Non-linear analysis of traffic flow

Abstract

Traffic flow prediction is an important application of the ITS technology. In this paper, we applied non-linear timeseries modeling techniques to analyze a traffic data. Our objective is to investigate the deterministic properties of traffic flow using a nonlinear time series analysis technique. The experiment is performed for inductance loop data collected from the San Antonio freeway system. Our study concludes that the traffic data exhibits chaotic properties and techniques based on phase space dynamics can be used to analyze and predict the traffic flow.

Multifractal classification of road traffic flows

“…Here we tried period of 18 h (that is to say, every day from 5:30 AM to 11:30 PM on 1/12/2004). Another reason of the segmentation is that weekend and weekday traffic flow patterns are of a different flavor [11]. The dataset contains the sum of 1200 segments of measurements after segmentation and necessary outlier detection and each have the length of 1080, and the number of samples is sufficient to obtain reliable measures of the multifractal properties.…”

“…The investigation of the temporal fluctuations of traffic flow signals has recently revealed its potential in giving information related to traffic flow prediction [11,13,15,18]. In the study of seemingly complex phenomena such as traffic flow, fractal analysis techniques, developed to draw qualitative and quantitative information from time series, have been applied recently to the study of a large of variety of irregular, nonstationary signals and by now have proved to be very useful to detect deep dynamical features.…”

“…In the study of seemingly complex phenomena such as traffic flow, fractal analysis techniques, developed to draw qualitative and quantitative information from time series, have been applied recently to the study of a large of variety of irregular, nonstationary signals and by now have proved to be very useful to detect deep dynamical features. These methods are mainly useful to detect the presence of long-range powerlaw correlations that have been found to exist in a wide variety of systems [10,11,15]. As soon as they are found, they are generally quantified by a scaling exponent.…”

“…Safanov et al [13] showed that fractal behavior in traffic can due to the delays in human reaction. Nair et al [11] and Shang and Li [15] indicated that fractal and chaotic characteristics exist in the traffic system and techniques based on phase space dynamics can be used to predict the traffic speed.…”

Chaotic analysis of traffic time series

“…Traffic data is highly nonlinear and also varies with times of day [19,22,31]. It changes abruptly when entering or leaving a congestion hour.…”