Parameter optimization method for air wave pressure massager based on deep learning algorithm

A technology of deep learning and optimization methods, applied in the medical field, can solve the problems of high retraining cost and low accuracy, and achieve the effect of eliminating redundant equipment

Active Publication Date: 2019-02-15
HARBIN INST OF TECH
View PDF11 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to solve the shortcomings of low accuracy and high retraining cost caused by only one trai

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
  • Parameter optimization method for air wave pressure massager based on deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0026] Specific embodiment one: a method for optimizing parameters of an air wave pressure massager based on a deep learning algorithm comprises the following steps:

[0027] Step 1: Collect the user's blood pressure and pulse data as a training set;

[0028] Step 2: Establish a deep learning structure model on the server;

[0029] Step 3: Input the training set of step 1 into the deep learning structure model established in step 2 for training, and obtain the trained deep learning structure model;

[0030] Step 4: Collect the blood pressure and pulse data of the user of the air wave pressure massager, input it into the deep learning structure model after training, the model outputs the parameters of the air wave pressure massager, and adjust the air wave pressure massager according to the output parameters of the air wave pressure massager Massage intensity, massage frequency and massage position, the parameters of the air wave pressure massager include massage intensity, ma...

specific Embodiment approach 2

[0044] Specific embodiment two: the difference between this embodiment and specific embodiment one is: the specific process of establishing the deep learning structure model on the server in the second step is:

[0045] The user's blood pressure and pulse data collected in step 1 are used as input, and the parameters of the air wave pressure massager are output through the activation function layer and the fully connected layer.

[0046] Other steps and parameters are the same as those in Embodiment 1.

specific Embodiment approach 3

[0047] Embodiment 3: The difference between this embodiment and Embodiment 1 or 2 is that the activation function of the excitation function layer is specifically:

[0048] Preprocess the collected user's blood pressure and pulse data;

[0049] Set the threshold range of blood pressure and pulse; if it is higher than the threshold range, the difference between it and the upper limit of the threshold is recorded as positive; if it is lower than the threshold range, the difference between it and the lower limit of the threshold is recorded as negative; in the threshold range Internally recorded as 0;

[0050] Take the softplus function for the preprocessed value as the activation function;

[0051] The softplus function is log(1+exp(t)), where t is a preprocessed value.

[0052] Other steps and parameters are the same as those in Embodiment 1 or Embodiment 2.

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 relates to a parameter optimization method for an air wave pressure massager based on a deep learning algorithm, relates to parameter optimization methods for air wave pressure massagers, and solves the problems of low accuracy and high retraining cost which are caused by the fact that existing deep learning is only trained once. The parameter optimization method for the air wave pressure massager based on the deep learning algorithm comprises the steps that 1, blood pressure and pulse data of a user is collected; 2, a deep learning structure model is established on a server; 3,a trained deep learning structure model is obtained; 4, the blood pressure and pulse data of the user is collected and input into the trained deep learning structure model, and massage intensity, massage frequency and massage positions of the air wave pressure massager are adjusted according to the output parameters of the air wave pressure massager; 5, the obtained trained deep learning structuremodel is trained through time T to obtain a new model; the deep learning structure model trained in step 4 is replaced with the new model, and step 4 is repeated. The parameter optimization method for the air wave pressure massager based on the deep learning algorithm is applied to the technical field of medical treatment.

Description

technical field [0001] The invention relates to the field of medical technology, in particular to an air wave pressure massager parameter optimization method based on a deep learning algorithm. Background technique [0002] The air wave pressure therapy instrument repeatedly inflates and deflates the multi-cavity airbags in order to form a circulatory pressure on the limbs and tissues, which can promote the flow of blood and lymph, and has been widely used in the treatment or alleviation of various diseases. But there are still the following problems: [0003] (1) At present, most massagers on the market can only complete simple massage operations, and can only monitor their own working status. [0004] (2) Existing medical products generally can only analyze a certain disease when analyzing data on human health, and the price is too high for ordinary people to bear. [0005] (3) In the existing medical big data prediction, parameter settings often depend on empirical valu...

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): A61H9/00A61B5/021
CPCA61B5/021A61B5/7267A61H9/005A61H2201/5007
Inventor 李湛于淼洪源铎杨司臣高会军贾译凇潘惠惠
Owner HARBIN INST OF 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