CN105011932A

CN105011932A - Fatigue driving electroencephalogram monitoring method based on degree of meditation and degree of concentration

Info

Publication number: CN105011932A
Application number: CN201510489130.0A
Authority: CN
Inventors: 汪梅; 温涛; 郭林
Original assignee: Xian University of Science and Technology
Current assignee: Xian University of Science and Technology
Priority date: 2015-08-11
Filing date: 2015-08-11
Publication date: 2015-11-04

Abstract

The invention discloses a fatigue driving electroencephalogram monitoring method based on the degree of meditation and the degree of concentration. The method includes the steps of 1, brain wave signal acquisition, wherein a brain electrical signal acquisition device is adopted to acquire and preprocess brain wave signals of a driver and synchronously transmit the brainwave signals to a brain electrical signal monitoring device; 2, brain wave signal analysis and processing, wherein analysis and processing are conducted on the brain wave signals acquired and preprocessed by the brain electrical signal acquisition device each second according to the sequence of sampling time, and whether the driver is in the fatigue state or not is judged; the brain electrical wave signals acquired and preprocessed in any second are analyzed and processed in the following steps of synchronous brain electrical wave storage, meditation degree and concentration degree extraction, fatigue degree calculation, threshold value comparison, driver fatigue degree calculation in continuous K seconds and fatigue driving judgment. The fatigue driving electroencephalogram monitoring method is simple in steps, reasonable in design, convenient to implement, good in use effect and capable of accurately monitoring the fatigue driving state of the driver easily, conveniently and fast.

Description

Fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree

Technical Field

The invention belongs to the technical field of brain wave monitoring, and particularly relates to a fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree.

Background

In recent years, with the increase of the number of automobiles and the enlargement of the scale of road construction, problems such as traffic accidents have been highlighted. China is the most populated country in the world, and the number of road traffic accident deaths is also the highest worldwide country, and is the first world in many years. The driver is fatigued to drive, which undoubtedly brings hidden danger to the safety of the driver and passengers. The research of the driving fatigue is divided into a subjective method and an objective method, and the subjective research methods comprise a subjective questionnaire, a driver self-record, a sleep habit questionnaire and a Stanford sleep scale. The objective study methods include electroencephalogram, electrooculogram, electromyogram, respiratory airflow, respiratory effect, temperature when arterial blood is saturated with oxygen, and electrocardiogram. Although the driving fatigue determination result of the above method is relatively accurate, the above method is generally measured before or after driving, and thus is advanced or delayed, rather than real-time, and it is difficult to install complicated detection instruments in a limited space of a cab; moreover, the mental state of the driver leaving or not entering the cab is different, and the measurement result of the accurate instrument is also greatly influenced.

Brain wave control technology has become one of the hot researches in recent years in the fields of biomedicine, computers, and the like. The traditional subcutaneous brain wave acquisition method is complex and inconvenient, so that the method is difficult to popularize in other fields. At present, the brain-computer interface technology is in the development and initial stage in China, and related research is less. The TGAM (thinkgear am) module is an ASIC module of brain wave sensor designed by NeuroSky science and technology for mass market application, and is also called TGAM electroencephalogram module (TGAM module for short). The tgam (thinkgear am) module can process and output brain wave frequency spectrum, brain wave signal quality, original brain wave and three eSense parameters of Neurosky: concentration, meditation (also called relaxation) and blink detection. In practical use, data transmitted by the TGAM module can be acquired through a serial port, and the TGAM module respectively transmits an original data packet (namely an original brain wave) at a frequency of 512Hz and transmits the original data packet through eSense at a frequency of 1Hz^TMAnd (5) processing the data packet by an algorithm. Thus, the TGAM module outputs concentration and meditation data one per second. Wherein concentration data (also referred to as a concentration index) indicates how strongly a user's mental "concentration" level or "attention" level is, the index value ranging from 0 to 100. The meditation data (also called the relaxation index) indicates the level of mental "calmness" or "relaxation" of the user, which index value ranges from 0 to 100.

Because the interface of the TGAM (thinkGear AM) module and the human body only needs a simple dry contact point, the TGAM (thinkGear AM) module can be easily applied to toys, video games and health equipment, and is suitable for the application of portable consumer products powered by batteries due to low energy consumption. Therefore, a fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree, which has the advantages of simple steps, reasonable design, convenience in implementation and good use effect, needs to be developed, and the fatigue driving state of the driver can be accurately monitored simply, conveniently and rapidly.

Disclosure of Invention

The invention aims to solve the technical problem of providing a fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree, which has the advantages of simple steps, reasonable design, convenient implementation, good use effect and capability of simply, conveniently and quickly accurately monitoring the fatigue driving state of a driver.

In order to solve the technical problems, the invention adopts the technical scheme that: a fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized by comprising the following steps:

step one, brain wave signal acquisition: acquiring and preprocessing a brain wave signal of a driver by adopting a brain wave signal acquisition device according to a preset sampling frequency, and synchronously transmitting the preprocessed brain wave signal to a brain wave signal monitoring device;

the electroencephalogram signal acquisition device and the electroencephalogram signal monitoring device are communicated in a wireless communication mode; the electroencephalogram signal acquisition device is a TGAM module, the TGAM module comprises an electroencephalogram signal extraction device for extracting electroencephalogram signals of a driver and an electroencephalogram signal preprocessing device for sampling and preprocessing the signals extracted by the electroencephalogram signal extraction device, the electroencephalogram signal preprocessing device is connected with the electroencephalogram signal extraction device, the electroencephalogram signal extraction device comprises a first electroencephalogram electrode for sampling the electric potential of the frontal lobe area of the driver in real time and a second electroencephalogram electrode and a third electroencephalogram electrode for sampling the electric potential of the ear of the driver in real time, and the first electroencephalogram electrode, the second electroencephalogram electrode and the third electroencephalogram electrode are all connected with the electroencephalogram signal preprocessing device; the electroencephalogram signal monitoring device comprises a main control chip, and a second wireless communication module and an alarm prompting unit which are respectively connected with the main control chip, wherein the alarm prompting unit is controlled by the main control chip and is connected with the main control chip; the electroencephalogram signal preprocessing device is connected with the first wireless communication module and is communicated with the main control chip through the first wireless communication module and the second wireless communication module;

step two, brain wave signal analysis and processing: the master control chip respectively analyzes and processes the brain wave signals collected and preprocessed by the brain wave signal acquisition device within every second according to the sequence of sampling time, and judges whether the driver is in a fatigue driving state at the moment according to the analysis and processing result; the analysis and processing methods of the brain wave signals collected and preprocessed by the brain wave signal acquisition device in each second are the same by the main control chip; when the brain wave signals collected and preprocessed by the brain wave signal acquisition device within any one second are analyzed and processed, the process is as follows:

step 201, brain wave signal synchronous storage: synchronously storing the brain wave signals collected and preprocessed by the brain wave signal acquisition device within one second;

step 202, extracting the meditation degree and the concentration degree: extracting a meditation degree M and a concentration degree A from the brain wave signals processed at that time;

step 203, fatigue degree calculation: according to the meditation degree M and the concentration degree A extracted in the step 202 and according to the formulaCalculating to obtain the fatigue degree of the driver at the moment

Step 204, threshold comparison: calling a threshold comparison module to calculate the fatigue degree of the driver at the moment obtained in the step 203And F₀And (3) comparing difference values: when in useF₀If so, it means the fatigue moment to be determined, and the process proceeds to step 205; otherwise, returning to the step 201, and analyzing and processing the brain wave signal which is acquired and preprocessed by the brain wave signal acquisition device within the next second;

wherein, F₀Determining a threshold value for a predetermined fatigue level F₀1.2 to 1.6;

step 205, calculating the fatigue degree of the driver in the next second: analyzing and processing the brain wave signals collected and preprocessed by the brain electrical signal acquisition device in the next second according to the method from the step 201 to the step 203, and calculating the fatigue degree of the driver in the next second after the fatigue moment to be judged

Step 206, repeating the step 206 for K-1 times, and obtaining the fatigue degree of the driver within K seconds after the fatigue moment to be determinedWherein K is a positive integer and K is 8-15;

step 207, fatigue driving judgment: calling the threshold comparison module to compare the fatigue degree of the driver within K seconds after the fatigue moment to be determined obtained in the step 206Are respectively reacted with F₀And (3) comparing difference values: when the fatigue degree of the driver within K seconds after the fatigue moment to be determinedAre all greater than F₀When it is, explain that the car is driving at this timeThe driver is in a fatigue driving state, and the main control chip controls the alarm prompt unit to give an alarm prompt; otherwise, the driver is in a normal driving state at the moment;

and 208, returning to the step 201, and analyzing and processing the brain wave signals collected and preprocessed by the brain wave signal acquisition device within the next second.

The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized in that: k in step 206 is 10.

The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized in that: f in step 204₀＝1.4。

The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized in that: in step 207, the fatigue degree of the driver is determined within K seconds after the fatigue timeAre all greater than F₀Before the main control chip controls the alarm prompting unit to perform alarm prompting, the main control chip also needs to call a multi-threshold comparison and judgment module to analyze and process the brain wave signals received in step 201, and verify the fatigue driving state of the driver at this time according to the analysis and processing result, and the process is as follows:

step B1, characteristic signal extraction: the main control chip calls a feature extraction module to extract 7 feature signals from the brain wave signals processed at the moment;

step B2, feature quantity determination: the main control chip takes the signal values of the 7 characteristic signals in the step B1 as the 7 characteristic quantities of the brain wave signals processed at the moment; the 7 characteristic signals are original brain waves, low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and wave signals respectively, and the 7 characteristic quantities are R, A respectively_L、A_H、B_L、B_HT and D;

when the electroencephalogram signal acquisition device acquires and preprocesses electroencephalogram signals of a driver in the first step, the sampling frequency of the original electroencephalogram is 512Hz, and the sampling frequencies of low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and waves are all 1 Hz; in the 7 feature signals, the number of the original brain wave signals is 512, and the number of low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and wave signals is one;

wherein R is an average value of signal values of 512 original brain wave signals extracted from the brain wave signals processed at that time, A_LA signal value of a low alpha wave signal extracted from the electroencephalogram signal processed at that time, A_HIs a signal value of a high alpha wave signal extracted from the electroencephalogram signal processed at that time, B_LIs the signal value of the low beta wave signal extracted from the electroencephalogram signal processed at that time, B_HIs a signal value of a high beta wave signal extracted from the electroencephalogram signals processed at this time, T is a signal value of a theta wave signal extracted from the electroencephalogram signals processed at this time, and D is a signal value of a wave signal extracted from the electroencephalogram signals processed at this time;

step B3, multi-threshold comparison: the main control chip judges threshold values according to 7 groups of predetermined fatigue driving and calls a threshold value comparison module to respectively perform threshold value comparison on the 7 characteristic quantities determined in the step B2, and a counter is adopted to record threshold value comparison results;

the initial count value of the counter is 0;

the 7 groups of fatigue driving judgment threshold values are respectively a group of original brain wave judgment threshold values, a group of low alpha wave judgment threshold values, a group of high alpha wave judgment threshold values, a group of low beta wave judgment threshold values, a group of high beta wave judgment threshold values, a group of theta wave judgment threshold values and a group of wave judgment threshold values; wherein the original brain wave judging threshold comprises an original brain wave fatigue threshold R_STAnd the original brain wave waking threshold R_WTThe low alpha wave judgment threshold comprises a low alpha wave fatigue threshold A_LSTAnd low alpha wave wakefulness threshold A_LWTSaidThe high alpha wave judgment threshold comprises a high alpha wave fatigue threshold A_HSTAnd a high alpha wave wakefulness threshold A_HWTThe low beta wave judgment threshold comprises a low beta wave fatigue threshold B_LSTAnd low beta wave wake threshold B_LWTThe high beta wave judgment threshold comprises a high beta wave fatigue threshold B_HSTAnd a high beta wave wake threshold B_HWTThe theta wave judging threshold comprises a theta wave fatigue threshold T_STAnd theta wave wakefulness threshold T_WTThe wave judging threshold value comprises a wave fatigue threshold value D_STSum wave wake threshold D_WT；

When the 7 feature quantities determined in the step B2 are respectively subjected to threshold comparison, the main control chip calls a threshold comparison module to judge the threshold and the feature quantity a of the feature quantity R and a group of original brain waves_LAnd a set of low alpha wave judgment threshold value and characteristic quantity A_HA set of high alpha wave judgment threshold values and characteristic quantity B_LAnd a set of low beta wave judgment threshold value and characteristic quantity B_HRespectively carrying out threshold comparison with a group of high beta wave judgment threshold values, a characteristic quantity T and a group of theta wave judgment threshold values, and a characteristic quantity D and a group of wave judgment threshold values;

when the characteristic quantity R is compared with a group of original brain wave judgment threshold values, the characteristic quantity R and the characteristic quantity R are compared firstly_STAnd (3) comparing difference values: when R < R_STThen, the main control chip adds 5 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the characteristic quantities R and R are combined_WTAnd (3) comparing difference values: when R > R_WTThen, the main control chip subtracts 5 from the count value of the timer; otherwise, the count value of the timer is unchanged;

for characteristic quantity A_LWhen the threshold value is compared with a group of low alpha wave judgment threshold values, the characteristic quantity A is firstly compared_LAnd A_LSTAnd (3) comparing difference values: when A is_L＜A_LSTThen, adding 1 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the characteristic quantity A is measured_LAnd A_LWTAnd (3) comparing difference values: when A is_L＞A_LWTThen, the count value of the timer is decreased1; otherwise, the count value of the timer is unchanged;

for characteristic quantity A_HWhen the characteristic quantity A is compared with a group of high alpha wave judgment threshold values_HAnd A_HSTAnd (3) comparing difference values: when A is_H＜A_HSTThen, adding 1 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the characteristic quantity A is measured_HAnd A_HWTAnd (3) comparing difference values: when A is_H＞A_HWTThen, subtracting 1 from the count value of the timer; otherwise, the count value of the timer is unchanged;

for characteristic quantity B_LWhen the characteristic quantity B is compared with a group of low beta wave judgment threshold values in a threshold value mode, the characteristic quantity B is firstly measured_LAnd B_LSTAnd (3) comparing difference values: when B is present_L＜B_LSTThen, adding 2 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the characteristic quantity B is measured_LAnd B_LWTAnd (3) comparing difference values: when B is present_L＞B_LWTThen, subtracting 2 from the count value of the timer; otherwise, the count value of the timer is unchanged;

for characteristic quantity B_HWhen the characteristic quantity B is compared with a group of high beta wave judgment threshold values in a threshold value way, the characteristic quantity B is firstly measured_HAnd B_HSTAnd (3) comparing difference values: when B is present_H＜B_HSTThen, adding 2 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the characteristic quantity B is measured_HAnd B_HWTAnd (3) comparing difference values: when B is present_H＞B_HWTThen, subtracting 2 from the count value of the timer; otherwise, the count value of the timer is unchanged;

when the characteristic quantity T is compared with a group of theta wave judgment threshold values, the characteristic quantity T and the characteristic quantity T are firstly compared_STAnd (3) comparing difference values: when T is less than T_STThen, adding 1 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the characteristic quantities T and T are compared_WTAnd (3) comparing difference values: when T > T_WTAt that time, the timer will be at that timeSubtracting 1 from the numerical value; otherwise, the count value of the timer is unchanged;

when the characteristic quantity D and a group of wave judging threshold values are respectively compared by the threshold values, the characteristic quantity D and the characteristic quantity D are firstly compared_STAnd (3) comparing difference values: when D is less than D_STThen, adding 6 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the characteristic quantities D and D are compared_WTAnd (3) comparing difference values: when D > D_WTThen, subtracting 6 from the count value of the timer; otherwise, the count value of the timer is unchanged;

step B4, fatigue driving judgment: and the main control chip judges the fatigue driving state of the driver at the moment according to the counting value of the counter after the multi-threshold comparison in the step B3: when the count value of the counter is larger than N, the driver is in a fatigue driving state at the moment after verification, and the main control chip controls an alarm prompting unit to perform alarm prompting; otherwise, the driver is in a fatigue driving state at the moment after verification;

wherein N is a positive integer and N is 52-58.

The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized in that: before the brain wave signal analysis processing in the step two, determining 7 groups of fatigue driving judgment threshold values in the step B3 by adopting a main control chip;

when the 7 groups of fatigue driving judgment threshold values in the step B3 are determined, firstly, acquiring brain wave signals of a driver within P seconds by using a brain wave signal acquisition device, and then determining the 7 groups of fatigue driving judgment threshold values according to the acquired brain wave signals of the driver within P seconds; wherein P is a positive integer and P is 50-70;

when 7 groups of fatigue driving judgment threshold values are determined according to the obtained brain wave signals of the driver within P seconds, the method comprises the following steps:

step B31, characteristic signal extraction: firstly, extracting from the obtained brain wave signal of the driver within P seconds512 × P original electroencephalogram signals, P low α wave signals, P high α wave signals, P low β wave signals, P high β wave signals, P θ wave signals, and P wave signals are extracted, and the pair a is aligned with the pair a_LM、A_LSD、A_HM、A_HSD、B_LM、B_LSD、B_HM、B_HSD、T_M、T_SD、D_MAnd D_SDRespectively calculating;

wherein R is_MAnd R_SDMean and standard deviation of signal values of 512 × P original brain wave signals, respectively, a_LMAnd A_LSDMean and standard deviation of the signal values of the P low alpha wave signals, A_HMAnd A_HSDMean and standard deviation of the signal values of the P high alpha wave signals, B_LMAnd B_LSDMean and standard deviation of the signal values of the P low beta wave signals, B_HMAnd B_HSDMean value and standard deviation of signal values of P high beta wave signals, T_MAnd T_SDMean and standard deviation of the signal values of the P theta wave signals, D_MAnd D_SDThe average value and the standard deviation of the signal values of the P wave signals are respectively;

step B32, threshold calculation: according to the formula R_ST＝r_S1R_M+r_S2R_SD (1)、R_WT＝r_W1R_M+r_W2R_SD(2)、A_LST＝a_LS1A_LM+a_LS2A_LSD (3)、A_LWT＝a_LW1A_LM+a_LW2A_LSD (4)、A_HST＝a_HS1A_HM+a_HS2A_HSD (5)、A_HWT＝a_HW1A_HM+a_HW2A_HSD (6)、B_LST＝b_LS1B_LM+b_LS2B_LSD(7)、B_LWT＝b_LW1B_LM+b_LW2B_LSD (8)、B_HST＝b_HS1B_HM+b_HS2B_HSD (9)、B_HWT＝b_HW1B_HM+b_HW2B_HSD (10)、T_ST＝t_S1T_M+t_S2T_SD (11)、T_WT＝t_W1T_M+t_W2T_SD(12)、D_ST＝d_S1D_M+d_S2D_SD(13) And D_WT＝d_W1D_M+d_W2D_SD(14) Are each to R_ST、R_WT、A_LST、A_LWT、A_HST、A_HWT、B_LST、B_LWT、B_HST、B_HWT、T_ST、T_WT、D_STAnd D_WTCalculating;

in the formula (1), r_S1And r_S2Is R_STTwo weighting coefficients of 0 < r_S1≤6，-3≤r_S2＜0；

In the formula (2), r_W1And r_W2Is R_WTTwo weighting coefficients of 0 < r_W1≤6，-3≤r_W2＜0；

In the formula (3), a_LS1And a_LS2Is A_LSTTwo weighting coefficients of 0 < a_LS1≤1，-1≤a_LS2＜0；

In the formula (4), a_LW1And a_LW2Is A_LWTTwo weighting coefficients of 0 < a_LW1≤1，-1≤a_LW2＜0；

In the formula (5), a_HS1And a_HS2Is A_HSTTwo weighting coefficients of 0 < a_HS1≤1，-1≤a_HS2＜0；

In the formula (6), a_HW1And a_HW2Is A_HWTTwo weighting coefficients of 0 < a_HW1≤1，-1≤a_HW2＜0；

In the formula (7), b_LS1And b_LS2Is B_LSTTwo weighting coefficients of 0 < b_LS1≤1，-1≤b_LS2＜0；

In the formula (8), b_LW1And b_LW2Is B_LWTTwo weighting coefficients of 0 < b_LW1≤1，-1≤b_LW2＜0；

In formula (9), b_HS1And b_HS2Is B_HSTTwo weighting coefficients of 0 < b_HS1≤1，-1≤b_HS2＜0；

In the formula (10), b_HW1And b_HW2Is B_HWTTwo weighting coefficients of 0 < b_HW1≤1，-1≤b_HW2＜0；

In formula (11), t_S1And t_S2Is T_STTwo weighting coefficients of 0 < t_S1≤1，-1≤t_S2＜0；

In the formula (12), t_W1And t_W2Is T_WTTwo weighting coefficients of 0 < t_W1≤1，-1≤t_W2＜0；

In the formula (13), d_S1And d_S2Is D_STTwo weighting coefficients of 0 < d_S1≤1，-1≤d_S2＜0；

In formula (14), d_W1And d_W2Is D_WTTwo weighting coefficients of 0 < d_W1≤1，-1≤d_W2＜0。

The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized in that: before the brain wave signal analysis processing in the step two, determining 7 sets of fatigue driving judgment threshold values in the step B3;

when 7 groups of fatigue driving judgment threshold values in the step B3 are determined, firstly, an electroencephalogram signal acquisition device is adopted to respectively acquire and preprocess electroencephalogram signals when a driver enters a sleep state from a non-sleep state and enters an awake state from a non-awake state; wherein R is_ST、A_LST、A_HST、B_LST、B_HST、T_STAnd D_STRespectively the signal values of original brain waves, low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and wave signals in the brain wave signals output by the brain wave signal acquisition device when the driver enters the sleep state from the non-sleep state, and R_WT、A_LWT、A_HWT、B_LWT、B_HWT、T_WTAnd D_WTThe signal values of the original brain wave, low alpha wave, high alpha wave, low beta wave, high beta wave, theta wave and wave signal in the brain wave signal output by the brain wave signal acquisition device when the driver enters the waking state from the non-waking state are respectively.

