Mobile health-empowered traditional ethnic sports: AI-based data analysis improving security

Abstract

Traditional ethnic sports shape the Chinese nation's solid national spirit, and mobile health development has been extended to various fields. In this study, we empower mobile health to traditional ethnic sports. Sensors used for collecting health data are worn on athletes and communicated with sink nodes through the network to provide better training guidance for traditional ethnic sports athletes through data analysis. However, the devices used to collect health data may come from many companies, and aggregating the data inevitably involves data security. As a new basic artificial intelligence technology, federated learning can use the health data of athletes to train the data analysis model in the case of original data localization, to solve the security and privacy problems in health data sharing to a certain extent. To this end, a differentially private-dynamic federated learning framework for dynamic aggregation weights under an untrusted central server is proposed, which sets a dynamic model aggregation weight, and this method directly learns federated learning from the data of different participants. The learning model aggregates the weights so that it is suitable for non-independent data environments. Experimental results show that the proposed framework not only provides local privacy guarantees, but also achieves higher accuracy and improves the security of mobile health data of traditional ethnic sports athletes in federated learning.