CN105615878B - A kind of fatigue driving eeg monitoring method - Google Patents
A kind of fatigue driving eeg monitoring method Download PDFInfo
- Publication number
- CN105615878B CN105615878B CN201610136802.4A CN201610136802A CN105615878B CN 105615878 B CN105615878 B CN 105615878B CN 201610136802 A CN201610136802 A CN 201610136802A CN 105615878 B CN105615878 B CN 105615878B
- Authority
- CN
- China
- Prior art keywords
- eeg
- time
- later
- eeg signals
- eeg signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
- A61B5/0006—ECG or EEG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/7405—Details of notification to user or communication with user or patient ; user input means using sound
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
- A61B2503/22—Motor vehicles operators, e.g. drivers, pilots, captains
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Psychology (AREA)
- Child & Adolescent Psychology (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Artificial Intelligence (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Social Psychology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of fatigue driving eeg monitoring methods, comprising steps of the connection of one, equipment and parameter initialization: EEG signals acquisition device being connect with EEG signals monitoring terminal, and is set to tired step parameter;Two, eeg signal acquires: being acquired and is pre-processed using eeg signal of the EEG signals acquisition device to driver, and eeg signal synchronous driving to EEG signals is monitored terminal;Three, eeg signal analysis is handled: EEG signals monitoring terminal calls eye electricity determination module to the acquisition of EEG signals acquisition device and pretreated eeg signal is analyzed and processed respectively, and process is as follows: number of winks judgment threshold is determining, fatigue driving judges that preceding eeg signal analysis processing and fatigue driving judge to start rear eeg signal analysis processing.The method of the present invention step is simple, design is reasonable and realizes that convenient, using effect is good, can carry out accurate measurements to the fatigue driving state of driver easy, quick, in real time.
Description
Technical field
The invention belongs to brain wave monitoring technical fields, more particularly, to a kind of fatigue driving eeg monitoring method.
Background technique
With the development of China's economic society, the growth that highway in China road construction is advanced by leaps and bounds, automobile and driver's
Quantity is also swift and violent therewith to be increased, and while offering convenience to daily life, the frequent generation of traffic accident is also brought to society
Great loss.Nowadays, the various technological means for reducing traffic accident and reduction casualties are all applied and are given birth to, when
Preceding at most adopted fatigue detecting means are that driver drives behavioural analysis, i.e., by recording and parsing driver turn direction
Disk, the behavioural characteristics such as touch on the brake, and differentiates whether driver is tired;But this mode is influenced pole by driver's driving habit
Greatly, ununified, scientific and effective decision theory is supported.Another kind of fatigue detection method is by image analysis means
Fatigue Assessment is carried out to driver face and eye feature, such method is analyzed by image variants system currently drives
Whether the person of sailing is tired, has certain real-time, but still without general applicability, because everyone biological characteristic is not
The same, the external manifestation of somebody's eyes can not represent the state of mind this moment, so there is also very big errors;Separately
Outside, the image variants system that such method uses at present mainly includes fatigue driving detecting system, hangers based on ARM
Piece formula fatigue alerting device, watch style fatigue driving detecting system, the touch fatigue driving detecting system of steering wheel etc., wherein being based on
The fatigue driving detecting system of ARM has a single function, and poor reliability the problem is that system constitutes excessively many and diverse;Hangers piece
The function of formula fatigue alerting device is very simple, bows and just alarms, however not necessarily just bows in view of dozing off, and drowsiness causes
Feature appearance of bowing ratio it is later, thus real-time is not so good;Watch style fatigue driving detecting system utilizes the bounce of pulse
Estimate whether people is tired, not the scientific basis of scientific theory support and authority, and not can solve problem sleeping suddenly;
The touch fatigue driving detecting system of steering wheel perceives whether driver holds using some sensors are installed on the steering wheel
Steering wheel, and whether driver holds steering wheel and is substantially not directly dependent upon with fatigue state, and makes after installing sensor
Steering wheel operation is inconvenient.
In addition, currently used fatigue driving detection means mostly all be drive before or drive after measure, be it is advanced or
Lag, and it is non real-time, furthermore it is also very difficult for disposing in the limited space of driver's cabin complicated detecting instrument;And
And driver is detached from driver's cabin or does not enter the state of mind of driver's cabin and is different.Therefore, it develops a set of vehicle-mounted, real-time
Study in Driver Fatigue State Surveillance System and corresponding fatigue driving monitoring method have become the mesh that domestic and international experts and scholars pursue jointly
Mark.
Summary of the invention
In view of the above-mentioned deficiencies in the prior art, the technical problem to be solved by the present invention is that providing a kind of fatigue driving
Eeg monitoring method, method and step is simple, design is reasonable and realizes that convenient, using effect is good, can be easy, quick, right in real time
The fatigue driving state of driver carries out accurate measurements, and practical value is high.
In order to solve the above technical problems, the technical solution adopted by the present invention is that: a kind of fatigue driving eeg monitoring method,
It is characterized in that: method includes the following steps:
Step 1: equipment connection and parameter initialization: EEG signals acquisition device is connect with EEG signals monitoring terminal,
And tired step parameter s_c is set by the main control chip that EEG signals monitor terminal;At this point, tired step parameter s_
The numerical value of c is 0;
The EEG signals acquisition device is Mindwave Mobile brain cubic earphone or TGAM module;The brain telecommunications
Number monitoring device includes main control chip and the clock circuit connecting respectively with main control chip and warning note unit;
Step 2: eeg signal acquires: using EEG signals acquisition device and according to preset sample frequency pair
The eeg signal of driver is acquired and pre-processes, and by pretreated eeg signal synchronous driving to EEG signals
Monitor terminal;
It include original eeg signal in the eeg signal, and the sample frequency of the original eeg signal is
512Hz;
Step 3: eeg signal analysis is handled: the main control chip of the EEG signals monitoring terminal calls eye electricity to determine
Module is acquired to EEG signals acquisition device and pretreated eeg signal is analyzed and processed, and process is as follows:
Step 3011, number of winks judgment threshold determine: according to sampling time sequencing to EEG signals acquisition device
It is acquired in the continuous P second and pretreated eeg signal is analyzed and processed respectively, and according to analysis and processing result to blink
Number judgment threshold n0It is determined;Wherein, P=2 × p, wherein p is positive integer and p >=20;
In this step, to acquisition in EEG signals acquisition device any second and pretreated eeg signal is analyzed
When processing, process is as follows:
The synchronous storage of step 30111, eeg signal: to being acquired in the EEG signals acquisition device received at this time one second
And pretreated eeg signal synchronizes storage, the eeg signal stored is currently pending eeg signal;
Step 30112, original eeg signal extract and eeg signal energy balane: from described in step 30111 when
Original eeg signal is extracted in preceding eeg signal to be processed, and the energy e of currently pending eeg signal is carried out
It calculates;
It include 512 original eeg signals, 512 original brains in the currently pending eeg signal
The signal value of i-th of original eeg signal is denoted as X in electric wave signali;
When calculating the energy e of currently pending eeg signal, according to formula It is counted
It calculates;In formula (7), N=512;
Step 30113, blink determine: according to the energy for the currently pending eeg signal being calculated in step 30112
E is measured, is judged whether driver in the second blinks, and obtain the blink decision content bk of this second: as e > E2When, bk=1;
Otherwise, bk=0;Wherein, E=280~320;
Step 30114, the synchronous storage of blink decision content: the blink decision content bk obtained in step 30113 is synchronized
The analysis treatment process of acquisition and pretreated eeg signal in this second of EEG signals acquisition device is completed in storage;
Step 30115, acquisition and pretreated eeg signal analysis is handled in next second: according to step 30111 to
Method described in step 30114, in EEG signals acquisition device lower second acquisition and pretreated eeg signal into
Row analysis processing, and obtain the blink decision content bk of this second;
Step 30116 repeats step 30115 P-2 times, until completing to acquire simultaneously in the EEG signals acquisition device continuous P second
The analysis treatment process of pretreated eeg signal, and obtain the blink decision content bk of each second;
Step 30117, blink decision content superposition: the blink of each second in the continuous P second obtained in step 30116 is determined
Value bk is overlapped, and obtains the sum of blink decision content bkZ;
Step 30118, number of winks judgment threshold determine: according to the sum of the blink decision content obtained in step 30117
Bkz, and according to formulaNumber of winks judgment threshold n is calculated0;
Wherein, n is positive integer and n >=4;
Also, n × Q=P, wherein Q is positive integer and Q=2~10;
Eeg signal analysis processing, process are as follows before step 3012, fatigue driving judge:
Acquisition and pretreated eeg signal analysis processing in next second after step 30121, judgment threshold determine: step
Number of winks judgment threshold n described in rapid 301180It is right according to method described in step 30111 to step 30114 after determination
It is acquired in EEG signals acquisition device lower second and pretreated eeg signal is analyzed and processed, and obtain blinking for this second
Eye decision content bk;
Step 30122 repeats step 30121 n-2 times, until completing number of winks judgment threshold described in step 30118
n0The analysis treatment process of acquisition and pretreated eeg signal in continuous n-1 seconds of EEG signals acquisition device after determination,
And obtain the blink decision content bk of each second;
Step 3013, fatigue driving judgement start rear eeg signal analysis processing: fatigue driving is completed in step 3012
Before judging after eeg signal analysis processing, the eye electricity determination module obtains EEG signals according to sampling time sequencing
Device interior acquisition per second and pretreated eeg signal is analyzed and processed respectively, and according to analysis and processing result at this time
Whether driver, which is in fatigue driving state, judges;
In this step, the eye electricity determination module is to acquisition and pretreated brain in EEG signals acquisition device any second
When electric wave signal is analyzed and processed, process is as follows:
Step 30131, eeg signal analysis processing: right according to method described in step 30111 to step 30114
EEG signals acquisition device acquires at this time and pretreated eeg signal is analyzed and processed, and show that blink at this time is sentenced
Definite value bk;
Step 30132, blink decision content superposition: by the blink decision content bk obtained in step 30131 and it is Q-1 second first in respectively
The blink decision content bk of second is overlapped, and the sum of the blink decision content of acquisition at this time bkz;
The sum of blink decision content bkz is the blink decision content bk of each second in EEG signals acquisition device is Q seconds continuous
Summation;
Step 30133, fatigue driving judgement: it according to the sum of the blink decision content obtained in step 30133 bkz, and combines
Identified number of winks judgment threshold n in step 301180, sentence to whether driver at this time is in fatigue driving state
It is disconnected: as bkz > n0When, illustrate that driver is in fatigue driving state at this time, the main control chip control warning note unit into
Row warning note;Otherwise, illustrate that driver is in normal driving state at this time;
Step 30134, return step 30131, to acquisition and pretreated brain in EEG signals acquisition device lower second
Electric wave signal is analyzed and processed.
