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

Parkinson's disease speech data classification system based on dbn and rf algorithms

A speech data, Parkinson's disease technology, applied in the field of intelligent classification algorithm, can solve the problem of lack of nonlinear feature processing ability and so on

Active Publication Date: 2021-04-27
CHONGQING UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Based on the current technology, the diagnosis method based on voice data is more effective, so some researchers have designed a classification algorithm based on voice to diagnose PD, but when performing feature extraction, most of them use linear transformation, which lacks nonlinearity. feature processing capability

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 speech data classification system based on dbn and rf algorithms
  • Parkinson's disease speech data classification system based on dbn and rf algorithms
  • Parkinson's disease speech data classification system based on dbn and rf algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.

[0024] A Parkinson's disease speech data classification system based on DBN and RF algorithms, including:

[0025] Voice data input module, for collecting the voice data of the patient to be tested;

[0026] The classification recognizer is used to classify and recognize the speech data. The classification recognizer includes a feature transformation module based on the DBN deep belief network and a classifier based on the RF random forest algorithm, and achieves a predetermined level by training and testing the original sample data set standards of eligibility;

[0027] The output module is used to output classification recognition results.

[0028] Such as figure 1 As shown, in the specific implementation process, the classification recognizer need...

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 speech data classification system for Parkinson's disease based on DBN and RF algorithms, which is characterized in that it comprises: a speech data input module for collecting the speech data of a patient to be tested; a classification recognizer for classifying the speech data Perform classification recognition, the classification recognizer includes a feature transformation module based on the DBN deep belief network and a classifier based on the RF random forest algorithm, and reaches the preset qualification standard through original sample data training and testing; the output module is used to output classification recognition results. The effect is: DBN is introduced into the Parkinson's disease speech data classification system, and better features are introduced through nonlinear transformation, thereby obtaining more satisfactory accuracy and ensuring the accuracy of Parkinson's disease diagnosis.

Description

technical field [0001] The invention relates to an intelligent classification algorithm in biomedical information processing, in particular to a Parkinson's disease voice data classification system based on DBN and RF algorithms. Background technique [0002] Parkinson's disease (PD) is a neurodegenerative disease of the central nervous system, symptoms mainly include tremor, stiffness, loss of muscle control, slow movement, poor balance and speech problems. So far, the disease has affected nearly 10 million people around the world, and China is also a high-incidence area of ​​Parkinson's disease. High-quality biomarkers are the key to the diagnosis and treatment of Parkinson's disease. Unfortunately, reliable PD biomarkers have not yet been identified. However, recent research has shown that speech signals (data) can help identify patients with Parkinson's disease from healthy people, since the vast majority of patients usually exhibit some degree of dysarthria. [0003]...

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 Patents(China)
IPC IPC(8): G10L15/08
CPCG10L15/08G10L15/083
Inventor 李勇明肖洁王品谢廷杰郑源林张小恒颜芳
Owner CHONGQING 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