Fatigue driving detection method based on electroencephalogram signals
An EEG signal, fatigue driving technology, applied in diagnostic recording/measurement, medical science, instruments, etc., can solve problems such as affecting driving safety and interfering with the normal operation of drivers, and achieve the effect of accurate and objective judgment.
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2017-03-15
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the field of fatigue driving detection, in particular to a method for detecting fatigue driving based on electroencephalogram signals. Background technique
[0002] In recent years, the number of motor vehicles and drivers has continued to increase, but the concept of traffic safety in society is obviously lagging behind, and road traffic safety is facing many challenges. In order to prevent fatigue driving, my country's traffic law stipulates that continuous driving for 4 hours is considered fatigue driving. However, since there are differences among individuals, it is necessary to take into account the differences in physique and living conditions of each driver. This time limit is difficult to grasp when implementing it. Therefore, it is necessary to study the mechanism and detection methods of fatigue driving. Fatigue driving detection methods are divided into the following three categories: detection methods based on faci...
Examples
Embodiment Construction
[0044] The following specific examples further illustrate the present invention, but are not intended to limit the present invention.
[0045] A method for detecting fatigue driving based on EEG signals, comprising the following steps:
[0046] S1: Collect the EEG signal of the driver while driving in real time, and perform the process of removing blink artifacts to obtain the EEG brain wave signal;
[0047] S1-1: Perform ICA on the EEG signal to obtain N independent components and a mixing matrix A;
[0048] S1-2: Calculate the CBI(j) of each component;
[0049] S1-3: Find out the largest component of CBI and use it as a candidate component;
[0050] S1-4: Check whether the candidate component satisfies the relevant conditions, if so, it is an eye blinking component, otherwise it is not;
[0051] S1-5: After determining the blink component, set the column of coefficients corresponding to the blink component in matrix A to zero, and then reconstruct the signal;
[0052] S2...