Establishment of Confidence Intervals for Average Vehicle Speeds

Abstract

Accurate forecasting of the average speed of vehicles is important for early detection of traffic congestion and density, as well as for the correct reporting of the green wave mode. For this purpose, to evaluate the forecasting of traffic indicators using the artificial intelligence method a confidence interval was established on the example of the city of Baku, the capital of the Republic of Azerbaijan. However, this confidence interval includes forecasts for the next few days based on observations of existing roads, not of planned and reconstructed roads. During the preparation of the report, the first 21 days of April 2019 were selected and based on the obtained data, the objective numerical assessment of the quantitative anticipation for the number of hours in a day, standardized deviation's objective statistical approximation, the quantile of the Student’s distribution, the lower limit, the upper limit and the values of the difference between them were determined, as well as the degree of freedom and the computed confidence interval. As a result of the reports, one confidence interval is given for each hour of the day, in which the indicator falls into this interval with 95% of the following days. It is also possible to determine the recommended speed limit, which is the most important part of the green wave mode, with the help of the mentioned prediction.

Keywords

• confidence interval
• average speed of vehicles
• traffic flow
• green wave
• recommended speed of movement
• road traffic management

Ortalama Araç Hızları İçin Güven Aralıklarının Oluşturulması

Abstract

Araçların ortalama hızlarının doğru tahmin edilmesi trafik sıkışıklığının ve yoğunluğunun erken tespiti ve aynı zamanda yeşil dalga modunun doğru raporlanması için önemlidir. Bu amaçla yapay zeka yöntemi kullanılarak trafik göstergelerinin tahminini değerlendirmek için Azerbaycan Cumhuriyeti'nin başkenti Bakü şehri örneğinde bir güven aralığı oluşturulmuştur. Ancak bu güven aralığı, planlanan ve yeniden yapılan yollara değil, mevcut yollara ilişkin gözlemlere dayalı olarak önümüzdeki birkaç gün için tahminleri içerir. Raporun hazırlanması sırasında 2019 Nisan ayının ilk 21 günü seçilmiş ve elde edilen verilere göre günün saatlerine ilişkin matematiksel beklenti için yansız istatistiksel tahmin, standart sapma için yansız istatistiksel tahmin, Student dağılımı, alt sınır, üst sınır ve aralarındaki farkın değerleri belirlenmiş, ayrıca serbestlik derecesi ve güven aralığı hesaplanmıştır. Raporlamalar sonucunda günün her saati için bu güven aralığı verilir ve gösterge takip eden günlerin %95'i ile bu aralığa düşer. Bahsi geçen tahmin yardımıyla yeşil dalga modunun en önemli parçası olan tavsiye edilen hız limitini belirlemek de mümkün olmaktadır.

Keywords

• : güven aralığı
• araçların ortalama hızı
• trafik akışı
• yeşil dalga
• önerilen hareket hızı
• karayolu trafik yönetimi

