Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/62883
Title: Parking lot availability prediction and patterns
Authors: Ning, Haoyan
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Issue Date: 2015
Abstract: In Singapore, some car parks’ availability information is available to Land Transport Authority of Singapore (LTA). Digital notice boards are used on the road to display the current availability of some popular car parks. Some iOS apps also provide such function. However there are high chances that the current availability is greater than zero and car park is full when the driver arrives especially during peak hours. In order to resolve the existing issues, a car park availability prediction model has to be developed which predicts the availability of the car park based on driver’s arrival time. Multiple linear regression is used as the prediction model. The report analyzes the features used for prediction and discusses the performance of the predictions. Another objective of the project is to develop an iOS app (iSPARK) to enhance the driving experience of the drivers. The iOS platform is selected because of the increasing downloads of iOS apps from Apple store. The app allows car parks search by current location or specified destination. It is also used to display the predicted availability for the resulting car parks. The app is an interface where it can be used by other related projects to perform data collection or to display the results.
URI: http://hdl.handle.net/10356/62883
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
fyp report onine.pdf
  Restricted Access
report2.14 MBAdobe PDFView/Open

Page view(s)

168
checked on Sep 22, 2020

Download(s)

18
checked on Sep 22, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.