Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for obtaining epilepsy EEG automatic classification model, and classification system

An automatic classification, epilepsy brain technology, applied in the field of biomedical engineering signal processing, can solve problems such as difficult trade-offs, reduce computing time, and less feature extraction, and achieve the effect of improving efficiency, obvious advantages, and reducing complexity

Pending Publication Date: 2020-09-25
HENAN UNIV OF SCI & TECH
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, while ensuring high classification accuracy and less feature extraction, it is also necessary to reduce the calculation time of processing, and it is difficult to balance between the two.

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 obtaining epilepsy EEG automatic classification model, and classification system
  • Method and system for obtaining epilepsy EEG automatic classification model, and classification system
  • Method and system for obtaining epilepsy EEG automatic classification model, and classification system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Such as figure 2 As shown, the acquisition method of a kind of epilepsy EEG automatic classification model shown in this embodiment is specifically implemented according to the following methods:

[0051] Step 1, carry out multilayer wavelet decomposition to the electroencephalogram signal to be classified, obtain the electroencephalogram signal of effective frequency band range, be denoted as effective electroencephalogram signal; The number of layers of wavelet decomposition is determined by the sampling frequency of the electroencephalogram signal to be classified;

[0052] Specifically, the EEG data to be classified used in this embodiment comes from the CHB-MIT scalp EEG database, which is collected at Boston Children's Hospital and consists of EEG records of pediatric patients with refractory epileptic seizures.

[0053] The sampling frequency of the EEG signal in this embodiment is 256 Hz, and the electrode placement method is the international 10-20 electrode p...

Embodiment 2

[0090] Such as Figure 6 As shown, a system for obtaining an automatic EEG classification model for epilepsy shown in this embodiment includes: an effective EEG signal acquisition module 1, a time-frequency map acquisition module 2, a classification module 3, a classification accuracy calculation module 4, and an output module 5 .

[0091] Wherein, the effective EEG signal acquisition module 1 is used to carry out multi-layer wavelet decomposition on the EEG signal to be classified to obtain the EEG signal in the effective frequency band range, which is denoted as an effective EEG signal. The number of layers of wavelet decomposition is determined by the sampling frequency of the EEG signal to be classified.

[0092] Time-frequency map acquisition module 2 is used to carry out short-time Fourier transform to effective EEG signal, and obtains the time-frequency map of reaction time and frequency.

[0093] Classification module 3 is used for utilizing TensorFlow framework to c...

Embodiment 3

[0105] Such as Figure 8 As shown, the epilepsy EEG automatic classification system shown in this embodiment includes: an effective EEG signal acquisition module 1, a time-frequency map acquisition module 2, a classification module 3 and an output module 5.

[0106] Wherein, the effective EEG signal acquisition module 1 is used to perform wavelet transformation on the EEG signal to be classified to obtain the EEG signal within the effective frequency band, which is recorded as an effective EEG signal.

[0107] Such as Figure 8 As shown, as an optional implementation, the effective EEG signal acquisition module 1 includes an EEG signal import unit 11 and a wavelet decomposition unit 12.

[0108] The EEG signal importing unit 11 is used to import the EEG signal to be classified into the wavelet decomposition unit 12 .

[0109] In this example, the EEG signals to be classified are from the CHB-MIT scalp EEG database, which is collected at Boston Children's Hospital and consist...

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 relates to a method and system for obtaining an epilepsy EEG automatic classification model. The system comprises an effective EEG signal obtaining module, a time frequency picture obtaining module, a classification module, a classification accuracy rate calculating module and an output module. The invention also discloses an epilepsy EEG signal automatic classification system. The system comprises an effective EEG signal obtaining module, a time frequency picture obtaining module, a classification module and an output module. According to the system and the method disclosed by the invention, time frequency pictures are subjected to automatic characteristic extraction by transfer learning, so that on the base that massive characteristic treatment time is shortened, work loadof parameter debugging and parameter learning is also reduced, network model building and training time is greatly saved, and the EEG signal classification efficiency of the system and the model can be improved.

Description

technical field [0001] The invention relates to the field of biomedical engineering signal processing, in particular to an acquisition method, system and classification system of an epileptic EEG automatic classification model. Background technique [0002] Epilepsy is a relatively common brain disorder. According to statistics from the World Health Organization in June 2019, there are about 50 million epilepsy patients in the world, accounting for about 0.6% to 0.8% of the total population, and the number is increasing at a rate of 2.4 million per year. Epilepsy has a large age span and tends to be younger. Serious threat to human health and development. Among the epilepsy population, adolescents and children under the age of 20 become the high-risk population. The causes of epilepsy are very complicated, and its pathogenesis has not been fully elucidated so far. In many cases, the structural or metabolic abnormalities that can explain the corresponding symptoms cannot be...

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): A61B5/00A61B5/0476G06N3/04G06N3/08
CPCA61B5/4094A61B5/7267G06N3/08G06N3/045
Inventor 杨晓利杨彬李振伟白永杰许俊超吴晓琴
Owner HENAN UNIV OF SCI & TECH