PROJECT TITLE :
Trend Modeling for Traffic Time Series Analysis: An Integrated Study
This paper discusses the trend modeling for traffic time series. First, we recount two types of definitions for an extended-term trend that appeared in previous studies and illustrate their intrinsic variations. We show that, by assuming an implicit temporal association among the time series observed at different days/locations, the PCA trend brings many blessings to traffic time series analysis. We have a tendency to conjointly describe and outline the so-called short-term trend that can't be characterized by existing definitions. Second, we tend to sequentially review the role that trend modeling plays in four major issues in traffic time series analysis: abnormal knowledge detection, information compression, missing data imputation, and traffic prediction. The relations between these issues are revealed, and the advantage of detrending is explained. For the primary three issues, we tend to summarize our findings in the last 10 years and strive to supply an integrated framework for future study. For traffic prediction downside, we have a tendency to present a new explanation on why prediction accuracy will be improved at data points representing the short-term trends if the traffic info from multiple sensors will be appropriately used. This finding indicates that the trend modeling is not only a method to specify the temporal pattern but is also connected to the spatial relation of traffic time series.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here