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

Epilepsy electroencephalogram recognition device based on multichannel electroencephalogram data and CNN-SVM

A technology for EEG data and identification devices, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve problems such as low efficiency and accuracy, time consumption and cost

Inactive Publication Date: 2020-05-19
TIANJIN UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method requires long-term observation, which is very time-consuming and cost-intensive, and the efficiency and accuracy are very low.

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
  • Epilepsy electroencephalogram recognition device based on multichannel electroencephalogram data and CNN-SVM
  • Epilepsy electroencephalogram recognition device based on multichannel electroencephalogram data and CNN-SVM
  • Epilepsy electroencephalogram recognition device based on multichannel electroencephalogram data and CNN-SVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described below in conjunction with the accompanying drawings and specific examples.

[0023] The present invention adopts 23-channel EEG signals, and the EEG signals are divided into normal EEG signals and epileptic EEG signals. CNN-SVM is used to construct a 2-category model, and the model is used to classify normal EEG and epileptic EEG, so as to achieve a higher accuracy of epileptic EEG recognition

[0024] see figure 1 , the original EEG used in the present invention. The signal comes from the EEG data of epileptic patients in the normal period and seizure period, the sampling frequency is 1024Hz, and the length of a single signal is 2048. Among them, (a) is a normal EEG signal, and (b) is an epileptic EEG signal. It can be seen that the two types of signals have obvious classification characteristics, so CNN-SVM can be used to classify them, so as to realize the identification of epilepsy diseases.

[0025] see figure 2 ...

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 an epilepsy electroencephalogram recognition device based on multichannel electroencephalogram data and CNN-SVM. The device comprises the following modules: a preprocessing module; a feature extraction module comprising: a convolution layer: extracting features from electroencephalogram signals by using the convolution layer, and selecting a ReLU function as an activationfunction; a pool layer: adopting a maximum value pooling mode; loss regularization: to prevent over-fitting, a missing regularization mechanism is applied; a model construction module comprising: constructing a two-classification model based on the SVM; taking the features extracted by the feature extraction module as a data set, and constructing a training set and a test set; using a Sigmoid function as a kernel function; and a model training module.

Description

technical field [0001] The invention relates to an epileptic EEG recognition device, which belongs to the fusion of CNN-SVM technology and the field of medical disease diagnosis. Background technique [0002] Epilepsy affects people of all ages and is a chronic disorder of the brain. About 70% of patients can effectively suppress the onset of epilepsy by taking antiepileptic drugs (cannot cure), but the remaining patients have no effect after taking drugs, and long-term use of antiepileptic drugs will also have side effects. Currently, in the field of medical disease diagnosis, the diagnosis of epilepsy is made by obtaining a detailed medical history, performing a neurological examination, and ancillary tests such as neuroimaging and EEG, that is, neurologists directly visually inspect the electroencephalogram (EEG). ), to study epileptiform abnormalities. The accuracy of visual inspection is dependent on the neurologist's expertise in EEG studies, and the quality of the s...

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): A61B5/0476A61B5/00
CPCA61B5/7267A61B5/4094A61B5/369
Inventor 吕辰刚陈雨心王增光陈旨娟刘宇恒常心怡杨希婷
Owner TIANJIN UNIV