The Assessment of Applying Chaos Theory for Daily Traffic Estimation

Abstract

Road traffic volumes in intercity roads are generally estimated by probability functions, statistical techniques or meta-heuristic approaches such as artificial neural networks. As the road traffic volumes depend on input variables and mainly road geometrical design, weather conditions, day or night time, weekend or national holidays and so on, these are also estimated by pattern recognition techniques. The main purpose of this research work is to check the using chaotic pattern of daily traffic volume and the performance of chaos theory for estimating daily traffic. In this paper, the existing chaotic behavior in daily traffic volume in intercity roads has been examined and also the performance of chaos theory is discussed and compared to probability functions. The ratio between the minimum and maximum of daily traffic volume is defined as chaos factor, and data, gathered through installed automatic traffic counters over one year, have been used in analytical process. Results revealed that daily traffic volumes have chaotic behavior with defined twenty-four hour time span. They also show that the application of chaos theory is better than uniform distribution function, while weaker than normal distribution function for estimating daily traffic volume.