Publication:

FedCoBott: Communication-Efficient Personalized Federated Learning for UWB LoS/NLoS Classification

 
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid0000-0001-5942-9440
cris.virtual.orcid0000-0003-1943-6261
cris.virtual.orcid0000-0001-5269-6909
cris.virtual.orcid0000-0002-0214-5751
cris.virtualsource.department78e08ab8-aadb-4883-92c9-643e40198fef
cris.virtualsource.department775007c5-854e-4f51-9a21-92e054f36393
cris.virtualsource.departmentc0f8fc9d-63d1-433a-af12-c9c6d1c2cf7b
cris.virtualsource.departmenteb7ed649-7114-4ead-84d3-05a804e8fb45
cris.virtualsource.orcid78e08ab8-aadb-4883-92c9-643e40198fef
cris.virtualsource.orcid775007c5-854e-4f51-9a21-92e054f36393
cris.virtualsource.orcidc0f8fc9d-63d1-433a-af12-c9c6d1c2cf7b
cris.virtualsource.orcideb7ed649-7114-4ead-84d3-05a804e8fb45
dc.contributor.authorDuong, Phuong B.
dc.contributor.authorNavidan, Hojjat
dc.contributor.authorFontaine, Jaron
dc.contributor.authorBroring, Arne
dc.contributor.authorShahid, Adnan
dc.contributor.authorDe Poorter, Eli
dc.date.accessioned2026-11-16T12:30:07Z
dc.date.available2026-11-16T12:30:07Z
dc.date.createdwos2026
dc.date.issued2026
dc.description.abstractUltra-wideband (UWB) localization is highly sensitive to multipath propagation and non-line of sight (NLoS) conditions, making accurate line of sight (LoS)/NLoS classification essential for robust positioning. Existing data-driven approaches commonly rely on centralized training, which requires transferring large volumes of raw channel impulse response (CIR) data and limits scalability in distributed deployments. We propose FedCoBott (Federated Communication Bottleneck), a communication-efficient personalized federated learning framework that exchanges only a compact layer while keeping the remaining model components client-specific. FedCoBott-Single processes raw CIR measurements and shares a bottleneck layer, whereas FedCoBott-Dual combines raw CIR measurements with CIR-derived features and shares a fusion layer. We evaluate FedCoBott using real-world UWB datasets under anchor-level, sub-environment-level, and cross-environment-level heterogeneity. Conventional federated baselines, including Federated Averaging (FedAvg) and Federated Proximal (FedProx), exhibit noticeable degradation under heterogeneous client data, whereas FedCoBott substantially mitigates this degradation and achieves near-centralized performance in several settings. Comparison with local-only training shows that the benefit of selective sharing is small in the nearly saturated anchor-level setting, clearer at the sub-environment level, and architecture-dependent across environments, where local-only dual-branch training remains more accurate. FedCoBott reduces communication by approximately 98.2% for the single branch and 96.1% for the dual branch relative to FedAvg and FedProx, and by up to 99.9% relative to centralized raw-data upload, while keeping raw data local. These results demonstrate an effective accuracy–communication trade-off for distributed UWB LoS/NLoS classification.
dc.description.wosFundingTextThis work was supported by European Union's Horizon Europe Research and Innovation Actions under Grant 101168560 (CoEvolution).
dc.identifier.doi10.1109/ojcoms.2026.3740787
dc.identifier.eissn2644-125X
dc.identifier.issn2644-125X
dc.identifier.urihttps://imec-publications.be/handle/20.500.12860/60802
dc.language.isoeng
dc.provenance.editstepusergreet.vanhoof@imec.be
dc.publisherIEEE
dc.source.beginpage13828
dc.source.endpage13847
dc.source.journalIEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY
dc.source.numberofpages20
dc.source.volume7
dc.title

FedCoBott: Communication-Efficient Personalized Federated Learning for UWB LoS/NLoS Classification

dc.typeJournal article
dspace.entity.typePublication
imec.internal.crawledAt2026-10-07
imec.internal.sourcecrawler
imec.internal.wosCreatedAt2026-11-13
Files

Original bundle

Name:
FedCoBott_Communication-Efficient_Personalized_Federated_Learning_for_UWB_LoS_NLoS_Classification.pdf
Size:
1.67 MB
Format:
Adobe Portable Document Format
Description:
Published
Publication available in collections: