Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Artificial intelligence method for multi-class electroencephalogram data recognition

A technology of EEG data and artificial intelligence, applied in the field of EEG data, to achieve the effect of improving recognition rate, low cost, and solving time-related problems

Inactive Publication Date: 2019-09-17
HUNAN UNIV
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide an artificial intelligence method for multi-category EEG data recognition in view of the few existing categories of scenes

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
  • Artificial intelligence method for multi-class electroencephalogram data recognition
  • Artificial intelligence method for multi-class electroencephalogram data recognition
  • Artificial intelligence method for multi-class electroencephalogram data recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] Attached below Figures 1 to 8 To further illustrate the preferred embodiment of the present invention, the present invention requires the user to wear a low-cost off-the-shelf EEG head-mounted device to collect EEG data: firstly, the EEG data is encoded and collected, and when the EEG head-mounted device shows a red light The collected data are all represented as 1, and the data collected when the EEG head-mounted device shows a blue light are all represented as 0. Within the specified time, four types of data can be collected, a) keep focused within the specified time, Code the EEG data collected in this case as 11. b) Focus first and then relax within the specified time, code the data collected in this situation as 10. c) Relax first and then focus within the specified time, code the data collected in this case as 01. d) Keep the relaxed state for a specified time, code the data collected in this situation as 00. The collected data is divided into training set and...

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 an artificial intelligence method for multi-class electroencephalogram data recognition, and belongs to the technical field of electroencephalogram data. The artificial intelligence method includes the steps: collecting electroencephalogram data of a user through low-cost electroencephalogram data collecting equipment and storing the electroencephalogram data in embedded equipment TX2; proposing a customized design, enhancing signal interpretation of a stack LSTM through an attention mechanism, capaturing multiple features, and achieving accurate recognition of individual EEG signals; and developing a low-cost, real-time and end-to-end BCI system which can run a designed DeepBrain model and an algorithm in an embedded robot platform, and executing various types of home task signal input according to an electroencephalogram of the user. The artificial intelligence method has the beneficial effects that the problem of time correlation between time series data is solved while a coding method is provided for achieving multi-class electroencephalogram data recognition, and then then the coding method is applied to multi-class scenes, and the cost is low; and the artificial intelligence method can effectively increase the recognition rate to 97.5%.

Description

technical field [0001] The invention relates to an artificial intelligence method for multi-category EEG data recognition, belonging to the technical field of EEG data. Background technique [0002] Brain-computer interface (BCI) design, as an emerging subfield of human-computer interaction (HCI), has made significant progress in recent years. Typically, BCI systems utilize wearable devices to collect electroencephalogram (EEG) signals and interpret them into various user intentions. This technique has been applied to many BCI systems in different scenarios. However, these existing systems have a common disadvantage, that is, most of them are experimental prototypes, or they are developed for institutional users (such as hospitals and governments), so the hardware cost is quite expensive, which hinders the widespread use in people's daily life application scenarios. The price of the EEG acquisition device is different, for example, the EMOTIVEPOC+ 14-channel mobile EEG de...

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): G06F3/01G06K9/00G06N3/04
CPCG06F3/015G06N3/049G06F2218/12
Inventor 吴迪万华雁刘四平栾韶华
Owner HUNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com