A kind of above-mentioned fatigue driving eeg monitoring method, it is characterized in that: carrying out eeg signal analysis processing in step 3
In the process, the main control chip of the EEG signals monitoring terminal also needs to call navigation module is synchronous to obtain the driven vehicle of driver
Vehicle essential information, the vehicle essential information includes vehicle geographical location and speed.
A kind of above-mentioned fatigue driving eeg monitoring method, it is characterized in that: EEG signals acquisition device described in step 1 with
It is communicated between EEG signals monitoring device with communication;
The TGAM module includes the EEG signals extraction element extracted to the eeg signal of driver and to brain
The extracted signal of electric signal extraction element carries out sampling and pretreated EEG signals pretreatment unit, the EEG signals are located in advance
Reason device connects with EEG signals extraction element, and the EEG signals extraction element includes carrying out to the current potential in driver's frontal lobe area
First electrode for encephalograms of real-time sampling and the second electrode for encephalograms and third that real-time sampling is carried out to ear's current potential of driver
Electrode for encephalograms, first electrode for encephalograms, the second electrode for encephalograms and third electrode for encephalograms with EEG signals pretreatment unit phase
It connects;
The EEG signals monitoring device further includes the second wireless communication module to connect respectively with main control chip and fatigue
Step parameter zero setting unit;
The EEG signals acquisition device connects with the first wireless communication module, and the EEG signals acquisition device passes through the
One wireless communication module and the second wireless communication module are communicated with main control chip.
A kind of above-mentioned fatigue driving eeg monitoring method, it is characterized in that: EEG signals monitoring terminal is smart phone.
A kind of above-mentioned fatigue driving eeg monitoring method, it is characterized in that: by EEG signals acquisition device and brain in step 1
When electric signal monitors terminal connection, the main control chip of EEG signals monitoring terminal and host computer need to also be connected with communication
It connects;
When main control chip described in step 3025 controls warning note unit progress warning note, the main control chip is synchronous
The fatigue driving warning message of the driver is sent to host computer.
A kind of above-mentioned fatigue driving eeg monitoring method, it is characterized in that: the monitoring of EEG signals described in step 1 terminal is also
Including the parameter input unit being connect with main control chip;
After being connect the main control chip of EEG signals monitoring terminal with host computer with communication in step 1, also need
Driver's essential information is inputted by parameter input unit, the main control chip deposits the driver's essential information inputted
It stores up and by driver's essential information synchronous driving to host computer;
Driver's essential information includes the name and contact method of driver.
A kind of above-mentioned fatigue driving eeg monitoring method, it is characterized in that: as bkz > n in step 301330When, the eye electricity
The fatigue driving judging result of determination module is that driver is in fatigue driving state at this time, and main control chip controls warning note
Before unit carries out warning note, the main control chip also needs to call brain electricity determination module to the fatigue of the eye electricity determination module
It drives judging result to be verified, and according to the verification result of the brain electricity determination module, whether tired is in driver at this time
Labor driving condition is determined: when the verification result of the brain electricity determination module is that driver is in fatigue driving state at this time
When, determine that driver is in fatigue driving state at this time, the warning note unit of main control chip control later carries out warning note;It is no
Then, determine that driver is in normal driving state at this time;
The main control chip calls the brain electricity determination module to the fatigue driving judging result of the eye electricity determination module
When being verified, process is as follows:
Step 302-1, the numerical value of tired step parameter s_c tired step parameter zero setting: is set as 0;
Step 302-2, eeg signal analysis is handled: the brain electricity determination module is right according to sampling time sequencing
It is acquired in continuous F second of EEG signals acquisition device after tired step parameter zero setting in step 302-1 and pretreated brain wave
Signal is analyzed and processed respectively;Wherein, F is positive integer and F=5~15;The brain electricity determination module obtains EEG signals
The analysis and processing method of device interior acquisition per second and pretreated eeg signal is all the same;The brain electricity determination module is to brain
Acquisition and when pretreated eeg signal is analyzed and processed in electric signal acquisition device any second, process is as follows:
The synchronous storage of step 3021, eeg signal: to being acquired in the EEG signals acquisition device received at this time one second
And pretreated eeg signal synchronizes storage;
Step 3022, meditation degree and focus are extracted: extracted from handled eeg signal at this time meditation degree M with it is special
Note degree A;
Step 3023, meditation degree correction value and time correcting parameter determine: the current time T provided according to clock circuit,
To at this time meditation degree correction value Δ M and time correcting parameter Δ T be determined respectively;
Wherein, when being determined to meditation degree correction value Δ M, when current time T is later than at 6 points and is not later than at 12, Δ M
=30~15;When current time T is later than at 12 points and is not later than at 15, Δ M=15~0;When current time T is later than 15 points and not
When being later than at 19, Δ M=0~15;It is later than 19 points and not late when current time T is later than at 0 point and is not later than 6 points or current time T
When 0, Δ M=0;
When being determined to time correcting parameter Δ T, when current time T is later than at 6 points and is not later than at 12, Δ T=2~
1.5;When current time T is later than at 12 points and is not later than at 15, Δ T=1.5~1.0;When current time T is later than 15 points and not late
When 19, Δ T=1.0~1.5;It is later than 19 points and not late when current time T is later than at 0 point and is not later than 6 points or current time T
When 0, Δ T=1.0;
Step 3024, tired step parameter increase and decrease processing: according to the meditation degree M and focus A extracted in step 3022,
And identified meditation degree correction value Δ M and time correcting parameter Δ T in step 3023 is combined, to tired step parameter s_ at this time
The numerical value of c is increased and decreased processing, and obtains increase and decrease treated tired step parameter s_c: whenWhen, it will be tired
The numerical value of labor step parameter s_c adds 1;Otherwise, the numerical value of tired step parameter s_c is judged: as tired step parameter s_c
Numerical value be 0 when, the numerical value of tired step parameter s_c remains unchanged;It, will be tired when the numerical value of tired step parameter s_c >=1
The numerical value of step parameter s_c subtracts 1;
Step 3025, fatigue driving judgement: according to the number of treated the tired step parameter s_c of increase and decrease in step 3024
Value, judges whether driver at this time is in fatigue driving state: when increase and decrease treated tired step in step 3024
When the numerical value > N of parameter s_c, judge that driver is in fatigue driving state at this time;Otherwise, judge that driver is at this time
Normal driving state;
Wherein, N is preset fatigue driving judgment threshold, and N is positive integer and N=2~8;
Step 3026, verification result obtain: according to the fatigue driving judging result obtained in step 3025, obtaining the brain
The verification result of electric determination module: when judging that driver is in fatigue driving state at this time in step 3025, the brain electricity
The verification result of determination module is that driver is in fatigue driving state at this time, and the fatigue of the eye electricity determination module is driven in completion
Sail the verification process of judging result;Otherwise, it also needs to judge whether to complete to acquire in continuous F seconds of EEG signals acquisition device and locate in advance
Whole analysis treatment processes of eeg signal after reason;
Also, acquisition and pretreated brain wave in continuous F seconds of EEG signals acquisition device is completed when judgement obtains
When whole analysis treatment processes of signal, the verification result of the brain electricity determination module is that driver is in normal driving shape at this time
State;Otherwise, 3026 are entered step;
Step 3026, return step 3021, to acquisition in EEG signals acquisition device lower second and pretreated brain electricity
Wave signal is analyzed and processed.
A kind of above-mentioned fatigue driving eeg monitoring method, it is characterized in that: p=30 described in step 3011;Step 30118
Described in n=30, Q=2;
N=3 described in step 3025.
A kind of above-mentioned fatigue driving eeg monitoring method, it is characterized in that: using time interval method to meditation in step 3023
When degree correction value Δ M is determined, when current time T is later than at 6 points and is not later than at 15, the time is more late, meditation degree correction value
Δ M is smaller;When current time T is later than at 15 points and is not later than at 19, the time is more late, and meditation degree correction value Δ M is bigger;
When being determined using time interval method to time correcting parameter Δ T in step 3023, when current time T is later than 6
When putting and being not later than at 15, the time is more late, and the time, correcting parameter Δ T was smaller;When current time T is later than at 15 points and is not later than at 19 points
When, the time is more late, and the time, correcting parameter Δ T was bigger.
