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

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

Federated 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...

Full description

Saved in:

Bibliographic Details
Main Authors:	Taha Z.K., Paw J.K.S., Tak Y.C., Kiong T.S., Kadirgama K., Benedict F., Ding T.J., Ali K., Abed A.M.
Other Authors:	57202301078
Format:	Article
Published:	Institute of Electrical and Electronics Engineers Inc. 2025
Subjects:	Data privacy Data reduction Feature extraction Accuracy Dimensionality reduction Features extraction Federated learning Human activity recognition Imbalance datum Local preprocessing Uncertainty Uncertainty symmetry Smartphones
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uniten.dspace-37055
record_format	dspace
spelling	my.uniten.dspace-370552025-03-03T15:47:01Z Advances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Data Taha Z.K. Paw J.K.S. Tak Y.C. Kiong T.S. Kadirgama K. Benedict F. Ding T.J. Ali K. Abed A.M. 57202301078 58168727000 36560884300 57216824752 12761486500 57194591957 38863172300 36130958600 57716714900 Data privacy Data reduction Feature extraction Accuracy Dimensionality reduction Features extraction Federated learning Human activity recognition Imbalance datum Local preprocessing Uncertainty Uncertainty symmetry Smartphones Federated 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. Final 2025-03-03T07:47:01Z 2025-03-03T07:47:01Z 2024 Article 10.1109/ACCESS.2024.3435910 2-s2.0-85200239234 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85200239234&doi=10.1109%2fACCESS.2024.3435910&partnerID=40&md5=b06455124946bb599748815d46a4c3b0 https://irepository.uniten.edu.my/handle/123456789/37055 12 186277 186295 Institute of Electrical and Electronics Engineers Inc. Scopus
institution	Universiti Tenaga Nasional
building	UNITEN Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Tenaga Nasional
content_source	UNITEN Institutional Repository
url_provider	http://dspace.uniten.edu.my/
topic	Data privacy Data reduction Feature extraction Accuracy Dimensionality reduction Features extraction Federated learning Human activity recognition Imbalance datum Local preprocessing Uncertainty Uncertainty symmetry Smartphones
spellingShingle	Data privacy Data reduction Feature extraction Accuracy Dimensionality reduction Features extraction Federated learning Human activity recognition Imbalance datum Local preprocessing Uncertainty Uncertainty symmetry Smartphones Taha Z.K. Paw J.K.S. Tak Y.C. Kiong T.S. Kadirgama K. Benedict F. Ding T.J. Ali K. Abed A.M. Advances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Data
description	Federated 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.
author2	57202301078
author_facet	57202301078 Taha Z.K. Paw J.K.S. Tak Y.C. Kiong T.S. Kadirgama K. Benedict F. Ding T.J. Ali K. Abed A.M.
format	Article
author	Taha Z.K. Paw J.K.S. Tak Y.C. Kiong T.S. Kadirgama K. Benedict F. Ding T.J. Ali K. Abed A.M.
author_sort	Taha Z.K.
title	Advances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Data
title_short	Advances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Data
title_full	Advances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Data
title_fullStr	Advances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Data
title_full_unstemmed	Advances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Data
title_sort	advances in federated learning: combining local preprocessing with adaptive uncertainty symmetry to reduce irrelevant features and address imbalanced data
publisher	Institute of Electrical and Electronics Engineers Inc.
publishDate	2025
_version_	1826077503376064512
score	13.244413

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

Similar Items