffic ) system, including data collection equipment (Sound Metter Level UC2010-2, Weather Station (Tehno Line WS 550), software to process them (SoundPLAN) and harmonised indicators (L den and L night - A-weighted long-term average sound level as defined in ISO 1996-2: 1987) in order to validate the results. The study refers to a major road section in agglomeration Cluj-Napoca and considers all aspects regarding the urban area (type of road, architecture, buildings etc.) and traffic (speed, traffic composition, traffic density flow etc.). Measurements made in major roads in Cluj-Napoca reveal overcoming of limit values for almost all intervals of day. Even if for the road network from Cluj-Napoca, many actions were taken, like lower speed limits, heavy traffic prohibited, improved surface course, the maximum values allowed for 2012 are exceeded and more actions are needed in order to achieve these targets. Monitoring noise levels on the urban road network through the equipment and methods according to the law leads to actual results and an appropriate implementation of action plans.

An averaging approach to estimate urban traffic speed using large-scale origin-destination data

Knowledge about the driving condition can be exploited by the energy management system of plug-in hybrid electric vehicle (PHEV) to optimise its fuel economy. However, estimating urban traffic speed can be a challenging problem, since the complexity of the road network requires a large amount of sensing coverage. GPS equipped vehicles have been used to address this problem, despite the drawback of high transmission cost due to the periodic locations reporting during the entire trip. This paper presents an alternative method to estimate urban traffic speed when only the trip distance, origin, destination and trip time are known, without the detailed information about the vehicle trajectory. Taxicab fleet data is used due to its wide area-coverage and large data availability. One month (15 million) observations of taxi origin-destination data in New York City is processed using cluster computers to create a traffic speed model of Manhattan at different times of day. The developed average traffic speed model is able to accurately predict the recorded trip duration from the taxicab data, and therefore, can be used to estimate energy consumption and optimise PHEV control.

Comprehensive Pricing Model of Urban Traffic Air Pollution Based on Bi-Level Programming

In order to reduce the negative impact of urban traffic air pollution, this paper firstly analyzes the relationship between urban traffic air pollution and vehicle speed, after providing the relationship model, the paper establishes a comprehensive pricing model of urban traffic air pollution based on bi-level programming, the model considers the traffic air pollution pricing, and includes the factors of congestion pricing, bus fee, pricing revenue redistribution on improvement of public transport services and the expansion of road capacity. The case study shows that the implementation of comprehensive pricing of urban traffic air pollution can reduce traffic pollution and unreasonable traffic flow, which is conducive to the sustainable development of the city.

The Impacts of Emergency Vehicle Signal Preemption on Urban Traffic Speed

We used GPS data from paratransit vehicles to evaluate the impact of emergency vehicles on urban traffic speeds. The results indicate that speed variance is significantly higher during emergency preemption and the mean speeds of traffic flowing in the same direction as the emergency vehicle and on crossing streets are lower during preemption than during normal conditions. Regression results indicate that traffic on major arterials and traffic in the opposite direction of the emergency vehicle tend to have higher speed during signal preemption. Signal preemption during peak periods and duration of preemption had a significant negative impact on traffic speeds. Also, the transition time has a negative impact on traffic speeds. The authors recommend further research on how to optimize (minimize) the preemption duration as well as transition time. Also, the impact of median type and number of lanes should be evaluated.

Estimation of Turkish road transport emissions

Using the COPERT III program, an inventory of Turkish road transport emissions was calculated and the contributions of road transport to global and local air pollutant emissions were examined for the year 2004. It was observed that passenger cars are the main source of CO, HC, and Pb emissions while heavy duty vehicles are mainly responsible for NO x , particulate matter (PM), and SO 2 emissions. Taking the emissions for the year 2004 as the baseline, a parametric study was conducted to determine the emission reduction potentials of different road transport strategies. The results indicated that the following road transport strategies; fleet renewal, promotion of public transportation, and faster urban traffic speed are very effective strategies for reducing regulated emissions and fuel consumption (FC) from a technical point of view. It was also noted that replacement of two-stroke motorcycles with four-stroke motorcycles is as effective as fleet renewal in reducing HC emissions.

The effects of mobile roadside speedometers on traffic speeds

A study was conducted to evaluate mobile roadside speedometers as a means of controlling urban traffic speeds under varied schedules of deployment and speed limit law enforcement. Speeds of cars passing the roadside speedometer were measured using nondetectable radar. The data indicate that, generally, the speedometer's presence reduced average traffic speeds by about 10% alongside the speedometer and about 7% at short distances downstream. The proportion of drivers exceeding the speed limit by at least 10 mph fell dramatically from 15%–20% to only 2% at one site on days the speedometer was deployed, and the device was particularly effective when deployed in school zones. However, the effect of the speedometer was limited to the times when it was actually deployed. Associated police enforcement is a key factor, as the effect of the speedometer decayed over time but could be long lasting with a minimal amount of enforcement activity in the area of the speedometer.

On Macroscopic Description of Urban Traffic Speeds

(1993). On Macroscopic Description of Urban Traffic Speeds. Journal of the Operational Research Society: Vol. 44, No. 2, pp. 209-210.

On Macroscopic Description of Urban Traffic Speeds: Response

On Macroscopic Description of Urban Traffic Speeds: Response

On Macroscopic Description of Urban Traffic Speeds: Response

"On Macroscopic Description of Urban Traffic Speeds: Response." Journal of the Operational Research Society, 44(2), p. 210

On Macroscopic Description of Urban Traffic Speeds

On Macroscopic Description of Urban Traffic Speeds

Urban Traffic Speeds—I: A Comparison of Proposed Expressions Relating Journey Speed to Distance from a Town Center

One of the best descriptors of traffic in a town is its speed and some knowledge of the way that it varies is clearly of interest and importance. This paper compares the suitability of five formulas that relate journey speed to distance from a town center for six towns in England and Wales. The formula that gives the most consistently good fit to the data from the towns studied here is of the form v = a − becr, where v is journey speed at radial distance r, and a, b, c, are constants. However, a formula of the power form v = arb also provides a reasonable description of the data from the towns studied. Although not necessarily being the best fitting formula for individual towns, the ease of use and interpretation of this power function and the fact that it requires only two constants may make it preferable for many studies of the variation of speed within towns. The disadvantage that this formula predicts zero speed at a town center is of little practical importance, since in practice, it can give fairly good estimates of the time taken to reach points in the neighborhood of the town center. It is also concluded that the wide variation of speeds at any particular distance from the center of the one town for which this was examined can be partly explained by the variation between radial routes.

Urban Traffic Speeds—II: Relation of the Parameters of Two Simpler Models to Size of the City and Time of Day

Using the data collected by the RRL in 1967 for eight English cities, average speeds on major roads have been calculated as a function of distance from the city center. Two rather simple types of function have been fitted to this empirical data, namely v = k · r1/3 and v = 60 − a · e−r/R, and the values of their parameters have been found to be related to the city size and to whether the observations were made in the peak or the off-peak periods. Data from other studies, in London and Göteborg (Sweden), are adduced to support the conclusions drawn.