AdaBoost algoritmasını kullanarak demiryolu trafik yönetimi için seyir süresinin tahmini

Year 2022, Volume: 24 Issue: 1, 300 - 312, 05.01.2022

Mehmet Taciddin Akçay Abdurrahim Akgundogdu Hasan Tiryaki

https://doi.org/10.25092/baunfbed.937333

Cited By: 1

Abstract

İstasyonlar arasında geçen seyir süresi belirlenirken bekleme süresi, hareket direnci, eğim, kurp, cer kuvveti, maximum hız, aracın kütlesi ve iki istasyon arası mesafe gibi bir takım tasarım parametreleri göz önünde bulundurulmaktadır. Bu parametreler aracın hareketine ait sistemin tanımının alt yapısını oluşturmaktadır. Ayrıca, hız profili oluşturulurken hat için tanımlanmış sefer sıklığının sağlanabilmesi için seyir süresine özellikle dikkat edilmelidir. Bu çalışmada şehiriçi metro sistemlerine ait istasyonlar arası seyir süresi değerinin makine öğrenmesi yöntemlerinden Adaptive Boosting yöntemi ile tahmini gerçekleştirilmiş ve iyi bilinen çeşitli yöntemler ile karşılaştırılmıştır. Kullanılan veriler çapraz doğrulama ve rastgele örnekleme yöntemleri ile önerilen modele uygulanmış ve belirleme katsayısı (R2) değerleri hesaplanmıştır.

Keywords

AdaBoost, demiryolu, makine öğrenmesi, seyir süresi, sinyalizasyon.

Prediction of travel time for railway traffic management by using the AdaBoost algorithm

Abstract

While determining the travel time between stations, a number of design parameters such as waiting time, motion resistance, slope, curve, traction force, maximum speed, vehicle mass, and distance between two stations are taken into consideration. These parameters form the infrastructure of the system definition of the motion of the vehicle. Furthermore, while creating the speed profile, special attention should be paid to the travel time in order to ensure the defined headway for the line. In this study, the travel time value between stations for intracity metro stations was predicted using the adaptive boosting method, which is one of the machine learning methods, and compared with various well-known methods. The data used were applied to the proposed model with the cross-validation and random sampling hold-out methods, and the values of the coefficient of determination (R2) were calculated.

