Unraveling Traffic Patterns: An Evaluation of Chaos Theory for Daily Traffic Estimation
Abstract
Intercity road traffic volumes are typically calculated using probability
functions, statistical methods, or meta-heuristic methods like artificial
neural networks. Road traffic volumes are calculated using pattern
recognition techniques since they depend on input variables such
as the geometry of the road, the time of day or night, weekends or
holidays, and other factors. The primary goal of this research project is
to evaluate how well the chaos theory performs when used to estimate
daily traffic volume utilising chaotic patterns. In this study, the daily
traffic volume on intercity routes is analysed for chaotic behaviour,
and the effectiveness of the chaos theory is reviewed and contrasted
with probability functions. Data collected over the course of a year
by installed automatic traffic counters were utilised in the analytical
process to establish chaos factor as the ratio between the minimum
and maximum daily traffic volume. The findings showed that daily
traffic levels exhibit chaotic behaviour during a specified twenty-fourhour
period. They also demonstrate that, for projecting daily traffic
volume, the application of chaos theory is stronger than the uniform
distribution function and inferior to the normal distribution function.
References
2. Ashok, K. and Ben-Akiva, M. E. (2002) “Estimation and prediction of time-depend- ent origin-destination flows with a stochastic mapping to path flows and link flows”, Trans- portation Science, Vol. 36, pp. 184-198
3. Bodle, R. (1967) “Evaluation of rural cover- age count duration for estimating annual aver- age daily traffic”,
Highway Research Record, Vol. 199, pp. 67-77
4. Caggiani, L., Dell’Orco, M., Marinelli, M. and Ottomanelli, M. (2012) “A meta-heuristic dynamic
traffic assignment model for O-D matrix estimation using aggregate data”, Pro- cedia - Social and Behavioral
Sciences, Vol. 54, pp. 685 – 695
5. Faghri, A. and Hua, J. (1995) “Roadway sea- sonal classification using neural networks”, Journal of
Computing in Civil Engineering, Vol. 9, No. 3, pp. 209- 215
6. Frazier, C. and Kockelman, K. M. (2004) “Chaos theory and transportation systems: In- structive example”,
Journal of Transportation Research Board, No. 1897, TRB, National Re- search Council, Washington, D.C.,
pp. 9–17
7. Gecchele G, Caprini A, Gastaldi M. Data mining methods for traffic monitoring data analysis. A case study”,
Procedia Social and Behavioral Sciences, 2011; 20: 455-464
8. Gleick, J. (1987) “Chaos: making a new sci- ence”, Copyright Vintage publishing compa- ny.
9. Juran, I., Prashker, J.N., Bekhor, S. and Ishai, I. (2009) “A dynamic traffic assignment mod- el for the assessment
of moving bottlenecks”, Transportation Research, Part C, Vol. 17, No. 3, pp. 240-258
10. Kiel, L. D. and Elliott, E. (1996) “Chaos theory in the social sciences, foundations and applications”,
University of Michigan.
11. Lawrence, W. L., Feng, Y. L. and Huang, Y. C. (2003) “Diagnosis of freeway traffic inci- dents with
chaos theory”, Journal of Eastern Asia Society for Transportation Studies, Vol. 5, pp. 2025-2038
12. Lingras, P. (1995) “Hierarchical grouping versus Kohonen neural networks”, Journal of ransportation
Engineering, Vol. 121(4): 364-368
13. Lingras P. 1995; Statistical and genetic al- gorithms classification of highways”, Journal of Transportation
Engineering, Vol. 127, No. 3, pp. 237- 243
14. Mahmoudabadi, A. and Fakharian, S. (2010) “Estimating missing traffic data using artifi- cial neural network”,
Proceedings of Second International Conference on Intelligent Net- work and Computing (ICINC 2010), Novem- ber 26 - 28, 2010, Kuala Lumpur, Malaysia, Vol. 2, pp. 144-147
15. Mahmoudabadi, A. and Ghazizadeh, A. (2013) “A hybrid PSO-fuzzy model for de- termining the category of
85th speed”, Jour- nal of Optimization, Volume 2013 Article ID 964262 Mahmoudabadi A. and Seyedhosseini
S. M. (2012
16. Application of chaos theory in haz- ardous materials transportation”, International Journal of Transportation
Engineering, Vol. 1, No. 1, pp. 15-22
17. Mahmoudabadi, A. and Seyedhosseini, S. M. (2012) “Time-risk tradeoff of hazmat routing problem in emergency situation”, Proceedings of the 2012 International Conference on In- dustrial Engineering and Operations Manage- ment, Istanbul, Turkey, July 3 – 6, 2012, pp. 344-351
18. Mingjun, J. and Huanwen, T. (2004) “Appli- cation of chaos in simulated annealing”, Cha- os, Solitons &
Fractals, Vol. 21, pp. 933–941
19. Rossi, R., Gastaldi, M., Gecchele, G. and Kikuchi, S. (2012) “Estimation of annual av- erage daily truck
traffic volume, uncertainty treatment and data collection requirements”, Procedia - Social and
Behavioral Sciences, Vol. 54, pp. 845 – 856 -Sharma, S. C. and Werner, A. (1981) “Im- proved method of
grouping province wide permanent traffic counters”, Transportation Research Record, Vol. 815, pp. 12-18 20. Sugihara, G. and May, R. M. (1990) “Non-
21. linear forecasting as a way of distinguishing chaos from measurement error in time series”, Nature, Vol. 344, pp. 734-741
22. Trepaniera, M., Leroux, M. H. and Marcel- lis-Warin, N. (2009) “Cross-analysis of haz- mat road accidents using
multiple databases”, Accident Analysis and Prevention, Vol. 41, pp. 1192–1198
23. Xh, Y., Yb, Y. and Zhang, Y. C. (2002) “A
24. hybrid chaotic genetic algorithm for short- term hydro system scheduling”, Mathematical Computer
Simulation Vol. 59, pp. 319–27
25. Zhao F, Li MY,Chow L. Al- ternatives for estimating seasonal factors on rural and urban roads in Florida”,
Research Office, Florida Department of Transportation 2004
