Recent Trends of Federated Learning for Smart Healthcare Systems

Author:

Handa Tanvi1ORCID,Singhal Ishita2ORCID,Chakraborty Pooja3ORCID,Kaur Geetpriya4

Affiliation:

1. Gian Sagar Dental College and Hospital, India

2. SGT University, India

3. Annai Fathima College of Arts and Science, India

4. Institute of Dental Studies and Technologies, India

Abstract

The Internet of Things (IoT) has brought a revolutionary change in the healthcare system. Smart devices have helped people maintain their health by collecting and storing a wide range of data. Artificial intelligence (AI) has made its promising way in several areas. They help in the early diagnosis of various diseases along with storage and interpretation of health data. However, due to the lack of communication between devices and the risk of transmission of data, the efficiency of AI devices is questionable. To avoid the transmission of data, Federation learning (FL) was highlighted as an approach where issues related to the security of sensitive data can be reduced significantly. The combination of FL, AI, and Explainable Artificial Intelligence (XAI) techniques can minimize several limitations and challenges in the healthcare system. This chapter presents an overview of FL's application in healthcare. Different studies presented data about FL and its usage in healthcare. Currently, this paradigm approach is successfully used by specialists in diagnostic purposes.

Publisher

IGI Global

Reference50 articles.

1. Artificial Intelligence in Endodontics: Current Applications and Future Directions

2. Iot-based smart cities: A survey.;H.Arasteh;2016 IEEE 16th International Conference on Environment and Electrical Engineering (EEEIC)

3. Medical Robots: Current Systems and Research Directions

4. Botnets and Internet of Things Security

5. BibiN.SikandarM.Ud DinI.AlmogrenA.AliS. (2020). In NazirS. (Ed.), IoMT-Based Automated Detection and Classification of Leukemia Using Deep Learning (pp. 1–12). J Healthc Eng.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3