Bulanık Mantık Destekli Trafik Yoğunluğu Tahmini

Year 2025, Volume: 10 Issue: 3, 184 - 197, 30.09.2025

Cem Özkurt , Ahmet Kala , Kübra Konuk , Ayşe Nur Saylam

https://doi.org/10.46578/humder.1680871

Abstract

Trafik yoğunluğu, modern şehirlerde bireysel seyahat sürelerini uzatan, çevresel kirliliği artıran ve ekonomik kayıplara yol açan önemli bir sorundur. İstanbul gibi büyük metropollerde ortalama trafik yoğunluğu %70'in üzerinde seyrederken, zirve saatlerde %85'e kadar çıkmaktadır. Artan nüfus ve araç sayısı, yalnızca günlük yaşamı zorlaştırmakla kalmayıp, şehir altyapısını da zorlamaktadır. Bu nedenle, trafik yoğunluğunu etkin bir şekilde yönetmek ve tahmin edebilmek, sürdürülebilir ulaşım ve akıllı şehir yönetimi açısından büyük önem taşımaktadır. Ancak, trafiği etkileyen faktörlerin dinamik ve belirsiz yapısı, geleneksel yöntemlerle yeterince doğru tahmin edilememektedir. Bu çalışmada, İstanbul Büyükşehir Belediyesi’nin (İBB) sağladığı 2022 yılına ait saatlik trafik yoğunluğu verileri ve Meteostat kaynaklı hava durumu verileri kullanılarak bulanık mantık tabanlı bir trafik yoğunluğu tahmin modeli geliştirilmiştir. Model, trafik yoğunluğunu etkileyen temel değişkenler olan araç sayısı, ortalama hız, sıcaklık ve yağış durumunu dikkate alarak Mamdani bulanık çıkarım yöntemi ile tasarlanmıştır. Geliştirilen model, doğrusal regresyon ve çoklu doğrusal regresyon gibi geleneksel istatistiksel yöntemlerle karşılaştırılmış ve daha düşük hata oranları ile bağımlı değişkendeki değişimi yüksek oranda açıklamıştır. Bu sonuçlar, bulanık mantık tabanlı sistemlerin belirsizlikleri daha iyi yönetebildiğini ve karmaşık trafik senaryolarında daha esnek ve gerçekçi tahminler üretebildiğini göstermektedir.

Keywords

Trafik Yoğunluğu Tahmini , Bulanık Mantık , Akıllı Ulaşım Sistemleri

Fuzzy Logic-Based Traffic Congestion Prediction

Abstract

Traffic congestion is a major issue in modern cities, leading to longer individual travel times, increased environmental pollution, and economic losses. In large metropolitan areas like Istanbul, the average traffic congestion level exceeds 70%, reaching up to 85% during peak hours. The growing population and number of vehicles not only complicate daily life but also strain urban infrastructure. Therefore, effectively managing and predicting traffic congestion is crucial for sustainable transportation and smart city management. However, the dynamic and uncertain nature of factors influencing traffic makes it difficult to achieve accurate predictions using traditional methods. In this study, a fuzzy logic-based traffic congestion prediction model was developed using hourly traffic congestion data from the Istanbul Metropolitan Municipality (İBB) for 2022 and weather data from Meteostat. The model was designed using the Mamdani fuzzy inference method, considering key variables affecting traffic congestion, including vehicle count, average speed, temperature, and precipitation. The developed model was compared with traditional statistical methods such as linear regression and multiple linear regression and demonstrated a higher ability to explain variations in the dependent variable with lower error rates. These results indicate that fuzzy logic-based systems can better manage uncertainties and generate more flexible and realistic predictions in complex traffic scenarios.

