Neural network-based parking system object detection and predictive modeling

Simple item page
dc.contributor.authorEl Khatib, Ziad
dc.contributor.authorBen Mnaouer, Adel
dc.contributor.authorMoussa, Sherif
dc.contributor.authorMashaal, Omar
dc.contributor.authorIsmail, Nor Azman
dc.contributor.authorAbas, Mohd Azman Bin
dc.contributor.authorAbdulgaleel, Fuad
dc.date.accessioned2022-12-21T06:32:52Z
dc.date.available2022-12-21T06:32:52Z
dc.date.copyright© 2023
dc.date.issued2023-03
dc.descriptionThis work is licensed under Creative Commons License and full text is openly accessible in CUD Digital Repository. The version of the scholarly record of this article is published in IAES International Journal of Artificial Intelligence (2023), available online at: http://doi.org/10.11591/ijai.v12.i1.pp66-78
dc.description.abstractA neural network-based parking system with real-time license plate detection and vacant space detection using hyper parameter optimization is presented. When number of epochs increased from 30, 50 to 80 and learning rate tuned to 0.001, the validation loss improved to 0.017 and training object loss improved to 0.040. The model means average precision mAP_0.5 is improved to 0.988 and the precision is improved to 99%. The proposed neural network-based parking system also uses a regularization technique for effective predictive modeling. The proposed modified lasso ridge elastic (LRE) regularization technique provides a 5.21 root mean square error (RMSE) and an R-square of 0.71 with a 4.22 mean absolute error (MAE) indicative of higher accuracy performance compared to other regularization regression models. The advantage of the proposed modified LRE is that it enables effective regularization via modified penalty with the feature selection characteristics of both lasso and ridge. © 2023, Institute of Advanced Engineering and Science. All rights reserved.
dc.identifier.citationEl Khatib, Z., Ben Mnaouer, A., Moussa, S., Mashaal, O., Ismail, N. A., Abas, M. A. B., & Abdulgaleel, F. (2023). Neural network-based parking system object detection and predictive modeling. IAES International Journal of Artificial Intelligence, 12(1), 66-78. doi:10.11591/ijai.v12.i1.pp66-78
dc.identifier.issn20894872
dc.identifier.urihttp://doi.org/10.11591/ijai.v12.i1.pp66-78
dc.identifier.urihttps://hdl.handle.net/20.500.12519/722
dc.language.isoen_US
dc.publisherInstitute of Advanced Engineering and Science
dc.relationAuthors Affiliations : El Khatib, Z., Department of Electrical and Computer Engineering, Canadian University Dubai, Dubai, United Arab Emirates; Ben Mnaouer, A., Department of Electrical and Computer Engineering, Canadian University Dubai, Dubai, United Arab Emirates; Moussa, S., Department of Electrical and Computer Engineering, Canadian University Dubai, Dubai, United Arab Emirates; Mashaal, O., Department of Electrical and Computer Engineering, Canadian University Dubai, Dubai, United Arab Emirates; Ismail, N.A., Department of Computer Science, Universiti Teknologi Malaysia, Johor Bahru, Malaysia; Abas, M.A.B., Department of Computer Science, Universiti Teknologi Malaysia, Johor Bahru, Malaysia; Abdulgaleel, F., Department of Computer Science, Universiti Teknologi Malaysia, Johor Bahru, Malaysia
dc.relation.ispartofseriesIAES International Journal of Artificial Intelligence; Volume 12, Issue 1
dc.rightsCreative Commons Attribution-ShareAlike 4.0 International License
dc.rights.holderCopyright : © 2023, Institute of Advanced Engineering and Science. All rights reserved.
dc.rights.urihttp://creativecommons.org/licenses/by-sa/4.0/
dc.subjectHyperparamter optimization
dc.subjectPredictive modeling
dc.subjectReal-time object detection
dc.subjectRegularization technique
dc.subjectYolo neural network
dc.titleNeural network-based parking system object detection and predictive modeling
dc.typeArticle
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
722.pdf
Size:
868.97 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.01 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Department of Electrical Engineering