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

Akram, J; Akram, A; Ingle, P; Jhaveri, RH; Anaissi, A; Akhunzada, A

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

Akram, J Akram, A Ingle, P Jhaveri, RH Anaissi, A

Akhunzada, A

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, PP, (99), pp. 1-20
Issue Date:: 2025-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (4.19 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Akram, J
dc.contributor.author	Akram, A
dc.contributor.author	Ingle, P
dc.contributor.author	Jhaveri, RH
dc.contributor.author	Anaissi, A https://orcid.org/0000-0002-8864-0314
dc.contributor.author	Akhunzada, A
dc.date.accessioned	2025-07-31T05:29:31Z
dc.date.available	2025-07-31T05:29:31Z
dc.date.issued	2025-01-01
dc.identifier.citation	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, PP, (99), pp. 1-20
dc.identifier.issn	1939-1404
dc.identifier.issn	2151-1535
dc.identifier.uri	http://hdl.handle.net/10453/188938
dc.description.abstract	Sixth-generation (6G) networks, offering ultra-low latency and high bandwidth, provide critical support for rapid data transmission in post-disaster environments where conventional infrastructure may be compromised. This study presents a privacy-preserving framework for post-disaster structural health monitoring (SHM) by integrating 6G-enabled Internet of Drone Things (IoDT) and spatial crowdsourcing. Drones and unmanned ground vehicles (UGVs) 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 non-independent and identically distributed (non-IID) 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 post-disaster scenarios by enabling timely and accurate damage assessment while preserving data privacy.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
dc.relation.isbasedon	10.1109/JSTARS.2025.3577648
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0406 Physical Geography and Environmental Geoscience, 0801 Artificial Intelligence and Image Processing, 0909 Geomatic Engineering
dc.subject.classification	3709 Physical geography and environmental geoscience
dc.subject.classification	4013 Geomatic engineering
dc.subject.classification	4601 Applied computing
dc.title	Privacy-Preserving Spatial Crowdsourcing Drone Services for Post-Disaster Infrastructure Monitoring: A Conditional Federated Learning Approach
dc.type	Journal Article
utslib.citation.volume	PP
utslib.for	0406 Physical Geography and Environmental Geoscience
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0909 Geomatic Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Provost
pubs.organisational-group	University of Technology Sydney/Provost/TD School
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2025-07-31T05:29:28Z
pubs.issue	99
pubs.publication-status	Published
pubs.volume	PP
utslib.citation.issue	99

Abstract:

Sixth-generation (6G) networks, offering ultra-low latency and high bandwidth, provide critical support for rapid data transmission in post-disaster environments where conventional infrastructure may be compromised. This study presents a privacy-preserving framework for post-disaster structural health monitoring (SHM) by integrating 6G-enabled Internet of Drone Things (IoDT) and spatial crowdsourcing. Drones and unmanned ground vehicles (UGVs) 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 non-independent and identically distributed (non-IID) 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 post-disaster scenarios by enabling timely and accurate damage assessment while preserving data privacy.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/188938