CN107595306A - A kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing - Google Patents
A kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing Download PDFInfo
- Publication number
- CN107595306A CN107595306A CN201710722181.2A CN201710722181A CN107595306A CN 107595306 A CN107595306 A CN 107595306A CN 201710722181 A CN201710722181 A CN 201710722181A CN 107595306 A CN107595306 A CN 107595306A
- Authority
- CN
- China
- Prior art keywords
- driver
- brain
- brain electricity
- classification
- early warning
- 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.)
- Pending
Links
Abstract
The invention discloses a kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing, including：Brain wave acquisition subsystem, brain electric analoging signal is obtained for gathering, and pretreatment obtains and transmission brain electricity data signal；Brain electricity analytical subsystem, for carrying out feature extraction and analysis to brain electricity data signal, carry out time domain waveform and show；Brain electricity data signal is identified using SVM more classification and identification algorithms, obtains and transmit the classification results for disperseing grade as the driving condition residing for driver；Early warning sub-device, including intelligent early-warning bracelet are driven, disperseing grade for the driving condition according to residing for driver carries out early warning control；Vehicle mounted surveillance device, disperse grade for the driving condition according to residing for driver and carry out early warning control.The present invention carries out Classification and Identification using EEG signals, judges that vehicle mounted surveillance driver is in severe dispersity, and carries out forewarning function, judges precision height, early warning is timely, easy to carry, easily operated, has higher practical value.
Description
Technical field
The present invention relates to a kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing, the technology for belonging to early warning system is led
Domain.
Background technology
The death toll caused by fatigue driving is about 30,000 people every year in China, and number of injured people is more than 400,000.It is so-called tired
Please sail, when referring to that driver travels for a long time in monotonous environment (such as on a highway or night), the four limbs of appearance
It is powerless, dispersion attention, judgement decline phenomena such as.If above-mentioned phenomenon, which occurs, in driver but still drives vehicle, easily make
Into traffic accident.And driver fatigue monitor system is exactly to carry out accurate real-time display to the driving condition of driver, work as driving
Member is reminded when feeling tired, and with the generation to avoid traffic accident, reduces traffic accident probability of happening.Therefore, invention is a kind of
Driver fatigue monitor system based on electroencephalogramsignal signal analyzing seems very necessary.
In recent years, with the rapid development of brain-computer interface (BCI) art so that only by the thinking activities of human brain
Realize that the control to external environment condition is possibly realized.Lot of documents points out, each rhythm and pace of moving things ripple of EEG signals (EEG) (δ ripples, θ ripples, α
Ripple, β ripples) have with the state such as the vigilance residing for human brain, fatigue and closely contact.When human body is in alertness, brain
β ripples in electric signal are significantly stronger than its all band in the activity of prefrontal area；And when human body is in fatigue state, β ripples will be by
Suppress, and activity of the θ ripples in temporal lobe region becomes the most notable.Therefore, sentenced using the situation of change of EEG signals rhythm and pace of moving things ripple
Disconnected driver's status has been possibly realized.
The content of the invention
The technical problems to be solved by the invention are overcome the deficiencies in the prior art, there is provided a kind of based on EEG signals point
The driver fatigue monitor system of analysis, solution can not judge to drive using the situation of change of EEG signals rhythm and pace of moving things ripple in the prior art
The problem of person's of sailing status and early warning, to detect the degree of fatigue of driver based on electroencephalogramsignal signal analyzing, it is intended to work as classification
Identification judges that system gives early warning prompting during driver fatigue.
It is of the invention specifically to solve above-mentioned technical problem using following technical scheme：
A kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing, including：
Brain wave acquisition subsystem, brain electric analoging signal is obtained for gathering, and according to the sample frequency of setting to brain electricity mould
Intend Signal Pretreatment and obtain and transmit brain electricity data signal；
Brain electricity analytical subsystem, for carrying out feature extraction and analysis to the brain electricity data signal of reception, and institute will be analyzed
Brain electricity data signal progress time domain waveform is obtained to show；Analysis gained brain electricity data signal is entered using SVM more classification and identification algorithms
Row identification, obtain and transmit the classification results for being disperseed grade by the driving condition residing for driver and being formed；
Drive early warning sub-device, including intelligent early-warning bracelet and vehicle mounted surveillance device；The intelligent early-warning bracelet, for root
Disperse grade according to the driving condition residing for driver in the classification results received and carry out early warning control；The vehicle mounted surveillance dress
Put, disperseing grade for the driving condition according to residing for driver in the classification results received carries out early warning control.
Further, as a preferred technical solution of the present invention：The brain wave acquisition subsystem includes capture setting
Brain electric analoging signal in the collection point of diverse location.
Further, as a preferred technical solution of the present invention：The brain wave acquisition subsystem is arranged on headgear.
