A Federated Learning-Based Framework for Accurately Identifying Human Activity in the Environment

Human Activity Recognition (HAR) refers to the detection of people’s activities during daily life using various types of sensors. Machine learning (ML) has contributed to recording many human activities and plays a meaningful role in Human Activity Recognition. Analysis of the data genera...

Full description

Saved in:
Bibliographic Details
Main Authors: Nwadher Suliman Al-Blihed, Dina M. Ibrahim
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11052285/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710241737867264
author Nwadher Suliman Al-Blihed
Dina M. Ibrahim
author_facet Nwadher Suliman Al-Blihed
Dina M. Ibrahim
author_sort Nwadher Suliman Al-Blihed
collection DOAJ
description Human Activity Recognition (HAR) refers to the detection of people’s activities during daily life using various types of sensors. Machine learning (ML) has contributed to recording many human activities and plays a meaningful role in Human Activity Recognition. Analysis of the data generated by HAR devices may involve deep learning models and algorithms of different kinds. These data are personal and may include some sensitive data. However, many applications of Human Activity Recognition are implemented using a centralized approach, which may negatively affect user information. Federated learning (FL)—a distributed machine learning approach—aims to distribute machine learning models to edge devices. For this study, we developed a system based on federated learning to support Human Activity Recognition through constructing a model for each client individually, using user-based training data and without data sharing. We built FL models, and conducted experiments based on multiple client divisions—namely, 2, 5, or 10 clients—using both model types. The deep learning models used were Convolutional Neural Network (CNN), Residual Network (ResNet), and Long Short-Term Memory (LSTM), and the performance measures used to evaluate these FL models were the Loss function and Accuracy. Our study yielded promising results: ResNet—which, to the best of our knowledge, has not been used in previous studies in this context—achieved the best results with five clients, attaining a 93.05% Accuracy.
format Article
id doaj-art-c563f4f592e049968cf52686bdf914aa
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c563f4f592e049968cf52686bdf914aa2025-08-20T03:14:58ZengIEEEIEEE Access2169-35362025-01-011311064811067010.1109/ACCESS.2025.358355611052285A Federated Learning-Based Framework for Accurately Identifying Human Activity in the EnvironmentNwadher Suliman Al-Blihed0Dina M. Ibrahim1https://orcid.org/0000-0002-7775-0577Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi ArabiaDepartment of Information Technology, College of Computer, Qassim University, Buraydah, Saudi ArabiaHuman Activity Recognition (HAR) refers to the detection of people’s activities during daily life using various types of sensors. Machine learning (ML) has contributed to recording many human activities and plays a meaningful role in Human Activity Recognition. Analysis of the data generated by HAR devices may involve deep learning models and algorithms of different kinds. These data are personal and may include some sensitive data. However, many applications of Human Activity Recognition are implemented using a centralized approach, which may negatively affect user information. Federated learning (FL)—a distributed machine learning approach—aims to distribute machine learning models to edge devices. For this study, we developed a system based on federated learning to support Human Activity Recognition through constructing a model for each client individually, using user-based training data and without data sharing. We built FL models, and conducted experiments based on multiple client divisions—namely, 2, 5, or 10 clients—using both model types. The deep learning models used were Convolutional Neural Network (CNN), Residual Network (ResNet), and Long Short-Term Memory (LSTM), and the performance measures used to evaluate these FL models were the Loss function and Accuracy. Our study yielded promising results: ResNet—which, to the best of our knowledge, has not been used in previous studies in this context—achieved the best results with five clients, attaining a 93.05% Accuracy.https://ieeexplore.ieee.org/document/11052285/Federated learninghuman activity recognitionconvolutional neural networklong short-term memoryresidual networks
spellingShingle Nwadher Suliman Al-Blihed
Dina M. Ibrahim
A Federated Learning-Based Framework for Accurately Identifying Human Activity in the Environment
IEEE Access
Federated learning
human activity recognition
convolutional neural network
long short-term memory
residual networks
title A Federated Learning-Based Framework for Accurately Identifying Human Activity in the Environment
title_full A Federated Learning-Based Framework for Accurately Identifying Human Activity in the Environment
title_fullStr A Federated Learning-Based Framework for Accurately Identifying Human Activity in the Environment
title_full_unstemmed A Federated Learning-Based Framework for Accurately Identifying Human Activity in the Environment
title_short A Federated Learning-Based Framework for Accurately Identifying Human Activity in the Environment
title_sort federated learning based framework for accurately identifying human activity in the environment
topic Federated learning
human activity recognition
convolutional neural network
long short-term memory
residual networks
url https://ieeexplore.ieee.org/document/11052285/
work_keys_str_mv AT nwadhersulimanalblihed afederatedlearningbasedframeworkforaccuratelyidentifyinghumanactivityintheenvironment
AT dinamibrahim afederatedlearningbasedframeworkforaccuratelyidentifyinghumanactivityintheenvironment
AT nwadhersulimanalblihed federatedlearningbasedframeworkforaccuratelyidentifyinghumanactivityintheenvironment
AT dinamibrahim federatedlearningbasedframeworkforaccuratelyidentifyinghumanactivityintheenvironment