A kind of above-mentioned fatigue driving eeg monitoring method, it is characterized in that: being carried out in step 3023 to meditation degree correction value Δ M
When determining, process is as follows:
Step A1, current time integral point value determines: being determined to the integral point value of current time T;The clock circuit mentions
The current time T of confession is to make for 24 hours, and the integral point value of current time T is denoted as nt, wherein nt be in current time T " when " number
Value;
Wherein, nt is integer and nt=0~23;
Step A2, meditation degree correction value Δ M is determined: according to nt identified in step A1, and current time T is combined, it is right
Meditation degree correction value Δ M at this time is determined: when current time T is later than at 6 points and is not later than at 12, according to formulaMeditation degree correction value Δ M is calculated;When current time T is later than 12 points and not late
When 15, according to formulaMeditation degree correction value Δ M is calculated;When current
When quarter T is later than at 15 points and is not later than at 19, according to formulaTo meditation degree correction value Δ M into
Row calculates;
In formula (1) and (2), bt1=12;In formula (3), bt2=15;
When being determined in step 3023 to time correcting parameter Δ T, process is as follows:
Step B1, current time integral point value determines: being determined to the integral point value of current time T;The clock circuit mentions
The current time T of confession is to make for 24 hours, and the integral point value of current time T is denoted as nt, wherein nt be in current time T " when " number
Value;
Wherein, nt is integer and nt=0~23;
Step B2, time correcting parameter Δ T is determined: according to nt identified in step B1, and current time T is combined, it is right
Time correcting parameter Δ T at this time is determined: when current time T is later than at 6 points and is not later than at 12, according to formulaTime correcting parameter Δ T is calculated;When current time T is later than 12 points and not
When being later than at 15, according to formulaTime correcting parameter Δ T is calculated;When current
When moment T is later than at 15 points and is not later than at 19, according to formulaTo time correcting parameter
Δ T is calculated;
In formula (1) and (2), bt1=12;In formula (3), bt2=15.
Compared with the prior art, the present invention has the following advantages:
1, method and step is simple, design is reasonable and it is convenient to realize, input cost is lower.
2, fatigue driving eeg monitoring speed is fast, and energy Synchronization Analysis processing obtains the brain electricity condition of driver.
3, used hardware configuration is simple, only includes that EEG signals acquisition device can be real with EEG signals monitoring terminal
Existing, wherein EEG signals monitoring terminal can be used smart phone, and structure is simple, small in size and can carry, and uses behaviour
Make simplicity, can effectively simplify the operating process of driver.Eeg signal reception and analysis processing can be completed, obtain by only needing mobile phone just
Location information is taken the functions such as to communicate with speed, with host computer.Used EEG signals acquisition device and EEG signals monitoring fill
The circuit set is simple, design rationally, easy-to-connect and easy to use, input cost is lower, and actual installation laying side
Just.
4, only one need to be developed on smart phone is able to achieve answering for presently disclosed fatigue driving eeg monitoring method
It is just able to achieve the analysis processing of eeg signal with software, while can will be communicated with host computer.
5, it is matched with navigation module, is based on electronic map, the current speed of driver and geographical location can be obtained in real time,
And the current speed and geographical location and fatigue driving eeg monitoring result synchronous driving of driver acquired in energy is to upper
Machine (i.e. server) carries out long-range, intelligence by location information and physical fatigue situation of the upper function to driver in this way and supervises
Control.
6, safe and reliable, fatigue driving contingency occurrence probability can be effectively reduced, is in fatigue driving when detecting driver
When state, EEG signals monitoring terminal can be alarmed in time to remind driver;On the other hand, EEG signals monitor terminal meeting
By fatigue driving warning message synchronous driving to host computer, display is synchronized (including in fatigue driving shape by host computer
Name and contact method of the driver of state etc.), host computer is according to the contact method of driver, to driving in a manner of call
Member is alerted.
7, eye electricity determination module is judged based on energy value, which is the number that EEG signals acquisition device directly exports
Value realizes that easy and data processing amount is small, monitoring velocity is fast, and to acquire in Q second and pretreated eeg signal is
One judges object, can effectively improve the accuracy of monitoring result.
8, eye electricity determination module is capable of calling using the main control chip of EEG signals monitoring terminal and brain electricity determination module carries out
Eye electricity is determined to determine to combine with brain electricity by processing, is overcome that accuracy existing for single judgment mode is lower, speed is slower etc. and is asked
Topic all has greatly improved in monitoring accuracy and monitoring velocity.Wherein, based on eye electricity determination module, and sentenced with brain electricity
Supplemented by cover half block, rate of false alarm can be effectively reduced.
9, brain electricity determination module synchronizes eeg signal using step fatigue determination method and is analyzed and processed, and right
The fatigue driving state of driver carries out real-time judge.Also, when being actually monitored, according to real-time acquisition and pretreated brain
Electric wave signal, and the meditation degree correction value of different time and time correcting parameter in one day corresponding is combined to be judged, it drives tired
Labor status monitoring result is very accurate, thus verification result is reliable.It is not to immediately arrive at judgement when practical driving fatigue judges
As a result, but judged using " benching tunnelling method ", by increase and decrease treated tired step parameter judgement, when tired step is joined
When number reaches preset fatigue driving judgment threshold, it just will do it warning note, generally use audio alert mode, such as control
Warning note unit processed issues the audio alert information of " please noting that safety ".
10, the decision-making foundation using eeg signal as physiological fatigue, with traditional behavioural characteristic analysis, image procossing
Technology etc. has very big inherent advantage, there is the theories integration of E.E.G prestige of science.
11, using effect is good and practical value is high, and economic benefit and social benefit are significant, can the easy fatigue to driver
Driving condition carries out real-time monitoring, and can control warning note unit according to monitoring result and carry out warning note, makes driver real
When be in clear state, the generation to cut down traffic accidents, thus there is real-time, monitoring effect is good.Also, the present invention is accurate using energy
The eeg signal analysis and processing method of fatigue driving is characterized, has been determined that objective fatigue driving detects foundation for driver, has been
It further researchs and develops vehicle-mounted, real-time drowsy driving warning system to lay a good foundation, is also traffic management department's science, reasonable
Fatigue driving is intervened on ground, reduces artificial traffic accident to greatest extent and provides reliable basis.Meanwhile the present invention is full-featured, tool
There is road guide, audio alert, speed prompt, position indicating, host computer the functions such as remotely to monitor, and it is easy to operate, be easy to
Universal, low in cost, realization simplicity.
In conclusion the method for the present invention step is simple, design is reasonable and realizes that convenient, using effect is good, it can be easy, quick
Accurate measurements are carried out to the fatigue driving state of driver.
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Detailed description of the invention
Fig. 1 is method flow block diagram of the invention.
Fig. 1-1 is the verification process flow diagram of brain electricity determination module of the present invention.
Fig. 2 is the schematic block circuit diagram of EEG signals acquisition device and EEG signals monitoring device of the present invention.
Fig. 3 is the circuit diagram of EEG signals acquisition device and the first wireless communication module of the present invention.Appended drawing reference is said
It is bright:
1-EEG signals acquisition device;1-1-EEG signals extraction element;
The first electrode for encephalograms of 1-11-;The second electrode for encephalograms of 1-12-;1-13-third electrode for encephalograms;
1-2-EEG signals pretreatment unit;2-EEG signals monitoring devices;
2-1-main control chip;2-2-warning note unit;
The second wireless communication module of 2-3-;2-4-parameter input unit;
2-5-fatigue step parameter zero setting unit;2-6-clock circuit;
3-the first wireless communication module;4-host computers.
Specific embodiment
A kind of fatigue driving eeg monitoring method as shown in Figure 1, comprising the following steps:
Step 1: equipment connection and parameter initialization: EEG signals acquisition device 1 and EEG signals monitoring terminal 2 are connected
It connects, and tired step parameter s_c is set by the main control chip 2-1 that EEG signals monitor terminal 2;At this point, tired platform
The numerical value of rank parameter s_c is 0;
The EEG signals acquisition device 1 is Mindwave Mobile brain cubic earphone or TGAM module;The brain telecommunications
Number monitoring device 2 includes main control chip 2-1 and the clock circuit 2-6 and warning note list that connect respectively with main control chip 2-1
First 2-2.
In actual use, the EEG signals monitoring device 2 is located in the driven vehicle of driver.
