FedWFC: Federated learning with weighted fuzzy clustering for handling heterogeneous data in MIoT networks
The diversity of sources and uneven distribution of medical data contributes to the statistical heterogeneity within the Medical Internet of Things (MIoT) networks. In this context, comprehensive analysis of patient data is imperative to provide more precise diagnoses and treatment strategies, rende...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824011888 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595946789142528 |
|---|---|
| author | Le Sun Shunqi Liu Ghulam Muhammad |
| author_facet | Le Sun Shunqi Liu Ghulam Muhammad |
| author_sort | Le Sun |
| collection | DOAJ |
| description | The diversity of sources and uneven distribution of medical data contributes to the statistical heterogeneity within the Medical Internet of Things (MIoT) networks. In this context, comprehensive analysis of patient data is imperative to provide more precise diagnoses and treatment strategies, rendering personalized medical treatment indispensable. Moreover, the transmission of medical data over networks raises concerns regarding data privacy, necessitating thorough consideration. To address these challenges, we propose FedWFC, a federated learning method that combines a novel importance weight with fuzzy k-means clustering to effectively handle the heterogeneous medical data in MIoT networks. Firstly, we utilize fuzzy k-means for clustering and partitioning local model parameters from MIoT devices, enabling centralized updates of multiple global models based on these clusters. This cluster-centric approach streamlines personalized updates for local models. Secondly, the introduction of the new importance weight allows us to tighten the optimization error bound for global model updates. Experiments show that FedWFC improves the macro F1 score by 4.24% and the micro accuracy by 4.99% compared with existing methods, highlighting its effectiveness in MIoT data processing. |
| format | Article |
| id | doaj-art-411038cd3c2140128db83f3129c25f71 |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-411038cd3c2140128db83f3129c25f712025-01-18T05:03:35ZengElsevierAlexandria Engineering Journal1110-01682025-01-01111194202FedWFC: Federated learning with weighted fuzzy clustering for handling heterogeneous data in MIoT networksLe Sun0Shunqi Liu1Ghulam Muhammad2Department of Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology, Nanjing 210044, ChinaDepartment of Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology, Nanjing 210044, ChinaDepartment of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, 11543, Saudi Arabia; Corresponding author.The diversity of sources and uneven distribution of medical data contributes to the statistical heterogeneity within the Medical Internet of Things (MIoT) networks. In this context, comprehensive analysis of patient data is imperative to provide more precise diagnoses and treatment strategies, rendering personalized medical treatment indispensable. Moreover, the transmission of medical data over networks raises concerns regarding data privacy, necessitating thorough consideration. To address these challenges, we propose FedWFC, a federated learning method that combines a novel importance weight with fuzzy k-means clustering to effectively handle the heterogeneous medical data in MIoT networks. Firstly, we utilize fuzzy k-means for clustering and partitioning local model parameters from MIoT devices, enabling centralized updates of multiple global models based on these clusters. This cluster-centric approach streamlines personalized updates for local models. Secondly, the introduction of the new importance weight allows us to tighten the optimization error bound for global model updates. Experiments show that FedWFC improves the macro F1 score by 4.24% and the micro accuracy by 4.99% compared with existing methods, highlighting its effectiveness in MIoT data processing.http://www.sciencedirect.com/science/article/pii/S1110016824011888Medical Internet of ThingsFederated learningStatistical heterogeneityImportance weightFuzzy k-means clustering |
| spellingShingle | Le Sun Shunqi Liu Ghulam Muhammad FedWFC: Federated learning with weighted fuzzy clustering for handling heterogeneous data in MIoT networks Alexandria Engineering Journal Medical Internet of Things Federated learning Statistical heterogeneity Importance weight Fuzzy k-means clustering |
| title | FedWFC: Federated learning with weighted fuzzy clustering for handling heterogeneous data in MIoT networks |
| title_full | FedWFC: Federated learning with weighted fuzzy clustering for handling heterogeneous data in MIoT networks |
| title_fullStr | FedWFC: Federated learning with weighted fuzzy clustering for handling heterogeneous data in MIoT networks |
| title_full_unstemmed | FedWFC: Federated learning with weighted fuzzy clustering for handling heterogeneous data in MIoT networks |
| title_short | FedWFC: Federated learning with weighted fuzzy clustering for handling heterogeneous data in MIoT networks |
| title_sort | fedwfc federated learning with weighted fuzzy clustering for handling heterogeneous data in miot networks |
| topic | Medical Internet of Things Federated learning Statistical heterogeneity Importance weight Fuzzy k-means clustering |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824011888 |
| work_keys_str_mv | AT lesun fedwfcfederatedlearningwithweightedfuzzyclusteringforhandlingheterogeneousdatainmiotnetworks AT shunqiliu fedwfcfederatedlearningwithweightedfuzzyclusteringforhandlingheterogeneousdatainmiotnetworks AT ghulammuhammad fedwfcfederatedlearningwithweightedfuzzyclusteringforhandlingheterogeneousdatainmiotnetworks |