Parking availability prediction in the Seattle city using spatio-temporal features

Shinde, Tejas Sanjay (2020) Parking availability prediction in the Seattle city using spatio-temporal features. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

Management of parking systems is a challenge considering the substantial growth of parking demand and the restricted capacity of the cities, which further leads to trouble locating a suitable parking. A solution to this would be an accurate parking prediction system. Researchers have presented numerous approaches to predict the availability using limited features. However, none of the studies in the literature have considered the exogenous spatial factors and the Park & Ride systems which are widely used by the commuters for switching to the public mode of transportation. To address this gap, this study unfolds a novel approach in predicting the availability using spatial factors such as the walking distances from the closest public transport stations and the Seattle financial centre along with the temporal factors including weather. Machine learning models such as BackPropagation Neural Network(BPNN), Random Forest(RF), and Extreme Gradient Boosting(XGBoost) are used in the presented study. Their performance is then optimized using GridSearchCV and assessed using R2 , RMSE, and MAE. The XGBoost accomplished the highest R2 of 97.65% with an error close to 0. This can help the commuters in accurately gauging the availability in advance. Also, the insights from this study will assist the Seattle Department of Transport in the management of parking demand.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	21 Jan 2021 11:14
Last Modified:	21 Jan 2021 11:14
URI:	https://norma.ncirl.ie/id/eprint/4422

Actions (login required)

View Item