Year 2017, Volume 3, Issue 2, Pages 1 - 18 2017-12-30

Adaptive Traffic Signal Control with Radial Basis Function Networks
Radyal Tabanlı Fonksiyon Ağları İle Adaptif Trafik Sinyal Kontrolü

Burcu ÇAĞLAR GENÇOSMAN [1]

30 72

In this study, a real-world isolated signalized intersection, which is controlled by the fixed-time signalization system, is considered. The numbers of arrivals are determined by the magnetic sensors embedded to lanes, and recorded to the database. In order to find the appropriate green time for each phase considering the adaptive traffic signal control system, the number of arrivals are grouped for a specific time interval, and simulations are performed using the arrivals and other information about vehicle movements gathered from the real world. Thus, the data set is constructed with arrivals and green times for each lane. One of the most popular artificial neural network (ANN) method; the Radial Basis Function (RBF) network is developed to predict the green times with adaptive traffic signal control system. The RBF network structure includes one hidden layer, four input neurons and four output neurons representing the arrivals and the green times for each lane respectively. The dataset, which consists of the data collected from the actual system for the specific time interval and the green times determined by the simulation, is divided into training and test sets. Then, these sets are used to analyze the performance of the RBF network. The estimated green times obtained by the RBF network is compared with the simulation outputs, and it is discovered that the RBF network is a successful method to predict adaptive green times.

Bu çalışmada sabit zamanlı sinyalizasyon sistemine sahip gerçek bir izole sinyalize kavşak ele alınmıştır. Kavşakta bulunan şeritlere yerleştirilen manyetik sensörler ile sisteme gelen araç sayıları anlık olarak veritabanına kaydedilmiştir. Tam trafik uyarmalı adaptif sinyalizasyon göz önünde bulundurularak, her faz için uygun adaptif yeşil süreleri bulmak için gerçek sistemden kavşağa gelen araç sayıları belirli bir zaman aralığı için gruplandırılmış ve sistemden toplanan diğer kavşak girdi parametreleri de kullanılarak simülasyonlar gerçekleştirilmiştir. Böylece her şerit için geliş adetlerini ve adaptif yeşil süreleri barındıran bir veritabanı oluşturulmuştur. Adaptif sinyal kontrol sistemi ile yeşil sürelerin tahmin edilmesinde, popüler Yapay Sinir Ağı (YSA) modellerinden olan Radyal Tabanlı Fonksiyon (RBF) ağları kullanılmıştır. RBF ağı gelişleri temsil eden bir girdi katmanı, yeşil süreleri temsil eden bir çıktı katmanı ve bir gizli katmandan oluşmaktadır. Belirli aralıklarda toplanan geliş adetlerini ve bu geliş adetlerine göre simülasyon ile belirlenen adaptif yeşil süreleri barındıran veritabanı eğitim ve test kümesine ayrılmıştır. Bu kümeler RBF ağının eğitiminde ve performans analizinde kullanılmıştır. RBF ağı ile tahmin edilen yeşil süreler simülasyon çıktıları ile karşılaştırılmış ve RBF ağının adaptif yeşil sürelerin tahmininde başarılı bir yöntem olduğu gözlenmiştir.

  • Abdulhai, B., Pringle, R., & Karakoulas, G. J. (2003). Reinforcement learning for true adaptive traffic signal control. Journal of Transportation Engineering, 129(3), 278-285.
  • Angulo, E., Romero, F. P., García, R., Serrano-Guerrero, J., & Olivas, J. A. (2011). An adaptive approach to enhanced traffic signal optimization by using soft-computing techniques. Expert Systems with Applications, 38(3), 2235-2247.
  • Araghi, S., Khosravi, A., & Creighton, D. (2015). A review on computational intelligence methods for controlling traffic signal timing. Expert systems with applications, 42(3), 1538-1550.
  • Arel, I., Liu, C., Urbanik, T., & Kohls, A. G. (2010). Reinforcement learning-based multi-agent system for network traffic signal control. IET Intelligent Transport Systems, 4(2), 128-135.
  • Başkan, Ö. (2004). İzole Sinyalize Kavşaklardaki Ortalama Taşıt Gecikmelerinin Yapay Sinir Ağları İle Modellenmesi. Fen Bilimleri Enstitüsü, İnşaat Mühendisliği Anabilim Dalı Yüksek Lisans Tezi, Denizli.
  • Gora, P. (2011). A genetic algorithm approach to optimization of vehicular traffic in cities by means of configuring traffic lights. Emerging Intelligent Technologies in Industry, Springer Berlin Heidelberg. 1-10.
  • Grégoire, P. L., Desjardins, C., Laumônier, J., & Chaib-draa, B. (2007). Urban traffic control based on learning agents. In Intelligent Transportation Systems Conference, ITSC 2007, 916-921.
  • Gündoğan, F., Karagöz, Z., Koçyiğit, N., Karadağ, A., Ceylan, H., & Murat, Y. Ş. (2014). An evaluation of adaptive traffic system control in İstanbul. Journal of Traffic and Logistics Engineering, 2(3), 198-201.
  • Haykin, S. S. (2009). Neural networks and learning machines. Pearson Vol.3, Upper Saddle River, NJ, USA.
  • He, J., & Hou, Z. (2012). Ant colony algorithm for traffic signal timing optimization. Advances in Engineering Software, 43(1), 14-18.
  • Hornik, K., Stinchcombe, M., & White, H. (1990). Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural networks, 3(5), 551-560.
  • Lee, J., Abdulhai, B., Shalaby, A., & Chung, E.-H. (2005). Real-time optimization for adaptive traffic signal control using genetic algorithms. Journal of Intelligent Transportation Systems: Technology, Planning, and Operations, 9(3), 111–122.
  • Liu, Z. (2007). A survey of intelligence methods in urban traffic signal control. IJCSNS International Journal of Computer Science and Network Security, 7(7), 105-112.
  • Mannion, P., Duggan, J., & Howley, E. (2016). An experimental review of reinforcement learning algorithms for adaptive traffic signal control. In Autonomic Road Transport Support Systems, 47-66.
  • Okkan, U., & Dalkılıç, H. Y. (2012). Radyal tabanlı yapay sinir ağları ile Kemer Barajı aylık akımlarının modellenmesi. Teknik Dergi, 23(112), 5957-5966.
  • Öztemel, E. (2003). Yapay Sinir Ağları. PapatyaYayıncılık, 1.Basım, Istanbul.
  • Prashanth, L. A., & Bhatnagar, S. (2011). Reinforcement learning with function approximation for traffic signal control. Intelligent Transportation Systems, IEEE Transactions on, 12(2), 412-421.
  • Spall, J. C., & Chin, D. C. (1997). Traffic-responsive signal timing for system-wide traffic control. Transportation Research Part C: Emerging Technologies, 5(3), 153-163.
  • Srinivasan, D., Choy, M. C., & Cheu, R. L. (2006). Neural networks for real-time traffic signal control. Intelligent Transportation Systems, IEEE Transactions, 7(3), 261-272.
  • Wen, Y., & Wu, T. (2005). Reduced-order rolling horizon optimization of traffic control based on ant algorithm. Journal-Zhejiang University Engineering Science, 39(6), 835.
  • Zhu, J. Z., Cao, J. X., & Zhu, Y. (2014). Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the adjacent intersections. Transportation Research Part C: Emerging Technologies, 47, 139-154.
Primary Language tr
Subjects
Journal Section Articles
Authors

Author: Burcu ÇAĞLAR GENÇOSMAN (Primary Author)

Bibtex @research article { jocrest454884, journal = {Journal of Current Researches on Engineering, Science and Technology}, issn = {}, eissn = {2651-2521}, address = {Huriye UÇAR}, year = {2017}, volume = {3}, pages = {1 - 18}, doi = {}, title = {Radyal Tabanlı Fonksiyon Ağları İle Adaptif Trafik Sinyal Kontrolü}, key = {cite}, author = {ÇAĞLAR GENÇOSMAN, Burcu} }
APA ÇAĞLAR GENÇOSMAN, B . (2017). Radyal Tabanlı Fonksiyon Ağları İle Adaptif Trafik Sinyal Kontrolü. Journal of Current Researches on Engineering, Science and Technology, 3 (2), 1-18. Retrieved from http://dergipark.org.tr/jocrest/issue/38918/454884
MLA ÇAĞLAR GENÇOSMAN, B . "Radyal Tabanlı Fonksiyon Ağları İle Adaptif Trafik Sinyal Kontrolü". Journal of Current Researches on Engineering, Science and Technology 3 (2017): 1-18 <http://dergipark.org.tr/jocrest/issue/38918/454884>
Chicago ÇAĞLAR GENÇOSMAN, B . "Radyal Tabanlı Fonksiyon Ağları İle Adaptif Trafik Sinyal Kontrolü". Journal of Current Researches on Engineering, Science and Technology 3 (2017): 1-18
RIS TY - JOUR T1 - Radyal Tabanlı Fonksiyon Ağları İle Adaptif Trafik Sinyal Kontrolü AU - Burcu ÇAĞLAR GENÇOSMAN Y1 - 2017 PY - 2017 N1 - DO - T2 - Journal of Current Researches on Engineering, Science and Technology JF - Journal JO - JOR SP - 1 EP - 18 VL - 3 IS - 2 SN - -2651-2521 M3 - UR - Y2 - 2019 ER -
EndNote %0 Journal of Current Researches on Engineering, Science and Technology Radyal Tabanlı Fonksiyon Ağları İle Adaptif Trafik Sinyal Kontrolü %A Burcu ÇAĞLAR GENÇOSMAN %T Radyal Tabanlı Fonksiyon Ağları İle Adaptif Trafik Sinyal Kontrolü %D 2017 %J Journal of Current Researches on Engineering, Science and Technology %P -2651-2521 %V 3 %N 2 %R %U
ISNAD ÇAĞLAR GENÇOSMAN, Burcu . "Radyal Tabanlı Fonksiyon Ağları İle Adaptif Trafik Sinyal Kontrolü". Journal of Current Researches on Engineering, Science and Technology 3 / 2 (December 2017): 1-18.