Application of Machine Learning Methods for Passenger Demand Prediction in Transfer Stations of Istanbul's Public Transportation System

Application of Machine Learning Methods for Passenger Demand Prediction in Transfer Stations of Istanbul's Public Transportation System

Hacer Yumurtaci Aydogmus, Yusuf Sait Turkan
Copyright: © 2020 |Pages: 21
DOI: 10.4018/978-1-7998-0301-0.ch011
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The rapid growth in the number of drivers and vehicles in the population and the need for easy transportation of people increases the importance of public transportation. Traffic becomes a growing problem in Istanbul which is Turkey's greatest urban settlement area. Decisions on investments and projections for the public transportation should be well planned by considering the total number of passengers and the variations in the demand on the different regions. The success of this planning is directly related to the accurate passenger demand forecasting. In this study, machine learning algorithms are tested in a real-world demand forecasting problem where hourly passenger demands collected from two transfer stations of a public transportation system. The machine learning techniques are run in the WEKA software and the performance of methods are compared by MAE and RMSE statistical measures. The results show that the bagging based decision tree methods and rules methods have the best performance.
Chapter Preview
Top

Background

Passenger demand estimation problem in public transport can be categorized into long term and short term demand forecasting problems. Long-term public transport passenger forecasting is used for long-term planning, strategic decisions and investments in public transport, while short-term forecasting is more effective in operational decisions. Conventional demand forecasting methods are generally classified as univariate time series approaches and multivariate demand modeling approaches. Multivariate demand modelling approaches can be undertaken using a conventional four-step travel planning model or direct demand models. Travel planning model including the steps of trip generation, trip distribution, mode choice, and assignment has been used in many demand forecasting applications (Bar-Gera and Boyce, 2003; Blainey and Preston, 2010; Dargay et al., 2010; Jovicic and Hansen, 2003; Owen and Philips, 1987; Preston, 1991; Wardman and Tyler, 2000; Wardman, 2006).

Complete Chapter List

Search this Book:
Reset