Keywords

Traffic Congestion Prediction , Fuzzy Logic , Intelligent Transportation Systems

References

• Lv, Y. et al. (2015). Traffic flow prediction with big data: A deep learning approach. IEEE Trans. Intell. Transp. Syst., 16(2), 865–873.
• Zhou, Y., & Ding, Y. (2019). Traffic congestion prediction based on XGBoost. Procedia Computer Science, 147, 568–573.
• Wu, Z. et al. (2019). Graph WaveNet for deep spatial-temporal graph modeling. IJCAI, 1907–1913.
• Abdou, A., Farrag, M., & Tolba, A. (2022). A fuzzy logic-based smart traffic management system. Journal of Computer Science, 18(11), 1085–1099.
• Jafari, S., Shahbazi, Z., & Byun, Y. (2021). Traffic control prediction design based on fuzzy logic and Lyapunov approaches to improve the performance of road intersection. Processes, 9(12), 2205.
• Desmira, D., Hamid, M., Bakar, N., Nurtanto, M., & Sunardi, S. (2022). A smart traffic light using a microcontroller based on the fuzzy logic. IAES International Journal of Artificial Intelligence, 11(3), 809–816.
• Mualifah, L., & Abadi, A. (2019). Optimizing the traffic control system of Sultan Agung Street Yogyakarta using fuzzy logic controller. Journal of Physics: Conference Series, 1320(1), 012028.
• İnağ, T., & Arıkan, M. (2024). A fuzzy based intelligent traffic light control (ITLC) method: An implementation in Ankara city. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 13(1), 292–306.
• Chen, W., Zhao, H., Li, T., & Liu, Y. (2015). Intelligent traffic signal controller based on type-2 fuzzy logic and SGAII. Journal of Intelligent & Fuzzy Systems, 29(6), 2611–2618.
• Karyaningsih, D., & Rizky, R. (2020). Implementation of fuzzy Mamdani method for traffic lights smart city in Rangkasbitung, Lebak Regency, Banten Province (Case study of the traffic light T-junction, Cibadak, By Pas Sukarno Hatta Street). Jurnal KomtekInfo, 7(3), 176–185.
• Chabchoub, A., Hamouda, A., Al-Ahmadi, S., & Chérif, A. (2021). Intelligent traffic light controller using fuzzy logic and image processing. International Journal of Advanced Computer Science and Applications, 12(4), 396–399.
• Tripathi, J., Kumar, D., & Singh, U. (2023). A review of different fuzzy models to evaluate vehicular traffic system. SAMRIDDHI: A Journal of Physical Sciences, Engineering and Technology, 15(1), 49–54.
• Nguyen, H., Le, H., Nguyễn, V., & Lam, H. (2024). Development of the intelligent traffic light system based on image processing and fuzzy control techniques. CTU Journal of Innovation and Sustainable Development, 16(3), 9–20.
• Wu, Y. (2024). Enhancing urban traffic flow through fuzzy logic-based signal light control optimization. International Journal of E-Collaboration, 20(1), 1–13.
• Agrawal, A., & Paulus, R. (2021). Smart intersection design for traffic, pedestrian and emergency transit clearance using fuzzy inference system. International Journal of Advanced Computer Science and Applications, 12(3), 516–522.
• Toan, T. (2021). Fuzzy-based quantification of congestion for traffic control. Transport and Communications Science Journal, 72(1), 1–8.
• Naderi, M., Mahdaee, K., & Rahmani, P. (2023). Hierarchical traffic light-aware routing via fuzzy reinforcement learning in software-defined vehicular networks. Peer-to-Peer Networking and Applications, 16(2), 1174–1198.
• Cunha, F., Villas, L., Boukerche, A., Maia, G., Viana, A., Mini, R., & Loureiro, A. A. F. (2016). Data communication in VANETs: Protocols, applications and challenges. Ad Hoc Networks, 44, 90–103.
• Ding, Q., Sun, B., & Zhang, X. (2016). A traffic-light-aware routing protocol based on street connectivity for urban vehicular ad hoc networks. IEEE Communications Letters, 20(8), 1635–1638.
• Collotta, M., Bello, L., & Pau, G. (2015). A novel approach for dynamic traffic lights management based on wireless sensor networks and multiple fuzzy logic controllers. Expert Systems With Applications, 42(13), 5403–5415.
• Sahu, S., Agarwal, R., & Tyagi, R. K. (2019). Fuzzy vehicle control system for single intersection. International Journal of Recent Technology and Engineering, 8(2S7), 457–462.
• Jiang, T., Wang, Z., & Chen, F. (2021). Urban traffic signals timing at four-phase signalized intersection based on optimized two-stage fuzzy control scheme. Mathematical Problems in Engineering, 2021, Article ID 5532568.
• Arifin, M., Razi, S., Haque, A., & Mohammad, N. (2019). A microcontroller based intelligent traffic control system. American Journal of Embedded Systems and Applications, 7(1), 21–26.
• Gupta, R., & Chaudhari, O. (2020). Application of fuzzy logic in prevention of road accidents using multi criteria decision alert. Current Journal of Applied Science and Technology, 39(36), 51–61.
• Zhao, Z. et al. (2017). LSTM network: A deep learning approach for short-term traffic forecast. IET Intelligent Transport Systems, 11(2), 68–75.
• Rudin, C. (2019). Stop explaining black box ML models for high stakes decisions and use interpretable models instead. Nature Machine Intelligence, 1(5), 206–215.
• Meteostat. (2025, March 10). Istanbul climate data (2022). https://meteostat.net/en/place/tr/istanbul?s=17060&t=2022-01-01/2022-12-31.
• İstanbul Büyükşehir Belediyesi. (2025, March 10). Hourly traffic density data set. https://data.ibb.gov.tr/dataset/hourly-traffic-density-data-set