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

Brain development data analysis method, system and equipment and storage medium

A data analysis and brain development technology, applied in the field of data processing, can solve problems such as limited deep learning algorithms, model overfitting, and difficulty in extracting effective information, so as to improve learning ability and expression ability, and solve overfitting problems Effect

Pending Publication Date: 2021-09-28
XI AN JIAOTONG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, deep learning has been proved to be one of the most powerful tools in big data analysis, but the application of traditional deep learning algorithms in bioinformatics is still very limited, mainly because when the sample size of data is much smaller than the number of features, It often leads to overfitting of the model, which leads to inaccurate data processing, and it is difficult to extract effective information from the data. Therefore, it is necessary to design a method for such data with high latitude and small sample characteristics to solve the problem There is a deep learning model to deal with the overfitting problem of high latitude and small sample data

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
  • Brain development data analysis method, system and equipment and storage medium
  • Brain development data analysis method, system and equipment and storage medium
  • Brain development data analysis method, system and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] refer to figure 1 , the brain development data analysis method of the present invention comprises the following steps:

[0051] 1) Collect registered brain development data;

[0052] 2) In the brain development data, the data features corresponding to each individual and their change values ​​are summarized into a piece of unit data to form a structured data matrix. The data matrix includes a sample size N and a sample feature p, where , the sample size N is relatively small compared to the feature p, that is, N<<p;

[0053] 3) Dividing the brain development data forming a structured data matrix into a training set and a test set;

[0054] The traditional deep learning algorithm includes a pre-training process (Pre-training) and a fine-tuning (Fine-tuning) process. For the fine-tuning process, the present invention utilizes the gradient calculation formula of the loss function with the graph Laplacian regular term, which is used in the In the parameter update during ...

Embodiment 2

[0069] The brain development data analysis system of the present invention includes:

[0070] A building block for constructing a graph-regular sparse deep auto-encoder model, the hidden layer in the graph-regular sparse deep auto-encoder model is formed by stacking N sparse auto-encoders with graph Laplacian regularization, and the graph regularization A graph Laplacian regularization term is added to the loss function of the sparse deep autoencoder model;

[0071] The training and fine-tuning module is used to train and fine-tune the graph-regular sparse deep self-encoding model;

[0072] Analysis module for brain development data analysis using the trained graph regularized sparse deep autoencoder model.

Embodiment 3

[0074] A computer device, comprising a memory, a processor, and a computer program stored in the memory and operable on the processor, when the processor executes the computer program, the steps of the brain development data analysis method are realized .

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 brain development data analysis method, system and device and a storage medium, and the method comprises the steps: constructing a graph regularization sparse depth self-encoding model, wherein a hidden layer in the graph regularization sparse depth self-encoding model is formed by stacking N sparse self-encoders with graph Laplacian regularization, a graph Laplacian regularization term is added into a loss function of the graph regularization sparse depth self-encoding model; carrying out training and fine tuning on the graph regular sparse depth self-encoding model; and performing brain development data analysis by using the trained graph regular sparse depth self-encoding model. The method, system and device and the storage medium can effectively solve the overfitting problem occurring when high-latitude small sample brain development data is processed.

Description

technical field [0001] The invention belongs to the field of data processing, and relates to a brain development data analysis method, system, equipment and storage medium. Background technique [0002] High-dimensional small-sample data is common in the biomedical field, such as genomic data, medical image data, protein data, etc. These data have the characteristics of small sample size but huge sample characteristics, especially brain development data. This feature poses certain challenges to the process of data processing and analysis. When the ratio of sample size to sample features is small, classical machine learning algorithms tend to fail because high-dimensional data may contain irrelevant and redundant features. At present, deep learning has been proved to be one of the most powerful tools in big data analysis, but the application of traditional deep learning algorithms in bioinformatics is still very limited, mainly because when the sample size of data is much sm...

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): G16H50/70G06N3/04G06N3/08
CPCG16H50/70G06N3/08G06N3/045
Inventor 乔琛胡鑫钰许发明刘岳晨任鑫黄崎
Owner XI AN JIAOTONG 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com