Abstract
İstanbul içerisinde her geçen gün artan insan ve araç sayısı beraberinde ciddi bir trafik yoğunluğu getirmektedir. Oluşan bu araç yoğunluğunun giderilmesi veya kontrol edilebilmesi için eldeki verilerin iyi yorumlanması gerekmektedir. İstanbul il sınırları içerisinde ölçümleri yapılan tüm hız verileri İstanbul Büyükşehir Belediyesi tarafından kayıt altına alınmaktadır. Fakat bu verilerin sayılar üzerinden yorumlanması oldukça güçtür. Görselleştirme, sayısal verilerden anlam çıkarılması ve yorum yapılabilmesi için sıkça başvurulan bir yöntemdir. Bu çalışmada trafik yoğunluğunu analiz ederek görselleştiren, kısa, orta ve uzun vadede hız tahmini yapan bir araç geliştirilmiştir.
Analiz kısmında İstanbul sınırları içerisinde birçok noktadaki sensörden alınan hız verileri belli bölge, zaman ve lokasyona göre özelleştirilmiş ve kullanıcıya talepleri doğrultusunda görsel bir içerik sunulmuştur. İçerik hazırlanırken ilgili bilgiler harita üzerinde işaretlenmiş veya sayısal grafiklerden yararlanılmıştır.
Trafik tahmini yapabilmek için regresyon ve temel istatistiksel veriye dayalı üç farklı yöntem denenmiş ve elde edilen sonuçlar karşılaştırılmıştır. Geliştirilen sistem günün farklı zaman dilimleri için çıkarılan regresyon modellerini kullanarak %21.8 Ortalama Mutlak Yüzde Hatası ve 8.5 Ortalama Mutlak Hata ile 1 hafta sonraya kadar trafik akışı tahmini yapabilmektedir.
Supporting Institution
TÜBİTAK
Project Number
TÜBİTAK 1001 Projesi 120E357
References
- Referans 1 Kumar, S. V., & Vanajakshi, L. (2015). Short-term traffic flow prediction using seasonal ARIMA model with limited input data. European Transport Research Review, 7(3), 21.
- Referans 2 Y. S. Jeong, Y. J. Byon, M. M. Castro-Neto, and S. M. Easa, “Supervised weighting-online learning algorithm for short-term traffic flow prediction,” IEEE Trans. Intell. Transp. Syst., vol. 14, no. 4, pp. 1700–1707, Dec. 2013.
- Referans 3 H. Chang, Y. Lee, B. Yoon, and S. Baek, “Dynamic near-term traffic flow prediction: System oriented approach based on past experiences,” IET Intell. Transport Syst., vol. 6, no. 3, pp. 292–305, Sep. 2012.
- Referans 4 J. W. C. van Lint, S. P. Hoogendoorn, and H. J. van Zuylen,“Accurate freeway travel time prediction with state-space neural networks under missing data,” Transportation Research Part C:Emerging Technologies, vol. 13, no. 5-6, pp. 347–369, 2005.
- Referans 5 M. Zhong, S. Sharma, and P. Lingras, “Short-term traffic prediction on different types of roads with genetically designed regression and time delay neural network models,” J. Comput. Civil Eng., vol. 19, no. 1, pp. 94–103, Jan. 2005.
- Referans 6 K. Kumar, M. Parida, and V. K. Katiyar, “Short term traffic flow prediction for a non urban highway using artificial neural network,” Proc. Soc. Behav. Sci., vol. 104, pp. 755–764, Dec. 2013.
- Referans 7 Y. Lv, Y. Duan, W. Kang, Z. Li, and F.-Y. Wang, “Traffic flow prediction with big data: a deep learning approach,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 2, pp. 865–873, 2015.
- Referans 8 Wu, Y., Tan, H., Qin, L., Ran, B., & Jiang, Z. (2018). A hybrid deep learning based traffic flow prediction method and its understanding. Transportation Research Part C: Emerging Technologies, 90, 166-180.
- Referans 9 Z. Zhao,W. Chen, X.Wu, P. C. Chen, and J. Liu, “LSTMnetwork: a deep learning approach for short-term traffic forecast,” IET Intelligent Transport Systems, vol. 11, no. 2, pp. 68–75, 2017.
- Referans 10 Chen, W., An, J., Li, R., Fu, L., Xie, G., Bhuiyan, M. Z. A., & Li, K. (2018). A novel fuzzy deep-learning approach to traffic flow prediction with uncertain spatial–temporal data features. Future Generation Computer Systems, 89, 78-88.
- Referans 11 Peng, H., Bobade, S. U., Cotterell, M. E., & Miller, J. A. (2018, June). Forecasting Traffic Flow: Short Term, Long Term, and When It Rains. In International Conference on Big Data (pp. 57-71). Springer, Cham.
- Referans 12 Peng, H., Bobade, S. U., Cotterell, M. E., & Miller, J. A. (2018, June). Forecasting Traffic Flow: Short Term, Long Term, and When It Rains. In International Conference on Big Data (pp. 57-71). Springer, Cham.
- Referans 13 Yandex controls, developer’s guide. [Online]. Available: https://yandex.com.tr/dev/maps/jsapi/doc/2.1/dg/concepts/controls.html/
- Referans 14 Yandex İstanbul için 3 yıllık trafik analizi. [Online]. Available: https://yandex.com.tr/company/press_center/infographics/istanbul_traffic
- Referans 15 E. Ostertagová, “Modelling using polynomial regression,”Procedia Engineering, vol. 48, pp. 500–506, 2012.
