Old people biological signal health monitoring method based on LSTM model

A technology of biological signals and health monitoring, applied in health index calculation, neural learning method, biological neural network model, etc.

Inactive Publication Date: 2021-04-30
浙江禾连网络科技有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although IoT and artificial intelligence have been widely used in health fields such as biosignals, there are few methods of using deep learning technology for personalized biosignal analysis and health monitoring of the elderly.

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
  • Old people biological signal health monitoring method based on LSTM model
  • Old people biological signal health monitoring method based on LSTM model
  • Old people biological signal health monitoring method based on LSTM model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The specific embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0037] Such as figure 1 and 2 Shown, a kind of old people's biological signal health monitoring method based on LSTM model is characterized in that, comprises the following modules:

[0038] (1) Data acquisition module: The healthy biosignals of the elderly are collected by IoT devices at different time intervals, and the corresponding multidimensional healthy biosignal original matrix data E is obtained. When the collected signal data meets sufficient training sets, Perform regularization preprocessing on the original matrix, and send the result as input data to the monitoring module for calculation. The present invention defines "0" as unhealthy, "1" as healthy, and marks the signals collected by healthy users as healthy. At the same time, for the accuracy of training, the method will also combine health data to automatically g...

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 discloses an old people biological signal health monitoring method based on an LSTM model, and the method employs an LSTM deep learning model which is related to a time sequence and has a better solution for the problems of gradient disappearance and gradient explosion in a long-sequence training process. Multi-dimensional biological signals collected by Internet of Things equipment from old people at different time intervals are used as model original data, and the model original data are input into an LSTM model after data preprocessing regularization, so that a relationship is established from a time dimension and different biological signal data dimensions. Health data in the past time and different biological signal data are used as standards for judging whether the human body is healthy or not, so that a better health condition monitoring effect is obtained. Meanwhile, a parameter debugging method in the model is provided on the basis of monitoring accuracy, and parameter values capable of being directly applied in the model are determined through experimental debugging.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence smart elderly care, and in particular relates to an LSTM model-based biological signal health monitoring method for the elderly. [0002] technical background [0003] With the increasing pressure of life, more and more people have sub-health or even chronic diseases, and the health problems of the elderly are especially concerned by people. [0004] At present, most of the health monitoring tools only monitor and display various health parameters of the current user in real time locally, or transmit the data to the mobile client via Bluetooth for display, without intelligent analysis and abnormal reminders. Although IoT and artificial intelligence have been widely used in health fields such as biosignals, there are few methods of using deep learning technology for personalized biosignal analysis and health monitoring of the elderly. [0005] As a deep learning model, LSTM is a spe...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G16H80/00G16H50/30G16H50/70G06N3/04G06N3/08
CPCG16H80/00G16H50/30G16H50/70G06N3/084G06N3/044G06N3/045
Inventor 朱敬华邓志豪
Owner 浙江禾连网络科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products