Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN Methods
<p>Passenger flow estimation of transit systems is essential for new decisions about additional facilities and feeder lines. For increasing the efficiency of an existing transit line, stations which are insufficient for trip production and attraction should be examined first. Such investigatio...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Zagreb, Faculty of Transport and Traffic Sciences
2012-01-01
|
| Series: | Promet (Zagreb) |
| Subjects: | |
| Online Access: | http://www.fpz.unizg.hr/traffic/index.php/PROMTT/article/view/264 |
| _version_ | 1811211309353533440 |
|---|---|
| author | Mustafa Özuysal Gökmen Tayfur Serhan Tanyel |
| author_facet | Mustafa Özuysal Gökmen Tayfur Serhan Tanyel |
| author_sort | Mustafa Özuysal |
| collection | DOAJ |
| description | <p>Passenger flow estimation of transit systems is essential for new decisions about additional facilities and feeder lines. For increasing the efficiency of an existing transit line, stations which are insufficient for trip production and attraction should be examined first. Such investigation supports decisions for feeder line projects which may seem necessary or futile according to the findings. In this study, passenger flow of a light rail transit (LRT) system in Izmir, Turkey is estimated by using multiple regression and feed-forward back-propagation type of artificial neural networks (ANN). The number of alighting passengers at each station is estimated as a function of boarding passengers from other stations. It is found that ANN approach produced significantly better estimations specifically for the low passenger attractive stations. In addition, ANN is found to be more capable for the determination of trip-attractive parts of LRT lines.</p> <p> </p> <strong>Keywords:</strong> light rail transit, multiple regression, artificial neural networks, public transportation |
| first_indexed | 2024-04-12T05:10:37Z |
| format | Article |
| id | doaj.art-adb11105270d4a008384b60637622816 |
| institution | Directory Open Access Journal |
| issn | 0353-5320 1848-4069 |
| language | English |
| last_indexed | 2024-04-12T05:10:37Z |
| publishDate | 2012-01-01 |
| publisher | University of Zagreb, Faculty of Transport and Traffic Sciences |
| record_format | Article |
| series | Promet (Zagreb) |
| spelling | doaj.art-adb11105270d4a008384b606376228162022-12-22T03:46:46ZengUniversity of Zagreb, Faculty of Transport and Traffic SciencesPromet (Zagreb)0353-53201848-40692012-01-0124111410.7307/ptt.v24i1.264170Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN MethodsMustafa ÖzuysalGökmen TayfurSerhan Tanyel<p>Passenger flow estimation of transit systems is essential for new decisions about additional facilities and feeder lines. For increasing the efficiency of an existing transit line, stations which are insufficient for trip production and attraction should be examined first. Such investigation supports decisions for feeder line projects which may seem necessary or futile according to the findings. In this study, passenger flow of a light rail transit (LRT) system in Izmir, Turkey is estimated by using multiple regression and feed-forward back-propagation type of artificial neural networks (ANN). The number of alighting passengers at each station is estimated as a function of boarding passengers from other stations. It is found that ANN approach produced significantly better estimations specifically for the low passenger attractive stations. In addition, ANN is found to be more capable for the determination of trip-attractive parts of LRT lines.</p> <p> </p> <strong>Keywords:</strong> light rail transit, multiple regression, artificial neural networks, public transportationhttp://www.fpz.unizg.hr/traffic/index.php/PROMTT/article/view/264light rail transitmultiple regressionartificial neural networkspublic transportation |
| spellingShingle | Mustafa Özuysal Gökmen Tayfur Serhan Tanyel Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN Methods Promet (Zagreb) light rail transit multiple regression artificial neural networks public transportation |
| title | Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN Methods |
| title_full | Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN Methods |
| title_fullStr | Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN Methods |
| title_full_unstemmed | Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN Methods |
| title_short | Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN Methods |
| title_sort | passenger flows estimation of light rail transit lrt system in izmir turkey using multiple regression and ann methods |
| topic | light rail transit multiple regression artificial neural networks public transportation |
| url | http://www.fpz.unizg.hr/traffic/index.php/PROMTT/article/view/264 |
| work_keys_str_mv | AT mustafaozuysal passengerflowsestimationoflightrailtransitlrtsysteminizmirturkeyusingmultipleregressionandannmethods AT gokmentayfur passengerflowsestimationoflightrailtransitlrtsysteminizmirturkeyusingmultipleregressionandannmethods AT serhantanyel passengerflowsestimationoflightrailtransitlrtsysteminizmirturkeyusingmultipleregressionandannmethods |