Electroencephalogram signal processing method based on synchronous compression wavelet transform and MLF-CNN

A MLF-CNN, EEG signal technology, applied in medical science, diagnosis, diagnostic recording/measurement, etc., can solve problems such as time resolution reduction, frequency resolution reduction, etc., to improve accuracy and time-frequency resolution. , the effect of preserving phase information

Pending Publication Date: 2022-08-02
ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional Fourier transform and wavelet transform have high resolution, but their frequency resolution decreases ...

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 processing method based on synchronous compression wavelet transform and MLF-CNN
  • Electroencephalogram signal processing method based on synchronous compression wavelet transform and MLF-CNN
  • Electroencephalogram signal processing method based on synchronous compression wavelet transform and MLF-CNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] In the model in this method, the CHB-MIT dataset was used as the EEG data for the study. The CHB-MIT dataset was collected at Boston Children's Hospital and contains a total of 24 EEG recordings of intractable epilepsy. All EEG data were sampled at a rate of 256Hz with a resolution of 16. Due to the missing temporal information of subject 24, we finally adopted the EEG data of the first 23 subjects. Fifteen minutes before the onset was selected as the pre-onset period, and the interictal data from at least 4 hours before the onset to 4 hours after the onset of the onset were selected to improve data quality and reduce interference.

[0056] Step 1. Data preprocessing

[0057] Denoise and filter the EEG signal data, and keep the 0-50Hz signal; remove the missing channels, keep FP1-F7, F7-T7, T7-P7, P7-O1, FP1-F3, F3-C3, C3-P3 ,P3-O1,FP2-F4,F4-C4,C4-P4,P4-O2,FP2-F8F8-T8,T8-P8,P8-O2,FZ-CZ,CZ-PZ channel signal. The time-domain data were divided into different segments, ...

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 belongs to the field of artificial intelligence, and discloses an electroencephalogram signal processing method based on synchronous compressed wavelet transform and MLF-CNN, comprising the following steps: step 1, data preprocessing: performing denoising and other processing on an original electroencephalogram signal, and retaining an effective signal; step 2, feature extraction: obtaining a time-frequency image of the electroencephalogram signal through SWT, adjusting the size of the time-frequency image to 128 * 128 * 18, and fitting a neural network by adopting bilinear interpolation; and step 3, classification: extracting multi-level feature information by using an MLF-CNN model based on VGG16, and carrying out training and testing. According to the method, high-level local energy distribution is provided by utilizing synchronous compression wavelet transform, so that the energy change of the electroencephalogram signal can be well shown on a time-frequency plane, and the problem that TF energy of continuous wavelet transform is seriously diffused near an actual energy axis, and consequently, the identification of the TF energy of the signal is inaccurate is solved.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and in particular relates to an EEG signal processing method based on synchronous compression wavelet transform and MLF-CNN. Background technique [0002] An EEG is a complex imbalance of signals produced by nerve cells in the cerebral cortex. According to the source of the signal, it can be divided into two types: scalp EEG (non-invasive) and intracranial EEG (invasive). In scalp EEG, small metal electrodes are placed on the scalp with good mechanical and electrical contact. An intracranial EEG is obtained with special electrodes implanted in the brain during surgery. The rhythmic EEG signal has multiple frequency bands, and the speed is different. According to the frequency band, it can be divided into the following five types: δ(<4Hz), θ(4-8Hz), α(8-13Hz), β(13-30Hz), γ(>30Hz). [0003] Feature extraction is to extract information related to research in EEG signals, so as to pr...

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): A61B5/369A61B5/372
CPCA61B5/369A61B5/372A61B5/726A61B5/7203A61B5/7225A61B5/7264
Inventor 陈芳妮童威张蕾张丽娟万健黄杰宋坤朋
Owner ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
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