Smart Solutions for Mega-Cities: Utilizing Long Short-Term Memory and Multi-Head Attention in Parking Prediction

Finding a parking space is a major concern in megacities, causing drivers to lose time and money while contributing to atmospheric pollution and global warming. This study proposes a method to predict parking slot availability by comparing Long Short-Term Memory (LSTM) and Multi-Head Attention (MHA)...

Full description

Saved in:
Bibliographic Details
Main Authors: Hasan Kemik, Tugba Dalyan, Murat Aydogan
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/13/12/449
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850241293794410496
author Hasan Kemik
Tugba Dalyan
Murat Aydogan
author_facet Hasan Kemik
Tugba Dalyan
Murat Aydogan
author_sort Hasan Kemik
collection DOAJ
description Finding a parking space is a major concern in megacities, causing drivers to lose time and money while contributing to atmospheric pollution and global warming. This study proposes a method to predict parking slot availability by comparing Long Short-Term Memory (LSTM) and Multi-Head Attention (MHA) methods using the CityPulse Smart City Datasets. The initial experiments assessed the impact of pollution and time features on prediction accuracy. In a subsequent experiment, the dataset was expanded by incorporating weather-related features and a broader time range while excluding pollution and time features, as informed by the initial results. Various experiments were conducted with different parameters, such as model depth and activation functions. The results demonstrated that MHA outperformed LSTM in predicting occupancy rates, achieving a Mean Absolute Error (MAE) score of 0.0589 on the extended dataset. This study marks a pioneering effort in using MHA for real-time parking occupancy prediction, showcasing significant success with fewer parameters and a smaller model size.
format Article
id doaj-art-ab4b7a32543e4b27b3ef3c7a1048e28c
institution OA Journals
issn 2220-9964
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj-art-ab4b7a32543e4b27b3ef3c7a1048e28c2025-08-20T02:00:38ZengMDPI AGISPRS International Journal of Geo-Information2220-99642024-12-01131244910.3390/ijgi13120449Smart Solutions for Mega-Cities: Utilizing Long Short-Term Memory and Multi-Head Attention in Parking PredictionHasan Kemik0Tugba Dalyan1Murat Aydogan2Department of Computer Engineering, İstanbul Bilgi University, 34050 Istanbul, TurkeyDepartment of Computer Engineering, İstanbul Bilgi University, 34050 Istanbul, TurkeyDepartment of Software Engineering, Firat University, 23100 Elazığ, TurkeyFinding a parking space is a major concern in megacities, causing drivers to lose time and money while contributing to atmospheric pollution and global warming. This study proposes a method to predict parking slot availability by comparing Long Short-Term Memory (LSTM) and Multi-Head Attention (MHA) methods using the CityPulse Smart City Datasets. The initial experiments assessed the impact of pollution and time features on prediction accuracy. In a subsequent experiment, the dataset was expanded by incorporating weather-related features and a broader time range while excluding pollution and time features, as informed by the initial results. Various experiments were conducted with different parameters, such as model depth and activation functions. The results demonstrated that MHA outperformed LSTM in predicting occupancy rates, achieving a Mean Absolute Error (MAE) score of 0.0589 on the extended dataset. This study marks a pioneering effort in using MHA for real-time parking occupancy prediction, showcasing significant success with fewer parameters and a smaller model size.https://www.mdpi.com/2220-9964/13/12/449smart citysmart parkingdeep learningLSTMMHA
spellingShingle Hasan Kemik
Tugba Dalyan
Murat Aydogan
Smart Solutions for Mega-Cities: Utilizing Long Short-Term Memory and Multi-Head Attention in Parking Prediction
ISPRS International Journal of Geo-Information
smart city
smart parking
deep learning
LSTM
MHA
title Smart Solutions for Mega-Cities: Utilizing Long Short-Term Memory and Multi-Head Attention in Parking Prediction
title_full Smart Solutions for Mega-Cities: Utilizing Long Short-Term Memory and Multi-Head Attention in Parking Prediction
title_fullStr Smart Solutions for Mega-Cities: Utilizing Long Short-Term Memory and Multi-Head Attention in Parking Prediction
title_full_unstemmed Smart Solutions for Mega-Cities: Utilizing Long Short-Term Memory and Multi-Head Attention in Parking Prediction
title_short Smart Solutions for Mega-Cities: Utilizing Long Short-Term Memory and Multi-Head Attention in Parking Prediction
title_sort smart solutions for mega cities utilizing long short term memory and multi head attention in parking prediction
topic smart city
smart parking
deep learning
LSTM
MHA
url https://www.mdpi.com/2220-9964/13/12/449
work_keys_str_mv AT hasankemik smartsolutionsformegacitiesutilizinglongshorttermmemoryandmultiheadattentioninparkingprediction
AT tugbadalyan smartsolutionsformegacitiesutilizinglongshorttermmemoryandmultiheadattentioninparkingprediction
AT murataydogan smartsolutionsformegacitiesutilizinglongshorttermmemoryandmultiheadattentioninparkingprediction