Wendy Weijermars

Predictions of Urban Volumes in Single Time Series

Congestion is increasing in many urban areas. This has led to a growing awareness of the importance of accurate traffic-flow predictions. In this paper, we introduce a prediction scheme that is based on an extensive study of volume patterns that were collected at about 20 urban intersections in the city of Almelo, The Netherlands. The scheme can be used for both short- and long-term predictions. It consists of 1) baseline predictions for a given preselected day, 2) predictions for the next 24 h, and 3) short-term predictions with horizons smaller than 80 min. We show that the predictions significantly improve when we adopt some straightforward assumptions about the correlations between and the noise levels within volumes. We conclude that 24-h predictions are much more accurate than baseline predictions and that errors in short-term predictions are even negligibly small during working days. We used a heuristic approach to optimize the model. As a consequence, our model is quite simple so that it can easily be used for practical applications.

Analyzing highway flow patterns using cluster analysis

Historical traffic patterns can be used for the prediction of traffic flows, as input for macroscopic traffic models, for the imputation of missing or erroneous data and as a basis for traffic management scenarios. This paper investigates the determination of historical traffic patterns by means of Wards hierarchical clustering procedure. Days were clustered before and after a pre-classification into working days and non-working days, using two different definitions of a daily traffic profile. The results of the clustering after preclassification are clearly better than before classification. Moreover, working days are easier to classify into distinctive, recurrent traffic patterns than non-working days. Finally, clustering on the basis of 15 minutes traffic flows resulted in a better classification of working days than the two-step clustering that used the total daily traffic flow, peak flows, peak times and ratios. The clustering on the basis of 15 minutes traffic flows resulted in a classification into five clusters that show distinct daily flow profiles and are representative for the days within the clusters. The day of the week and vacation periods are determinative for the cluster a working day is classified to.

Detection of invalid loop detector data in urban areas

Urban traffic data can be used for purposes besides actuated signal control. However, it is important for the data to be of sufficient quality. This paper discusses a procedure for detecting invalid traffic data produced by single-loop detectors at signalized intersections. Basic quality checks—based on minimum and maximum flow thresholds—are used to detect erroneous data, whereas quality checks based on the principle of conservation of vehicles are introduced to detect inaccurate data. In most cases, the principle of conservation of vehicles implies that flow measurements have to be consistent between upstream and monitoring detectors within one intersection. The basic quality checks are appropriate for detecting erroneous data. Moreover, quality checks based on the principle of conservation of vehicles are a useful addition to basic quality checks, because they are appropriate for detecting inaccurate traffic data not detected by the basic quality checks. However, because flows are inconsistent between ...

Daily Flow Profiles Of Urban Traffic

Estimation of average annual daily traffic (AADT) on the basis of short-term traffic counts provides some insight into seasonal and day-to-day variability of urban traffic flows. However, insights into the differences in daily flow profiles between weekdays are limited. In this paper, daily flow profiles on a main route in a city in the Netherlands are analyzed. The total amount of traffic as the shapes of the daily profiles are also compared for various weekdays. The differences are examined both qualitatively and quantitatively using ANOVA analysis. Findings, indicating that the daily flow profile varies throughout the week, are presented.