Step 2: eeg signal acquires: using EEG signals acquisition device 1 and according to preset sample frequency pair
The eeg signal of driver is acquired and pre-processes, and by pretreated eeg signal synchronous driving to EEG signals
Monitor terminal 2;
It include original eeg signal in the eeg signal, and the sample frequency of the original eeg signal is
512Hz。
Step 3: eeg signal analysis is handled: the main control chip 2-1 of the EEG signals monitoring terminal 2 calls eye electricity
Determination module is acquired to EEG signals acquisition device 1 and pretreated eeg signal is analyzed and processed, and process is as follows:
Step 3011, number of winks judgment threshold determine: according to sampling time sequencing to EEG signals acquisition device 1
It is acquired in the continuous P second and pretreated eeg signal is analyzed and processed respectively, and according to analysis and processing result to blink
Number judgment threshold n0It is determined;Wherein, P=2 × p, wherein p is positive integer and p >=20;
In this step, to acquisition in any second of EEG signals acquisition device 1 and pretreated eeg signal divides
When analysis processing, process is as follows:
The synchronous storage of step 30111, eeg signal: to being adopted in the EEG signals acquisition device received at this time 1 one seconds
Collect and pretreated eeg signal synchronizes storage, the eeg signal stored is currently pending brain wave letter
Number;
Step 30112, original eeg signal extract and eeg signal energy balane: from described in step 30111 when
Original eeg signal is extracted in preceding eeg signal to be processed, and the energy e of currently pending eeg signal is carried out
It calculates;
It include 512 original eeg signals, 512 original brains in the currently pending eeg signal
The signal value of i-th of original eeg signal is denoted as X in electric wave signali;
When calculating the energy e of currently pending eeg signal, according to formula It is counted
It calculates;In formula (7), N=512;
Step 30113, blink determine: according to the energy for the currently pending eeg signal being calculated in step 30112
E is measured, is judged whether driver in the second blinks, and obtain the blink decision content bk of this second: as e > E2When, bk=1;
Otherwise, bk=0;Wherein, E=280~320;
Step 30114, the synchronous storage of blink decision content: the blink decision content bk obtained in step 30113 is synchronized
The analysis treatment process of acquisition and pretreated eeg signal in 1 this second of EEG signals acquisition device is completed in storage;
Step 30115, acquisition and pretreated eeg signal analysis is handled in next second: according to step 30111 to
Method described in step 30114, in EEG signals acquisition device 1 lower second acquisition and pretreated eeg signal into
Row analysis processing, and obtain the blink decision content bk of this second;
Step 30116 repeats step 30115 P-2 times, until completing to acquire simultaneously in the 1 continuous P second of EEG signals acquisition device
The analysis treatment process of pretreated eeg signal, and obtain the blink decision content bk of each second;
Step 30117, blink decision content superposition: the blink of each second in the continuous P second obtained in step 30116 is determined
Value bk is overlapped, and obtains the sum of blink decision content bkZ;
Step 30118, number of winks judgment threshold determine: according to the sum of the blink decision content obtained in step 30117
Bkz, and according to formulaNumber of winks judgment threshold n is calculated0;
Wherein, n is positive integer and n >=4;
Also, n × Q=P, wherein Q is positive integer and Q=2~10;
Eeg signal analysis processing, process are as follows before step 3012, fatigue driving judge:
Acquisition and pretreated eeg signal analysis processing in next second after step 30121, judgment threshold determine: step
Number of winks judgment threshold n described in rapid 301180It is right according to method described in step 30111 to step 30114 after determination
It is acquired in EEG signals acquisition device 1 lower second and pretreated eeg signal is analyzed and processed, and obtain this second
Blink decision content bk;
Step 30122 repeats step 30121 n-2 times, until completing number of winks judgment threshold described in step 30118
n0The analysis treatment process of acquisition and pretreated eeg signal in EEG signals acquisition device 1 continuous n-1 seconds after determination,
And obtain the blink decision content bk of each second;
Step 3013, fatigue driving judgement start rear eeg signal analysis processing: fatigue driving is completed in step 3012
Before judging after eeg signal analysis processing, the eye electricity determination module obtains EEG signals according to sampling time sequencing
The interior acquisition per second of device 1 and pretreated eeg signal is analyzed and processed respectively, and according to analysis and processing result to this
When driver whether be in fatigue driving state and judge;
In this step, the eye electricity determination module in any second of EEG signals acquisition device 1 acquisition and it is pretreated
When eeg signal is analyzed and processed, process is as follows:
Step 30131, eeg signal analysis processing: right according to method described in step 30111 to step 30114
EEG signals acquisition device 1 acquires at this time and pretreated eeg signal is analyzed and processed, and obtains blink at this time
Decision content bk;
Step 30132, blink decision content superposition: by the blink decision content bk obtained in step 30131 and it is Q-1 second first in respectively
The blink decision content bk of second is overlapped, and the sum of the blink decision content of acquisition at this time bkz;
The sum of blink decision content bkz is the blink decision content bk of each second in EEG signals acquisition device 1 continuous Q seconds
Summation;
Step 30133, fatigue driving judgement: it according to the sum of the blink decision content obtained in step 30133 bkz, and combines
Identified number of winks judgment threshold n in step 301180, sentence to whether driver at this time is in fatigue driving state
It is disconnected: as bkz > n0When, illustrate that driver is in fatigue driving state at this time, the main control chip 2-1 controls warning note unit
2-2 carries out warning note;Otherwise, illustrate that driver is in normal driving state at this time;
Step 30134, return step 30131, to acquisition and pretreated brain in EEG signals acquisition device 1 lower second
Electric wave signal is analyzed and processed.
In the present embodiment, with wireless between EEG signals acquisition device described in step 11 and EEG signals monitoring device 2
Communication mode is communicated.
The TGAM module includes the EEG signals extraction element 1-1 extracted to the eeg signal of driver and right
The extracted signal of EEG signals extraction element 1-1 carries out sampling and pretreated EEG signals pretreatment unit 1-2, the brain electricity
Signal conditioner 1-2 connects with EEG signals extraction element 1-1, and the EEG signals extraction element 1-1 includes to driving
The current potential in personnel leaf area carries out the first electrode for encephalograms 1-11 of real-time sampling and is adopted in real time to ear's current potential of driver
The the second electrode for encephalograms 1-12 and third electrode for encephalograms 1-13, the first electrode for encephalograms 1-11, the second electrode for encephalograms 1-12 of sample
Connect with EEG signals pretreatment unit 1-2 with third electrode for encephalograms 1-13.
Meanwhile the EEG signals monitoring device 2 further includes the second radio communication mold to connect respectively with main control chip 2-1
Block 2-3 and tired step parameter zero setting unit 2-5.In the present embodiment, the fatigue step parameter zero setting unit 2-5 is and master control
The keys or buttons of chip connection.
In actual use, the EEG signals acquisition device 1 connects with the first wireless communication module 3, the EEG signals
Acquisition device 1 is communicated by the first wireless communication module 3 and the second wireless communication module 2-3 with main control chip 2-1.
The Mindwave Mobile brain cubic earphone or TGAM (ThinkGear AM) module are U.S. NeuroSky
(mind reads science and technology) company is that general marketplace applies designed acquiring brain waves and prefinished products.Wherein TGAM module is the U.S.
NeuroSky (mind reads science and technology) company is that general marketplace applies designed brain-wave sensor module ASIC, also referred to as TGAM brain electricity mould
Block (abbreviation TGAM module).
The Mindwave Mobile brain cubic earphone or TGAM module can handle and export frequency of brain wave spectrum, brain
The eSense parameter of electric signal quality, original brain wave and three Neurosky: focus and is blinked at meditation degree (also referred to as allowance)
Eye detecting.In actual use, the Mindwave Mobile brain cubic earphone and TGAM module transfer mistake can be obtained by serial ports
The data come, the Mindwave Mobile brain cubic earphone and TGAM module send initial data respectively with the frequency of 512Hz
It wraps (i.e. original brain wave), and is sent with the frequency of 1Hz through eSenseTMData packet after algorithm process.Due to described
The interface of Mindwave Mobile brain cubic earphone and TGAM module and human body only needs a simple stem grafting contact, can be very
Readily apply in toy, video-game and health equipment, and since energy consumption is small, is suitable for use in battery powered portable
Consumer products using upper.
In actual use, the Mindwave Mobile brain cubic earphone and the acquisition of TGAM module and pretreated brain
It include original eeg signal in electric wave signal.Also, (i.e. Mindwave Mobile brain is vertical for the EEG signals acquisition device 1
Square earphone or TGAM module) eeg signal of output is frequency-region signal after Fast Fourier Transform (FFT) (i.e. FFT transform).
In the time domain, the original eeg signal is the signal that current potential changes over time, and wherein the unit of current potential is μ V (i.e. microvolt),
The unit of time is s.In actual use, the time domain letter of original eeg signal can also be exported with EEG signals acquisition device 1
Number, then Fast Fourier Transform (FFT) is carried out using the control chip of peripheral hardware.
After Fast Fourier Transform (FFT), time-domain signal is transformed to frequency-region signal.For frequency-region signal, independent variable is
Frequency, horizontal axis are frequencies, and the longitudinal axis is the amplitude of the frequency signal, the frequency content of expression signal.
After Fast Fourier Transform (FFT), the spectrogram usually said is obtained.Spectrogram describes the frequency structure and frequency of signal
The relationship of rate and the frequency signal amplitude.
Herein, the original eeg signal is frequency-region signal, and the signal value of the original eeg signal is signal
Amplitude, i.e., the ordinate value being calculated through Fast Fourier Transform (FFT).The original eeg signal is that EEG signals obtain dress
1 signal directly exported is set, direct use is only needed, thus is realized very easy.
1 internal analysis of EEG signals acquisition device exports eeg signal automatically, and handles output Neurosky and obtain
The eSense focus and allowance exponent data for obtaining patent, are finally exported by UART interface.This module samples rate is 512Hz,
Frequency range 3Hz-100Hz exports the E.E.G original waveform data (i.e. original brain wave data) of 512Hz, the independence of 8 groups of 1Hz
Brain wave data and eSense exponent data.Thus, it is acquired in one second and includes 512 institutes in pretreated eeg signal
State original eeg signal, corresponding 512 initial data parcels.
The format of each initial data parcel is 04 80 02 xxHigh xxLow xxCheckSum of AA AA, preceding
The AA AA 04 80 02 in face be it is constant, rear three bytes change always, and xxHigh and xxLow form initial data
rawdata.Thus, it only include a useful data inside an initial data parcel, i.e. rawdata, an initial data is small
Packet is exactly an original eeg signal data.Above-mentioned data format, referring to U.S. NeuroSky (mind reads science and technology), company is related
Eeg signal data format explanation, this is existing common knowledge.
In actual use, 0XAA 0XAA 0X20 beginning is found in the character string that EEG signals acquisition device 1 exports
Character string, that the 3rd character of the character string represents is poorsingle, and what the 31st character represented is meditation degree, the 33rd
What character represented is concentration degree (also referred to as focus).
In actual use, the EEG signals monitoring device 2 is laid in the vehicle that driver is driven.The alarm mentions
Show that unit 2-2 is voice alerting unit.
As shown in figure 3, the EEG signals pretreatment unit 1-2 is the research and development of U.S. NeuroSky company in the present embodiment
TGAM chip.The EEG pin of the output termination TGAM chip of the first electrode for encephalograms 1-11, the second electrode for encephalograms 1-12's
The REF pin of output termination TGAM chip, the EEG_GND pin of the output termination TGAM chip of third electrode for encephalograms 1-13.It is real
Border is in use, the second electrode for encephalograms 1-12 is reference electrode.
In actual use, the end EEG of the TGAM chip inputs the brain telecommunications that the first electrode for encephalograms 1-11 is sampled
Number, the effect at the end EEG_shiled be shielding before the sampled EEG signals of the first electrode for encephalograms 1-11 input TGAM chip this
The interference of section time;The end REF inputs the EEG signals that the second electrode for encephalograms 1-2 is sampled, and the second electrode for encephalograms 1-12 is adopted
Ear's EEG signals of sample can effectively filter out self start type brain wave as reference potential;The end REF_shiled mainly shields the
The interference of this period before the sampled EEG signals input TGAM chip of two electrode for encephalograms 1-12;E.E.G ground wire is also connected to people
The EEG signals that the ear of body, i.e. third electrode for encephalograms 1-13 are sampled, main effect is to shield human body head or less
The influence of electric wave, for example electrocardio wave is exactly a kind of stronger interference wave, and the connection of E.E.G ground wire can effectively filter out electrocardio wave.?