The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized in that: the electroencephalogram signal monitoring device in the first step further comprises a third wireless communication module connected with the main control chip; the main control chip is communicated with the upper computer through a third wireless communication module;

and in the step B4, when the count value of the counter is larger than N, the main control chip synchronously transmits the fatigue driving state of the driver to the upper computer through the third wireless communication module.

The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized in that: the electroencephalogram signal preprocessing device is a TGAM chip developed by Neurosky company in the United states; the output end of the first brain electrode is connected with an EEG pin of the TGAM chip, the output end of the second brain electrode is connected with a REF pin of the TGAM chip, and the output end of the third brain electrode is connected with an EEG _ GND pin of the TGAM chip.

The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized in that: in the first step, the main control chip is an Arduino controller; the first wireless communication module and the second wireless communication module are both Bluetooth wireless communication modules; the third wireless communication module is a GPRS wireless communication module.

The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized in that: in the step one, the first brain electrode is placed on the left forehead of the driver determined according to the 10-20 system electrode placement method, and the second brain electrode and the third brain electrode are both placed in the left temple of the driver determined according to the 10-20 system electrode placement method.

Compared with the prior art, the invention has the following advantages:

1. the method has the advantages of simple steps, reasonable design, convenient implementation and low input cost.

2. The fatigue driving electroencephalogram monitoring speed is high, and the electroencephalogram state of the driver can be obtained through synchronous analysis and processing.

3. The method is simple and convenient to use and operate, is convenient to realize, and can directly and effectively utilize the output data (particularly the meditation degree data and the concentration degree data) of the TGAM module.

4. The electroencephalogram signal acquisition device and the electroencephalogram signal monitoring device are simple in circuit, reasonable in design, convenient to wire, simple and convenient to use and operate, low in input cost and convenient to install and lay actually.

5. The driving fatigue state is judged according to the meditation degree and concentration degree data, the driving fatigue state of the driver can be accurately monitored in real time, and the method is simple in step.

6. The driving fatigue state is further verified by matching with a multi-threshold comparison and judgment method, particularly the meditation degree and concentration degree data are used as a basic method for judging the driving fatigue state, and the multi-threshold comparison and judgment method is used as a verification method, so that the accuracy and the effectiveness of a fatigue starting state monitoring result can be effectively ensured. The multi-threshold comparison and judgment method adopts a multi-threshold comparison mode to judge the fatigue degree of the driver in real time. Moreover, each threshold is determined by adopting the weighting of the mean value and the standard deviation of a plurality of signal values, and different thresholds are adopted by different drivers; because the brain wave signals of each person have certain difference, the difference of the brain wave signals can be reduced by collecting the brain wave signals of a user (namely a driver) and determining the corresponding threshold value, so that the threshold value has the characteristic of self-adaption, and the driving fatigue state monitoring result of the method is very accurate. Meanwhile, the multi-threshold comparison and judgment method represents the fatigue degree through a counter, and is visual, convenient and accurate; when the fatigue testing device is actually used, the larger the count value of the counter is, the larger the fatigue degree of a driver is; conversely, the smaller the count value of the counter, the smaller the fatigue degree of the driver.

7. The fatigue driving state monitoring device has the advantages of good use effect, high practical value, remarkable economic benefit and social benefit, capability of simply monitoring the fatigue driving state of the driver in real time, capability of controlling the alarm prompting unit to give an alarm prompt according to a monitoring result, capability of enabling the driver to be in a clear state in real time, reduction of traffic accidents, real-time performance and good monitoring effect. In addition, the invention adopts a brain wave signal analysis processing method capable of accurately representing fatigue driving, establishes a judgment model capable of accurately describing fatigue driving, determines objective fatigue driving detection basis for a driver, lays a foundation for further researching and developing a vehicle-mounted and real-time fatigue driving alarm system, and provides reliable basis for scientific and reasonable intervention of fatigue driving by a traffic management department and maximum reduction of man-made traffic accidents.

In conclusion, the method has the advantages of simple steps, reasonable design, convenience in implementation and good use effect, and can simply, conveniently and quickly accurately monitor the fatigue driving state of the driver.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

Drawings

FIG. 1 is a block diagram of the process flow of the present invention.

FIG. 2 is a schematic circuit diagram of an electroencephalogram signal acquisition device and an electroencephalogram signal monitoring device according to the present invention.

FIG. 3 is a schematic circuit diagram of the electroencephalogram signal acquisition device and the first wireless communication module according to the present invention.

FIG. 4 is a schematic circuit diagram of the electroencephalogram signal monitoring device of the present invention.

Description of reference numerals:

1-an electroencephalogram signal acquisition device; 1-an electroencephalogram signal extraction device;

1-11-a first brain electrode; 1-12-a second brain electrode; 1-13-third brain electrode;

1-2-an electroencephalogram signal preprocessing device; 2-an electroencephalogram signal monitoring device;

2-1, a main control chip; 2-a second wireless communication module;

2-3-a third wireless communication module; 2-4-a power supply unit;

2-5, an alarm prompting unit; 2-6-parameter input unit; 2-7-a display;

3-a first wireless communication module; and 4, an upper computer.

Detailed Description

As shown in fig. 1, the fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree comprises the following steps:

step one, brain wave signal acquisition: the electroencephalogram signal acquisition device 1 is adopted to acquire and preprocess the electroencephalogram signal of a driver according to a preset sampling frequency, and the preprocessed electroencephalogram signal is synchronously transmitted to the electroencephalogram signal monitoring device 2;

the electroencephalogram signal acquisition device 1 and the electroencephalogram signal monitoring device 2 are communicated in a wireless communication mode; the electroencephalogram signal acquisition device 1 is a TGAM module, the TGAM module comprises an electroencephalogram signal extraction device 1-1 for extracting electroencephalogram signals of a driver and an electroencephalogram signal preprocessing device 1-2 for sampling and preprocessing the signals extracted by the electroencephalogram signal extraction device 1-1, the electroencephalogram signal preprocessing device 1-2 is connected with the electroencephalogram signal extracting device 1-1, the electroencephalogram signal extraction device 1-1 comprises a first electroencephalogram electrode 1-11 for sampling the electric potential of the frontal lobe area of the driver in real time, a second electroencephalogram electrode 1-12 and a third electroencephalogram electrode 1-13 for sampling the electric potential of the ear of the driver in real time, the first brain electrode 1-11, the second brain electrode 1-12 and the third brain electrode 1-13 are all connected with the brain signal preprocessing device 1-2; the electroencephalogram signal monitoring device 2 comprises a main control chip 2-1, a second wireless communication module 2-2 and an alarm prompting unit 2-5, wherein the second wireless communication module 2-2 and the alarm prompting unit 2-5 are respectively connected with the main control chip 2-1, and the alarm prompting unit 2-5 is controlled by the main control chip 2-1 and is connected with the main control chip 2-1; the electroencephalogram signal preprocessing device 1-2 is connected with the first wireless communication module 3, and the electroencephalogram signal preprocessing device 1-2 is communicated with the main control chip 2-1 through the first wireless communication module 3 and the second wireless communication module 2-2;

step two, brain wave signal analysis and processing: the main control chip 2-1 respectively analyzes and processes the brain wave signals collected and preprocessed by the brain wave signal acquisition device 1 within one second according to the sampling time sequence, and judges whether the driver is in a fatigue driving state at the moment according to the analysis and processing result; moreover, the analysis and processing methods of the electroencephalogram signals collected and preprocessed by the electroencephalogram signal acquisition device 1 in each second by the main control chip 2-1 are the same; when the brain wave signals collected and preprocessed by the brain wave signal acquisition device 1 within any one second are analyzed and processed, the process is as follows:

step 201, brain wave signal synchronous storage: synchronously storing the brain wave signals which are acquired and preprocessed by the brain wave signal acquisition device 1 within one second;

Step 204, threshold comparison: calling a threshold comparison module to calculate the fatigue degree of the driver at the moment obtained in the step 203And F₀And (3) comparing difference values: when in useF₀If so, it means the fatigue moment to be determined, and the process proceeds to step 205; otherwise, returning to the step 201, analyzing and processing the brain wave signal acquired and preprocessed by the brain wave signal acquisition device 1 within the next second;

step 205, calculating the fatigue degree of the driver in the next second: analyzing and processing the brain wave signals collected and preprocessed by the brain electrical signal acquisition device 1 in the next second according to the method from the step 201 to the step 203, and calculating the fatigue degree of the driver in the next second after the fatigue moment to be determined

Step 206, repeating the step 206 for K-1 times, and obtaining the fatigue degree of the driver within K seconds after the fatigue moment to be determinedWherein K is a positive integer and K is 8-15; that isThat is, calculating the fatigue degree of the driver for continuous K seconds;

step 207, fatigue driving judgment: calling the threshold comparison module to compare the fatigue degree of the driver within K seconds after the fatigue moment to be determined obtained in the step 206Are respectively reacted with F₀And (3) comparing difference values: when the fatigue degree of the driver within K seconds after the fatigue moment to be determinedAre all greater than F₀When the driver is in a fatigue driving state, the main control chip 2-1 controls the alarm prompt unit 2-5 to give an alarm prompt; otherwise, the driver is in a normal driving state at the moment;

and 208, returning to the step 201, and analyzing and processing the brain wave signals collected and preprocessed by the brain wave signal acquisition device 1 within the next second.

In this embodiment, K is 10 in step 206.

In this embodiment, step F in step 204₀＝1.4。

In actual use, K and F can be adjusted according to specific requirements₀The value size of the signal is correspondingly adjusted.