- Referans 16 Google. Googlemaps. [Online]. Available: https://developers.google.com/maps/documentation/?hl=tr
- Referans 17 F. Yasli, H. İ. Turkmen, and M. A. Guvensan, “Long-term traffic speed estimation via regression using weekly day patterns,” in 2019 Innovations in Intelligent Systems and Applications Conference (ASYU).IEEE, pp. 1–6
Abstract
The number of people and vehicles that are increasing day by day brings a serious traffic density to İstanbul. In order to eliminate or control this vehicle density, historical data should be interpreted well. All speed data that were measured in the provincial borders of Istanbul were recorded numerically by Istanbul Metropolitan Municipality. However, it is very difficult to evaluate these numerical data efficiently. Visualization is a frequently used method to infererence from numerical data and evaluation of it. In this study, a tool that analyzes and visualizes traffic density and estimates speed in the short, medium and long term has been developed.
In the analysis part, the speed data received from the sensors at many points within the borders of Istanbul are customized according to a specific region, time and location and a visual content is presented to the user on their demands. Relevant information was marked on the map or numerical graphics were used in order to present visual content.
In order to peroform traffic forecasting, three different methods based on regression and basic statistical data were employed and the obtained results were compared. Developed system can predict up to 1 week with a 21.8% Mean Absolute Percentage Error and 8.5 Mean Absolute Error by exploiting regression models that are generated for diffrent time slots of a whole day.
Project Number
TÜBİTAK 1001 Projesi 120E357
References
- Referans 1 Kumar, S. V., & Vanajakshi, L. (2015). Short-term traffic flow prediction using seasonal ARIMA model with limited input data. European Transport Research Review, 7(3), 21.
- Referans 2 Y. S. Jeong, Y. J. Byon, M. M. Castro-Neto, and S. M. Easa, “Supervised weighting-online learning algorithm for short-term traffic flow prediction,” IEEE Trans. Intell. Transp. Syst., vol. 14, no. 4, pp. 1700–1707, Dec. 2013.
- Referans 3 H. Chang, Y. Lee, B. Yoon, and S. Baek, “Dynamic near-term traffic flow prediction: System oriented approach based on past experiences,” IET Intell. Transport Syst., vol. 6, no. 3, pp. 292–305, Sep. 2012.
- Referans 4 J. W. C. van Lint, S. P. Hoogendoorn, and H. J. van Zuylen,“Accurate freeway travel time prediction with state-space neural networks under missing data,” Transportation Research Part C:Emerging Technologies, vol. 13, no. 5-6, pp. 347–369, 2005.
- Referans 5 M. Zhong, S. Sharma, and P. Lingras, “Short-term traffic prediction on different types of roads with genetically designed regression and time delay neural network models,” J. Comput. Civil Eng., vol. 19, no. 1, pp. 94–103, Jan. 2005.
- Referans 6 K. Kumar, M. Parida, and V. K. Katiyar, “Short term traffic flow prediction for a non urban highway using artificial neural network,” Proc. Soc. Behav. Sci., vol. 104, pp. 755–764, Dec. 2013.
- Referans 7 Y. Lv, Y. Duan, W. Kang, Z. Li, and F.-Y. Wang, “Traffic flow prediction with big data: a deep learning approach,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 2, pp. 865–873, 2015.
- Referans 8 Wu, Y., Tan, H., Qin, L., Ran, B., & Jiang, Z. (2018). A hybrid deep learning based traffic flow prediction method and its understanding. Transportation Research Part C: Emerging Technologies, 90, 166-180.
- Referans 9 Z. Zhao,W. Chen, X.Wu, P. C. Chen, and J. Liu, “LSTMnetwork: a deep learning approach for short-term traffic forecast,” IET Intelligent Transport Systems, vol. 11, no. 2, pp. 68–75, 2017.
- Referans 10 Chen, W., An, J., Li, R., Fu, L., Xie, G., Bhuiyan, M. Z. A., & Li, K. (2018). A novel fuzzy deep-learning approach to traffic flow prediction with uncertain spatial–temporal data features. Future Generation Computer Systems, 89, 78-88.
- Referans 11 Peng, H., Bobade, S. U., Cotterell, M. E., & Miller, J. A. (2018, June). Forecasting Traffic Flow: Short Term, Long Term, and When It Rains. In International Conference on Big Data (pp. 57-71). Springer, Cham.
- Referans 12 Peng, H., Bobade, S. U., Cotterell, M. E., & Miller, J. A. (2018, June). Forecasting Traffic Flow: Short Term, Long Term, and When It Rains. In International Conference on Big Data (pp. 57-71). Springer, Cham.
- Referans 13 Yandex controls, developer’s guide. [Online]. Available: https://yandex.com.tr/dev/maps/jsapi/doc/2.1/dg/concepts/controls.html/
- Referans 14 Yandex İstanbul için 3 yıllık trafik analizi. [Online]. Available: https://yandex.com.tr/company/press_center/infographics/istanbul_traffic
- Referans 15 E. Ostertagová, “Modelling using polynomial regression,”Procedia Engineering, vol. 48, pp. 500–506, 2012.
- Referans 16 Google. Googlemaps. [Online]. Available: https://developers.google.com/maps/documentation/?hl=tr
- Referans 17 F. Yasli, H. İ. Turkmen, and M. A. Guvensan, “Long-term traffic speed estimation via regression using weekly day patterns,” in 2019 Innovations in Intelligent Systems and Applications Conference (ASYU).IEEE, pp. 1–6
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Engineering |
| Journal Section | Research Articles |
| Authors | |
| Project Number | TÜBİTAK 1001 Projesi 120E357 |
| Publication Date | December 30, 2021 |
| Published in Issue | Year 2021 Volume: 33 Issue: 4 |