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

Electroencephalogram signal recognition fuzzy system and method with transfer learning ability

An EEG signal, fuzzy system technology, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve problems such as classifier performance degradation

Active Publication Date: 2015-04-22
JIANGNAN UNIV
View PDF5 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These three signals all contain independent data distribution characteristics, and there are certain differences between them. If the classifier based on (1) and (2) signal training is used to directly classify and identify the (3) signal data, The performance of this classifier will drop dramatically, making traditional smart modeling techniques such as fuzzy systems inapplicable

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
  • Electroencephalogram signal recognition fuzzy system and method with transfer learning ability
  • Electroencephalogram signal recognition fuzzy system and method with transfer learning ability
  • Electroencephalogram signal recognition fuzzy system and method with transfer learning ability

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0117] Figure 10 and Figure 11 The results of the abscissa in the effect diagram of 1 and 2 are respectively using such as Figure 4 The EEG signals and Figure 8 The EEG signals measured during seizures in epileptic patients were used as training sets; Figure 4 The EEG signals and Figure 6 , The performance effect of the EEG signal recognition fuzzy system with transfer learning ability constructed by using the EEG signals of the epileptic patients during the interictal period in 7 as a test set. In this embodiment, the migration item parameter λ is set to 0.001, and the number of fuzzy rules is set to 10. However, the present invention should not be limited to the content disclosed in the embodiment and the accompanying drawings. Therefore, all equivalents or modifications that do not deviate from the spirit disclosed in the present invention fall within the protection scope of the present invention.

Embodiment 2

[0119] Figure 10 and Figure 11 The results of the abscissas of 3 and 4 in the effect diagram are respectively used as Figure 5 EEG signals and Figure 8 The EEG signals measured during seizures in epileptic patients were used as training sets; Figure 4 The EEG signals and Figure 6 , The performance effect of the EEG signal recognition fuzzy system with transfer learning ability constructed by using the EEG signals of the epileptic patients during the interictal period in 7 as a test set. In this embodiment, the migration item parameter λ is set to 0.1, and the number of fuzzy rules is set to 15. However, the present invention should not be limited to the content disclosed in the embodiment and the accompanying drawings. Therefore, all equivalents or modifications that do not deviate from the spirit disclosed in the present invention fall within the protection scope of the present invention.

Embodiment 3

[0121] Figure 10 and Figure 11 The results of the horizontal coordinates of 5 and 6 in the effect diagram are respectively used as Figure 4 , EEG signals of healthy subjects in 5 and Figure 8 The EEG signals measured during seizures in epileptic patients were used as training sets; Figure 4 , EEG signals of healthy subjects in 5 and Figure 6 , The performance effect of the EEG signal recognition fuzzy system with transfer learning ability constructed by using the EEG signals of the epileptic patients during the interictal period in 7 as a test set. In this embodiment, the migration item parameter λ is set to 0.15, and the number of fuzzy rules is set to 15. However, the present invention should not be limited to the content disclosed in the embodiment and the accompanying drawings. Therefore, all equivalents or modifications that do not deviate from the spirit disclosed in the present invention fall within the protection scope of the present invention.

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 an electroencephalogram signal recognition fuzzy system and method with the transfer learning ability. In a traditional intelligent recognition method, a training set and a testing set of a model are assumed to conform to the same data distribution, and therefore the good classification performance can be obtained only when data in a training domain and data in a testing domain conform to the same distribution. The electroencephalogram signal recognition fuzzy method helps epileptic electroencephalogram signal recognition under the transfer learning environment by means of the transfer learning strategy. The 0-order TSK type fuzzy system modeling technology with the direct-pushing type transfer learning ability is built based on the fuzzy system. The technology has the transfer learning ability and is not confined to the assumption of the uniform data distribution of the training domain and the testing domain, a certain difference is allowed to exist between the data in the training domain and the data in the testing domain, the good performance is kept on the condition of the same data distribution of the training domain and the testing domain, and the recognition effect of the finally-obtained model under the diversified electroencephalogram signal recognition problems is greatly improved.

Description

technical field [0001] The invention belongs to the field of signal recognition and application, in particular to a fuzzy-system EEG signal recognition method with transfer learning capability. Background technique [0002] Epilepsy is a transient brain dysfunction caused by sudden abnormalities of brain neurons. About 80% of epilepsy patients have certain EEG abnormalities. Among the main intelligent identification methods at present, the fuzzy system shows unique advantages compared with other main intelligent identification methods because of its good explainability and strong learning ability. For example, the fuzzy system expert knowledge rule base constructed for epilepsy can provide empirical knowledge for doctors' future diagnosis. [0003] Although the fuzzy system has shown some effectiveness in EEG signal recognition, this technique assumes that the training set and test set of the model obey the same data distribution, so it can only be obtained when the traini...

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
IPC IPC(8): A61B5/0476
CPCA61B5/4094A61B5/369
Inventor 邓赵红杨昌健蒋亦樟王士同
Owner JIANGNAN 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