In this embodiment, in step 207, the fatigue degree of the driver within K seconds after the fatigue time to be determinedAre all greater than F₀Before the main control chip 2-1 controls the alarm prompting unit 2-5 to prompt an alarm, a multi-threshold comparison and judgment module is required to be called to analyze the brain wave signals received in step 201, and the fatigue driving state of the driver at this time is verified according to the analysis and processing result, and the process is as follows:

step B1, characteristic signal extraction: the main control chip 2-1 calls a feature extraction module to extract 7 feature signals from the brain wave signals processed at the moment;

step B2, feature quantity determination: the main control chip 2-1 takes the signal values of the 7 characteristic signals in step B1 as the 7 characteristic quantities of the brain wave signal processed at this time; the 7 characteristic signals are original brain waves, low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and wave signals respectively, and the 7 characteristic quantities are R, A respectively_L、A_H、B_L、B_HT and D;

when the electroencephalogram signal acquisition device 1 acquires and preprocesses electroencephalogram signals of a driver in the first step, the sampling frequency of the original electroencephalogram is 512Hz, and the sampling frequencies of low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and waves are all 1 Hz; in the 7 feature signals, the number of the original brain wave signals is 512, and the number of low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and wave signals is one;

step B3, multi-threshold comparison: the main control chip 2-1 judges threshold values according to 7 groups of predetermined fatigue driving and calls a threshold value comparison module, respectively performs threshold value comparison on the 7 characteristic quantities determined in the step B2, and records the threshold value comparison results by adopting a counter;

the initial count value of the counter is 0;

the 7 groups of fatigue driving judgment threshold values are respectively a group of original brain wave judgment threshold values, a group of low alpha wave judgment threshold values, a group of high alpha wave judgment threshold values, a group of low beta wave judgment threshold values, a group of high beta wave judgment threshold values, a group of theta wave judgment threshold values and a group of wave judgment threshold values; wherein the original brain wave judging threshold comprises an original brain wave fatigue threshold R_STAnd the original brain wave waking threshold R_WTThe low alpha wave judgment threshold comprises a low alpha wave fatigue threshold A_LSTAnd low alpha wave wakefulness threshold A_LWTThe high alpha wave judging threshold comprises a high alpha wave fatigue threshold A_HSTAnd a high alpha wave wakefulness threshold A_HWTThe low beta wave judgment threshold comprises a low beta wave fatigue threshold B_LSTAnd low beta wave wake threshold B_LWTThe high beta wave judgment threshold comprises a high beta wave fatigue threshold B_HSTAnd a high beta wave wake threshold B_HWTThe theta wave judging threshold comprises a theta wave fatigue threshold T_STAnd theta wave wakefulness threshold T_WTThe wave judging threshold value comprises a wave fatigue threshold value D_STSum wave wake threshold D_WT；

When the 7 feature quantities determined in step B2 are respectively subjected to threshold comparison, the main control chip 2-1 calls a threshold comparison module to determine a threshold and a feature quantity a for the feature quantity R and a group of original brain waves_LAnd a set of low alpha wave judgment threshold value and characteristic quantity A_HA set of high alpha wave judgment threshold values and characteristic quantity B_LAnd a set of low beta wave judgment threshold value and characteristic quantity B_HRespectively carrying out threshold comparison with a group of high beta wave judgment threshold values, a characteristic quantity T and a group of theta wave judgment threshold values, and a characteristic quantity D and a group of wave judgment threshold values;

when the characteristic quantity R is compared with a group of original brain wave judgment threshold values, the characteristic quantity R and the characteristic quantity R are compared firstly_STAnd (3) comparing difference values: when R < R_STThen, the main control chip 2-1 adds 5 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the metal powder is mixedCharacteristic quantities R and R_WTAnd (3) comparing difference values: when R > R_WTThen, the main control chip 2-1 subtracts 5 from the count value of the timer; otherwise, the count value of the timer is unchanged;

for characteristic quantity A_LWhen the threshold value is compared with a group of low alpha wave judgment threshold values, the characteristic quantity A is firstly compared_LAnd A_LSTAnd (3) comparing difference values: when A is_L＜A_LSTThen, adding 1 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the characteristic quantity A is measured_LAnd A_LWTAnd (3) comparing difference values: when A is_L＞A_LWTThen, subtracting 1 from the count value of the timer; otherwise, the count value of the timer is unchanged;

for characteristic quantity B_HWhen the characteristic quantity B is compared with a group of high beta wave judgment threshold values in a threshold value way, the characteristic quantity B is firstly measured_HAnd B_HSTAnd (3) comparing difference values: when B is present_H＜B_HSTAt this time, the count value of the timer is countedAdding 2; otherwise, the count value of the timer is unchanged; then, the characteristic quantity B is measured_HAnd B_HWTAnd (3) comparing difference values: when B is present_H＞B_HWTThen, subtracting 2 from the count value of the timer; otherwise, the count value of the timer is unchanged;

when the characteristic quantity T is compared with a group of theta wave judgment threshold values, the characteristic quantity T and the characteristic quantity T are firstly compared_STAnd (3) comparing difference values: when T is less than T_STThen, adding 1 to the count value of the timer; otherwise, the count value of the timer is unchanged; then, the characteristic quantities T and T are compared_WTAnd (3) comparing difference values: when T > T_WTThen, subtracting 1 from the count value of the timer; otherwise, the count value of the timer is unchanged;

step B4, fatigue driving judgment: the main control chip 2-1 judges the fatigue driving state of the driver at this time according to the count value of the counter after the multi-threshold comparison in the step B3 is completed: when the count value of the counter is larger than N, the driver is in a fatigue driving state at the moment after verification, and the main control chip 2-1 controls the alarm prompting unit 2-5 to perform alarm prompting; otherwise, the driver is in a fatigue driving state at the moment after verification;

wherein N is a positive integer and N is 52-58.

In practical use, the brain wave signals collected and preprocessed by the TGAM module comprise original brain waves, alpha waves, beta waves, theta waves and wave signals, wherein the alpha waves are divided into three wave bands, namely low alpha waves, midle alpha waves and high alpha waves; the beta wave is divided into three bands, namely a low beta wave, a midle beta wave and a high beta wave.

The electroencephalogram signal output by the electroencephalogram signal acquisition device 1 is a frequency domain signal that has been subjected to fast fourier transform (i.e., FFT transform).

In the time domain, the original brain waves, low α waves, high α waves, low β waves, high β waves, θ waves and wave signals are signals whose electric potential varies with time, where the unit of electric potential is μ V (i.e., microvolts) and the unit of time is s. In actual use, the electroencephalogram signal acquisition device 1 may output time domain signals of the original electroencephalogram, low α wave, high α wave, low β wave, high β wave, θ wave, and wave signal, and then perform fast fourier transform using an external control chip.

And after fast Fourier transform, converting the time domain signal into a frequency domain signal. For a frequency domain signal, the argument is the frequency, the horizontal axis is the frequency, the vertical axis is the amplitude of the frequency signal, and the frequency component of the signal is expressed.

After a fast fourier transformation, a so-called spectrogram is obtained. The spectrogram describes the frequency structure of a signal and the relationship of the frequency to the amplitude of the frequency signal.

In this embodiment, the original electroencephalograms, the low α waves, the high α waves, the low β waves, the high β waves, the θ waves, and the wave signals are all frequency domain signals, and the signal values of the original electroencephalograms, the low α waves, the high α waves, the low β waves, the high β waves, the θ waves, and the wave signals in step B2 are all signal amplitudes, that is, vertical coordinate values calculated by fast fourier transform.

In actual use, the original brain waves, the low α waves, the high α waves, the low β waves, the high β waves, the θ waves and the wave signals in step B2 may all be time domain signals, and in this case, the signal values of the original brain waves, the low α waves, the high α waves, the low β waves, the high β waves, the θ waves and the wave signals in step B2 may all be potential values, that is, voltage values.

In this embodiment, the original electroencephalograms, the low α waves, the high α waves, the low β waves, the high β waves, the θ waves, and the wave signals are all signals directly output by the TGAM module, and therefore, the signal values of the original electroencephalograms, the low α waves, the high α waves, the low β waves, the high β waves, the θ waves, and the wave signals are all signal values of the signals output by the TGAM module, and only need to be used directly, which is very simple and convenient to implement.

In this embodiment, the meditation degree M and concentration degree a in step 202 are both data directly output by the TGAM module, and only need to be directly used, so the implementation is very simple. The signal values of the original electroencephalograms, low α waves, high α waves, low β waves, high β waves, θ waves, and wave signals are data of the signals output by the TGAM module.

In this embodiment, before performing the brain wave signal analysis processing in step two, the main control chip 2-1 is first used to determine the fatigue driving judgment threshold values of the 7 groups in step B3;

when 7 groups of fatigue driving judgment threshold values in the step B3 are determined, firstly, acquiring brain wave signals of a driver within P seconds by using the brain wave signal acquisition device 1, and then determining 7 groups of fatigue driving judgment threshold values according to the acquired brain wave signals of the driver within P seconds; wherein P is a positive integer and P is 50-70;

step B31, characteristic signal extraction: firstly, 512 xP original brain wave signals, P low alpha wave signals, P high alpha wave signals, P low beta wave signals, P high beta wave signals, P theta wave signals and P wave signals are extracted from the obtained brain wave signals of the driver within P seconds, and the A is processed_LM、A_LSD、A_HM、A_HSD、B_LM、B_LSD、B_HM、B_HSD、T_M、T_SD、D_MAnd D_SDRespectively calculating;

wherein R is_MAnd R_SDThe levels of the signal values of the respective 512 × P original brain wave signalsMean and standard deviation, A_LMAnd A_LSDMean and standard deviation of the signal values of the P low alpha wave signals, A_HMAnd A_HSDMean and standard deviation of the signal values of the P high alpha wave signals, B_LMAnd B_LSDMean and standard deviation of the signal values of the P low beta wave signals, B_HMAnd B_HSDMean value and standard deviation of signal values of P high beta wave signals, T_MAnd T_SDMean and standard deviation of the signal values of the P theta wave signals, D_MAnd D_SDThe average value and the standard deviation of the signal values of the P wave signals are respectively;

In the formula (10), b_HW1And b_HW2Is B_HWTThe two weighting coefficients of (a) to (b),0＜b_HW1≤1，-1≤b_HW2＜0；

In this example, 0.5 < a_LS1≤1，0.5＜a_LW1≤1，0.5＜a_HS1≤1，0.5＜a_HW1≤1，0.5＜b_LS1≤1，0.5＜b_LW1≤1，0.5＜b_HS1≤1，0.5＜b_HW1≤1，0.5＜t_S1≤1，0.5＜t_W1≤1，0.5＜d_S1≤1，0.5＜d_W1≤1。

In actual use, r can be adjusted according to specific requirements_S1、r_S2、r_W1、r_W2、a_LS1、a_LS2、a_LW1、a_LW2、a_HS1、a_HS2、a_HW1、a_HW2、b_LS1、b_LS2、b_LW1、b_LW2、b_HS1、b_HS2、b_HW1、b_HW2、t_S1、t_S2、t_W1、t_W2、d_S1、d_S2、d_W1And d_W2The value size of the signal is correspondingly determined.

For simplicity of implementation, r_S1、r_S2、r_W1、r_W2、a_LS1、a_LS2、a_LW1、a_LW2、a_HS1、a_HS2、a_HW1、a_HW2、b_LS1、b_LS2、b_LW1、b_LW2、b_HS1、b_HS2、b_HW1、b_HW2、t_S1、t_S2、t_W1、t_W2、d_S1、d_S2、d_W1And d_W2A value can be randomly selected from the above range.

