Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


Dissertation_Thesis_Yuxiao_Zhao0417.pdf (2.03 MB)

ETD Abstract Container

Abstract Header

Parking Availability Prediction based on Machine Learning Approaches: A Case Study in the Short North Area

Zhao, Yuxiao
http://rave.ohiolink.edu/etdc/view?acc_num=osu1587147304509822

Abstract Details

2020, Master of Science, Ohio State University, Computer Science and Engineering.
Parking availability information can help drivers make decisions on where to park, reduce road congestion, and balance the parking demand. This study utilizes the historic parking meter transactions to estimate the parking occupancy aggregated by parking zones in the Short North, Columbus. Daily and weekly recurring patterns are identified from the parking availability time series. Clustering algorithms are used to cluster the average weekly time series of each parking zone to identify similar parking patterns. And machine learning algorithms are trained to make predictions for each cluster of zones based on input features, including time of the day, day of the week, and month. The study compares different clustering algorithms and machine learning algorithms to choose the model with the best performance. Agglomerative clustering shows more solid outcomes than k-means clustering. Multilayer perceptron (MLP) with two hidden layers and 50 hidden units each layer outperforms other machine learning algorithms and MLPs with other parameters. This study shows the potential of using historical transaction data and machine learning algorithms to make parking availability predictions. The pipeline of data collection, data cleaning, data exploration, data transformation, feature engineering, model selection, modeling, and model evaluations in this study could be reproduced to apply to other areas.
Dave Ogle (Advisor)
Thomas Bihari (Committee Member)
55 p.
Computer Science
machine learning; parking prediction; clustering; smart city

Recommended Citations

Citations

  • Zhao, Y. (2020). Parking Availability Prediction based on Machine Learning Approaches: A Case Study in the Short North Area [Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1587147304509822

    APA Style (7th edition)

  • Zhao, Yuxiao. Parking Availability Prediction based on Machine Learning Approaches: A Case Study in the Short North Area. 2020. Ohio State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1587147304509822.

    MLA Style (8th edition)

  • Zhao, Yuxiao. "Parking Availability Prediction based on Machine Learning Approaches: A Case Study in the Short North Area." Master's thesis, Ohio State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1587147304509822

    Chicago Manual of Style (17th edition)

osu1587147304509822
2,634
© 2020, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.