Investigation of Favorable Neural Network Methods to Estimate Traffic Components

Yıl 2023, , 377 - 383, 20.06.2023

Sedat Ozcanan

https://doi.org/10.24012/dumf.1219818

Öz

Neural networks provide the opportunity to estimate specific components of engineering problems. They are decomposed complex problems into different parts. Thus, it can be easy to compete with each of them through neural networks. In this paper, it was purposed to estimate the average speed of a 6-line road’s cross-section by observed traffic variables, such as numbers of vehicles and occupancy values, using radial basis function neural network (RBFNN), generalized regression neural network (GRNN) and the feed-forward back propagation neural network (FFBPNN) models. A comparison was fulfilled between different neural networks and checked against multivariate linear regression (MVLR), a conventional statistical model. After each simulation of neural networks, results show that different forecasts were obtained under the same conditions. The best forecasting is made by FFBPNN, GRNN, and RBFNN, respectively. When compared with multivariate linear regression (MVLR), FFBPNN performs better than MVLR, but GRNN and RBFNN perform lower than it.

Anahtar Kelimeler

Estimate traffic components, Artificial neural network, FFBPNN, RBFNN, GRNN, MVLR, Trafik bileşenlerini tahmin etme, Yapay sinir ağı, FFBPNN, RBFNN, GRNN, MVLR

Trafik Bileşenlerini Tahmin Etmek İçin Uygun Sinir Ağı Yöntemlerinin Araştırılması

Öz

Sinir ağları, mühendislik problemlerinin belirli bileşenlerini tahmin etme fırsatı sağlar. Karmaşık problemleri farklı parçalara ayırırlar. Böylece, sinir ağları aracılığıyla her biri ile rekabet etmek kolay olabilmektedir. Bu çalışmada, radyal tabanlı fonksiyon sinir ağı (RBFNN), genelleştirilmiş regresyon sinir ağı (GRNN) ve ileri beslemeli geri yayılımlı sinir ağı (FFBPNN) modelleri kullanılarak araç sayısı ve yoğunluk/işgal değerleri gibi gözlenen trafik değişkenleri ile 6 hatlı bir yolun enkesitindeki ortalama hızın tahmin edilmesi amaçlanmıştır. Bunun için sinir ağları arasında bir karşılaştırma yapılarak, ayrıca sonuçlar geleneksel bir istatistiksel model olan çok değişkenli doğrusal regresyona (MVLR) ile kontrol edilmiştir. Yapay sinir ağlarının her simülasyonundan sonra, sonuçlar aynı koşullar altında farklı tahminlerin elde edildiğini göstermektedir. En iyi tahmin sırasıyla FFBPNN, GRNN ve RBFNN tarafından yapılmıştır. Çok değişkenli doğrusal regresyon (MVLR) ile karşılaştırıldığında, FFBPNN, MVLR'den daha iyi performans gösterirken GRNN ve RBFNN, ondan daha düşük performans göstermiştir.

