This paper provides a comprehensive study of Federated Learning (FL) with an emphasis on components, challenges, applications and FL environment. FL can be applicable in multiple fields and domains in real-life models. in the medical system, the privacy of patients records and their medical condition is critical data, therefore collaborative learning or federated learning comes into the picture. On other hand build an intelligent system assist the medical staff without sharing the data lead into the FL concept and one of the applications that are used is a brain tumor diagnosis intelligent system based on AI methods that can efficiently work in a collaborative environment.this paper will introduce some of the applications and related work in the medical field and work under the FL concept then summarize them to introduce the main limitations of their work.
翻译:本文件对联邦学习联合会(FL)进行了全面研究,重点是组成部分、挑战、应用和FL环境。FL可以适用于现实生活模式的多个领域和领域。在医疗系统中,病人记录及其健康状况的隐私是关键数据,因此合作学习或联合学习进入了全局。另一方面,建立一个智能系统,协助医务人员,但不分享数据引导进入FL概念,而所使用的应用之一是基于AI方法的脑肿瘤诊断智能系统,该系统可在合作环境中有效工作。本文件将介绍医疗领域的一些应用和相关工作以及根据FL概念开展的工作,然后总结介绍其工作的主要局限性。