Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach

<p dir="ltr">Sixth-generation (6G) networks, offering ultra-low latency and high bandwidth, provide critical support for rapid data transmission in postdisaster environments where conventional infrastructure may be compromised. This study presents a privacy-preserving framework for p...

Full description

Saved in:
Bibliographic Details
Main Author: Junaid Akram (13389717) (author)
Other Authors: Awais Akram (11890289) (author), Palash Ingle (21512921) (author), Rutvij H. Jhaveri (16850751) (author), Ali Anaissi (2837591) (author), Adnan Akhunzada (20151648) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513532422258688
author Junaid Akram (13389717)
author2 Awais Akram (11890289)
Palash Ingle (21512921)
Rutvij H. Jhaveri (16850751)
Ali Anaissi (2837591)
Adnan Akhunzada (20151648)
author2_role author
author
author
author
author
author_facet Junaid Akram (13389717)
Awais Akram (11890289)
Palash Ingle (21512921)
Rutvij H. Jhaveri (16850751)
Ali Anaissi (2837591)
Adnan Akhunzada (20151648)
author_role author
dc.creator.none.fl_str_mv Junaid Akram (13389717)
Awais Akram (11890289)
Palash Ingle (21512921)
Rutvij H. Jhaveri (16850751)
Ali Anaissi (2837591)
Adnan Akhunzada (20151648)
dc.date.none.fl_str_mv 2025-06-09T03:00:00Z
dc.identifier.none.fl_str_mv 10.1109/jstars.2025.3577648
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Privacy-Preserving_Spatial_Crowdsourcing_Drone_Services_for_Post-Disaster_Infrastructure_Monitoring_A_Conditional_Federated_Learning_Approach/29274449
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Civil engineering
Communications engineering
Control engineering, mechatronics and robotics
Information and computing sciences
Artificial intelligence
Distributed computing and systems software
Machine learning
Anomaly detection
Drones
Federated learning (FL)
Spatial crowdsourcing
Structural health monitoring (SHM)
dc.title.none.fl_str_mv Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Sixth-generation (6G) networks, offering ultra-low latency and high bandwidth, provide critical support for rapid data transmission in postdisaster environments where conventional infrastructure may be compromised. This study presents a privacy-preserving framework for postdisaster structural health monitoring (SHM) by integrating 6G-enabled Internet of Drone Things and spatial crowdsourcing. Drones and unmanned ground vehicles collect real-time imagery of damaged infrastructure. To address privacy concerns and reduce communication overhead, we employ federated learning (FL), which enables decentralized model training on local devices without transmitting raw data. A key challenge in FL is the presence of nonindependent and identically distributed data across clients, which degrades global model performance. To mitigate this, we propose personalized conditional federated averaging (PC-FedAvg), a selective aggregation method that incorporates only client models with low validation loss into the global update. The PC-FedAvg framework is built on EfficientNetV2 and includes personalized model adaptation to enhance generalization on heterogeneous data. Experimental results on the “Concrete Crack Images for Classification” dataset demonstrate that PC-FedAvg outperforms baseline FL methods in accuracy and stability. This approach improves the effectiveness and reliability of SHM systems in real-world postdisaster scenarios by enabling timely and accurate damage assessment while preserving data privacy.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/jstars.2025.3577648" target="_blank">https://dx.doi.org/10.1109/jstars.2025.3577648</a></p>
eu_rights_str_mv openAccess
id Manara2_4f276acfc2bd63b60eb047b5f9660470
identifier_str_mv 10.1109/jstars.2025.3577648
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29274449
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning ApproachJunaid Akram (13389717)Awais Akram (11890289)Palash Ingle (21512921)Rutvij H. Jhaveri (16850751)Ali Anaissi (2837591)Adnan Akhunzada (20151648)EngineeringCivil engineeringCommunications engineeringControl engineering, mechatronics and roboticsInformation and computing sciencesArtificial intelligenceDistributed computing and systems softwareMachine learningAnomaly detectionDronesFederated learning (FL)Spatial crowdsourcingStructural health monitoring (SHM)<p dir="ltr">Sixth-generation (6G) networks, offering ultra-low latency and high bandwidth, provide critical support for rapid data transmission in postdisaster environments where conventional infrastructure may be compromised. This study presents a privacy-preserving framework for postdisaster structural health monitoring (SHM) by integrating 6G-enabled Internet of Drone Things and spatial crowdsourcing. Drones and unmanned ground vehicles collect real-time imagery of damaged infrastructure. To address privacy concerns and reduce communication overhead, we employ federated learning (FL), which enables decentralized model training on local devices without transmitting raw data. A key challenge in FL is the presence of nonindependent and identically distributed data across clients, which degrades global model performance. To mitigate this, we propose personalized conditional federated averaging (PC-FedAvg), a selective aggregation method that incorporates only client models with low validation loss into the global update. The PC-FedAvg framework is built on EfficientNetV2 and includes personalized model adaptation to enhance generalization on heterogeneous data. Experimental results on the “Concrete Crack Images for Classification” dataset demonstrate that PC-FedAvg outperforms baseline FL methods in accuracy and stability. This approach improves the effectiveness and reliability of SHM systems in real-world postdisaster scenarios by enabling timely and accurate damage assessment while preserving data privacy.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/jstars.2025.3577648" target="_blank">https://dx.doi.org/10.1109/jstars.2025.3577648</a></p>2025-06-09T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/jstars.2025.3577648https://figshare.com/articles/journal_contribution/Privacy-Preserving_Spatial_Crowdsourcing_Drone_Services_for_Post-Disaster_Infrastructure_Monitoring_A_Conditional_Federated_Learning_Approach/29274449CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/292744492025-06-09T03:00:00Z
spellingShingle Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach
Junaid Akram (13389717)
Engineering
Civil engineering
Communications engineering
Control engineering, mechatronics and robotics
Information and computing sciences
Artificial intelligence
Distributed computing and systems software
Machine learning
Anomaly detection
Drones
Federated learning (FL)
Spatial crowdsourcing
Structural health monitoring (SHM)
status_str publishedVersion
title Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach
title_full Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach
title_fullStr Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach
title_full_unstemmed Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach
title_short Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach
title_sort Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach
topic Engineering
Civil engineering
Communications engineering
Control engineering, mechatronics and robotics
Information and computing sciences
Artificial intelligence
Distributed computing and systems software
Machine learning
Anomaly detection
Drones
Federated learning (FL)
Spatial crowdsourcing
Structural health monitoring (SHM)