Neural network blood pressure prediction method and mobile phone based on human face
A neural network and prediction method technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of low accuracy of long-term prediction, and achieve the effect of convenient and high accuracy in predicting blood pressure
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment example 1
[0080] Implementation Case 1, The blood pressure prediction model adopts the BP neural network blood pressure prediction model. Such as figure 2 As shown, it is an implementation example of the network structure of the BP neural network prediction model. The steps of training the BP neural network blood pressure prediction model are as follows:
[0081] 1) Prepare training samples. The input of each sample is a face feature vector. In this case, the face feature vector is a three-dimensional feature vector (x 1 ,x 2 , x 3 ), the output is the corresponding systolic blood pressure, diastolic blood pressure and pulse rate, forming a three-dimensional output vector (z 1 ,z 2 , z 3 ).
[0082] 2) Determine the BP network structure, that is, determine the number of layers in the middle layer and the number of neurons in each middle layer. The number of neurons in the input layer is the dimension of the face feature vector. The face feature vector dimension of this implemen...
Embodiment example 2
[0092] Implementation Case 2, The blood pressure prediction model adopts the integrated neural network blood pressure prediction model, and the weak blood pressure prediction model adopts the BP neural network blood pressure prediction model of the implementation case 1.
[0093] The training steps of the integrated neural network blood pressure prediction model are as follows:
[0094] 1) Prepare training sample set , where N=1000 is the input face feature vector, is the output vector: (systolic, diastolic, pulse rate).
[0095] 2) Calculate training samples The selection probability of is P( i )=1 / 1000, the number of iterations t=1, .
[0096] 3) Perform the following steps 10 times in a loop:
[0097] [1] According to the selection probability of each sample, a local training set is generated by sampling from the training set S with playback;
[0098] [2] Train the BP neural network blood pressure prediction model on the local training set to obtain the BP ne...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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