That is third electrode for encephalograms 1-13 is the electrode for acquiring brain wave ground signalling.
In the present embodiment, first wireless communication module 3 and the second wireless communication module 2-3 are Bluetooth wireless communication
Module.Also, the Bluetooth wireless communication module is HL-MD08R-C2A module.In actual use, first wireless communication
Module 3 and the second wireless communication module 2-3 can also use other types of wireless communication module.
In the present embodiment, the first electrode for encephalograms 1-11 is placed on according to 10-and what 20 system electrode placement methods determined drives
On the left antinion for the person of sailing, the second electrode for encephalograms 1-12 and third electrode for encephalograms 1-13 are both placed according to 10-20 systems electricity
On in the left temporo for the driver that pole placement methods determine.Wherein, 10-20 system electrode placement methods, i.e., international electroencephalography can provide
Normal electrode placement methods.Thus, what EEG signals extraction element 1-1 was mainly acquired is prefrontal area, specifically left antinion (FP1)
Current potential in this electrode site.The second electrode for encephalograms 1-12 and third electrode for encephalograms 1-13 are both placed in left temporo (T3)
In this electrode site.
In the present embodiment, the model TGAM1 of the TGAM chip, first wireless communication module 3 and second is wireless
Communication module 2-3 is BlueTooth chip.When physical cabling, the TXD pin and the first radio communication mold of the TGAM chip
The RX pin of block 3 connects.The power end of the TGAM chip and the VCC pin of TGAM chip connect+3.3V power end.
In the present embodiment, the EEG signals monitoring terminal 2 further includes the display unit connecting with main control chip 2-1.It is real
In the use process of border, display is synchronized to information such as the meditation degree M and focus A of driver by the display unit, side
Just user dynamically surveys the electrical activity of brain state of oneself.
In the present embodiment, as bkz > n in step 301330When, the fatigue driving judging result of the eye electricity determination module
Be in fatigue driving state for driver at this time, and main control chip 2-1 control warning note unit 2-2 carry out warning note it
Before, the main control chip 2-1 also need to call brain electricity determination module to the fatigue driving judging result of the eye electricity determination module into
Row verifying, and according to the verification result of the brain electricity determination module, it is carried out to whether driver at this time is in fatigue driving state
Determine: when the verification result of the brain electricity determination module is that driver is in fatigue driving state at this time, determination drives at this time
Member is in fatigue driving state, and main control chip 2-1 controls warning note unit 2-2 and carries out warning note later;Otherwise, it determines this
When driver be in normal driving state;
As Figure 1-1, the main control chip 2-1 calls the brain electricity determination module to the tired of the eye electricity determination module
When please sailing judging result and being verified, process is as follows:
Step 302-1, the numerical value of tired step parameter s_c tired step parameter zero setting: is set as 0;
Step 302-2, eeg signal analysis is handled: the brain electricity determination module is right according to sampling time sequencing
It is acquired in EEG signals acquisition device 1 continuous F second after tired step parameter zero setting in step 302-1 and pretreated brain wave
Signal is analyzed and processed respectively;Wherein, F is positive integer and F=5~15;The brain electricity determination module obtains EEG signals
The analysis and processing method of the interior acquisition per second of device 1 and pretreated eeg signal is all the same;The brain electricity determination module pair
Acquisition and when pretreated eeg signal is analyzed and processed in any second of EEG signals acquisition device 1, process is as follows:
The synchronous storage of step 3021, eeg signal: to being acquired in the EEG signals acquisition device received at this time 1 one seconds
And pretreated eeg signal synchronizes storage;
Step 3022, meditation degree and focus are extracted: extracted from handled eeg signal at this time meditation degree M with it is special
Note degree A;
Step 3023, meditation degree correction value and time correcting parameter determine: the current time provided according to clock circuit 2-6
T, at this time meditation degree correction value Δ M and time correcting parameter Δ T be determined respectively;
Wherein, when being determined to meditation degree correction value Δ M, when current time T is later than at 6 points and is not later than at 12, Δ M
=30~15;When current time T is later than at 12 points and is not later than at 15, Δ M=15~0;When current time T is later than 15 points and not
When being later than at 19, Δ M=0~15;It is later than 19 points and not late when current time T is later than at 0 point and is not later than 6 points or current time T
When 0, Δ M=0;
When being determined to time correcting parameter Δ T, when current time T is later than at 6 points and is not later than at 12, Δ T=2~
1.5;When current time T is later than at 12 points and is not later than at 15, Δ T=1.5~1.0;When current time T is later than 15 points and not late
When 19, Δ T=1.0~1.5;It is later than 19 points and not late when current time T is later than at 0 point and is not later than 6 points or current time T
When 0, Δ T=1.0;
Step 3024, tired step parameter increase and decrease processing: according to the meditation degree M and focus A extracted in step 3022,
And identified meditation degree correction value Δ M and time correcting parameter Δ T in step 3023 is combined, to tired step parameter s_ at this time
The numerical value of c is increased and decreased processing, and obtains increase and decrease treated tired step parameter s_c: whenWhen, it will be tired
The numerical value of labor step parameter s_c adds 1;Otherwise, the numerical value of tired step parameter s_c is judged: as tired step parameter s_c
Numerical value be 0 when, the numerical value of tired step parameter s_c remains unchanged;It, will be tired when the numerical value of tired step parameter s_c >=1
The numerical value of step parameter s_c subtracts 1;
Step 3025, fatigue driving judgement: according to the number of treated the tired step parameter s_c of increase and decrease in step 3024
Value, judges whether driver at this time is in fatigue driving state: when increase and decrease treated tired step in step 3024
When the numerical value > N of parameter s_c, judge that driver is in fatigue driving state at this time;Otherwise, judge that driver is at this time
Normal driving state;
Wherein, N is preset fatigue driving judgment threshold, and N is positive integer and N=2~8;
Step 3026, verification result obtain: according to the fatigue driving judging result obtained in step 3025, obtaining the brain
The verification result of electric determination module: when judging that driver is in fatigue driving state at this time in step 3025, the brain electricity
The verification result of determination module is that driver is in fatigue driving state at this time, and the fatigue of the eye electricity determination module is driven in completion
Sail the verification process of judging result;Otherwise, it also needs to judge whether to complete to acquire in EEG signals acquisition device 1 continuous F second and pre-
Treated, and the whole of eeg signal analyze treatment processes;
Also, acquisition and pretreated brain wave in EEG signals acquisition device 1 continuous F seconds is completed when judgement obtains
When whole analysis treatment processes of signal, the verification result of the brain electricity determination module is that driver is in normal driving shape at this time
State;Otherwise, 3026 are entered step;
Step 3026, return step 3021, to acquisition in EEG signals acquisition device 1 lower second and pretreated brain electricity
Wave signal is analyzed and processed.
In actual use, when the eye electricity determination module judges that driver is in fatigue driving state at this time, institute
State main control chip 2-1 recall the brain electricity determination module to also need call brain electricity determination module to the eye electricity determination module
Fatigue driving judging result is verified, thus can effectively reduce rate of failing to report, overcomes the existing monitoring of single judgment method accurate
The problem of property and monitoring velocity.On the other hand, the monitoring accuracy of the eye electricity determination module and the brain electricity determination module is equal
It is higher.
Wherein, being later than does not include 6 points in 6 points, and being not later than at 12 points includes 12 points;Being later than does not include 12 points in 12 points, not late
It include 15 points in 15 points;Being later than does not include 15 points in 15 points, and being not later than includes 19 points in 19 points.
The energy e for the currently pending eeg signal being calculated in step 30112 is the parameter of reflection blink intensity,
The numerical value of energy e is bigger, and blink intensity is bigger.Herein, determine to work as e > E2When, illustrate that blink intensity has reached the journey of blink
Primary blink artificially occurs at this time for degree.
In the present embodiment, N=3 described in step 3025.
In actual use, according to specific needs, the value size of N is adjusted accordingly.
In the present embodiment, p=30 described in step 3011;N=30 described in step 30118, Q=2.
In actual use, according to specific needs, the value size of p and Q is adjusted accordingly.
In actual use, when being determined using time interval method to meditation degree correction value Δ M in step 3023, when
When current time T is later than at 6 points and is not later than at 15, the time is more late, and meditation degree correction value Δ M is smaller;When current time T is later than 15
When putting and being not later than at 19, the time is more late, and meditation degree correction value Δ M is bigger;
When being determined using time interval method to time correcting parameter Δ T in step 3023, when current time T is later than 6
When putting and being not later than at 15, the time is more late, and the time, correcting parameter Δ T was smaller;When current time T is later than at 15 points and is not later than at 19 points
When, the time is more late, and the time, correcting parameter Δ T was bigger.
Thus, the meditation degree correction value Δ M and time correcting parameter Δ T that the present invention uses is obtain according to current time
Dynamic value, design rationally, can effectively improve fatigue driving monitoring accuracy.The original of above-mentioned setting is carried out to meditation degree correction value Δ M
Because being: will be gradually in a state of fatigue from 6 points to 12 human bodies of the morning, meditation degree is gradually increased, and reduces the amendment of meditation degree
Value Δ M also complies with rule;When point being that people is most tired in one day from 12 points to 15, meditation degree correction value Δ M can also reduce;From
15 points to 19 people have slowly restored spirit again, thus meditation degree correction value Δ M can slowly increase again;Other time default meditation
Spending correction value Δ M is 0.Thus, the determination process of meditation degree correction value Δ M is simple, reasonable and using effect is good.
Correspondingly, when fatigue, meditation degree and focus will appear multiple proportion, but can change with time and
Variation, for multiple proportion nearly all between 1 to 2, this coefficient can be with the proportional growth of the fatigue state of human body.Together
Reason, 6:00 AM is to 12 points of the morning, and the time, correcting parameter Δ T can reduce, and value range is between 2.0~1.5;From 12 points to 15
Point, the time, correcting parameter Δ T can also reduce, and value range is 1.5~1.0;From 15 points to 19 point, time correcting parameter Δ T meeting
Increase, value range is 1.0~1.5.
