A parameter training algorithm for EEG signals in a multi-classifier single-channel mode

A multi-classifier and EEG signal technology, applied in the field of parameter training algorithms, can solve problems such as excessive data storage space and single classifier

Pending Publication Date: 2019-01-08
ACADEMY OF MILITARY MEDICAL SCI
View PDF9 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of too large data storage space in the EEG signal acquisition process and the single classifier in the EEG signal processing, the present invention provides a parameter training algorithm in the EEG signal-oriented multi-classifier single-channel mode

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
  • A parameter training algorithm for EEG signals in a multi-classifier single-channel mode
  • A parameter training algorithm for EEG signals in a multi-classifier single-channel mode
  • A parameter training algorithm for EEG signals in a multi-classifier single-channel mode

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In order to describe the present invention more specifically, the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0056] The schematic diagram of the parameter training algorithm in the EEG-signal-oriented multi-classifier single-path mode of the present invention is as follows: Figure 8 shown.

[0057] Before using the parameter training algorithm in multi-classifier single-pass mode, such as figure 1 It is shown that the feature extraction of the EEG signal is required. The process is as follows: obtain the original EEG signal from the electrode sensor, pass through a high-pass filter to obtain a signal containing only the action potential and a stable amplitude, and accurately obtain the action potential waveform through the threshold detection method. Feature extraction and waveform classification generate neuron action potential sequence data, and the action p...

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 parameter training algorithm for EEG signals in a multi-classifier single-channel mode, belonging to the technical field of EEG signal processing. The algorithm includes a system initialization parameter setting module, a multi-classifier training module, a compression coding module, and an indexing and the best classifier finding module. The multi-classifier training module includes a convolutional neural network, a support vector machine, a K nearest neighbor, and a feedforward neural network. The input original signal is compressed into index data according to Huffman coding mode, and the Huffman compression algorithm re-encodes the original data by extracting a common identifier. The classification accuracy of the classifier is tested according to the index data synthesized from the original data. The invention can flexibly select the optimal classification model according to different EEG signal characteristics, and the compression index algorithm makes full use of the cache for information storage, reduces hardware overhead, reduces algorithm complexity, and is convenient for subsequent algorithm expansion.

Description

technical field [0001] The invention relates to the technical field of electroencephalogram signal processing, in particular to a parameter training algorithm in a multi-classifier single-path mode for electroencephalogram signals. Background technique [0002] Brain-computer interface technology refers to the construction of a new information transmission circuit between the brain and the external environment through the computer without relying on brain nerves and muscle tissue, which can directly realize the information exchange between the brain and the external environment. It is a new type of human interaction. The way. It provides a new way to communicate with the outside world for groups suffering from muscle injuries and disorders, and has great application prospects in military, medical and other fields. [0003] With the development of artificial intelligence, biomedicine, pattern recognition and other fields, brain-computer interface has made rapid progress. Th...

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): G06K9/00G06K9/62
CPCG06F2218/08G06F2218/12G06F18/24147G06F18/241G06F18/2411
Inventor 周瑾张华亮王常勇韩久琦柯昂徐葛森
Owner ACADEMY OF MILITARY MEDICAL SCI
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