Unlock instant, AI-driven research and patent intelligence for your innovation.

Intelligent medical system based on edge calculation and federated learning

An edge computing and medical system technology, applied in the field of smart medical system, can solve the problems of real-time, privacy, intelligence, etc., to avoid network congestion, avoid leakage, and improve the response speed.

Pending Publication Date: 2021-12-31
GUILIN UNIVERSITY OF TECHNOLOGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of this invention is to solve the problems of real-time, privacy and intelligence existing in the existing smart medical system, and propose a smart medical system based on edge computing and federated learning

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent medical system based on edge calculation and federated learning
  • Intelligent medical system based on edge calculation and federated learning
  • Intelligent medical system based on edge calculation and federated learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0022] like figure 1 As shown, a smart medical system based on edge computing and federated learning includes medical data acquisition subsystem 1, edge computing subsystem 2, and federated server subsystem 3. Medical data acquisition subsystem 1 includes body surface electromyography sensor 1-1, medical pressure sensor 1-2, human body temperature sensor 1-3, X-ray CT sensor 1-4, optical fiber sensor 1-5; edge computing subsystem 2 Including principal component analysis method 2-1 of data preprocessing module, variance analysis method 2-2 and convolutional neural network CNN algorithm of model training module 2-3, centralized ring topology of edge network module 2-4, improvement LCR ring election algorithm 2-5, heartbeat detection mechanism 2-6; federated server subsystem 3 includes federated averaging algorithm 3-1.

[0023] The medical data acquisition subsystem 1 is connected to the edge computing subsystem 2, and the edge computing subsystem 2 is connected to the federate...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an intelligent medical system based on edge computing and federated learning, which collects medical data by using edge devices such as a medical sensor and the like, and stores the collected data in a local edge server. The edge server forms a centralized annular edge network by using network equipment such as a router, processes and analyzes local data by using a principal component analysis method and a variance analysis method, and performs model training by using a convolutional neural network (CNN) algorithm. And each medical institution uploads the locally trained model gradient to the federal server, a federal server performs aggregation processing on the model gradient by using a federal average algorithm and returns a new model gradient, and each medical institution performs local model updating according to the new model gradient. And through continuous iteration, the medical model effect is continuously improved. Therefore, better intelligent medical service is realized while the data security and privacy are protected.

Description

technical field [0001] The invention belongs to the technical field of edge computing and machine learning, in particular to an intelligent medical system based on edge computing and federated learning. Background technique [0002] With the continuous advancement of science and technology, the service methods of all walks of life have also undergone earth-shaking changes. More and more intelligent devices have replaced manual services to provide people with more efficient and convenient smart services, and the medical field has always been a part of it that has attracted much attention. At the same time, with the popularity of IoT terminal devices in the medical field, various wearable body sensors and medical devices are used in medical services. These IoT terminal devices can collect a large amount of medical data and upload the data to remote cloud servers through the network Perform processing and analysis to provide patients with accurate and fast medical services. I...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G16H40/67G16H50/20G06F21/62G06K9/62G06N3/04G06N3/08G06N20/00H04L29/08
CPCG16H40/67G16H50/20G06F21/6245G06N3/08G06N20/00H04L67/1051H04L67/12G06N3/045G06F18/2135
Inventor 谢晓兰郭杨刘亚荣
Owner GUILIN UNIVERSITY OF TECHNOLOGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com