FedStack: Personalized activity monitoring using stacked federated learning

作者：

Highlights：

• A novel federated architecture, FedStack, is proposed to overcome the heterogeneity limitation in traditional federated learning.

• Enhanced personalized patient monitoring by adopting the proposed novel federated architecture to classify physical activities.

• FedStack framework outperformed the baseline models’ performance in federated learning.

摘要

•A novel federated architecture, FedStack, is proposed to overcome the heterogeneity limitation in traditional federated learning.•Enhanced personalized patient monitoring by adopting the proposed novel federated architecture to classify physical activities.•FedStack framework outperformed the baseline models’ performance in federated learning.

论文关键词：Federated learning,ANN,CNN,Bi-LSTM,RPM,HAR

论文评审过程：Received 28 June 2022, Revised 12 September 2022, Accepted 19 September 2022, Available online 23 September 2022, Version of Record 30 September 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109929