To realize simplicity and further increasing detection accuracy, in the present embodiment, to meditation degree correction value in step 3023
When Δ M is determined, process is as follows:
Step A1, current time integral point value determines: being determined to the integral point value of current time T;The clock circuit 2-6
The current time T of offer is to make for 24 hours, and the integral point value of current time T is denoted as nt, wherein nt be in current time T " when " number
Value;
Wherein, nt is integer and nt=0~23;
Step A2, meditation degree correction value Δ M is determined: according to nt identified in step A1, and current time T is combined, it is right
Meditation degree correction value Δ M at this time is determined: when current time T is later than at 6 points and is not later than at 12, according to formulaMeditation degree correction value Δ M is calculated;When current time T is later than 12 points and not late
When 15, according to formulaMeditation degree correction value Δ M is calculated;When current
When quarter T is later than at 15 points and is not later than at 19, according to formulaTo meditation degree correction value Δ M into
Row calculates;
In formula (1) and (2), bt1=12;In formula (3), bt2=15.
In the present embodiment, when being determined in step 3023 to time correcting parameter Δ T, process is as follows:
Step B1, current time integral point value determines: being determined to the integral point value of current time T;The clock circuit 2-6
The current time T of offer is to make for 24 hours, and the integral point value of current time T is denoted as nt, wherein nt be in current time T " when " number
Value;
Wherein, nt is integer and nt=0~23;
Step B2, time correcting parameter Δ T is determined: according to nt identified in step B1, and current time T is combined, it is right
Time correcting parameter Δ T at this time is determined: when current time T is later than at 6 points and is not later than at 12, according to formulaTime correcting parameter Δ T is calculated;When current time T is later than 12 points and not
When being later than at 15, according to formulaTime correcting parameter Δ T is calculated;When current
When moment T is later than at 15 points and is not later than at 19, according to formulaTo time correcting parameter
Δ T is calculated;
In formula (1) and (2), bt1=12;In formula (3), bt2=15.
In the present embodiment, current time T is denoted as nt:fz, wherein nt be current time T in " when " numerical value, fz is current
The numerical value " divided " in moment T.Thus, nt and fz be respectively in current time T " when " and " dividing " numerical value, directly read.
In the present embodiment, when connecting EEG signals acquisition device 1 with EEG signals monitoring terminal 2 in step 1, also need
The main control chip 2-1 of EEG signals monitoring terminal 2 is connect with host computer 4 with communication;
When main control chip 2-1 described in step 305 controls warning note unit 2-2 progress warning note, the master control core
The synchronous fatigue driving warning message that the driver is sent to host computer 4 of piece 2-1.
In actual use, it is attached between the main control chip 2-1 and host computer 4 with communication.
In the present embodiment, it further includes the parameter connecting with main control chip 2-1 that EEG signals described in step 1, which monitor terminal 2,
Input unit 2-4.
The main control chip 2-1 of EEG signals monitoring terminal 2 is connect with host computer 4 with communication in step 1
Afterwards, it also needs to input driver's essential information by parameter input unit 2-4, the main control chip 2-1 is to the driver inputted
Essential information carries out storage and by driver's essential information synchronous driving to host computer 4.
Driver's essential information includes the name and contact method of driver.
In the present embodiment, the EEG signals monitoring terminal 2 is smart phone.
In actual use, the EEG signals monitoring terminal 2 can also use other types of data processing terminal, such as slap
Upper computer, ipad etc..
It is carried out in the present embodiment, in step 3 in eeg signal analysis treatment process, the EEG signals monitor terminal 2
Main control chip 2-1 also need to call the synchronous vehicle essential information for obtaining the driven vehicle of driver of navigation module, the vehicle
Essential information includes vehicle geographical location and speed.
Also, the main control chip 2-1 can control warning note unit 2-2, and (such as 5s) casting is once worked as at regular intervals
Preceding locating geographical location is not necessarily to divert one's attention to see the mobile phone map when driving and unsafe accident occurs.
In actual use, the vehicle mounted guidance software that the navigation module can also use, such as high moral navigation software.Together
When, when judging that driver is in driving fatigue state, what the main control chip 2-1 navigation module synchronization obtained is driven
Sail the vehicle essential information of vehicle, driver and the monitoring personnel remotely monitored by host computer 4 can be to driver at
Position when fatigue state is accurately held, in this way when driver, which drives vehicle appearance position, to be changed, host computer 4 or brain
Electric signal monitors terminal 2 and can issue voice prompting by warning note unit 2-2 or play music, is pierced again to driver
Swash;Also, remote monitoring personnel can also remind driver by way of mobile phone communication, and driver is reminded to be at this time
It is no to meet safe driving requirement.
In addition, driver presses tired step parameter zero setting unit 2-5 after driver currently switchs to waking state, lead to
It crosses main control chip 2-1 and the numerical value of tired step parameter s_c is set as 0.
It, need to also be from handled brain wave at this time before carrying out meditation degree and focus extraction in the present embodiment, in step 302
Poorsingle is extracted in signal, and according to the numerical value of poorsingle to the wearing appearance of EEG signals acquisition device 1 at this time
Whether gesture is correctly judged: when the numerical value of poorsingle is greater than 200, illustrating the wearing appearance of EEG signals acquisition device 1
Gesture is incorrect;Otherwise, illustrate the wearing correct set of EEG signals acquisition device 1.
In actual use, the warning note unit 2-2 is voice alerting unit.According to the numerical value of poorsingle
It is complete by the main control chip 2-1 to the process whether the wearing posture of EEG signals acquisition device 1 at this time is correctly judged
At when judging the wearing fault of EEG signals acquisition device 1, warning note unit 2-2 issues voice prompting, such as
" your wearing posture is wrong " voice broadcast, more can make detection process more accurate in this way, prevent because not wearing ear
Machine leads to the outflow of wrong data.Poorsingle is the data that EEG signals acquisition device 1 directly exports, and need to only be extracted i.e.
It can.
The above is only presently preferred embodiments of the present invention, is not intended to limit the invention in any way, it is all according to the present invention
Technical spirit any simple modification to the above embodiments, change and equivalent structural changes, still fall within skill of the present invention
In the protection scope of art scheme.
Claims (8)
1. a kind of fatigue driving eeg monitoring method, it is characterised in that: method includes the following steps:
Step 1: equipment connection and parameter initialization: even by EEG signals acquisition device (1) and EEG signals monitoring terminal (2)
It connects, and tired step parameter s_c is set by the main control chip (2-1) of EEG signals monitoring terminal (2);At this point, tired
The numerical value of labor step parameter s_c is 0;
The EEG signals acquisition device (1) is Mindwave Mobile brain cubic earphone or TGAM module;The EEG signals
Monitoring device (2) includes main control chip (2-1) and the clock circuit (2-6) connecting respectively with main control chip (2-1) and alarm
Prompt unit (2-2);
Step 2: eeg signal acquires: using EEG signals acquisition device (1) and according to preset sample frequency to driving
The eeg signal for the person of sailing is acquired and pre-processes, and pretreated eeg signal synchronous driving to EEG signals is supervised
It surveys terminal (2);
It include original eeg signal in the eeg signal, and the sample frequency of the original eeg signal is 512Hz;
The eeg signal of EEG signals acquisition device (1) output is the frequency-region signal after Fast Fourier Transform (FFT);
Step 3: eeg signal analysis is handled: the main control chip (2-1) of EEG signals monitoring terminal (2) calls eye electricity
Determination module is acquired to EEG signals acquisition device (1) and pretreated eeg signal is analyzed and processed, and process is as follows:
Step 3011, number of winks judgment threshold determine: connecting according to sampling time sequencing to EEG signals acquisition device (1)
It is acquired in P seconds continuous and pretreated eeg signal is analyzed and processed respectively, and according to analysis and processing result to blink time
Number judgment threshold n0It is determined;Wherein, P=2 × p, wherein p is positive integer and p >=20;
In this step, to acquisition in EEG signals acquisition device (1) any second and pretreated eeg signal is analyzed
When processing, process is as follows:
The synchronous storage of step 30111, eeg signal: to being acquired in the EEG signals acquisition device received at this time (1) one second
And pretreated eeg signal synchronizes storage, the eeg signal stored is currently pending eeg signal;
Step 30112, original eeg signal extract and eeg signal energy balane: from described in step 30111 currently to
Original eeg signal is extracted in processing eeg signal, and the energy e of currently pending eeg signal is calculated;
It include 512 original eeg signals, 512 original brain waves in the currently pending eeg signal
The signal value of i-th of original eeg signal is denoted as X in signali;
When calculating the energy e of currently pending eeg signal, according to formula(7) it is calculated;It is public
In formula (7), N=512;
Step 30113, blink determine: according to the energy e for the currently pending eeg signal being calculated in step 30112,
Judge whether driver in the second blinks, and obtain the blink decision content bk of this second: as e > E2When, bk=1;Otherwise,
Bk=0;Wherein, E=280~320;
Step 30114, the synchronous storage of blink decision content: synchronizing storage to the blink decision content bk obtained in step 30113,
Complete the analysis treatment process of acquisition and pretreated eeg signal in EEG signals acquisition device (1) this second;
Acquisition and pretreated eeg signal analysis processing in step 30115, next second: according to step 30111 to step
Method described in 30114, to acquisition in EEG signals acquisition device (1) next second and pretreated eeg signal carries out
Analysis processing, and obtain the blink decision content bk of this second;
Step 30116, P-2 times repeat step 30115, until complete EEG signals acquisition device (1) the continuous P second in acquisition and it is pre-
The analysis treatment process of treated eeg signal, and obtain the blink decision content bk of each second;
Step 30117, blink decision content superposition: to the blink decision content bk of each second in the continuous P second obtained in step 30116
It is overlapped, and obtains the sum of blink decision content bkZ;
Step 30118, number of winks judgment threshold determine: according to the sum of blink decision content obtained in step 30117 bkz,
And according to formulaNumber of winks judgment threshold n is calculated0;
Wherein, n is positive integer and n >=4;
Also, n × Q=P, wherein Q is positive integer and Q=2~10;
Eeg signal analysis processing, process are as follows before step 3012, fatigue driving judge:
Acquisition and pretreated eeg signal analysis processing in next second after step 30121, judgment threshold determine: step
The n of number of winks judgment threshold described in 301180After determination, according to method described in step 30111 to step 30114, to brain
It is acquired in electric signal acquisition device (1) next second and pretreated eeg signal is analyzed and processed, and obtain this second
Blink decision content bk;
Step 30122 repeats step 30121 n-2 times, until completing number of winks judgment threshold n described in step 301180It determines
The analysis treatment process of EEG signals acquisition device (1) interior acquisition in continuous n-1 seconds and pretreated eeg signal afterwards, and obtain
Obtain the blink decision content bk of each second;
Step 3013, fatigue driving judgement start rear eeg signal analysis processing: fatigue driving judgement is completed in step 3012
After preceding eeg signal analysis processing, the eye electricity determination module is according to sampling time sequencing to EEG signals acquisition device
(1) interior acquisition per second and pretreated eeg signal is analyzed and processed respectively, and according to analysis and processing result at this time
Whether driver, which is in fatigue driving state, judges;
In this step, the eye electricity determination module is to acquisition and pretreated brain in EEG signals acquisition device (1) any second
When electric wave signal is analyzed and processed, process is as follows:
Step 30131, eeg signal analysis processing: according to method described in step 30111 to step 30114, to brain electricity
Signal acquisition device (1) acquires at this time and pretreated eeg signal is analyzed and processed, and show that blink at this time is sentenced
Definite value bk;
Step 30132, blink decision content superposition: by the blink decision content bk obtained in step 30131 and it is Q-1 seconds first in each second
Blink decision content bk is overlapped, and the sum of the blink decision content of acquisition at this time bkz;
The sum of blink decision content bkz is the total of the blink decision content bk of each second in EEG signals acquisition device (1) is Q seconds continuous
With;
Step 30133, fatigue driving judgement: according to the sum of the blink decision content obtained in step 30133 bkz, and step is combined
Identified number of winks judgment threshold n in 301180, judge whether driver at this time is in fatigue driving state: when
Bkz > n0When, illustrate that driver is in fatigue driving state at this time, the main control chip (2-1) controls warning note unit (2-
2) warning note is carried out;Otherwise, illustrate that driver is in normal driving state at this time;
Step 30134, return step 30131, to acquisition in EEG signals acquisition device (1) next second and pretreated brain electricity
Wave signal is analyzed and processed;
It is carried out in step 3 in eeg signal analysis treatment process, the main control chip (2- of EEG signals monitoring terminal (2)
1) it also needs to call the synchronous vehicle essential information for obtaining the driven vehicle of driver of navigation module, the vehicle essential information includes
Vehicle geographical location and speed.
2. a kind of fatigue driving eeg monitoring method described in accordance with the claim 1, it is characterised in that: the electricity of brain described in step 1
It is communicated between signal acquisition device (1) and EEG signals monitoring device (2) with communication;
The TGAM module includes the EEG signals extraction element (1-1) extracted to the eeg signal of driver and to brain
Electric signal extraction element (1-1) extracted signal carries out sampling and pretreated EEG signals pretreatment unit (1-2), the brain
Electric signal pretreatment unit (1-2) connects with EEG signals extraction element (1-1), EEG signals extraction element (1-1) packet
It includes and the first electrode for encephalograms (1-11) of real-time sampling is carried out to the current potential in driver's frontal lobe area and to ear's current potential of driver
The second electrode for encephalograms (1-12) and third electrode for encephalograms (1-13) of progress real-time sampling, first electrode for encephalograms (1-11),
Second electrode for encephalograms (1-12) and third electrode for encephalograms (1-13) connect with EEG signals pretreatment unit (1-2);
The EEG signals monitoring device (2) further includes the second wireless communication module (2- to connect respectively with main control chip (2-1)
And tired step parameter zero setting unit (2-5) 3);
The EEG signals acquisition device (1) connects with the first wireless communication module (3), the EEG signals acquisition device (1)
It is communicated by the first wireless communication module (3) and the second wireless communication module (2-2) with main control chip (2-1).
3. a kind of fatigue driving eeg monitoring method according to claim 1 or 2, it is characterised in that: the EEG signals
Monitoring terminal (2) is smart phone.
4. a kind of fatigue driving eeg monitoring method described in accordance with the claim 1, it is characterised in that: the electricity of brain described in step 1
Signal monitoring terminal (2) further includes the parameter input unit (2-4) connecting with main control chip (2-1);
The main control chip (2-1) of EEG signals monitoring terminal (2) is connect with host computer (4) with communication in step 1
Afterwards, it also needs to input driver's essential information by parameter input unit (2-4), the main control chip (2-1) is driven to what is inputted
The person's of sailing essential information carries out storage and by driver's essential information synchronous driving to host computer (4);
Driver's essential information includes the name and contact method of driver.
5. a kind of fatigue driving eeg monitoring method according to claim 1 or 2, it is characterised in that: in step 30133 when
Bkz > n0When, the fatigue driving judging result of the eye electricity determination module is that driver is in fatigue driving state, and master at this time
Before controlling chip (2-1) control warning note unit (2-2) progress warning note, the main control chip (2-1) also needs to call brain
Electric determination module verifies the fatigue driving judging result of the eye electricity determination module, and according to the brain electricity determination module
Verification result, whether driver at this time is determined in fatigue driving state: when the verifying of the brain electricity determination module
As a result for when driver is in fatigue driving state at this time, determining driver at this time is in fatigue driving state, later master control core
Piece (2-1) controls warning note unit (2-2) and carries out warning note;Otherwise, it determines driver is in normal driving state at this time;
The main control chip (2-1) calls the brain electricity determination module to the fatigue driving judging result of the eye electricity determination module
When being verified, process is as follows:
Step 302-1, the numerical value of tired step parameter s_c tired step parameter zero setting: is set as 0;
Step 302-2, eeg signal analysis is handled: the brain electricity determination module is according to sampling time sequencing, to step
EEG signals acquisition device (1) continuously acquires in F seconds after tired step parameter zero setting in 302-1 and pretreated brain wave is believed
It number is analyzed and processed respectively;Wherein, F is positive integer and F=5~15;The brain electricity determination module obtains EEG signals and fills
The analysis and processing method for setting (1) interior acquisition per second and pretreated eeg signal is all the same;The brain electricity determination module pair
Acquisition and when pretreated eeg signal is analyzed and processed in EEG signals acquisition device (1) any second, process is as follows:
The synchronous storage of step 3021, eeg signal: to being acquired simultaneously in the EEG signals acquisition device received at this time (1) one second
Pretreated eeg signal synchronizes storage;
Step 3022, meditation degree and focus are extracted: extracting meditation degree M and focus from handled eeg signal at this time
A;
Step 3023, meditation degree correction value and time correcting parameter determine: the current time T provided according to clock circuit (2-6),
To at this time meditation degree correction value Δ M and time correcting parameter Δ T be determined respectively;
Wherein, when being determined to meditation degree correction value Δ M, when current time T is later than at 6 points and is not later than at 12, Δ M=30
~15;When current time T is later than at 12 points and is not later than at 15, Δ M=15~0;When current time T is later than at 15 points and is not later than
At 19, Δ M=0~15;It is later than at 19 points when current time T is later than at 0 point and is not later than 6 points or current time T and is not later than at 0 point
When, Δ M=0;
When being determined to time correcting parameter Δ T, when current time T is later than at 6 points and is not later than at 12, Δ T=2~1.5;
When current time T is later than at 12 points and is not later than at 15, Δ T=1.5~1.0;When current time T is later than at 15 points and is not later than 19
When point, Δ T=1.0~1.5;It is later than at 19 points when current time T is later than at 0 point and is not later than 6 points or current time T and is not later than 0
When point, Δ T=1.0;
Step 3024, tired step parameter increase and decrease processing: it according to the meditation degree M and focus A extracted in step 3022, and ties
Identified meditation degree correction value Δ M and time correcting parameter Δ T in step 3023 is closed, to tired step parameter s_c's at this time
Numerical value is increased and decreased processing, and obtains increase and decrease treated tired step parameter s_c: whenWhen, by tired platform
The numerical value of rank parameter s_c adds 1;Otherwise, the numerical value of tired step parameter s_c is judged: when the number of tired step parameter s_c
When value is 0, the numerical value of tired step parameter s_c is remained unchanged;When the numerical value of tired step parameter s_c >=1, by tired step
The numerical value of parameter s_c subtracts 1;
Step 3025, fatigue driving judgement: right according to the numerical value of treated the tired step parameter s_c of increase and decrease in step 3024
Whether driver is in fatigue driving state and judges at this time: as increase and decrease treated tired step parameter s_ in step 3024
When the numerical value > N of c, judge that driver is in fatigue driving state at this time;Otherwise, judge that driver is at this time normally to drive
Sail state;
Wherein, N is preset fatigue driving judgment threshold, and N is positive integer and N=2~8;
Step 3026, verification result obtain: according to the fatigue driving judging result obtained in step 3025, obtaining the brain electricity and sentence
The verification result of cover half block: when judging that driver is in fatigue driving state at this time in step 3025, the brain electricity determines
The verification result of module is that driver is in fatigue driving state at this time, and the fatigue driving of the eye electricity determination module is sentenced in completion
The verification process of disconnected result;Otherwise, it also needs to judge whether to complete EEG signals acquisition device (1) interior acquisition in continuous F seconds and locate in advance
Whole analysis treatment processes of eeg signal after reason;
Also, acquisition and pretreated brain wave letter in EEG signals acquisition device (1) continuous F second is completed when judgement obtains
Number whole analysis treatment process when, the verification result of the brain electricity determination module is that driver is in normal driving shape at this time
State;Otherwise, 3026 are entered step;
Step 3026, return step 3021, to acquisition and pretreated brain wave in EEG signals acquisition device (1) next second
Signal is analyzed and processed.