In this embodiment, before the threshold value is calculated in step B32, the main control chip 2-1 needs to be used to compare r_S1、r_S2、r_W1、r_W2、a_LS1、a_LS2、a_LW1、a_LW2、a_HS1、a_HS2、a_HW1、a_HW2、b_LS1、b_LS2、b_LW1、b_LW2、b_HS1、b_HS2、b_HW1、b_HW2、t_S1、t_S2、t_W1、t_W2、d_S1、d_S2、d_W1And d_W2The determination is made as follows:

step B321, acquiring brain wave signals of the driver in the sleep state and the waking state and extracting characteristic signals: acquiring brain wave signals within m1 seconds of a driver in a sleeping state and brain wave signals within m2 seconds of the driver in an awake state by using a brain wave signal acquisition device 1, extracting 512 × m1 original brain wave signals, m1 low alpha wave signals, m1 high alpha wave signals, m1 low beta wave signals, m1 high beta wave signals, m1 theta wave signals and m1 wave signals from the brain wave signals within m1 seconds of the driver in the sleeping state, and extracting 512 × m2 original brain wave signals, m2 low alpha wave signals, m2 high alpha wave signals, m2 low beta wave signals, m2 high beta wave signals, m2 theta wave signals and m2 wave signals from the brain wave signals within m2 seconds of the driver in the awake state;

wherein m1 and m2 are positive integers, m1 is more than or equal to 5, and m2 is more than or equal to 5;

step B322, determining the initial value of the weighting coefficient:

from (0, 6)]In the random extraction of a number as r_S1Randomly extracting a number from [ -3, 0) as r_S2An initial value of (1);

from (0, 6)]In the random extraction of a number as r_W1Randomly extracting a number from [ -3, 0) as r_W2An initial value of (1);

from (0, 1)]In the random extraction of a number as a_LS1Randomly extracting a number from [ -1, 0) as a_LS2An initial value of (1);

from (0, 1)]In the random extraction of a number as a_LW1Randomly extracting a number from [ -1, 0) as a_LW2An initial value of (1);

from (0, 1)]In the random extraction of a number as a_HS1Randomly extracting a number from [ -1, 0) as a_HS2An initial value of (1);

from (0, 1)]In the random extraction of a number as a_HW1Randomly extracting a number from [ -1, 0) as a_HW2An initial value of (1);

from (0, 1)]In the random extraction of a number as b_LS1Randomly extracting a number from [ -1, 0) as b_LS2An initial value of (1);

from (0, 1)]In the random extraction of a number as b_LW1Randomly extracting a number from [ -1, 0) as b_LW2An initial value of (1);

from (0, 1)]In the random extraction of a number as b_HS1Randomly extracting a number from [ -1, 0) as b_HS2An initial value of (1);

from (0, 1)]In the random extraction of a number as b_HW1Randomly extracting a number from [ -1, 0) as b_HW2An initial value of (1);

from (0, 1)]Randomly extracting a number as t_S1Randomly extracting a number from [ -1, 0) as t_S2An initial value of (1);

from (0, 1)]Randomly extracting a number as t_W1Randomly extracting a number from [ -1, 0) as t_W2An initial value of (1);

from (0, 1)]In the random extraction of a number as d_S1Randomly extracting a number from [ -1, 0) as d_S2An initial value of (1);

from (0, 1)]In the random extraction of a number as d_W1Randomly extracting a number from [ -1, 0) as d_W2An initial value of (1);

step B323, weighting coefficient increase and decrease adjustment: according to the brain wave signal within m1 seconds of the driver in the sleep state acquired in the step B321, r determined in the step B322 is compared with r_S1、r_S2、a_LS1、a_LS2、a_HS1、a_HS2、b_LS1、b_LS2、b_HS1、b_HS2、t_S1、t_S2、d_S1And d_S2Respectively carrying out increase and decrease adjustment; meanwhile, r determined in step B322 is determined according to the electroencephalogram signal of the driver in the awake state acquired in step B321 within m2 seconds_W1、r_W2、a_LW1、a_LW2、a_HW1、a_HW2、b_LW1、b_LW2、b_HW1、b_HW2、t_W1、t_W2、d_W1And d_W2Respectively carrying out increase and decrease adjustment;

wherein, to r_S1And r_S2When performing the increase/decrease adjustment, r is adjusted from first to last using the 512 × m1 original electroencephalogram signals extracted in step B321_S1And r_S2Performing increase and decrease adjustment 512 Xm 1 times, wherein the increase and decrease adjustment method is the same for each time; wherein, any one original brain wave signal pair r in 512 × m1 original brain wave signals is used_S1And r_S2When the adjustment is made, the process is as follows：

Step 1-1, will be at this moment r_S1And r_S2Substituting the numerical value of (A) into the formula (1), calculating the original brain wave fatigue threshold before increasing and decreasing adjustment, and recording as R_ST'；

Step 1-2, comparing the signal value of the original brain wave signal used at this time with the R value in step 1-1_ST' making a difference comparison: when the signal value of the original brain wave signal is less than R_STWhen r is_S1And r_S2The value of (A) is unchanged; otherwise, for r_S1And r_S2All reduce and adjust to make the signal value of the original brain wave signal more than or equal to R_ST”；

Wherein R is_ST"to reduce the adjusted r_S1And r_S2Substituting the numerical value of the brain wave into the formula (1), and calculating to obtain a threshold value for reducing the fatigue of the adjusted original brain wave;

step 1-3, using a next pair r of original brain wave signals of 512 xm 1 original brain wave signals according to the method described in the steps 1-1 to 1-2_S1And r_S2Performing increase and decrease adjustment;

1-4, repeating the steps 1-3 for a plurality of times until the 512 xm 1 original brain wave signal pairs r are completed_S1And r_S2The increase and decrease adjustment process of (1);

to a_LS1And a_LS2When the adjustment is performed, the m1 low alpha wave signals extracted in step B321 are used to adjust a_LS1And a_LS2Performing m1 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any low alpha wave signal pair a in m1 low alpha wave signals is used_LS1And a_LS2When the adjustment is carried out, the process is as follows:

step 3-1, will be a at this time_LS1And a_LS2Substituting the value of (A) into the formula (3), calculating the fatigue threshold of low alpha wave before increasing and decreasing adjustment, and recording the fatigue threshold as A_LST'；

Step 3-2 of using the low alpha wave signalSignal value and A described in step 3-1_LST' making a difference comparison: when the signal value of the low alpha wave signal is less than A_LSTWhen a_LS1And a_LS2The value of (A) is unchanged; otherwise, for a_LS1And a_LS2All reduce and adjust to make the signal value of the low alpha wave signal equal to or larger than A_LST”；

Wherein A is_LST"to reduce a after adjustment_LS1And a_LS2Substituting the numerical value of the alpha wave into the formula (3) to calculate the low alpha wave fatigue threshold value after the adjustment is reduced;

step 3-3, using the next low alpha wave signal pair a of m1 low alpha wave signals according to the method described in step 3-1 to step 3-2_LS1And a_LS2Performing increase and decrease adjustment;

step 3-4, repeating step 3-3 for a plurality of times until m1 low alpha wave signal pairs a are completed_LS1And a_LS2The increase and decrease adjustment process of (1);

to a_HS1And a_HS2When the adjustment is performed, the m1 high α wave signals extracted in step B321 are used to adjust a from first to last_HS1And a_HS2Performing m1 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any high alpha wave signal pair a in m1 high alpha wave signals is used_HS1And a_HS2When the adjustment is carried out, the process is as follows:

step 5-1, will be a at this time_HS1And a_HS2Substituting the numerical value of (A) into the formula (5), calculating the fatigue threshold value of high alpha wave before increasing and decreasing adjustment, and recording the fatigue threshold value as A_HST'；

Step 5-2, comparing the signal value of the high alpha wave signal used at the moment with the A in the step 5-1_HST' making a difference comparison: when the signal value of the high alpha wave signal is less than A_HSTWhen a_HS1And a_HS2The value of (A) is unchanged; otherwise, for a_HS1And a_HS2All the signals are reduced and adjusted to make the signal value of the high alpha wave signal be greater than or equal to A_HST”；

Wherein,A_HST"to reduce a after adjustment_HS1And a_HS2Substituting the numerical value of the alpha wave into the formula (5) to calculate the fatigue threshold value of the high alpha wave after the adjustment is reduced;

step 5-3, using the next high alpha wave signal pair a of m1 high alpha wave signals according to the method described in step 5-1 to step 5-2_HS1And a_HS2Performing increase and decrease adjustment;

step 5-4, repeating step 5-3 for a plurality of times until m1 pairs of high alpha wave signals a are completed_HS1And a_HS2The increase and decrease adjustment process of (1);

to b is_LS1And b_LS2When the adjustment is performed, the m1 low beta wave signals extracted in step B321 are used to adjust B from first to last_LS1And b_LS2Performing m1 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any one low beta wave signal pair b in m1 low beta wave signals is used_LS1And b_LS2When the adjustment is carried out, the process is as follows:

step 7-1, will be b at this point_LS1And b_LS2Substituting the value of (A) into the formula (7), calculating the fatigue threshold of low beta wave before increasing or decreasing adjustment, and recording the fatigue threshold as B_LST'；

Step 7-2, comparing the signal value of the low beta wave signal used at the moment with the B signal in the step 7-1_LST' making a difference comparison: when the signal value of the low beta wave signal is less than B_LSTWhen, b_LS1And b_LS2The value of (A) is unchanged; otherwise, for b_LS1And b_LS2All reduce and adjust to make the signal value of the low beta wave signal equal to or larger than B_LST”；

Wherein, B_LST"adjusted to reduce b_LS1And b_LS2Substituting the numerical value of the formula (7) into the formula (7), and calculating to obtain a low beta wave fatigue threshold value after adjustment is reduced;

step 7-3, using the next low beta wave signal pair b of m1 low beta wave signals according to the method described in step 7-1 to step 7-2_LS1And b_LS2Go on to increaseSubtracting and adjusting;

step 7-4, repeating the step 7-3 for a plurality of times until m1 low beta wave signal pairs b are completed_LS1And b_LS2The increase and decrease adjustment process of (1);

to b is_HS1And b_HS2When performing the increase/decrease adjustment, the m1 high beta-wave signals extracted in step B321 are used to adjust the B wave signal from first to last_HS1And b_HS2Performing m1 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any high beta wave signal pair b in m1 high beta wave signals is used_HS1And b_HS2When the adjustment is carried out, the process is as follows:

step 9-1, will be b at this point_HS1And b_HS2Substituting the numerical value of (A) into the formula (9), calculating the fatigue threshold value of high beta wave before increasing and decreasing adjustment, and recording the fatigue threshold value as B_HST'；

Step 9-2, comparing the signal value of the high beta wave signal used in the step with the signal value B in the step 9-1_HST' making a difference comparison: when the signal value of the high beta wave signal is less than B_HSTWhen, b_HS1And b_HS2The value of (A) is unchanged; otherwise, for b_HS1And b_HS2All the signals are reduced and adjusted to make the signal value of the high beta wave signal equal to or more than B_HST”；

Wherein, B_HST"adjusted to reduce b_HS1And b_HS2Substituting the numerical value of the formula (9) into the formula (9), and calculating to obtain a high beta wave fatigue threshold value after adjustment is reduced;

step 9-3, using the next high beta-wave signal pair b of the m1 high beta-wave signals according to the method described in step 9-1 to step 9-2_HS1And b_HS2Performing increase and decrease adjustment;

step 9-4, repeating step 9-3 for a plurality of times until m1 high beta wave signal pairs b are completed_HS1And b_HS2The increase and decrease adjustment process of (1);

for t_S1And t_S2When the adjustment is performed, m1 θ wave signals extracted in step B321 are usedFirst to last to t_S1And t_S2Performing m1 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any one theta wave signal pair t in m1 theta wave signals is used_S1And t_S2When the adjustment is carried out, the process is as follows:

step 11-1, will this time t_S1And t_S2Substituting the value of (A) into the formula (11), calculating the fatigue threshold value of theta wave before increasing and decreasing adjustment, and recording as T_ST'；

