EEG classification method based on helm combined with ptsne and lda feature fusion

A technology of feature fusion and classification methods, applied in character and pattern recognition, instruments, computing, etc., can solve problems such as EEG feature extraction that cannot be solved well

Active Publication Date: 2021-03-02
BEIJING UNIV OF TECH
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, PCA, LDA and PTSNE all have advantages and disadvantages, and each algorithm alone cannot solve the problem of EEG feature extraction well.

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
  • EEG classification method based on helm combined with ptsne and lda feature fusion
  • EEG classification method based on helm combined with ptsne and lda feature fusion
  • EEG classification method based on helm combined with ptsne and lda feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described below in conjunction with the accompanying drawings and specific implementation details.

[0027] The flow process of the method involved in the present invention comprises the following steps:

[0028] (1) EEG signal preprocessing.

[0029] First, randomly scramble and normalize the obtained EEG data. Then, considering the complexity and instability of EEG signals, we use overlapping sliding window segmentation to preserve useful information in EEG signals. Based on earlier work in the laboratory, A1 and A2 dominant electrodes were also chosen, each with 896 dimensions. The data of each electrode is divided into 9 segments by a time window of 500 ms and overlapping windows of 125 ms, and each data segment has 128 dimensions.

[0030] (2) Feature extraction and fusion

[0031] Copy the segmented data segments in electrodes A1 and A2 into two equal parts, and each part uses different methods to extract features.

[003...

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 a motor imagery EEG classification method based on HELM combined with PTSNE manifold and LDA feature fusion, and improves the classification accuracy. In terms of feature extraction, on the one hand, using PCA combined with LDA to extract linear features can not only eliminate noise, but also consider the label information of training data; Complex nonlinear intrinsic manifold features. In terms of feature classification, the HELM algorithm with high classification accuracy is used to classify and identify motor imagery EEG signals.

Description

technical field [0001] The invention belongs to the technical field of EEG signal processing, and in particular relates to a motor imagery EEG classification method based on HELM combined with PTSNE manifold and LDA feature fusion. Background technique [0002] The EEG signal of motor imagery is used to identify the state of the brain, and the human brain imagination can be controlled according to the EEG signal. The analysis of EEG signals is of great help to patients with encephalopathy. Since the collected EEG signal is a non-stationary signal with strong randomness and lack of regularity intuitively in the waveform, it is necessary to use an effective feature extraction method to improve the classification accuracy of EEG signals. [0003] The commonly used feature extraction methods in EEG analysis are time domain, frequency domain and time-frequency domain combination. In the time domain, although peak detection is highly targeted, it is also highly subjective. Alth...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06F2218/08G06F2218/12G06F18/2132G06F18/2135G06F18/253
Inventor 段立娟连召洋乔元华陈军成
Owner BEIJING UNIV OF TECH
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