Open AccessRegression‐based parking space availability prediction for the Ubike system
Author(s) -
Leu JenqShiou,
Zhu ZheYi
Publication year - 2015
Publication title -
iet intelligent transport systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.579
H-Index - 45
eISSN - 1751-9578
pISSN - 1751-956X
DOI - 10.1049/iet-its.2014.0094
Subject(s) - economic shortage , parking space , transport engineering , support vector machine , regression analysis , linear regression , service (business) , regression , engineering , computer science , machine learning , statistics , mathematics , business , linguistics , philosophy , marketing , government (linguistics)
Numerous vehicles exist worldwide such as cars, motorcycles and bicycles. Although parking for such vehicles is available in many places, parking problems still always exist, such as full lots or a lack of lots. Commuters seeking a parking space expend time when spaces are occupied, and resources are wasted when parking spaces are empty. On the other hand, biking is a green vehicle in a fuel‐shortage situation and also a good exercise for people. The Ubike system is a popular short‐distance transit vehicle system in Taipei City that also has the parking problem. Therefore, this study uses two common regression schemes – linear regression and support vector regression (SVR) to predict the number of bicycles in Ubike stations to determine the number of available parking spaces. It also uses the proportional selection method to increase accuracy and reduce training time for SVR. Some evaluations are conducted to validate the feasibility of the two regression‐based service availability prediction schemes for the Ubike system.