Step 11-2, the signal value of the theta wave signal used at this time and the T described in step 11-1_ST' making a difference comparison: when the signal value of the theta wave signal is less than T_STWhen, t_S1And t_S2The value of (A) is unchanged; otherwise, for t_S1And t_S2All reduce and adjust to make the signal value of theta wave signal equal to or greater than T_ST”；

Wherein, T_ST"to reduce t after adjustment_S1And t_S2Substituting the numerical value of the equation (11) into the formula (11), and calculating the fatigue threshold value of the theta wave after the adjustment is reduced;

step 11-3, using the next theta wave signal pair t of the m1 theta wave signals according to the method from step 11-1 to step 11-2_S1And t_S2Performing increase and decrease adjustment;

step 11-4, repeating the step 11-3 for multiple times until m1 theta wave signal pairs t are completed_S1And t_S2The increase and decrease adjustment process of (1);

to d_S1And d_S2When the adjustment is performed, the m1 wave signals extracted in step B321 are used to adjust d from beginning to end_S1And d_S2Performing m1 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any wave signal pair d in m1 wave signals is used_S1And d_S2When the adjustment is carried out, the process is as follows:

step 13-1, will d at this point_S1And d_S2The value of (2) is substituted into the formula (13), and the wave fatigue threshold value before increasing and decreasing adjustment is calculated and recorded asD_ST'；

Step 13-2, comparing the signal value of the wave signal used at this time with D in step 13-1_ST' making a difference comparison: when the signal value of the wave signal is < D_STWhen d is_S1And d_S2The value of (A) is unchanged; otherwise, for d_S1And d_S2All reduce and adjust to make the signal value of the wave signal equal to or greater than D_ST”；

Wherein D is_ST"to reduce by adjusting d_S1And d_S2Substituting the numerical value of the wave fatigue threshold value into a formula (13) and calculating to obtain a wave fatigue threshold value after adjustment;

step 13-3, using the next wave signal pair d of m1 theta wave signals according to the method described in step 13-1 to step 13-2_S1And d_S2Performing increase and decrease adjustment;

step 13-4, repeating step 13-3 for a plurality of times until m1 wave signal pairs d are completed_S1And d_S2The increase and decrease adjustment process of (1);

to r_W1And r_W2When performing the increase/decrease adjustment, r is adjusted from first to last using the 512 × m2 original electroencephalogram signals extracted in step B321_W1And r_W2Performing increase and decrease adjustment 512 Xm 2 times, wherein the increase and decrease adjustment method is the same for each time; wherein, any one original brain wave signal pair r in 512 × m2 original brain wave signals is used_W1And r_W2When the adjustment is carried out, the process is as follows:

step 2-1, will be at this moment r_W1And r_W2Substituting the value of (A) into the formula (2), calculating to obtain the original brain wave waking threshold before increasing and decreasing adjustment, and recording as R_WT'；

Step 2-2, comparing the signal value of the original brain wave signal utilized at the time with the R value in the step 2-1_WT' making a difference comparison: when the signal value of the original brain wave signal is greater than R_WTWhen r is_W1And r_W2The value of (A) is unchanged; otherwise, for r_W1And r_W2Are all increased and adjusted toThe signal value of the original brain wave signal is less than or equal to R_WT”；

Wherein R is_WT"to adjust the increase r_W1And r_W2Substituting the numerical value of the brain wave into a formula (2), and calculating to obtain an increased and adjusted original brain wave waking threshold;

step 2-3, using a next pair r of the 512 xm 2 original brain wave signals according to the method described in the steps 2-1 to 2-2_W1And r_W2Performing increase and decrease adjustment;

step 2-4, repeating step 2-3 for a plurality of times until completing 512 xm 2 original brain wave signal pairs r_W1And r_W2The increase and decrease adjustment process of (1);

to a_LW1And a_LW2When the adjustment is performed, the m2 low alpha wave signals extracted in step B321 are used to adjust a_LW1And a_LW2Performing m2 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any low alpha wave signal pair a in m2 low alpha wave signals is used_LW1And a_LW2When the adjustment is carried out, the process is as follows:

step 4-1, will be a at this time_LW1And a_LW2Substituting the value of (A) into the formula (4), calculating the low alpha wave wakefulness threshold before increasing and decreasing adjustment, and recording the value as A_LWT'；

Step 4-2, the signal value of the low alpha wave signal utilized at the moment and the A in the step 4-1_LWT' making a difference comparison: when the signal value of the low alpha wave signal is more than A_LWTWhen a_LW1And a_LW2The value of (A) is unchanged; otherwise, for a_LW1And a_LW2All make increase adjustment to make the signal value of the low alpha wave signal less than or equal to A_LWT”；

Wherein A is_LWT"to adjust the increase_LW1And a_LW2Substituting the numerical value of the alpha wave into a formula (4), and calculating to obtain a low alpha wave wakefulness threshold value after the adjustment is increased;

step (ii) of4-3, using the next low alpha wave signal pair a of m2 low alpha wave signals according to the method described in step 4-1 to step 4-2_LW1And a_LW2Performing increase and decrease adjustment;

step 4-4, repeating step 4-3 for a plurality of times until m2 low alpha wave signal pairs a are completed_LW1And a_LW2The increase and decrease adjustment process of (1);

to a_HW1And a_HW2When the adjustment is performed, the m2 high α wave signals extracted in step B321 are used to adjust a from first to last_HW1And a_HW2Performing m2 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any high alpha wave signal pair a in m2 high alpha wave signals is used_HW1And a_HW2When the adjustment is carried out, the process is as follows:

step 6-1, will be a at this time_HW1And a_HW2Substituting the numerical value of (A) into the formula (6), calculating the high alpha wave wakefulness threshold before increasing and decreasing adjustment, and recording the threshold as A_HWT'；

Step 6-2, the signal value of the high alpha wave signal used at the moment and the A in the step 6-1_HWT' making a difference comparison: when the signal value of the high alpha wave signal is more than A_HWTWhen a_HW1And a_HW2The value of (A) is unchanged; otherwise, for a_HW1And a_HW2All the signals are increased and adjusted to make the signal value of the high alpha wave signal less than or equal to A_HWT”；

Wherein A is_HWT"to adjust the increase_HW1And a_HW2Substituting the numerical value of the alpha value into the formula (6), and calculating the increased and adjusted high alpha wave wakefulness threshold;

step 6-3, according to the method described in the step 6-1 to the step 6-2, using the next high alpha wave signal pair a of m2 high alpha wave signals_HW1And a_HW2Performing increase and decrease adjustment;

step 6-4, repeating step 6-3 for a plurality of times until m2 pairs of high alpha wave signals a are completed_HW1And a_HW2The increase and decrease adjustment process of (1);

to b is_LW1And b_LW2When the adjustment is performed, the m2 low beta wave signals extracted in step B321 are used to adjust B from first to last_LW1And b_LW2Performing m2 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any one low beta wave signal pair b in m2 low beta wave signals is used_LW1And b_LW2When the adjustment is carried out, the process is as follows:

step 8-1, will be b at this time_LW1And b_LW2Substituting the value of (A) into the formula (8), calculating the low beta wave wakefulness threshold before increasing or decreasing, and recording as B_LWT'；

Step 8-2, comparing the signal value of the low beta wave signal used in the current time with the B signal in the step 8-1_LWT' making a difference comparison: when the signal value of the low beta wave signal is larger than B_LWTWhen, b_LW1And b_LW2The value of (A) is unchanged; otherwise, for b_LW1And b_LW2All make increase adjustment to make the signal value of the low beta wave signal less than or equal to B_LWT”；

Wherein, B_LWT"to adjust the increase b_LW1And b_LW2Substituting the numerical value of the (D) into a formula (8), and calculating to obtain an increased and adjusted low beta wave wakefulness threshold;

step 8-3, using the next low beta wave signal pair b of m2 low beta wave signals according to the method described in step 8-1 to step 8-2_LW1And b_LW2Performing increase and decrease adjustment;

step 8-4, repeating step 8-3 for a plurality of times until m2 low beta wave signal pairs b are completed_LW1And b_LW2The increase and decrease adjustment process of (1);

to b is_HW1And b_HW2When performing the increase/decrease adjustment, the m2 high beta-wave signals extracted in step B321 are used to adjust the B wave signal from first to last_HW1And b_HW2Performing m2 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any high beta wave signal pair b in m2 high beta wave signals is used_HW1And b_HW2Go on to increaseWhen the adjustment is reduced, the process is as follows:

step 10-1, will be b at this point_HW1And b_HW2Substituting the value of (A) into the formula (10), calculating the high beta wave wakefulness threshold before increasing or decreasing, and recording the value as B_HWT'；

Step 10-2, comparing the signal value of the high beta wave signal used at this time with the signal value B in the step 10-1_HST' making a difference comparison: when the signal value of the high beta wave signal is larger than B_HWTWhen, b_HW1And b_HW2The value of (A) is unchanged; otherwise, for b_HW1And b_HW2All the signals are increased and adjusted to make the signal value of the high beta wave signal less than or equal to B_HWT”；

Wherein, B_HWT"to adjust the increase b_HW1And b_HW2Substituting the numerical value of (b) into the formula (9), and calculating the increased and adjusted high beta wave waking threshold;

step 10-3, using the next high beta-wave signal pair b of the m2 high beta-wave signals according to the method described in the step 10-1 to the step 10-2_HW1And b_HW2Performing increase and decrease adjustment;

step 10-4, repeating step 10-3 for a plurality of times until m2 high beta wave signal pairs b are completed_HW1And b_HW2The increase and decrease adjustment process of (1);

for t_W1And t_W2When the increase/decrease adjustment is performed, m2 θ wave signals extracted in step B321 are used, and t is adjusted from first to last_W1And t_W2Performing m2 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any one theta wave signal pair t in m2 theta wave signals is used_W1And t_W2When the adjustment is carried out, the process is as follows:

step 12-1, let t at this time_W1And t_W2Substituting the value of (A) into the formula (12), calculating the theta wave wakefulness threshold before increasing and decreasing adjustment, and recording as T_WT'；

Step 12-2, the signal value of the theta wave signal used at this time and the step 12-1The T is_ST' making a difference comparison: when the signal value of the theta wave signal is greater than T_WTWhen, t_W1And t_W2The value of (A) is unchanged; otherwise, for t_W1And t_W2All increase and adjust to make the signal value of the theta wave signal less than or equal to T_WT”；

