Passenger Demand Prediction for Fast Ferries Based on Neural Network and Support Vector Machine

Abstract

Public transportation is quite important in Istanbul whose population is growing continuously. Similar to other types of public transportation, the number of passengers transported by marine vessels increases each year. In order to fulfill this increasing demand for transportation of people, maritime transportation should be administrated and developed efficiently. Decisions on investments and projections for the capacities of the lines should be well planned by considering the total number of passengers and the variations in the demand on the lines. The success of such planning is directly related to the correct estimation of the number of passengers in each line. In this study, passenger demand prediction was performed for a fast ferries company, one of the maritime companies in the world carrying highest number of passengers. Within this scope, for different lines, by using Artificial Neural Network and Support Vector Machine methods, total annual number of passengers were estimated and the success of the prediction models were analyzed.

Keywords

• -

Kaynakça

1. CHOUDHRY, R., GARG, K., (2008), A hybrid machine learning system for stock market forecasting. World Academy of Science, Engineering and Technology, 39(3), 315-318.
2. CORNELL UNIVERSITY, Cornell Department of Mathematics, Numbers Math Activities, Season:2 Episode:219,. Retrieved on July 2, 2015, available from World Wide Web: www.math.cornell.edu/~numb3rs/kostyuk/num219.htm.
3. DTREG, Introduction to Support Vector Machine (SVM) Models. Retrieved on July 2, 2015, available from World Wide Web: https://www.dtreg.com/solution/view/20.
4. ERDAL, H. I., KARAKURT, O. (2013), Advancing monthly streamflow prediction accuracy of CART models using ensemble learning paradigms, Journal of Hydrology, 477, 119-128.
5. ERDAL, H., (2015), Contribution of machine learning methods to the construction industry: Prediction of compressive strength, Pamukkale Univ Muh Bilim Derg, 21 (3), 109-114.
6. GÜLEZ, K., Yapay sinir ağlarının kontrol mühendisliğindeki uygulamaları. (Lecture notes, 2008) Yıldız Teknik University, Retrieved on July 2, 2015, available from World Wide Web: http://www.yildiz.edu.tr/~gulez/3k1n.pdf.
7. GÜLLÜ, H., PALA, M., İYİSAN, R., (2007), Yapay sinir ağları ile en büyük yer ivmesinin tahmin edilmesi. Sixth National Conference on Earthquake Engineering, Istanbul, Turkey.
8. İETT, İstanbul`da Toplu Taşıma, Retrieved on February 20, 2016, available from World Wide Web: http://www.iett.gov.tr/tr/main/pages/istanbulda-toplu-tasima/95

9. İSTANBUL BÜYÜKŞEHİR BELEDİYESİ, (2014), 2013 Faaliyet Raporu. İstanbul, Mali Hizmetler Daire Başkanlığı, Strateji Geliştirme Müdürlüğü. Retrieved on March 15, 2015, available from World Wide Web: http://www.ibb.istanbul/tr-TR/BilgiHizmetleri/Yayinlar/FaaliyetRaporlari/Documents/2013/ibb_faaliyet_Raporu_pdf/ibb_faaliyetraporu2013.pdf
10. KARAGÜLLE, F. (2008), Destek vektör makinelerini kullanarak yüz bulma (Master dissertation), Trakya University.
11. ÖZER, K., (2009), İstanbul deniz otobüslerinin bir hattında yolcu talep tahmini (Master dissertation), Marmara University.
12. PALMER, A., MONTANO, J. J., SESÉ, A., (2006), Designing an artificial neural network for forecasting tourism time series. Tourism Management, 27(5), 781-790.
13. SMOLA, A., SCHÖLKOPF, B., MÜLLER, K. R. SMOLA, A., SCHÖLKOPF, B., MÜLLER, K. R., (1998), in Proceedings of the 8th International Conference on Artificial Neural Networks, 79-83.
14. VAPNIK, V. N., CHERVONENKIS A., (1964), A note on one class of perceptrons. Automation and Remote Control, 25, 838-845.
15. WEIGEND, A. S., HUBERMAN, B. A., RUMELHART, D. E., (1992), Predicting sunspots and exchange rates with connectionist networks. In Santa Fe Institute Studies in the Sciences of Complexity-Proceedings, 12, 395-395, Addison-Wesley Publishing Co.
16. YUMURTACI AYDOGMUS, H., ERDAL, H. I., KARAKURT, O., NAMLI, E., TURKAN, Y. S., ERDAL, H., (2015), A comparative assessment of bagging ensemble models for modeling concrete slump flow, Computers and Concrete, 16, (5), 741-757.