6. a kind of fatigue driving eeg monitoring method according to claim 5, it is characterised in that: described in step 3011
P=30;N=30 described in step 30118, Q=2;
N=3 described in step 3025.
7. a kind of fatigue driving eeg monitoring method according to claim 5, it is characterised in that: when being used in step 3023
Between interval method when being determined to meditation degree correction value Δ M, when current time T is later than at 6 points and is not later than at 15, the time is got over
Evening, meditation degree correction value Δ M are smaller;When current time T is later than at 15 points and is not later than at 19, the time is more late, the amendment of meditation degree
It is bigger to be worth Δ M;
In step 3023 using time interval method time correcting parameter Δ T is determined when, when current time T be later than 6 points and
When being not later than at 15, the time is more late, and the time, correcting parameter Δ T was smaller;When current time T is later than at 15 points and is not later than at 19,
Time is more late, and the time, correcting parameter Δ T was bigger.
8. a kind of fatigue driving eeg monitoring method according to claim 5, it is characterised in that: to meditation in step 3023
When degree correction value Δ M is determined, process is as follows:
Step A1, current time integral point value determines: being determined to the integral point value of current time T;The clock circuit (2-6) mentions
The current time T of confession is to make for 24 hours, and the integral point value of current time T is denoted as nt, wherein nt be in current time T " when " number
Value;
Wherein, nt is integer and nt=0~23;
Step A2, meditation degree correction value Δ M is determined: according to nt identified in step A1, and current time T is combined, at this time
Meditation degree correction value Δ M be determined: when current time T is later than at 6 points and is not later than at 12, according to formulaMeditation degree correction value Δ M is calculated;When current time T is later than 12 points and not late
When 15, according to formulaMeditation degree correction value Δ M is calculated;When current
When quarter T is later than at 15 points and is not later than at 19, according to formulaTo meditation degree correction value Δ M into
Row calculates;
In formula (1) and (2), bt1=12;In formula (3), bt2=15;
When being determined in step 3023 to time correcting parameter Δ T, process is as follows:
Step B1, current time integral point value determines: being determined to the integral point value of current time T;The clock circuit (2-6) mentions
The current time T of confession is to make for 24 hours, and the integral point value of current time T is denoted as nt, wherein nt be in current time T " when " number
Value;
Wherein, nt is integer and nt=0~23;
Step B2, time correcting parameter Δ T is determined: according to nt identified in step B1, and current time T is combined, at this time
Time correcting parameter Δ T be determined: when current time T is later than at 6 points and is not later than at 12, according to formulaTime correcting parameter Δ T is calculated;When current time T is later than 12 points and not late
When 15, according to formulaTime correcting parameter Δ T is calculated;When current
When moment T is later than at 15 points and is not later than at 19, according to formulaTo time correcting parameter
Δ T is calculated;
In formula (1) and (2), bt1=12;In formula (3), bt2=15.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610136802.4A CN105615878B (en) | 2016-03-10 | 2016-03-10 | A kind of fatigue driving eeg monitoring method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610136802.4A CN105615878B (en) | 2016-03-10 | 2016-03-10 | A kind of fatigue driving eeg monitoring method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105615878A CN105615878A (en) | 2016-06-01 |
CN105615878B true CN105615878B (en) | 2019-05-31 |
Family
ID=56031542
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610136802.4A Expired - Fee Related CN105615878B (en) | 2016-03-10 | 2016-03-10 | A kind of fatigue driving eeg monitoring method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105615878B (en) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106599839B (en) * | 2016-12-13 | 2019-07-12 | 清华大学 | The parallel noise-reduction method and device of the electromagnetic field feature of the exogenous interference of vehicle-mounted brain electricity |
CN106691443B (en) * | 2017-01-11 | 2020-06-26 | 中国科学技术大学 | Wearable driver fatigue-prevention intelligent monitoring and early warning system based on electroencephalogram |
CN107296596A (en) * | 2017-07-18 | 2017-10-27 | 西安科技大学 | The staff's fatigue monitoring system and method for a kind of underground coal mine |
CN108095741A (en) * | 2018-01-30 | 2018-06-01 | 上海智勇教育培训有限公司 | A kind of mental fatigue Tachistoscope device and method based on EEG signals |
CN109009173B (en) * | 2018-08-30 | 2022-02-01 | 北京机械设备研究所 | Fatigue detection and regulation method based on electroencephalogram-eye movement bimodal signals |
CN109480872B (en) * | 2018-11-08 | 2021-09-17 | 哈尔滨工业大学 | Driving fatigue detection method based on electroencephalogram signal frequency band energy ratio characteristics |
CN109464152B (en) * | 2019-01-09 | 2021-11-26 | 浙江强脑科技有限公司 | Method and device for detecting brain fatigue state and computer readable storage medium |
CN110126835A (en) * | 2019-04-12 | 2019-08-16 | 中国平安财产保险股份有限公司 | Interference method, device, computer equipment and the storage medium of driving behavior |
CN110507319B (en) * | 2019-09-04 | 2022-04-15 | 杭州回车电子科技有限公司 | Fatigue degree detection method and equipment |
CN111449652B (en) * | 2020-05-06 | 2022-11-29 | 北方工业大学 | Construction safety monitoring method and device based on brain wave analysis |
CN112754498B (en) * | 2021-01-11 | 2023-05-26 | 一汽解放汽车有限公司 | Driver fatigue detection method, device, equipment and storage medium |
CN113080971A (en) * | 2021-04-12 | 2021-07-09 | 北京交通大学 | Method and system for judging fatigue state by detecting blink signals |
CN114159077B (en) * | 2022-02-09 | 2022-05-31 | 浙江强脑科技有限公司 | Meditation scoring method, device, terminal and storage medium based on electroencephalogram signals |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6070098A (en) * | 1997-01-11 | 2000-05-30 | Circadian Technologies, Inc. | Method of and apparatus for evaluation and mitigation of microsleep events |
CN102125429A (en) * | 2011-03-18 | 2011-07-20 | 上海交通大学 | Alertness detection system based on electro-oculogram signal |
CN105011951A (en) * | 2014-04-24 | 2015-11-04 | 闽南师范大学 | Device for extracting eye blinking times by brain waves and method |
-
2016
- 2016-03-10 CN CN201610136802.4A patent/CN105615878B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6070098A (en) * | 1997-01-11 | 2000-05-30 | Circadian Technologies, Inc. | Method of and apparatus for evaluation and mitigation of microsleep events |
CN102125429A (en) * | 2011-03-18 | 2011-07-20 | 上海交通大学 | Alertness detection system based on electro-oculogram signal |
CN105011951A (en) * | 2014-04-24 | 2015-11-04 | 闽南师范大学 | Device for extracting eye blinking times by brain waves and method |
Non-Patent Citations (3)
Title |
---|
EEG Eye-Blinking Artefacts Power Spectrum Analysis;Plamen Manoilov;《International Conference on Computer Systems and Technologies - CompSysTech’06》;20061231;正文第3-4页 * |
Electrooculogram Analysis and Development of a System for Defining Stages of Drowsiness;Birgitta Thorslund;《Publication of Swedish National Road & Transport Research Institute》;20041231;正文16,24-26,40页 * |
基于脑-机接口的驾驶员疲劳度检测预警***研究;孙宇;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑 (月刊 ) 》;20150915;正文12-25页,正文40-46页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105615878A (en) | 2016-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105615878B (en) | A kind of fatigue driving eeg monitoring method | |
CN105595996B (en) | A kind of fatigue driving eeg monitoring method of electricity and brain electricity comprehensive judgement | |
CN105595997B (en) | A kind of fatigue driving eeg monitoring method determined based on step fatigue | |
CN104146722B (en) | Driving fatigue detecting and grading early warning method based on head signals | |
CN105015552B (en) | Driver status monitoring system and its control method | |
CN111166357A (en) | Fatigue monitoring device system with multi-sensor fusion and monitoring method thereof | |
CN105373219B (en) | Wearable device and its operating method | |
CN105015551B (en) | Driver status monitoring system, the method for controlling the system and vehicle | |
CN104796485B (en) | A kind of the elderly Yunan County health service platform and big data processing method | |
CN106691443B (en) | Wearable driver fatigue-prevention intelligent monitoring and early warning system based on electroencephalogram | |
CN110013249B (en) | Portable adjustable head-mounted epilepsy monitor | |
CN105054951B (en) | A kind of fatigue driving eeg monitoring method based on frequency of wink identification | |
CN107226123A (en) | A kind of multi-mode biological response steering wheel | |
CN105105773B (en) | A kind of fatigue driving eeg monitoring method compared based on multi-threshold | |
CN201691930U (en) | Human movement state monitoring device | |
CN106491104A (en) | Driver status intelligent real time monitoring system and method based on Intelligent worn device | |
CN103021134A (en) | Monitoring and alarm device for fatigue driving of automobile | |
CN106725384A (en) | A kind of Intelligent bracelet system for the monitoring of pregnant woman's sign | |
CN103985224B (en) | The method and system of prompting are given based on smart machine detection human fatigue | |
CN103606245A (en) | Fatigue driving detection early warning system based on Bluetooth brain wave earphone and Android mobile phone | |
CN102874113A (en) | Safety protection system used in sudden disease of driver | |
CN104821061A (en) | Wearable fall early warning system and application method thereof | |
CN109624984A (en) | A kind of mobile Internet intelligent vehicle-mounted system | |
CN114652532B (en) | Multifunctional brain-controlled wheelchair system based on SSVEP and attention detection | |
CN105193430A (en) | Protective device, wearable equipment, protecting method and display system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190531 Termination date: 20210310 |