A new methodology developed to monitor traffic flow

June 9, 2014

The most recent edition of the scientific journal Transportation Research Part B, one of the most recognised in its category, has published the research conducted by Iván Guardiola of the University of Science and Technology of Missouri, Fermín Mallor of the NUP/UPNA-Public University of Navarre, and Teresa León of the University of Valencia. The work has developed a new mathematical methodology to monitor traffic flow so that medium and long-term forecasts can be made.

"If we know not only the volume of the traffic but also the way in which the is taking place, we can detect when the traffic is undergoing a significant change. This information can be used, for example, when decisions are taken about signs (, directions, etc.), road capacity, and other aspects," explained Fermín Mallor, Prof of the Department of Statistics and Operational Research.

What is new about this research is that it applies the so-called curve statistics to the specific problem of or monitoring. The use of the methodology is illustrated by using traffic recorded on an American freeway between 2004 and 2011, although "the methodology, the underlying procedure, can be extrapolated to any spot where we would like to monitor the traffic," pointed out the researcher. It is not just a useful methodology in the context of traffic analysis but when it is properly adapted, it can be applied to the monitoring and control of any phenomenon from which data are gathered at a high frequency rate (something routine thanks to the use of sensors) and whose monitoring is significant for detecting changes (temperature, noise, vibration, etc.).

One of the key aspects of the methodology applied is its capacity to detect changes in traffic flow patterns. This is achieved by combining the functional analysis of data (or curve analyses) and control techniques of a multivariate quality. Curve statistics is a new form of analysis based on the profile or shape that is generated by the data targeted by the study. This mathematical approach allows the data gathered to be put to maximum use by going beyond the traditional analyses based on the creation and study of variables like maximum traffic flow, time it takes to reach maximum flow, total daily flow, etc.

The results make it possible to interpret the main causes responsible for variations in traffic from one day to the next. In the data analysed a very different pattern between working days and public holidays was obtained. It is also possible to quantify the significance of factors like holiday, shopping and travel periods. Its main use, however, is to detect changes in the traffic due, for example, to demographic expansion in nearby areas, the creation of new commercial and leisure areas, etc.

The article highlights four clear advantages in the use of this : the maximum exploitation of the volume of data obtained, the cut in dimensionality, the graphic representation of each daily profile and the development of a method to take strategic decisions.

Explore further: 9 million bicycles, but what about the cars in Beijing?

More information: Guardiola, I., León, T., Mallor, F. (2014). A functional approach to monitor and recognize patterns of daily traffic profiles. Transportation Research Part B, 65: 119-136.

Related Stories

9 million bicycles, but what about the cars in Beijing?

March 27, 2012

Forget the fact of there being "9 million bicycles in Beijing, that's not a fact. Indeed, motor vehicle traffic is fast becoming a big problem that has led to unsustainable pollution and draconian rules in some parts of the ...

Internet traffic rise needs infrastructure upgrade

June 21, 2013

Australian internet traffic will increase by more than five times to hit one exabyte (one billion gigabytes) of data a month by 2016, a University of Adelaide mathematician and internet researcher has predicted.

Faster maintenance for traffic control systems

May 6, 2014

A new app from Siemens halves the time needed for technicians to service intelligent traffic management systems on highways. The automatic display panels on sign gantries are controlled by sensors, and the exchange of data ...

Netflix's share of peak Internet traffic rises

May 14, 2014

Netflix increased its share of fixed-line Internet traffic in North America in the first half of 2014, accounting for 34 percent of data flowing to consumers during peak times, up from 32 percent in the latter half of 2013.

Recommended for you

Nevada researchers trying to turn roadside weed into biofuel

November 26, 2015

Three decades ago, a University of Nevada researcher who obtained one of the first U.S. Energy Department grants to study the potential to turn plants into biofuels became convinced that a roadside weed—curly top gumweed—was ...


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.