Publication:
Advances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Data

Simple item page
dc.citedby0
dc.contributor.authorTaha Z.K.en_US
dc.contributor.authorPaw J.K.S.en_US
dc.contributor.authorTak Y.C.en_US
dc.contributor.authorKiong T.S.en_US
dc.contributor.authorKadirgama K.en_US
dc.contributor.authorBenedict F.en_US
dc.contributor.authorDing T.J.en_US
dc.contributor.authorAli K.en_US
dc.contributor.authorAbed A.M.en_US
dc.contributor.authorid57202301078en_US
dc.contributor.authorid58168727000en_US
dc.contributor.authorid36560884300en_US
dc.contributor.authorid57216824752en_US
dc.contributor.authorid12761486500en_US
dc.contributor.authorid57194591957en_US
dc.contributor.authorid38863172300en_US
dc.contributor.authorid36130958600en_US
dc.contributor.authorid57716714900en_US
dc.date.accessioned2025-03-03T07:47:01Z
dc.date.available2025-03-03T07:47:01Z
dc.date.issued2024
dc.description.abstractFederated learning is increasingly being considered for sensor-driven human activity recognition, offering advantages in terms of privacy and scalability compared to centralized methods. However, challenges such as feature selection and client imbalanced data persist. In this study, FLP-DS2MOTE-USA is suggested, a system that integrates federated local preprocessing, adaptive thresholding based on uncertainty symmetry, and a density- sensitive synthetic minority over-sampling approach. Each client preprocesses data locally and employs DS2MOTE for class balancing. On the server side, adaptive thresholding based on uncertainty symmetry is utilized to identify the optimal client for training the global mode. Evaluation on two distinct datasets - Human Activity Recognition with Smartphones and Human Activity Recognition (OpenPose) - reveals that our model outperforms FedAvg, FedSgd, FedSmote, and FedNova, achieving accuracies of 90.57% and 96.58%, respectively. In addition, FLP-DS2MOTE-USA minimizes update size and network overhead on the Human Activity Recognition with Smartphones, while achieving improvements on the OpenPose dataset. Overall, the proposed method not only addresses issues of imbalanced data but also reduces computational complexity via streamlined local preprocessing, and server-side mechanisms ensure client privacy. It outperforms traditional federated learning techniques in both accuracy and efficiency. ? 2013 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1109/ACCESS.2024.3435910
dc.identifier.epage186295
dc.identifier.scopus2-s2.0-85200239234
dc.identifier.spage186277
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85200239234&doi=10.1109%2fACCESS.2024.3435910&partnerID=40&md5=b06455124946bb599748815d46a4c3b0
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/37055
dc.identifier.volume12
dc.pagecount18
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.sourceScopus
dc.sourcetitleIEEE Access
dc.subjectData privacy
dc.subjectData reduction
dc.subjectFeature extraction
dc.subjectAccuracy
dc.subjectDimensionality reduction
dc.subjectFeatures extraction
dc.subjectFederated learning
dc.subjectHuman activity recognition
dc.subjectImbalance datum
dc.subjectLocal preprocessing
dc.subjectUncertainty
dc.subjectUncertainty symmetry
dc.subjectSmartphones
dc.titleAdvances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Dataen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS