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

A health status evaluation system based on deep learning of multidimensional physiological big data

A technology of health status and physiological data, applied in the direction of instruments, calculations, character and pattern recognition, etc., can solve problems such as treatment delays and shortage of medical resources

Active Publication Date: 2019-09-03
CHONGQING UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

One of the reasons is the relative shortage of medical resources. People with a fast pace of life often go to the hospital for examination and treatment after they have serious physical problems, which leads to delays in treatment.

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
  • A health status evaluation system based on deep learning of multidimensional physiological big data
  • A health status evaluation system based on deep learning of multidimensional physiological big data
  • A health status evaluation system based on deep learning of multidimensional physiological big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] A health status evaluation system based on multi-dimensional physiological big data deep learning, characterized in that: comprising a background analysis system and a detection device;

[0030] The background analysis system for the original physiological data sample C q When performing an analysis, the following steps are involved:

[0031] 1) Obtain raw physiological data sample C q , q is the physiological data sample number, q=1, 2...,

[0032] in: is a physiological parameter, sample C q Among them, there are m kinds of physiological parameters (such as blood pressure, heart rate, body weight, body temperature, etc.), and each physiological parameter is collected at time t, t=1, 2...n 0 ;

[0033] 2): The original physiological data sample C q , normalized to get Build physiological datasets {S1, S2...}

[0034] 3) Feature extraction

[0035] 3-1) The physiological data sample S in the selected physiological data set q Input variable, set the length ...

Embodiment 2

[0066] A health status evaluation system based on multi-dimensional physiological big data deep learning, characterized in that: comprising a background analysis system and a detection device;

[0067] The background analysis system for the original physiological data sample C q When performing an analysis, the following steps are involved:

[0068] 1) Obtain raw physiological data sample C q , q is the physiological data sample number, q=1, 2...,

[0069] in: is a physiological parameter, sample C q , there are m kinds of physiological parameters, and each physiological parameter is collected at time t, t=1, 2...n 0 ;

[0070] 2): The original physiological data sample C q , normalized to get Build physiological datasets {S1, S2...}

[0071] 3) Feature extraction (in abnormal physiological signal detection, the network structure design is as follows figure 2 As shown, it mainly includes two parts: feature learning and anomaly detection)

[0072] 3-1) The physio...

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 health status evaluation system based on deep learning of multidimensional physiological big data, which utilizes a non-supervised convolutional neural network to extract features of physiological time-series data, and then utilizes multivariate Gaussian distribution for feature abnormality detection. The results show that it is an efficient anomaly detection system for physiological signals that can learn high-level features of signals from original physiological signals and multivariate Gaussian distribution anomaly detection. Users can identify certain early symptoms and take corresponding preventive measures in advance to reduce the risk of disease.

Description

technical field [0001] The present invention relates to medical testing equipment. Background technique [0002] In recent years, our life has become more and more closely connected with various smart devices, and modern life is increasingly inseparable from these smart devices. Using these smart devices, people nowadays can record various physiological signals anytime and anywhere, such as blood pressure, blood sugar, EEG, ECG, EMG, body temperature, breathing and other physiological signals. By analyzing these signals, we can understand Some information about the current state of our bodies. [0003] However, the incidence of various types of chronic non-communicable diseases is increasing. One of the reasons is the relative shortage of medical resources. People with a fast pace of life often go to the hospital for examination and treatment after they have serious physical problems, which leads to delays in treatment. Contents of the invention [0004] It is an object...

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): G06K9/00
CPCG06F2218/08G06F2218/12
Inventor 王楷熊庆宇赵友金孙国坦马龙昆刘通
Owner CHONGQING UNIV
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