Wherein, T_WT"to adjust t after increase_W1And t_W2Substituting the numerical value of (a) into the formula (12) to calculate the theta wave wakefulness threshold after the increase adjustment;

step 12-3, using the next theta wave signal pair t of the m2 theta wave signals according to the method described in the step 12-1 to the step 12-2_W1And t_W2Performing increase and decrease adjustment;

step 12-4, repeating the step 12-3 for multiple times until m2 theta wave signal pairs t are completed_W1And t_W2The increase and decrease adjustment process of (1);

to d_W1And d_W2When the adjustment is performed, the m2 wave signals extracted in step B321 are used to adjust d from beginning to end_W1And d_W2Performing m2 times of increase and decrease adjustment, wherein the increase and decrease adjustment methods are the same; wherein, any wave signal pair d in m2 wave signals is used_W1And d_W2When the adjustment is carried out, the process is as follows:

step 14-1, will d at this point_W1And d_W2Substituting the value of (D) into equation (14), calculating the wakefulness threshold before increasing or decreasing, and recording as D_WT'；

Step 14-2, comparing the signal value of the wave signal used at this time with D in step 14-1_ST' making a difference comparison: when the signal value of the wave signal is > D_WTWhen d is_W1And d_W2The value of (A) is unchanged; otherwise, for d_W1And d_W2All carry out increase adjustment to make the signal value of the wave signal less than or equal to D_WT”；

Wherein D is_WT"to adjust d after increasing_W1And d_W2The numerical value of (C) is substituted into the formula (14) to calculate(ii) the derived increased adjusted wave wake threshold;

step 14-3, using the next wave signal pair d of m2 theta wave signals according to the method described in steps 14-1 to 14-2_W1And d_W2Performing increase and decrease adjustment;

step 14-4, repeating step 14-3 for a plurality of times until m2 wave signal pairs d are completed_W1And d_W2The increase and decrease adjustment process.

Thus, the present invention employs the above method for r_S1、r_S2、r_W1、r_W2、a_LS1、a_LS2、a_LW1、a_LW2、a_HS1、a_HS2、a_HW1、a_HW2、b_LS1、b_LS2、b_LW1、b_LW2、b_HS1、b_HS2、b_HW1、b_HW2、t_S1、t_S2、t_W1、t_W2、d_S1、d_S2、d_W1And d_W2A determination is made.

In this embodiment, r is corrected in step B323_S1、r_S2、a_LS1、a_LS2、a_HS1、a_HS2、b_LS1、b_LS2、b_HS1、b_HS2、t_S1、t_S2、d_S1And d_S2When the adjustment is increased or decreased, the adjustment amount is decreased by 0.01-0.1 each time; to r_W1、r_W2、a_LW1、a_LW2、a_HW1、a_HW2、b_LW1、b_LW2、b_HW1、b_HW2、t_W1、t_W2、d_W1And d_W2When the adjustment is respectively increased or decreased, the adjustment amount is increased by 0.01-0.1 each time.

During actual use, the adjustment quantity can be correspondingly adjusted according to specific requirements for each reduction and each increase.

In the actual use process, the step two is carried outWhen the fatigue driving determination threshold values of the 7 sets in step B3 are determined before the electroencephalogram signal analysis processing, the determination may be performed by the following method: firstly, respectively acquiring and preprocessing brain wave signals when a driver enters a sleep state from a non-sleep state and enters a waking state from a non-waking state by adopting a brain wave signal acquisition device 1; wherein R is_ST、A_LST、A_HST、B_LST、B_HST、T_STAnd D_STRespectively the signal values R of the original brain wave, low alpha wave, high alpha wave, low beta wave, high beta wave, theta wave and wave signal in the brain wave signal output by the brain wave acquisition device 1 when the driver enters the sleep state from the non-sleep state_WT、A_LWT、A_HWT、B_LWT、B_HWT、T_WTAnd D_WTThe signal values of the original brain wave, low alpha wave, high alpha wave, low beta wave, high beta wave, theta wave and wave signal in the brain wave signal output by the brain wave signal acquisition device 1 when the driver enters the waking state from the non-waking state are respectively.

In this embodiment, N is 55 in step B4. In actual use, the value of N can be adjusted correspondingly according to specific requirements.

In this embodiment, the obtained brain wave signal of the driver within P seconds is a brain wave signal acquired and preprocessed by the brain wave signal acquisition device 1 within P seconds;

in the step B321, the brain wave signal within m1 seconds of the driver in the sleep state is the brain wave signal acquired and preprocessed by the brain wave signal acquiring device 1 within m1 seconds, and the brain wave signal within m2 seconds of the driver in the waking state is the brain wave signal acquired and preprocessed by the brain wave signal acquiring device 1 within m2 seconds.

In this embodiment, in the first step, the main control chip 2-1 is an Arduino controller.

In practical use, the main control chip 2-1 may also adopt other types of controllers, such as an ARM controller.

In this embodiment, the electroencephalogram signal monitoring device 2 in the first step further includes a third wireless communication module 2-3 connected to the main control chip 2-1; the main control chip 2-1 is communicated with the upper computer 4 through a third wireless communication module 2-3;

in the step B4, when the count value of the counter is greater than N, the main control chip 2-1 synchronously transmits the fatigue driving state of the driver to the upper computer 4 through the third wireless communication module 2-3.

When the electroencephalogram monitoring device is actually used, the electroencephalogram signal monitoring device 2 is arranged in a vehicle driven by a driver, the main control chip 2-1 and the second wireless communication module 2-2 are uniformly arranged on an electronic circuit board, and the electronic circuit board is arranged in a shell; the alarm prompting units 2-5 are arranged on the shell.

Meanwhile, the electroencephalogram signal monitoring device 2 further comprises a power supply unit 2-4 connected with the main control chip 2-1.

In this embodiment, the alarm prompt units 2 to 5 are voice prompt units and are arranged on the housing.

As shown in fig. 3, in this embodiment, the electroencephalogram signal preprocessing device 1-2 is a TGAM chip developed by NeuroSky, usa. The output end of the first brain electrode 1-11 is connected with an EEG pin of the TGAM chip, the output end of the second brain electrode 1-12 is connected with a REF pin of the TGAM chip, and the output end of the third brain electrode 1-13 is connected with an EEG _ GND pin of the TGAM chip. In actual use, the second brain electrode 1-12 is a reference electrode.

In the actual use process, the EEG end of the TGAM chip inputs the EEG signals sampled by the first EEG electrodes 1-11, and the EEG _ shifted end plays a role in shielding the interference of the time before the EEG signals sampled by the first EEG electrodes 1-11 are input into the TGAM chip; the REF end inputs the electroencephalogram signals sampled by the second electroencephalogram electrodes 1-2, and the ear electroencephalogram signals sampled by the second electroencephalogram electrodes 1-12 are used as reference potentials, so that spontaneous electroencephalograms can be effectively filtered; the REF _ shifted end is mainly used for shielding the interference of the time before the electroencephalogram signals sampled by the second electroencephalogram electrodes 1-12 are input into the TGAM chip; the brain wave ground wire is also connected to the ear of the human body, namely the brain wave signals sampled by the third brain wave electrodes 1-13, the main function is to shield the influence of electric waves below the head of the human body, for example, the heart wave is a stronger interference wave, and the connection of the brain wave ground wire can effectively filter the heart wave. That is, the third brain electrode 1-13 is an electrode for collecting brain wave ground signals.

In this embodiment, the first wireless communication module 3 and the second wireless communication module 2-2 are both bluetooth wireless communication modules.

And the Bluetooth wireless communication module is an HL-MD08R-C2A module.

In practice, the first wireless communication module 3 and the second wireless communication module 2-2 may also adopt other types of wireless communication modules.

In this embodiment, the first EEG electrode 1-11 is placed on the left forehead of the driver determined according to the 10-20 system electrode placement method, and the second EEG electrode 1-12 and the third EEG electrode 1-13 are both placed in the upper left temple of the driver determined according to the 10-20 system electrode placement method. Among them, the 10-20 system electrode placement method is the standard electrode placement method specified by the international electroencephalogram society.

Therefore, the electroencephalogram signal extraction device 1-1 mainly collects the prefrontal area, specifically, the left prefrontal (F)_P1) The potential at this electrode site. The second brain electrode 1-12 and the third brain electrode 1-13 are both placed on the electrode site in the left temporal middle (T3).

In this embodiment, the TGAM chip has a TGAM1 model, and the first wireless communication module 3 and the second wireless communication module 2-2 are both BlueTooth chips. When actually wired, the TXD pin of the TGAM chip is connected with the RX pin of the first wireless communication module 3. And the power supply end of the TGAM chip and the VCC pin of the TGAM chip are both connected with a +3.3V power supply end.

As shown in fig. 4, in this embodiment, the alarm prompting unit 2-5 is a speaker LS, one end of the speaker LS is connected to the 8 th pin of the Arduino controller, and the other end of the speaker LS is grounded.

In this embodiment, the GPRS wireless communication module is a GTM-900C wireless communication module.

When actually wiring, the RX pin of the Arduino controller is connected with the RX pin of the second wireless communication module 2-2, and the TX pin of the Arduino controller is connected with the RX pin of the GTM-900C wireless communication module.

Meanwhile, the electroencephalogram signal monitoring device 2 further comprises a parameter input unit 2-6 and a display 2-7, and the parameter input unit 2-6 and the display 2-7 are arranged on the shell.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and all simple modifications, changes and equivalent structural changes made to the above embodiment according to the technical spirit of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree is characterized by comprising the following steps:

step one, brain wave signal acquisition: the electroencephalogram signal acquisition device (1) is adopted to acquire and preprocess the electroencephalogram signal of a driver according to a preset sampling frequency, and the preprocessed electroencephalogram signal is synchronously transmitted to the electroencephalogram signal monitoring device (2);

the electroencephalogram signal acquisition device (1) and the electroencephalogram signal monitoring device (2) are communicated in a wireless communication mode; the electroencephalogram signal acquisition device (1) is a TGAM module, the TGAM module comprises an electroencephalogram signal extraction device (1-1) for extracting electroencephalogram signals of a driver and an electroencephalogram signal preprocessing device (1-2) for sampling and preprocessing the signals extracted by the electroencephalogram signal extraction device (1-1), the electroencephalogram signal preprocessing device (1-2) is connected with the electroencephalogram signal extraction device (1-1), the electroencephalogram signal extraction device (1-1) comprises a first electroencephalogram electrode (1-11) for sampling the electric potential of a frontal lobe area of the driver in real time and a second electroencephalogram electrode (1-12) and a third electroencephalogram electrode (1-13) for sampling the electric potential of the ear of the driver in real time, and the first electroencephalogram electrode (1-11), the second electroencephalogram electrode (1-12) and the third electroencephalogram electrode (1-13) are all connected with the electroencephalogram signal preprocessing device (1-2) connecting; the electroencephalogram signal monitoring device (2) comprises a main control chip (2-1), and a second wireless communication module (2-2) and an alarm prompting unit (2-5) which are respectively connected with the main control chip (2-1), wherein the alarm prompting unit (2-5) is controlled by the main control chip (2-1) and is connected with the main control chip (2-1); the electroencephalogram signal preprocessing device (1-2) is connected with the first wireless communication module (3), and the electroencephalogram signal preprocessing device (1-2) is communicated with the main control chip (2-1) through the first wireless communication module (3) and the second wireless communication module (2-2);

step two, brain wave signal analysis and processing: the master control chip (2-1) respectively analyzes and processes the brain wave signals collected and preprocessed by the brain wave signal acquisition device (1) within each second according to the sampling time sequence, and judges whether the driver is in a fatigue driving state at the moment according to the analysis and processing result; moreover, the analysis and processing methods of the brain wave signals collected and preprocessed by the brain wave signal acquisition device (1) in each second by the main control chip (2-1) are the same; when the brain wave signals collected and preprocessed by the brain wave signal acquisition device (1) within any one second are analyzed and processed, the process is as follows:

step 201, brain wave signal synchronous storage: synchronously storing the brain wave signals collected and preprocessed by the brain wave signal acquisition device (1) within one second;

