Method and system for analyzing personalized information and audio data for mini-mental state examination

A technology of audio data and mental state, applied in the field of digital medicine, can solve the problem of unpredictable and judgement of the probability and degree of nervous system disorders of subjects, so as to achieve comprehensive and reliable extraction of features, avoid pain, and save time and energy. Effect

Active Publication Date: 2016-11-09
INST OF SOFTWARE - CHINESE ACAD OF SCI
View PDF8 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the traditional sound signal analysis, binary classification training is generally performed by analyzing the relationship between sound characteristics and whether the subject has a disease. Only two results can be obtained: the subject is sick or not, and it is impossible to predict and judge the subject. Probability and degree of neurological disorders in 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
  • Method and system for analyzing personalized information and audio data for mini-mental state examination
  • Method and system for analyzing personalized information and audio data for mini-mental state examination
  • Method and system for analyzing personalized information and audio data for mini-mental state examination

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to enable those skilled in the art to better understand the present invention, specific embodiments are used below in conjunction with the accompanying drawings to make detailed descriptions, but they do not constitute a limitation to the present invention.

[0048] The present invention can be adopted as figure 1 , 2 Understand the operating scenarios and framework of the present invention, which mainly include collecting training data, data preprocessing, constructing pathological recognition models, and data fitting and analysis. Among them, subjects only need to collect training data, and the others can be predicted by computer assistance. Whether suffering from mental illness and degree. The algorithm is to process and train data experiments under the conditions of matlab7.10.0, such as image 3 Shown as follows:

[0049] 1) Collect training data. This part of the work is the basis of the experiment and prepares for subsequent processing and training. The speci...

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 method and a system for analyzing personalized information and audio data for mini-mental state examination. The method includes acquiring the personalized information of testees, allowing the testees to complete questions specified by the MMSE (mini-mental state examination), simultaneously recording speaking audio frequencies, extracting acoustic characteristics of the voice audio frequencies for pathological characteristics and representing the acoustic characteristics by the aid of high-order statistics; reducing redundancy of the characteristics by the aid of characteristic selection processes; fusing the acoustic characteristics with reduced dimensions and the personalized information of the testees with one another to obtain personalized characteristics; building pathological models of speaking conditions and mini-mental state examination cognition relations of the testees by the aid of the acquired data and analyzing the personalized information and the audio data by the aid of cross validation processes. The method and the system have the advantages that optional intrusive therapy can be omitted, physical states of the testees can be predicted only by means of analyzing relations between the acquired data and the pathological models, accordingly, the examination time and money can be saved, suffering experienced by the testees in examination procedures can be relieved, and influence of subjective judgment of doctors on results can be reduced.

Description

Technical field [0001] The invention belongs to the field of digital medical treatment, and specifically relates to a method and system for analyzing personalized information and audio data for a simple mental state scale. Background technique [0002] Nervous system disorders, including Alzheimer's disease, Parkinson's disease, small vessel disease, stroke and other similar diseases, are mostly caused by damage to the brain, spinal cord, and cranial nerve cells that cause changes in the body. The various organs and main manifestations of the human body are directly or indirectly under the regulation and control of the nervous system. Therefore, the nervous system is damaged. The main manifestations are difficulty in normal, clear and effective pronunciation and inconvenience of movement, and cognitive decline. Among them, language expression is an effective way of people's daily emotional communication. Damage not only affects the patient's physical and mental health, but also g...

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): A61B5/00
Inventor 李洋陈辉张凤军田丰王宏安
Owner INST OF SOFTWARE - CHINESE ACAD OF SCI
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