References

1. Ahmadov, G. M., & Baghirov, M. I. (2019). Application of Coordinated Regulatory System on Matbuat Avenue During Off-Peak Hours of the Day. Scientific Works, 4, 4.
2. Chen, L., Xing, Y., Zhang, J., & Na, X. (2018). Levenberg–Marquardt backpropagation training of multilayer neural networks for state estimation of a safety-critical cyber-physical system. IEEE Transactions on Industrial Informatics, 14(8), 3436–3446. doi: 10.1109/TII.2017.2777460
3. Chen, Z., Wang, B., & Gorban A. N. (2020). Multivariate Gaussian and Student-t process regression for multi-output prediction. Neural Computing and Applications, 32(8), 3005–3028. doi: 10.1007/s00521-019-04687-8
4. Hurst, S. (2010). The Characteristic Function of the Student t-Distribution (Financial Mathematics Research Report No. 95/6). Canberra: Centre for Mathematics and its Applications, School of Mathematical Sciences, ANU. https://www.worldcat.org/title/characteristic-function-of-the-student-t-distribution/oclc/37065789
5. Jiang, H., & Learned-Miller, E. (2017). Face detection with the faster R-CNN Proceedings of the 12th IEEE International Conference on Automatic Face & Gesture Recognition, 650–657. doi: 10.1109/FG.2017.82
6. Jing, J., Filev, D., Kurt, A., Ozatay, E., Michelini, J., & Ozguner U. (2017). Vehicle speed prediction using a cooperative method of fuzzy Markov model and autoregressive model. Proceedings of the IEEE Intelligent Vehicles Symposium, 881–886.
7. Kai, C., Yi, Z., & Fangyan D. (2015) A LSTM-based method for stock returns prediction: a case study of China stock market. Proceedings of the IEEE International Conference on Big Data (Big Data), 2823–2824. doi: 10.1109/BigData.2015.7364089
8. Lefèvre, S., Sun, Ch., Bajcsy, R., & Laugier, C. (2014). Comparison of parametric and non-parametric approaches for vehicle speed prediction. Proceedings of the American Control Conference, 3494-3499. doi: 10.1109/ACC.2014.6858871

9. Lu, K., Xin, T., Shuyan, J., Jianmin, X., & Yinhai, W. (2022). Optimization model for regional green wave coordinated control based on ring-and-barrier structure. Journal of Intelligent Transportation Systems, 26(1), 68-80. doi:10.1080/15472450.2020.1795847
10. Moreno-Lopez, M., & Kalita, J. (2017). Deep learning applied to NLP (arXiv:1703.03091vl). doi: 10.48550/arXiv.1703.03091
11. Poznyak, A. S. (2009). 3-Mathematical Expectation, Advanced Mathematical Tools for Automatic Control Engineers: Stochastic Techniques. Elsevier.
12. Sandercock, P.A. (2015). Short History of Confidence Intervals. Stroke, 46(8), 184-187. doi: 10.1161/STROKEAHA.115.007750
13. Shah, A., Wilson, A. G., & Ghahramani Z. (2014). Student-t processes as alternatives to Gaussian processes. Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS), 877–885.
14. Sun, R., Zhuang, X., Wu, Ch., Zhao, G., & Zhang K. (2015). The estimation of vehicle speed and stopping distance by pedestrians crossing streets in a naturalistic traffic environment. Transportation Research Part F: Traffic Psychology and Behaviour, 30, 97–106. doi: 10.1016/j.trf.2015.02.002
15. Thelwall, M., & Fairclough, R. (2017). The accuracy of confidence intervals for field normalized indicators. Journal of Informatics, 11(2), 530-540. doi: 10.1016/j.joi.2017.03.004
16. Valiyev, A. (2013). Baku. Cities, 31, 625-640. doi: 10.1016/j.cities.2012.11.004
17. Xiaolei, M., Zhimin, T., Wang, Y., & Yunpeng, W. (2015). Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C, 54, 187–197. doi: 10.1016/j.trc.2015.03.014
18. Yufang, L., Mingnuo, Ch., & Wanzhong, Zh. (2019). Investigating long-term vehicle speed prediction based on BP-LSTM algorithms. IET Intelligent Transport Systems, 13(8), 1281-1290. doi: 10.1049/iet-its.2018.5593
19. Zhang, J., Shang, H., Li, X., & Yao, Y. (2020). An integrated arterial coordinated control model considering green wave on branch roads and pedestrian crossing time at intersections. Journal of Management Science and Engineering, 5(4), 303-317. doi:10.1016/j.jmse.2020.09.004
20. Zhang, D., Min, L., Lan, Q., Zhang, Y., Jingcheng, L., & Jun, L. (2021). Analytical modeling of piezoelectric 6-degree-of-freedom accelerometer about cross-coupling degree. Measurement, 181. doi: 10.1016/j.measurement.2021.109630