Step 204, threshold comparison: calling a threshold comparison module to calculate the fatigue degree of the driver at the moment obtained in the step 203And F₀And (3) comparing difference values: when in useIf so, it means the fatigue moment to be determined, and the process proceeds to step 205; otherwise, returning to the step 201, and analyzing and processing the brain wave signals collected and preprocessed by the brain wave signal acquisition device (1) in the next second;

step 205, calculating the fatigue degree of the driver in the next second: analyzing and processing the brain wave signals collected and preprocessed by the brain electrical signal acquisition device (1) in the next second according to the method from the step 201 to the step 203, and calculating the fatigue degree of the driver in the next second after the fatigue time to be judged

Step 206, repeating the step 206 for K-1 times, and obtaining the fatigue degree of the driver within K seconds after the fatigue moment to be determinedWherein K is a positive integerAnd K is 8-15;

step 207, fatigue driving judgment: calling the threshold comparison module to compare the fatigue degree of the driver within K seconds after the fatigue moment to be determined obtained in the step 206Are respectively reacted with F₀And (3) comparing difference values: when the fatigue degree of the driver within K seconds after the fatigue moment to be determinedAre all greater than F₀When the driver is in a fatigue driving state, the main control chip (2-1) controls the alarm prompting unit (2-5) to give an alarm prompt; otherwise, the driver is in a normal driving state at the moment;

and 208, returning to the step 201, and analyzing and processing the brain wave signals collected and preprocessed by the brain wave signal acquisition device (1) in the next second.

2. The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree as claimed in claim 1, wherein: k in step 206 is 10.

3. The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree as claimed in claim 1 or 2, characterized in that: f in step 204₀＝1.4。

4. The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree as claimed in claim 1 or 2, characterized in that: in step 207, the fatigue degree of the driver is determined within K seconds after the fatigue timeAre all greater than F₀Before the main control chip (2-1) controls the alarm prompt unit (2-5) to carry out alarm prompt, the main control chip also controls the alarm prompt unit to carry out alarm prompt beforeA multi-threshold comparison and determination module is required to be invoked to analyze and process the received brain wave signals in step 201, and verify the fatigue driving state of the driver at that time according to the analysis and processing result, the process is as follows:

step B1, characteristic signal extraction: the main control chip (2-1) calls a feature extraction module to extract 7 feature signals from the brain wave signals processed at the moment;

step B2, feature quantity determination: the main control chip (2-1) takes the signal values of the 7 characteristic signals in the step B1 as the 7 characteristic quantities of the brain wave signals processed at the moment; the 7 characteristic signals are original brain waves, low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and wave signals respectively, and the 7 characteristic quantities are R, A respectively_L、A_H、B_L、B_HT and D;

when the electroencephalogram signal acquisition device (1) collects and preprocesses electroencephalogram signals of a driver in the first step, the sampling frequency of the original electroencephalogram is 512Hz, and the sampling frequencies of low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and waves are all 1 Hz; in the 7 feature signals, the number of the original brain wave signals is 512, and the number of low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and wave signals is one;

step B3, multi-threshold comparison: the main control chip (2-1) judges threshold values according to 7 groups of predetermined fatigue driving and calls a threshold value comparison module, respectively compares the threshold values of the 7 characteristic quantities determined in the step B2, and records the threshold value comparison results by adopting a counter;

the initial count value of the counter is 0;

When the 7 feature quantities determined in the step B2 are respectively compared with the threshold value, the main control chip (2-1) calls a threshold value comparison module to judge the threshold value and the feature quantity A of the feature quantity R and a group of original brain wave_LAnd a set of low alpha wave judgment threshold value and characteristic quantity A_HA set of high alpha wave judgment threshold values and characteristic quantity B_LAnd a set of low beta wave judgment threshold value and characteristic quantity B_HRespectively carrying out threshold comparison with a group of high beta wave judgment threshold values, a characteristic quantity T and a group of theta wave judgment threshold values, and a characteristic quantity D and a group of wave judgment threshold values;

when the characteristic quantity R is compared with a group of original brain wave judgment threshold values, the characteristic quantity R and the characteristic quantity R are compared firstly_STAnd (3) comparing difference values: when R < R_STThen, the main control chip (2-1) adds 5 to the count value of the timer; otherwise, the timing is carried outThe count value of the device is not changed; then, the characteristic quantities R and R are combined_WTAnd (3) comparing difference values: when R > R_WTThen, the main control chip (2-1) subtracts 5 from the count value of the timer; otherwise, the count value of the timer is unchanged;

for characteristic quantity B_HWhen the characteristic quantity B is compared with a group of high beta wave judgment threshold values in a threshold value way, the characteristic quantity B is firstly measured_HAnd B_HSTAnd (3) comparing difference values: when B is present_H＜B_HSTThen, adding 2 to the count value of the timer; otherwise, the count value of the timer is unchanged; after that time, the user can use the device,the characteristic quantity B_HAnd B_HWTAnd (3) comparing difference values: when B is present_H＞B_HWTThen, subtracting 2 from the count value of the timer; otherwise, the count value of the timer is unchanged;

step B4, fatigue driving judgment: and the main control chip (2-1) judges the fatigue driving state of the driver at the moment according to the counting value of the counter after the multi-threshold comparison in the step B3 is completed: when the count value of the counter is larger than N, the driver is in a fatigue driving state at the moment after verification, and the main control chip (2-1) controls the alarm prompting unit (2-5) to perform alarm prompting; otherwise, the driver is in a fatigue driving state at the moment after verification;

wherein N is a positive integer and N is 52-58.

5. The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree as claimed in claim 4, wherein: before the brain wave signal analysis processing in the step two, a main control chip (2-1) is adopted to determine 7 groups of fatigue driving judgment threshold values in the step B3;

when 7 groups of fatigue driving judgment threshold values in the step B3 are determined, firstly, acquiring brain wave signals of a driver within P seconds by using a brain wave signal acquisition device (1), and then determining 7 groups of fatigue driving judgment threshold values according to the acquired brain wave signals of the driver within P seconds; wherein P is a positive integer and P is 50-70;

step B32, threshold calculation: according to the formula R_ST＝r_S1R_M+r_S2R_SD(1)、R_WT＝r_W1R_M+r_W2R_SD(2)、A_LST＝a_LS1A_LM+a_LS2A_LSD(3)、A_LWT＝a_LW1A_LM+a_LW2A_LSD(4)、A_HST＝a_HS1A_HM+a_HS2A_HSD(5)、A_HWT＝a_HW1A_HM+a_HW2A_HSD(6)、B_LST＝b_LS1B_LM+b_LS2B_LSD(7)、B_LWT＝b_LW1B_LM+b_LW2B_LSD(8)、B_HST＝b_HS1B_HM+b_HS2B_HSD(9)、B_HWT＝b_HW1B_HM+b_HW2B_HSD(10)、T_ST＝t_S1T_M+t_S2T_SD(11)、T_WT＝t_W1T_M+t_W2T_SD(12)、D_ST＝d_S1D_M+d_S2D_SD(13) And D_WT＝d_W1D_M+d_W2D_SD(14) Are each to R_ST、R_WT、A_LST、A_LWT、A_HST、A_HWT、B_LST、B_LWT、B_HST、B_HWT、T_ST、T_WT、D_STAnd D_WTCalculating;

In the formula (6), a_HW1And a_HW2Is A_HWTTwo weights ofCoefficient, 0 < a_HW1≤1，-1≤a_HW2＜0；

6. The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree as claimed in claim 4, wherein: before the brain wave signal analysis processing in the step two, determining 7 sets of fatigue driving judgment threshold values in the step B3;

when 7 groups of fatigue driving judgment threshold values in the step B3 are determined, firstly, the electroencephalogram signal acquisition device (1) is adopted to respectively acquire electroencephalogram signals when the driver enters a sleep state from a non-sleep state and enters an awake state from a non-awake stateAnd pre-treating; wherein R is_ST、A_LST、A_HST、B_LST、B_HST、T_STAnd D_STRespectively the signal values of original brain waves, low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and wave signals in the brain wave signals output by the brain wave signal acquisition device (1) when the driver enters the sleep state from the non-sleep state, R_WT、A_LWT、A_HWT、B_LWT、B_HWT、T_WTAnd D_WTThe electroencephalogram signal acquisition device (1) outputs the signal values of original electroencephalogram waves, low alpha waves, high alpha waves, low beta waves, high beta waves, theta waves and wave signals in electroencephalogram signals when a driver enters an awake state from a non-awake state.

7. The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree as claimed in claim 1 or 2, characterized in that: the electroencephalogram signal monitoring device (2) in the first step further comprises a third wireless communication module (2-3) connected with the main control chip (2-1); the main control chip (2-1) is communicated with the upper computer (4) through a third wireless communication module (2-3);

and in the step B4, when the count value of the counter is larger than N, the main control chip (2-1) synchronously transmits the fatigue driving state of the driver to the upper computer (4) through the third wireless communication module (2-3).

8. The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree as claimed in claim 1 or 2, characterized in that: the electroencephalogram signal preprocessing device (1-2) is a TGAM chip developed by Neurosky corporation in the United states; the output end of the first brain electrode (1-11) is connected with an EEG pin of the TGAM chip, the output end of the second brain electrode (1-12) is connected with a REF pin of the TGAM chip, and the output end of the third brain electrode (1-13) is connected with an EEG _ GND pin of the TGAM chip.

9. The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree as claimed in claim 1 or 2, characterized in that: in the first step, the main control chip (2-1) is an Arduino controller; the first wireless communication module (3) and the second wireless communication module (2-2) are both Bluetooth wireless communication modules; the third wireless communication module (2-3) is a GPRS wireless communication module.

10. The fatigue driving electroencephalogram monitoring method based on meditation degree and concentration degree as claimed in claim 1 or 2, characterized in that: in the step one, the first brain electrode (1-11) is placed on the left forehead of the driver determined according to the 10-20 system electrode placement method, and the second brain electrode (1-12) and the third brain electrode (1-13) are both placed in the left temple of the driver determined according to the 10-20 system electrode placement method.