Anahtar Kelimeler

Trafik bileşenlerini tahmin etme, Yapay sinir ağı, FFBPNN, RBFNN, GRNN, MVLR

Kaynakça

• [1] M. Oravec, M. Petráš, F. Pilka, “Video Traffic Prediction Using Neural Networks,” Acta Polytechnica Hungarica, Vol. 5, No. 4, 2008.
• [2] C.M. Bishop, Neural Networks for Pattern Recognition; Oxford University Press: Oxford, UK, 1995.
• [3] L. Mussone, and L. Florio, “Neural network models for classification and forecasting of freeway traffic flow stability,” Control Engineering Practice, 4, pp. 153-164, 1996.
• [4] M. S. Dougherty, and M. R. Cobbett, “Short term inter urban traffic forecasts using neural networks” International Journal of Forecasting, 13, pp.21-31, 1997.
• [5] M. Dougherty, M. Van Der Voort, and S. Watson, “Combining Kohonen maps with ARIMA time series models to forecast traffic flow” Transportation Research Part C, 4, pp. 307-318, 1996.
• [6] Chen, H. and Grant Muller, S. “Use of sequential learning for short term traffic flow forecasting” Transportation Research Part C, 9, pp. 319-336, 2001.
• [7] H. Yin, S. C. Wong, J. Xu, and C. K. Wong, “Urban traffic flow prediction using a fuzzy –neural approach” Transportation Research Part C, 10, pp. 85-98, 2002.
• [8] G. Salvo, G. Amato, P. Zito, “Bus speed estimation by neural networks to improve the automatic fleet management” European Transport \ Trasporti Europei n. 37 (2007): 93-104, 2007.
• [9] M. F. Tafti, “The application of artificial neural networks to anticipate the average journey time of traffic in the vicinity of merges” Knowledge-Based Systems, 14, pp. 203-211, 2001.
• [10] La Franca, L., Migliore, M., Salvo, G. and Carollo, F. (2004) “The automatic vehicle monitoring to improve the urban public transport management”, XI convegno CODATU Towards a more attractive Urban Transportation, Bucharest, 22-24 aprile 2004.
• [11] A. Costa, and R.N. Markellos, Evaluating public transport efficiency with neural network models. Transpn Res.-C, Vol.5, No. 5, pp. 301-312, 1997. https://doi.org/10.1016/S0968-090X(97)00017-X
• [12] H.B. Celikoglu, “Application of radial basis function and generalized regression neural networks in non-linear utility function specification for travel mode choice modelling”, Mathematical and Computer Modelling, 44 (2006), pp. 640–658, 2006.
• [13] H. B. Celikoglu, and H. K. Cigizoglu, “Modelling public transport trips by radial basis function neural networks”, Mathematical and computer modelling, pp. 480-489, 2007.
• [14] W. Jiang, "Cellular traffic prediction with machine learning: A survey," Expert Systems with Applications, vol. 201, p. 117163, 2022. [Online]. Available: https://doi.org/10.1016/j.eswa.2022.117163.
• [15] W. Jiang and J. Luo, "Graph neural network for traffic forecasting: A survey," Expert Systems with Applications, vol. 207, p. 117921, 2022. https://doi.org/10.1016/j.eswa.2022.117921
• [16] A. Gedik, "Short-term Traffic Volume Prediction for the Merging Roads by Artificial Neural Network," El-Cezerî Journal of Science and Engineering, vol. 7, no. 3, pp. 1496-1508, 2020. DOI:10.31202/ecjse.773088
• [17] M. Nandal, N. Mor, and H. Sood, An Overview of Use of Artificial Neural Network in Sustainable Transport System, in V. Singh et al. (Eds.), Computational Methods and Advances in Intelligent Systems and Computing, Springer Nature Singapore Pte Ltd., pp. 89-98, 2021. doi: 10.1007/978-981-15-6876-3_7
• [18] W. Jiang, J. Luo, M. He, and W. Gu, "Graph Neural Network for Traffic Forecasting: The Research Progress," ISPRS International Journal of Geo-Information, vol. 12, no. 3, p. 100, 2023. https://doi.org/10.3390/ijgi12030100
• [19] B. Sun, D. Zhao, X. Shi, and Y. He, "Modeling Global Spatial-Temporal Graph Attention Network for Traffic Prediction," IEEE Access, vol. 9, pp. 56594-56604, 2021. doi: 10.1109/ACCESS.2021.3049556.
• [20] W. Long, Z. Xiao, D. Wang, H. Jiang, J. Chen, Y. Li, and M. Alazab, "Unified Spatial-Temporal Neighbor Attention Network for Dynamic Traffic Prediction," IEEE Transactions on Vehicular Technology, vol. 72, no. 2, pp. 1515-1528, 2023. doi: 10.1109/TVT.2022.3157666.
• [21] X. Li, Y. Xu, X. Zhang, W. Shi, Y. Yue, and Q. Li, "Improving short-term bike sharing demand forecast through an irregular convolutional neural network," Transportation Research Part C, vol. 147, p. 103984, 2023. https://doi.org/10.1016/j.trc.2022.103984
• [22] W. Jiang, "Vehicle destination prediction with spatial clustering and machine learning," Internet Technology Letters, e403, 2022. https://doi.org/10.1002/itl2.403
• [23] X. Zhu, H. Fang, H. Jiang, J. Bai, V. Havyarimana, and H. Chen, "Understanding Urban Area Attractiveness Based on Private Car Trajectory Data Using a Deep Learning Approach," IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 8, pp. 12343-12353, 2022. doi: 10.1109/TITS.2022.3121798.
• [24] B. Feng, J. Xu, Y. Zhang, and Y. Lin, "Multi-Step Traffic Speed Prediction Based on Ensemble Learning on an Urban Road Network," Applied Sciences, vol. 11, no. 10, p. 4423, May 2021. doi: 10.3390/app11104423.
• [25] X. Zhan, S. Zhang, W. Y. Szeto, and X. Chen, "Multi-Step-Ahead Traffic Speed Forecasting Using Multi-Output Gradient Boosting Regression Tree," Journal of Intelligent Transportation Systems, vol. 24, no. 2, pp. 125-141, Feb. 2020. doi: 10.1080/15472450.2019.1582950.
• [26] A. T. Karasahin and A. E. Tumer, "Real time traffic signal timing approach based on artificial neural network," MANAS Journal of Engineering, vol. 8, no. 1, pp. 48-54, 2020.
• [27] A. E. Adewale and A. Hadachi, "Neural Networks Model for Travel Time Prediction Based on OD-Travel Time Matrix," IEEE Access, vol. 9, pp. 50819-50829, 2021. doi: 10.1109/ACCESS.2021.3069372.
• [28] Z. Liu, R. Zhang, C. Wang, Z. Xiao, and H. Jiang, "Spatial-Temporal Conv-Sequence Learning With Accident Encoding for Traffic Flow Prediction," IEEE Transactions on Network Science and Engineering, vol. 9, no. 3, pp. 1074-1084, May 2022. doi: 10.1109/TNSE.2022.3087487.
• [29] MATLAB (2022). Matlab and statistics toolbox release (2022b). The MathWorks, Inc., Natick, Massachusetts, USA.
• [30] HCM (2000) “Highway Capacity Manual” Transportation Research Board, National Research Board, 2000, USA.