A New Approach to Estimating Destinations in Open Automated Fare Collection Systems based on errors-against-errors strategy

Articles in Press

Document Type : Article

Authors

1 Department of Civil and Environment Engineering, Tarbiat Modares University, Tehran, Iran

2 Faculty of Civil and environment Engineering, Tarbiat Modares University, Tehran, Iran

Abstract

In transit systems,automatic fare collection systems(AFCs)are widely used.Passengers are often required to use their smart cards only when entering stops,so their destination is unknown.Most of the methods proposed for addressing this problem, require network-level AFC data.Data regarding AutomatedVehicleLocation(AVL)may also be required.However,the problem remains unresolved when only one line's AFC data is available.The purpose of this paper is to solve this issue for specific applications,such as crowding analysis or crowding-related problems such as calculating perceived travel times.In our proposed method,rather than minimizing errors,the model is constructed so that desirable errors are produced to counter undesirable errors.The task is accomplished by employing an imbalanced binary class classification based on thresholding solutions for each stop.A classification indicates whether a passenger is alighting or has already alighted at the study or previous stops.Although the model may produce incorrect predictions for a particular stop,it will be adjusted to make a deliberate error:for every incorrect prediction of alighting, there will be a few incorrect predictions of not alighting.As a result of this technique,we are able to estimate how many passengers are on board the bus.In fact,the proposed model of this paper has the functionality of an Automatic Passenger Counting(APC)system when the line does not have one.

Keywords

Main Subjects

Scientia Iranica

Articles in Press, Accepted Manuscript
Available Online from 10 July 2024

Files

History

  • Receive Date: 02 January 2023
  • Revise Date: 10 April 2024
  • Accept Date: 10 July 2024

Share

How to cite

Statistics