Patient pulse condition diagnosis system based on neural network

A neural network and diagnostic system technology, applied in the field of pulse diagnosis system, can solve problems such as difficulty in gaining trust in doctor's pulse diagnosis level and difficulty in improving pulse diagnosis ability training, and achieve the effects of saving time and labor costs, stabilizing the model, and ensuring accuracy

Pending Publication Date: 2022-07-29
HARBIN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Among the four basic diagnoses of traditional Chinese medicine, TCM pulse is an extremely important diagnostic link. It can not only directly reflect the overall health status of the patient, but also provide auxiliary diagnostic factors for many specific diseases. However, the training of a doctor's ability to diagnose pulse It often takes a very long time and enough patient samples for training. This situation makes it difficult for some young doctors to improve their pulse diagnosis ability, making it difficult for doctors to gain trust in their pulse diagnosis level. Therefore, the invention of this paper To a certain extent, it also promotes the relationship between doctors and patients.

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
  • Patient pulse condition diagnosis system based on neural network
  • Patient pulse condition diagnosis system based on neural network
  • Patient pulse condition diagnosis system based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below with reference to the accompanying drawings, so that those skilled in the art can refer to the description text to implement the present invention.

[0034] The invention works in the Ubuntu16.04.4LTS environment, and uses PyTorch as the framework to build. The main parameters are: the initial learning rate is 0.001, the momentum parameter is 0.942, the weight coefficient is 0.0005, and the training threshold is 0.62. Diversity, corresponding data enhancement is carried out on the fluctuation frequency and fluctuating vibration of the pulse, and each step selects whether to use it or not with a probability of 0.5.

[0035] The technical scheme adopted in the present invention is: a neural network-based patient pulse condition diagnosis system, comprising the following steps:

[0036] (1) Acquisition of patient’s wrist pulse information data;

[0037] (2) The division of the patient's wrist pulse information samples;...

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 condition diagnosis system based on a neural network. The pulse condition diagnosis system comprises a pulse diagnosis sleeve for acquiring wrist pulse pulsation data of a patient and a pulse condition diagnosis system based on the neural network. A wrist pulse receptor of the pulse diagnosis sleeve is a device for acquiring wrist pulse beat data of a patient, the pulse diagnosis sleeve is connected with a pulse condition diagnosis system of a computer and used for data transmission, and a sensor is arranged in the pulse diagnosis sleeve and used for accurately sensing the wrist pulse beat data of the patient. The core technology of the diagnosis system comprises the following steps: acquiring wrist pulse information data of a patient; dividing the wrist pulse information sample of the patient; extracting features of the wrist pulse information of the patient; and constructing a patient pulse symbology type recognition model based on a neural network. The pulse condition pulsation features are extracted by using CSPDarknet53, a pulse diagnosis recognition module is constructed on a verification set, a pulse diagnosis data set is re-clustered by using a K-means algorithm, and accurate and representative pulse condition classification is obtained.

Description

technical field [0001] The invention relates to a pulse condition diagnosis system based on a neural network, which belongs to the field of artificial intelligence deep learning. Background technique [0002] Among the four basic diagnostics of traditional Chinese medicine, pulse detection is an extremely important diagnostic link. It can not only directly reflect the overall health status of patients, but also provide auxiliary diagnostic factors for many specific diseases. However, the training of a doctor's ability to diagnose pulses It often takes a very long time and enough patient samples for training, which makes it difficult for some young doctors to improve the pulse diagnosis ability, and makes it difficult for doctors to trust the level of pulse diagnosis. Therefore, the invention of this paper To a certain extent, it also promotes the doctor-patient relationship. [0003] In the existing TCM pulse diagnosis technology, the doctor perceives the patient's pulse am...

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): A61B5/02A61B5/00G06F30/27G06K9/62G06F119/02
CPCA61B5/02007A61B5/4854A61B5/7264A61B5/7267A61B5/702G06F30/27G06F2119/02G06F18/23213G06F18/214
Inventor 张玉王青罗智勇
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