Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Heart rate prediction method and device based on deep learning

A technology of deep learning and heart rate, applied in the field of data processing, can solve problems such as not being able to prevent diseases well

Active Publication Date: 2019-06-18
南京睿蜂健康医疗科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the detection of heart rate mainly relies on complex algorithms and hardware, but the detection of heart rate is not accurate enough, so that people cannot prevent diseases well and observe their own health status at all times

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
  • Heart rate prediction method and device based on deep learning
  • Heart rate prediction method and device based on deep learning
  • Heart rate prediction method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0115] As an embodiment, the device also includes:

[0116] The model training module is used to train the LSTM model according to different motion states corresponding to the input motion posture signal, and obtain the final LSTM model after training.

[0117] As an implementation manner, the model training module includes:

[0118] Multiple sets of signal acquisition unit, used to acquire multiple sets of signals, each set of signals includes ECG signals, pulse signals and exercise posture signals under various exercise states;

[0119] The training unit is used to input the multiple sets of signals to the pre-established long-short-term memory network LSTM model according to the different motion states for training, obtain the respective neural network parameters of the LSTM models of different motion states after training, and obtain the final LSTM Model.

[0120] As an implementation manner, the multiple groups of signal acquisition units include:

[0121] The initial ...

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 embodiment of the invention provides a heart rate predication method and a heart rate predication device based on deep learning, and belongs to the field of data processing. The method comprises the following steps: first, acquiring to-be-detected pulse signals and moving posture signals, then inputting the to-be-detected pulse signals and moving posture signals to a pretrained final long-short term memory network LSTM (long-short term memory) model, according to the moving states corresponding to the moving posture signals, selecting LSTM models corresponding to the moving states in the final LSTM model for carrying out electrocardiosignal predication, and thus the electrocardiosignal signals are further acquired. With the adoption of the technical scheme, through the moving posture signals, the training model is divided into the plurality of LSTM models corresponding to the different states, meanwhile, electrocardiosignal training and prediction are carried out on the LSTM models, and thus the accurate heart rate value is effectively predicated.

Description

technical field [0001] The present invention relates to the field of data processing, in particular to a heart rate prediction method and device based on deep learning. Background technique [0002] With the development of science and technology, people are more and more concerned about their own health issues. Heart rate is an important indicator of the periodic change information of the human heart, and its change and difference have also become a basic indicator reflecting the heart disease of the tested person. And the heart rate can mainly act on the following aspects: 1. Prognosis detection of heart disease; the heart rate speed and difference of heart disease patients are related to higher survival rate. If the heart rate is always higher than normal, or if the difference between the fastest and slowest heart rate is small, the chance of death is quite high. 2. Prompt whether the amount of exercise is appropriate; heart rate can be used to measure the amount of exerc...

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 Patents(China)
IPC IPC(8): G16H50/70
CPCA61B5/024A61B5/7246A61B5/7267
Inventor 高军峰党鑫荣凡稳陈冉
Owner 南京睿蜂健康医疗科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com