Keywords

AdaBoost, machine learning, railway, travel time, signalization

References

• Riccardo, R., Massimiliano, G., “An empirical analysis of vehicle time headways on rural two-lane two-way roads”, Procedia - Social and Behavioral Sciences, 2012, 54: 865 – 874.
• Suweda, I., W., “Time Headway Analysis to Determine the Road Capacity”, Jurnal Spektran, 2016, 4 (2): 71-75.
• Nakamura, H., “Analysis of minimum train headway on a moving block system by genetic algorithm”, Transactions on the Built Environment, 1998, 34: 1014-1022.
• Jang, J., Park, C, Kim, B., Choi, N., “Modeling of Time Headway Distribution on Suburban Arterial: Case Study from South Korea”, ”, Procedia - Social and Behavioral Sciences, 2011, 16: 240 – 247.
• Maurya, A., K., Das, S., Dey, S., Nama, S., “Study on Speed and Time-headway Distributions on Two-lane Bidirectional Road in Heterogeneous Traffic Condition”, Transportation Research Procedia, 2016, 17: 428 – 437.
• Maurya, A., K., Dey, S., Das, S., “Speed and Time Headway Distribution under Mixed Traffic Condition”, Journal of the Eastern Asia Society for Transportation Studies, 2015, 11: 1774-1792.
• Minh, C., C., Sano, K., Matsumoto, S., “The Speed, Flow and Headway Analyses of Motorcycle Traffic”, Journal of the Eastern Asia Society for Transportation Studies, 2005, 6: 1496 – 1508.
• Domenichini, L., Salerno, G., Fanfani, F., Bacchi, M., Giaccherini, A., Costalli, L., Baroncelli, C., “Travel time in case of accident prediction model”, Procedia - Social and Behavioral Sciences 53, 2012, 1079 – 1088.
• Tatomir, B., Rothkrantz, L., J., M., Suson, A., C., Travel time prediction for dynamic routing using Ant Based Control. In: Proceedings of the 2009 Winter Simulation Conference (WSC), 2009, 1069–1078.
• Kisgyörgy, L. and L.R. Rilett, Travel time prediction by advanced neural network. Periodica Polytechnica Ser. Civ. Eng, 2002, 46(1), 15–32.
• Li R, Rose G, Chen H, and Shen J. Effective Long Term Travel Time Prediction with Fuzzy Rules for Tollway, Neural Computing and Applications, 2017, 30, 2921–2933.
• A. Narayanan, N. Mitrovic, M. T. Asif, J. Dauwels, and P. Jaillet, “Travel time estimation using speed predictions,” in Intelligent Transportation Systems (ITSC), 2015 IEEE 18th International Conference on. IEEE, 2015, 2256–2261.
• A. Gal, A. Mandelbaum, F. Schnitzler, and A. Senderovich, “Traveling time prediction in scheduled transportation with journey segments,” Inform. Syst., 2017, 64: 266-280.
• Li, Y., Gunopulos, D., Lu, C. and Guibas, L. 2017. UrbanTravel Time Prediction using a Small Number of GPS Floating Cars. InSIGSPA-TIAL GIS. ACM, 2017, 3: 1-10.
• Bauer, D., & Tulic, M. Travel time predictions: should one modelspeeds or travel times?European Transport Research Review, 2018, 10(46): 1-12.
• Zychowski, A.; Junosza-Szaniawski, K.; Kosicki, A. Travel Time Prediction for Trams in Warsaw.In Proceedings of the 10th International Conference on Computer Recognition Systems (CORES),Polanica Zdroj, Poland, 22–24 May 2017; Kurzynski, M., Wozniak, M., Burduk, R., Eds.; Springer InternationalPublishing: Cham, Germany, 2017, 53–61
• J. Rupnik, J. Davies, B. Fortuna, A. Duke, and S. S. Clarke, “Travel timeprediction on highways,” in International Conference on Computer andInformation Technology, 2015, 1435–144.
• Woodard, D.; Nogin, G.; Koch, P.; Racz, D.; Goldszmidt, M.; Horvitz, E. Predicting travel time reliabilityusing mobile phone GPS data.Transp. Res. Part C, 2017,75, 30–44.
• S. hak, S. Kim, K. Jang, et al. Real-hime hravel hime Prediction Using Multi-Level k-Nearest Neighbor Algorithm and Data Fusion Method. 2014 International Conference on Computing in Civil and Building Engineering, 2014.
• Yusuf, A., “Advanced Machine Learning Models for Online Travel-time Prediction on Freeways”, PhD. Thesis, Georgia Institute of Technology.
• Faheem, H., Hashim, I., H., “Analysis of Traffic Characteristics at Multi-lane Divided Highways, Case Study from Cairo-Aswan Agriculture Highway”, International Refereed Journal of Engineering and Science (IRJES), 2014, 3 (1): 58-65.
• Mathew, T., V., Rao, K., V., K.,” Fundamental Parameters of Traffic Flow”, Introduction to Transportation Engineering, NPTEL, May 3, 2007.
• Geistefeldt, J., “Capacity effects of variable speed limits on German freeways”, Procedia - Social and Behavioral Sciences, 2011, 16: 48 – 56.
• Freund, Yoav, Robert Schapire, and Naoki Abe. "A short introduction to boosting." Journal-Japanese Society For Artificial Intelligence, 1999, 14 (5), 771-780.
• Yoav Freund and Robert E. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 1997, 55(1): 119-139.