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

Fatigue detection method and device based on GPDC graph convolutional neural network and storage medium

A convolutional neural network and fatigue detection technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as manual extraction, complex and cumbersome operations, irregularities, etc., and achieve the effect of improving detection performance

Inactive Publication Date: 2020-08-18
WUYI UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, brain network features often need to be manually extracted, there is no unified data standard, it is often not standardized, and the operation is complicated and cumbersome

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
  • Fatigue detection method and device based on GPDC graph convolutional neural network and storage medium
  • Fatigue detection method and device based on GPDC graph convolutional neural network and storage medium
  • Fatigue detection method and device based on GPDC graph convolutional neural network and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Reference figure 1 , Embodiment 1 of the present invention provides a fatigue detection method based on GPDC graph convolutional neural network, and one of the embodiments includes but is not limited to the following steps:

[0054] Step S100, collecting initial brain electricity data.

[0055] In this embodiment, the initial EEG data is collected in this step to prepare for the subsequent driving fatigue detection and provide a data basis.

[0056] In step S200, the initial EEG data is processed to obtain a first EEG signal.

[0057] In this embodiment, this step organizes and processes the collected initial EEG data to further prepare for driving fatigue detection.

[0058] In step S300, the first EEG signal is segmented and a directed static network is calculated through generalized biased coherence.

[0059] In this embodiment, the generalized biased coherence (GPDC) in this step is a frequency-domain causal analysis method of multi-channel EEG signals. The causal relationshi...

Embodiment 2

[0124] Reference image 3 The second embodiment of the present invention provides a fatigue detection device 1000 based on a GPDC graph convolutional neural network, including:

[0125] The collecting unit 1100 is used to collect initial brain electricity data;

[0126] The processing unit 1200 is configured to process the initial EEG data to obtain a first EEG signal;

[0127] The operating unit 1300 is configured to segment the first EEG signal and calculate a directed static network through generalized bias coherent calculation;

[0128] The screening processing unit 1400 is configured to screen out important connection information from the directed static network, and obtain a brain function matrix according to the important connection information;

[0129] The establishment unit 1500 is configured to establish a directed brain function network through the brain function matrix;

[0130] A modeling unit 1600, configured to model the extracted EEG features into a graph signal through ...

Embodiment 3

[0141] The third embodiment of the present invention also provides a computer-readable storage medium that stores executable instructions of a fatigue detection device based on a GPDC graph convolutional neural network, and fatigue detection based on a GPDC graph convolutional neural network The device executable instructions are used to make the fatigue detection device based on the GPDC graph convolutional neural network execute the above-mentioned fatigue detection method based on the GPDC graph convolutional neural network, for example, execute the above-described fatigue detection method figure 1 Steps S100 to S800 in the method to achieve image 3 The functions of the units 1000-1800 in.

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 fatigue detection method and device based on a GPDC graph convolutional neural network and a storage medium. The fatigue detection method comprises the steps of collecting initial electroencephalogram data, processing the initial electroencephalogram data to obtain a first electroencephalogram signal, segmenting the first electroencephalogram signal, calculating a directed static network through generalized partial directional coherence, screening important connection information from the directed static network, performing binarization processing on the important connection information to obtain a brain function matrix, establishing a directed brain function network through a brain function matrix, modeling the extracted electroencephalogram features into a graphsignal through the directed brain function network, inputting the trained graph signal into a graph convolutional neural network, carrying out network training optimization to obtain a driving fatigue detection model, inputting the tested graph signal into the driving fatigue detection model, and carrying out identification and detection to obtain a feedback result, thereby improving the detection performance in a driving fatigue state.

Description

Technical field [0001] The invention relates to the field of artificial intelligence, in particular to a fatigue detection method, device and storage medium based on a GPDC graph convolutional neural network. Background technique [0002] Safe driving plays a vital role in public health, and driver fatigue can be life-threatening. Driving requires a high degree of concentration for a long time. As the driver's attention and response ability in the external environment is reduced, it is easy to cause serious road collisions. Therefore, it is of great significance to develop a vehicle-mounted fatigue detection system to monitor the driver's mental state in real time. At present, the commonly used methods of driving fatigue research mainly use various sensors to obtain car driving parameters, driver behavior video technology, and collect and analyze driver physiological parameters, such as electrocardiogram (ECG), electromyography (EMG), electroencephalogram ( EEG). The fatigue o...

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): A61B5/18A61B5/04A61B5/0476A61B5/00G06N3/04G06N3/08
CPCA61B5/18A61B5/7253A61B5/7267G06N3/08A61B5/316A61B5/369G06N3/045
Inventor 王洪涛唐聪裴子安许林峰岳洪伟
Owner WUYI 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