Parkinson's disease diagnosis method based on hybrid kernel function support vector machine model

A support vector machine and hybrid kernel function technology, applied in the field of pattern recognition, can solve problems such as dimension growth, direct calculation difficulties, and infinite dimensions, and achieve high classification accuracy, improve accuracy, and improve diagnostic efficiency.

Inactive Publication Date: 2018-12-28
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] If the low-dimensional samples are directly mapped to high-dimensional, the number of dimensions will show explosive growth, and may even be as many as infinite dimensions, so it is very difficult to directly calculate

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
  • Parkinson's disease diagnosis method based on hybrid kernel function support vector machine model
  • Parkinson's disease diagnosis method based on hybrid kernel function support vector machine model
  • Parkinson's disease diagnosis method based on hybrid kernel function support vector machine model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] A method for diagnosing Parkinson's disease based on a mixed kernel function support vector machine model, comprising the steps of:

[0057] S1: Collect voice signals from Parkinson's patients and healthy people;

[0058] S2: performing feature extraction on the speech signal; wherein, performing feature extraction on the speech signal is to use a speech signal processing algorithm to extract speech features;

[0059] In addition, the extracted features include average base frequency F0_ave, minimum base frequency F0_min, maximum base frequency F0_max, five features measuring base frequency changes Jitter, Jitter(Abs), RAP, PPQ, DDP, six features measuring amplitude changes Shimmer , Shimmer(dB), APQ3, APQ5, APQ, DDA, noise harmonic ratio NHR, harmonic noise ratio HNR, cycle density entropy RPDE, correlation D2, trend fluctuation analysis DFA, and three nonlinear fundamental frequency changes Features spread1, spread2, PPE.

[0060] S3: Construct a mixed kernel functi...

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 parkinson's disease diagnosis method based on a hybrid kernel function support vector machine model. The method comprises steps that firstly, acquisition of speech signals for Parkinson patients and healthy people is performed; secondly, feature extraction of the speech signals is performed; thirdly, a hybrid kernel function of the support vector machine model is constructed; fourthly, the intelligent optimization algorithm is utilized to optimize a penalty parameter C, a Gaussian kernel function parameter g in the hybrid kernel function, a Sigmoid kernel function parameter h and a proportional parameter t in the establishment process of the support vector machine model, based on the optimization result, the optimal support vector machine model is established, andlastly, the optimal support vector machine model is utilized to classify and predict the to-be-detected speech, and diagnosis of Parkinson's diseases is achieved. The method is advantaged in that newideas are provided for diagnosis of the Parkinson's diseases, medical cost is reduced, diagnosis efficiency is improved, and accuracy of Parkinson's disease diagnosis is improved.

Description

technical field [0001] The invention relates to a method for diagnosing Parkinson's disease, in particular to a method for diagnosing Parkinson's disease based on a mixed kernel function support vector machine model, and belongs to the technical field of pattern recognition. Background technique [0002] Parkinson's disease is a common chronic neurological disease with a very high incidence among neurodegenerative diseases. Living with Parkinson's can impair movement, language, and other functions such as mood, behavior, thinking, and feeling. Parkinson's disease is a long-term chronic disease of the central nervous system that affects the motor system, and generally appears slowly over time. In the early stages of the illness, tremors, stiffness, delay in movement, and difficulty walking are most evident, after which problems with thinking and movement also occur. [0003] Studies have shown that due to the lack of dopamine, a substance that controls body movements, Parki...

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): G16H50/20G06K9/62
CPCG16H50/20G06F18/2411
Inventor 季薇张锦博
Owner NANJING UNIV OF POSTS & TELECOMM
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