Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond

<p dir="ltr">Occupancy detection is crucial for various applications, including smart buildings, security systems, and energy management. This paper introduces a novel convolutional neural network (CNN) architecture based on an image encoding approach for accurate occupancy detection...

Full description

Saved in:
Bibliographic Details
Main Author: Aya Nabil Sayed (17317006) (author)
Other Authors: Sakib Mahmud (15302404) (author), Faycal Bensaali (12427401) (author), Muhammad E. H. Chowdhury (14150526) (author), Yassine Himeur (14158821) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513533217079296
author Aya Nabil Sayed (17317006)
author2 Sakib Mahmud (15302404)
Faycal Bensaali (12427401)
Muhammad E. H. Chowdhury (14150526)
Yassine Himeur (14158821)
author2_role author
author
author
author
author_facet Aya Nabil Sayed (17317006)
Sakib Mahmud (15302404)
Faycal Bensaali (12427401)
Muhammad E. H. Chowdhury (14150526)
Yassine Himeur (14158821)
author_role author
dc.creator.none.fl_str_mv Aya Nabil Sayed (17317006)
Sakib Mahmud (15302404)
Faycal Bensaali (12427401)
Muhammad E. H. Chowdhury (14150526)
Yassine Himeur (14158821)
dc.date.none.fl_str_mv 2025-06-03T03:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s00521-025-11348-6
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Optimizing_energy_efficiency_through_precise_occupancy_detection_A_tailored_CNN_architecture_for_smart_buildings_and_beyond/30540707
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Machine learning
Smart buildings
Occupancy detection
Feature extraction
Image encoding
Convolutional neural network
dc.title.none.fl_str_mv Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Occupancy detection is crucial for various applications, including smart buildings, security systems, and energy management. This paper introduces a novel convolutional neural network (CNN) architecture based on an image encoding approach for accurate occupancy detection. Our network effectively extracts relevant features from occupancy images by leveraging deep learning and image processing techniques, enabling reliable and real-time detection. We employed an image encoding method that converts environmental time-series data into 2D image representations—either grayscale or RGB-like—depending on the input requirements of the CNN model. This transformation captures spatial and temporal characteristics of the data, allowing the network to learn more expressive occupancy-related patterns from raw 1D input. Additionally, we developed a custom CNN architecture optimized for the encoded images, enabling the network to identify key features and understand complex spatial relationships. We evaluated the performance of our CNN through extensive testing on well-known occupancy datasets. The results highlight the superiority of our approach, outperforming existing techniques in accuracy, precision, recall, and F1-score. Our model achieved impressive accuracies of 98.45%, 99.05%, and 97.32% across the three datasets used in this study.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00521-025-11348-6" target="_blank">https://dx.doi.org/10.1007/s00521-025-11348-6</a></p>
eu_rights_str_mv openAccess
id Manara2_50c26bf087b03ed562f48ef779ffb0b1
identifier_str_mv 10.1007/s00521-025-11348-6
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30540707
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyondAya Nabil Sayed (17317006)Sakib Mahmud (15302404)Faycal Bensaali (12427401)Muhammad E. H. Chowdhury (14150526)Yassine Himeur (14158821)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationMachine learningSmart buildingsOccupancy detectionFeature extractionImage encodingConvolutional neural network<p dir="ltr">Occupancy detection is crucial for various applications, including smart buildings, security systems, and energy management. This paper introduces a novel convolutional neural network (CNN) architecture based on an image encoding approach for accurate occupancy detection. Our network effectively extracts relevant features from occupancy images by leveraging deep learning and image processing techniques, enabling reliable and real-time detection. We employed an image encoding method that converts environmental time-series data into 2D image representations—either grayscale or RGB-like—depending on the input requirements of the CNN model. This transformation captures spatial and temporal characteristics of the data, allowing the network to learn more expressive occupancy-related patterns from raw 1D input. Additionally, we developed a custom CNN architecture optimized for the encoded images, enabling the network to identify key features and understand complex spatial relationships. We evaluated the performance of our CNN through extensive testing on well-known occupancy datasets. The results highlight the superiority of our approach, outperforming existing techniques in accuracy, precision, recall, and F1-score. Our model achieved impressive accuracies of 98.45%, 99.05%, and 97.32% across the three datasets used in this study.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00521-025-11348-6" target="_blank">https://dx.doi.org/10.1007/s00521-025-11348-6</a></p>2025-06-03T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s00521-025-11348-6https://figshare.com/articles/journal_contribution/Optimizing_energy_efficiency_through_precise_occupancy_detection_A_tailored_CNN_architecture_for_smart_buildings_and_beyond/30540707CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/305407072025-06-03T03:00:00Z
spellingShingle Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond
Aya Nabil Sayed (17317006)
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Machine learning
Smart buildings
Occupancy detection
Feature extraction
Image encoding
Convolutional neural network
status_str publishedVersion
title Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond
title_full Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond
title_fullStr Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond
title_full_unstemmed Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond
title_short Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond
title_sort Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond
topic Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Machine learning
Smart buildings
Occupancy detection
Feature extraction
Image encoding
Convolutional neural network