Long-term-electroencephalogram automatic epilepsy detection method based on convolutional neural network

A convolutional neural network and detection method technology, applied in the field of long-range EEG automatic epilepsy detection, can solve the problems of missed detection, wrong detection, relying on prior knowledge, unable to guarantee representativeness, etc., to achieve the effect of automatic detection

Inactive Publication Date: 2018-06-29
HOHAI UNIV CHANGZHOU
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods have shown good detection results on different subject data sets, but there are still some missed and wrong detections that cannot b

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
  • Long-term-electroencephalogram automatic epilepsy detection method based on convolutional neural network
  • Long-term-electroencephalogram automatic epilepsy detection method based on convolutional neural network
  • Long-term-electroencephalogram automatic epilepsy detection method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0038] A long-range EEG automatic epilepsy detection method based on convolutional neural network, the steps are as follows:

[0039] (1) Preprocessing the EEG signals of epilepsy patients;

[0040] (1.1), synchronously sampling and labeling the long-range multi-channel EEG signals of epilepsy patients;

[0041] (1.2), use band-pass filter to do denoising processing for each frame of EEG signal;

[0042] (2) Construct a channel-exclusive convolutional neural network;

[0043] (3) Train the network to obtain the detector.

[0044] In the above step (1.1), the process of synchronous sub-frame sampling and labeling includes the following steps:

[0045] (a1), determine the frame length and fra...

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

PropertyMeasurementUnit
Bandwidthaaaaaaaaaa
Login to view more

Abstract

The invention discloses a long-term-electroencephalogram automatic epilepsy detection method based on a convolutional neural network. The method includes the following steps that long-term multichannel electroencephalogram signals of epilepsy patients are subjected to synchronous framing sampling, and are labeled; each frame of electroencephalogram signal is denoised with band-pass filter; the channel-exclusive convolutional neural network is constructed; the network is trained, and a detector is obtained. According to the long-term-electroencephalogram automatic epilepsy detection method based on the convolutional neural network, the channel-exclusive convolutional neural network is benefited from the deep learning technology, a deep abstraction of an electroencephalogram mode is obtainedthrough layer-by-layer convolution correlation computation, and automatic detection of epilepsy seizures is achieved.

Description

technical field [0001] The invention relates to a long-range EEG automatic epilepsy detection method based on a convolutional neural network, and belongs to the technical field of clinical detection of epileptic seizures. Background technique [0002] Automatic epilepsy detection is to extract the salient features that distinguish between seizures and intermittent phases from multi-channel EEG for classification and recognition. It is of great significance in the clinical diagnosis of epilepsy and provides a reliable method for real-time adjuvant treatment of epilepsy. [0003] Multi-channel EEG and image signals have the characteristics of low signal-to-noise ratio and high complexity. There are many automatic detection methods based on feature extraction, such as sample entropy analysis, wavelet neural network, empirical mode decomposition, etc. These methods have shown good detection results on different subject data sets, but there are still some missed and wrong detecti...

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): A61B5/00A61B5/0476
CPCA61B5/4094A61B5/7235A61B5/7264A61B5/369
Inventor 刘小峰邹朗周旭蒋爱民
Owner HOHAI UNIV CHANGZHOU
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap