Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for predicting drunk driving and fatigue driving based on heart rate variability (HRV) and adversarial network

A technology for fatigue driving and networking, applied in the field of intelligent transportation, can solve problems such as inconvenience, loud ECG signal noise, and difficulty for drivers, and achieve the effect of easy acceptance and noise reduction.

Pending Publication Date: 2021-03-26
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is very inconvenient, and the driver is not easy to accept this method
Use the method of non-contact measurement ECG signal to often cause original ECG signal to produce a large amount of noise again, for example the non-contact measurement method that uses in the invention that publication number is CN110710957A, CN109171702A needs to adopt complex means to eliminate noise

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
  • Method for predicting drunk driving and fatigue driving based on heart rate variability (HRV) and adversarial network
  • Method for predicting drunk driving and fatigue driving based on heart rate variability (HRV) and adversarial network
  • Method for predicting drunk driving and fatigue driving based on heart rate variability (HRV) and adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] A method for predicting drunk driving and fatigue driving based on HRV and adversarial networks, such as figure 1 shown, including the following steps:

[0050] S1. Use the ECG sensor embedded in the steering wheel to measure the continuous ECG signal from the driver's palm;

[0051] S2. Use wavelet decomposition to denoise the ECG signal; the specific steps are as follows:

[0052] S21, denoise the original ECG signal obtained in step S1 based on 4th wavelet decomposition, and obtain wavelet coefficients;

[0053] S22, adopt soft threshold value algorithm to update wavelet coefficient, the similarity of the direction of wavelet is recorded as λ, specifically as follows:

[0054]

[0055] Where N is the number of signals, and σ is the standard deviation of the noise, which is estimated by the formula:

[0056]

[0057] where d s Represents the sth wavelet coefficient, median(|d s |) is the wavelet coefficient d s , the median value, set the adjustment coeffici...

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 method for predicting drunk driving and fatigue driving based on heart rate variability (HRV) and an adversarial network. The method includes the steps: measuring continuouselectrocardiograph signals from the palm of a driver by using an electrocardiograph sensor embedded in a steering wheel; denoising the electrocardiograph signals by using wavelet decomposition; detecting R waves of the denoised electrocardiograph signals by adopting a self-adaptive difference threshold method, and extracting a tiny fluctuation (HRV) of an R-R interval; and judging the fatigue state and the drunk driving state of the driver by using a model including the generative adversarial network and a convolutional neural network (CNN) according to the obtained tiny fluctuation (HRV) of the R-R interval. According to the method, the electrocardiograph signals of the driver are detected by using an electrocardiograph (ECG) electrode embedded in the steering wheel, the method is more scientific and convenient, and the driver can accept the method more easily. The model provided by the invention has good anti-noise performance and high prediction precision.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation, in particular to a method for predicting drunk driving and fatigue driving based on HRV and confrontation network. Background technique [0002] Over the past few decades, the increased use of in-vehicle electronics and telematics systems has led to the design and implementation of many driver intoxication or fatigue detection systems. For example, detection systems based on changes in vehicle parameters, driver behavior patterns and physiological signals. Compared with other methods, detection using physiological parameters has better accuracy and reliability, because there is less interference of external factors on this characteristic. [0003] Many physiological parameters such as electroencephalogram (EEG), electrocardiogram (ECG), electrooculogram (EOG) and electromyography (EMG) can be used to measure the level of drunkenness and fatigue of the driver. Among these 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
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/346
CPCA61B5/6893A61B5/7203A61B5/726A61B5/7267
Inventor 杜广龙韩瑞光王致尧
Owner SOUTH CHINA UNIV OF TECH