Pulse wave model prediction method based on neural network

A neural network and model prediction technology, applied in diagnostic recording/measurement, medical science, sensors, etc., to achieve strong practicability, improve effectiveness, and fast and accurate prediction methods

Pending Publication Date: 2021-01-29
HARBIN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a kind of pulse wave model prediction method based on neural network in order to solve the existing urgent problem of a kind of pulse wave prediction method

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
  • Pulse wave model prediction method based on neural network
  • Pulse wave model prediction method based on neural network
  • Pulse wave model prediction method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0020] A kind of neural network-based pulse wave model prediction method of the present embodiment, such as figure 1 As shown, the method is realized through the following steps:

[0021] Step 1. Obtain information through various sensors of the smart wearable device worn by the monitored person; specifically:

[0022] The microprocessor of the smart wearable device controls the pulse sensor to obtain the pulse wave information of the monitored person in real time, controls the acceleration sensor to obtain the attitude information of the monitored person in real time, and finally packs the pulse wave data and attitude data according to the set data format. The bluetooth module sends to the smart phone of the monitored person;

[0023] Step 2. The smart phone of the monitored person performs data preprocessing on the received pulse wave data and attitude data, and then stores them locally. After displaying them through the UI, the preprocessed data is packaged and uploaded in...

specific Embodiment approach 2

[0027] The difference from the first specific embodiment is that a neural network-based pulse wave model prediction method in this embodiment,

[0028] The step of data preprocessing described in step 2 comprises, adopts smooth prior method to correct pulse wave baseline excursion, and removes motion artifact while carrying out waveform segmentation; In addition, acceleration information is converted into cardiovascular state value;

[0029] Wherein, the process of correcting the pulse wave baseline drift by the smooth prior method is specifically:

[0030] Assuming that the original pulse wave signal is f, it should contain two parts of the signal:

[0031] f=f stat +f trend

[0032] Among them, f stat is a stationary signal in f; f trend is the baseline drift signal of f; where:

[0033] f stat =Hq+v

[0034] in, is the observation matrix, is the regression parameter, N refers to the signal length, M refers to the number of regression parameters, and v is the obs...

specific Embodiment approach 3

[0049] Different from the specific embodiment 1 or 2, in the present embodiment, a neural network-based pulse wave model prediction method, the process of predicting the cardiovascular data type in real time through the prediction evaluation model described in step 3 includes:

[0050] First, carry out the training of the model, specifically:

[0051] First perform DBSCAN clustering on the pulse wave, and then use the clustered label as the target value to train the classification models of pulse wave and cardiovascular state respectively;

[0052] Then, make the actual forecast, specifically:

[0053]Firstly, the state is determined by the cardiovascular state value, and then the pulse wave mutation degree is measured by the probability of the pulse wave conforming to the corresponding state, and then the pulse wave model is predicted.

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 a pulse wave model prediction method based on a neural network and belongs to the field of image recognition. According to the pulse wave model prediction method based on a neural network, intelligent wearable equipment worn by a monitored person is provided with a plurality of sensors to obtain information; a smart phone of a monitored person pre-processes the received pulse wave data and posture data, locally stores the preprocessed pulse wave data and posture data, packages the preprocessed data in a software background while displaying the preprocessed pulse wave data and posture data through a UI, and uploads the packaged data to a server; the server unpacks and recovers the received pulse wave data and posture data according to the corresponding network interfaces, stores the received data into a server database, finally performs training of a pulse wave prediction model by using a neural network, and predicts the pulse wave data in real time through the pulse wave prediction model. By fusing pulse wave and acceleration information, the pulse wave prediction method which is good in generalization ability and high in practicability is designed.

Description

technical field [0001] The invention relates to a neural network-based pulse wave model prediction method. Background technique [0002] With the development of society and economy, people's pace of life is gradually accelerating, followed by increasingly prominent sub-health problems. Sub-health is a critical state between health and disease. Although it does not meet the standard of any disease, it will appear in various negative states, such as mental state, resistance, immunity decline and other symptoms. If it cannot be detected and controlled or improved in time, it will easily lead to more serious physical and mental diseases, among which cardiovascular disease is the most serious. [0003] With the aggravation of the sub-health problems of the people in our country, the situation of cardiovascular diseases is also becoming more and more serious, facing the high prevalence, high mortality, and high disability rate, there is an urgent need for a pulse wave prediction ...

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): A61B5/02A61B5/11
CPCA61B5/0022A61B5/02A61B5/1116A61B5/7275A61B5/7267
Inventor 苏子美张海啸
Owner HARBIN UNIV OF SCI & TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap