Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGUO, SHUAI ZHI(郭帥志)-
dc.identifier.citationGuo, S. Z. (2020). Predicting awaiting time for an available parking space by using artificial neural network: a case study of Macao (OAPS)). Retrieved from University of Macau, Outstanding Academic Papers by Students Repository.en_US
dc.description.abstractThe awaiting time for the next available parking space is important to solve the parking problem and achieve the social optimum. For example, in Macau, the utilization ratio of parking resources is low, and the distribution of parking resources is uneven. Previous studies have not focused on the study of awaiting time but only on the prediction of occupation sequence. Further, there is no specialized research based on real cases in Macau. The main objective of this study is to design a prediction system to predict the time of waiting for parking in Macau. Meanwhile, this paper showed why the awaiting time is the key point to solve the parking problem. The parking information is collected from DSAT which will be used as the training data set in the BP-ANN model, with the guidance of traditional statistical model (ARIMA) and optimization of genetic algorithm, an intermediate product of the awaiting time to be obtained which is the departure rate. Finally, through the Poisson model and infinitesimal calculus, the awaiting time is obtained. About the final result, the error of departure rate will not exceed 0.14 cars per minute which are about 14.4% to the mean value, the error for the awaiting time in short-term prediction will not exceed 2.7 minutes.en_US
dc.titlePredicting awaiting time for an available parking space by using artificial neural network: a case study of Macaoen_US
dc.contributor.departmentDepartment of Civil and Environmental Engineeringen_US
dc.description.instructorProf. Kun Pang KOUen_US
dc.contributor.facultyFaculty of Science and Technologyen_US
dc.description.programmeBachelor of Science in Civil and Environmental Engineeringen_US
Appears in Collections:FST OAPS 2020

Files in This Item:
File Description SizeFormat 
OAPS_2020_FST_007.pdf69.65 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.