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

Multi-modal feature selection method for optimizing Parkinson's disease voice data

A feature selection method and voice data technology, which is applied in the fields of medical technology and evolutionary computing, can solve the problems of high time cost of the algorithm, and can only provide a single prediction solution, so as to reduce the data dimension, avoid loss, and reflect the effect of search ability

Pending Publication Date: 2021-02-02
GUANGDONG UNIV OF TECH
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a multi-modal feature selection method for optimizing Parkinson's speech data, in order to overcome the defects of existing algorithms that have high time cost and can only provide a single prediction scheme

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
  • Multi-modal feature selection method for optimizing Parkinson's disease voice data
  • Multi-modal feature selection method for optimizing Parkinson's disease voice data
  • Multi-modal feature selection method for optimizing Parkinson's disease voice data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0085]In order to reflect the function and significance of the multi-modal feature method proposed by the present invention, the present invention uses the Parkinson's disease detection data set of Oxford University as an example. The data set has 195 voice data, and each voice data has 22 dimensions. The experimental results are shown in the table:

[0086]

[0087]In the table, the feature string 1 indicates that the attribute of the voice data is selected, and 0 indicates that the attribute is not selected. When feature selection is not performed, that is, based on all attribute columns, the classification accuracy rate is only 96.41%. However, the classification accuracy rate of the feature selection method designed by the present invention is increased to 99.49%, not only the required attributes are reduced, but also at least three prediction schemes are found. This shows that the feature selection method of the present invention not only effectively reduces the data dimension and im...

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 multi-modal feature selection method for optimizing Parkinson's disease speech data. The method comprises the following steps: establishing a Parkinson's disease speech dataset, initializing a population based on a particle swarm algorithm, and determining feature character strings of individuals according to a real number encoding scheme; dividing individuals in the population into an ecological niche according to the individual fitness values; updating the historical optimal value and the historical optimal position of each individual, and updating the position andthe adaptive value of the optimal individual in each niche; updating the position and the speed of each individual, and according to the feature character string of each individual, evaluating the adaptive value of each individual in combination with the Parkinson's disease voice data set; taking the updated individuals as a new population, and comparing the new population with the initialized population to obtain a new generation of population; performing screening, reserving optimal individuals of the two populations, removing repeated individuals to obtain a new generation of population, and performing evolving; and outputting all optimal individuals of each generation, wherein the feature combination of the optimal individuals is used for assisting in judging whether Parkinson's disease exists or not.

Description

Technical field[0001]The invention relates to the fields of medical technology and evolutionary computing technology, and in particular to a multimodal feature method for reducing the dimensions of Parkinson's voice data.Background technique[0002]At present, the cause of Parkinson's disease is not clear, and it cannot be completely cured. Being able to detect the disease at an early stage is of great significance for improving patients’ life experience and treating Parkinson’s disease. At present, researchers have proposed a variety of solutions to assist doctors in diagnosing Parkinson's disease, including hand-drawn signal diagnosis and voice data prediction. In recent years, more and more researchers have used speech signal processing algorithms, machine learning algorithms and support vector machines to analyze speech data to determine Parkinson's disease. The speech data collected by the researchers are also published in UCI databases, such as the Parkinson's speech data set of...

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): G16H50/70G16H50/20G06N3/00G06F16/65G06F16/63G06F16/61
CPCG16H50/70G06N3/006G06F16/61G16H50/20G06F16/65G06F16/63
Inventor 胡晓敏张首荣李敏陈伟能
Owner GUANGDONG UNIV OF TECH
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