Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power consumption.However,most wearable health data is distributed across d...Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power consumption.However,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy regulations.The first challenge addressed in this paper is communicating in a privacy-preserving manner among different organizations.The second technical challenge is handling the dynamic expansion of the federation without model retraining.To address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model performance.Based on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical challenge.FedIERF introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model incrementally.The experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the federation.This opens up opportunities for cooperation between different organizations in wearable health monitoring.展开更多
基金supported by the National Natural Science Foundation of China under Grant Nos.62002187,62002189,61972383,61972237 and 61976127the Science Research Project of Hebei Education Department of China under Grant No.QN2023184。
文摘Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power consumption.However,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy regulations.The first challenge addressed in this paper is communicating in a privacy-preserving manner among different organizations.The second technical challenge is handling the dynamic expansion of the federation without model retraining.To address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model performance.Based on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical challenge.FedIERF introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model incrementally.The experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the federation.This opens up opportunities for cooperation between different organizations in wearable health monitoring.