Further, as a preferred technical solution of the present invention：The brain wave acquisition subsystem is believed brain electrical analogue
Number pretreatment includes overvoltage protection and passive HF filtering process.
Further, as a preferred technical solution of the present invention：The brain wave acquisition subsystem uses Bluetooth transmission
Mode is by brain electricity digital data transmission.
Further, as a preferred technical solution of the present invention：The brain electricity analytical subsystem is classified more using SVM
Brain electricity data signal is identified recognizer, specifically includes：
Wavelet decomposition is carried out to the single lead signals in brain electricity data signal, the power and each ripple of calculating for obtaining each ripple exist
Proportion in general power；Characteristic parameter is determined according to the difference of specific gravity between the different lead signals of acquisition, and as
The input vector of the more classification and identification algorithms of SVM；
Establish the more classification and identification algorithms of SVM and choose kernel function of the RBF kernel functions as the algorithm, to as low-dimensional sample
The characteristic parameter of space input vector is converted to the inner product value of high-dimensional feature space, and according to gained high-dimensional feature space
Inner product is worth to linear classification plane and carries out Classification and Identification, obtains the driving condition residing for driver and disperses grade.
Further, as a preferred technical solution of the present invention：Driver institute obtained by the brain electricity analytical subsystem
The driving condition at place, which disperses grade, includes three scattered grades.
Further, as a preferred technical solution of the present invention：The intelligent early-warning bracelet is using vibration or instruction
Lamp mode carries out early warning.
Further, as a preferred technical solution of the present invention：The vehicle mounted surveillance device is using display or voice
Mode carries out early warning.
The present invention uses above-mentioned technical proposal, can produce following technique effect：
Driver fatigue monitor system provided by the invention based on electroencephalogramsignal signal analyzing, three subsystems have been directed to it
System：Brain wave acquisition subsystem, brain electricity analytical subsystem and driving early warning subsystem.Subsystems are again mutually auxiliary independently of each other
Coordinate, full-duplex data interaction is carried out according to specific agreement.
Present invention employs portable brain electric collecting device, and the brain electricity data signal collected is sent into brain electricity analytical
System carries out feature extraction, and carrying out Classification and Identification using the more classification and identification algorithms of SVM determines classification results, by residing for driver
Driving condition be divided into that notice is concentrated, slight scattered and severe disperses Three Estate, classification and recognition can be improved, number
It is more accurate according to processing procedure.Classification results are transferred to portable intelligent early warning bracelet and car eventually through Radio Transmission Technology
Carry in monitoring arrangement, to remind driver to have a short interval, should not continue to drive a vehicle.In this, the present invention is truly realized a reality
Fatigue driving early warning subsystem, and it judges precision height, early warning is timely, easy to carry, easily operated, has higher
Practical value.
Brief description of the drawings
Fig. 1 is the schematic diagram of the driver fatigue monitor system of the invention based on electroencephalogramsignal signal analyzing.
Fig. 2 is the schematic diagram of midbrain electricity acquisition subsystem of the present invention.
Fig. 3 is the display schematic diagram of vehicle mounted surveillance device in the present invention.
Fig. 4 is the display interface schematic diagram of vehicle mounted surveillance device in the present invention.
Embodiment
Embodiments of the present invention are described with reference to Figure of description.
As shown in figure 1, the present invention devises a kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing, system master
To include three subsystems, be specially：Brain wave acquisition subsystem, brain electricity analytical subsystem and driving early warning sub-device.Each height
System is complemented each other again independently of each other, and full-duplex data interaction is carried out according to specific agreement.Its main process is as follows:
Step 1, gathered using brain wave acquisition subsystem and obtain brain electric analoging signal, and according to the sample frequency of setting to brain
Electric analoging signal pretreatment obtains and transmission brain electricity data signal.
In the present embodiment, brain wave acquisition subsystem is preferably disposed in headgear, by the use of headgear on set collecting device as
Wearable EEG signals acquisition device, is specifically shown in Fig. 2, its can capture setting in the brain electrical analogue of the collection point of diverse location
Signal, the EEG signals of four leads are such as gathered, collection point is located at FP1, FP2 (forehead) and T3, T4 (temporal lobe).Gather position
For 1,2,3,4；Take collection headgear, 5,6,7,8 on headgear will be adjacent to corresponding limit, wherein 9 be the placement section of Acquisition Circuit
Position, 10 be the placement position of lithium battery.
The operation of brain wave acquisition subsystem includes three steps：Pretreatment, digital-to-analogue conversion and it is wirelessly transferred.Brain electrical analogue
Signal sampling, using ear-lobe as reference electrode, gather the brain electric analoging signal of four specified electrode points.
Step 11：The pretreatment of brain electric analoging signal, it is preferable that the pretreatment of brain electric analoging signal have overvoltage protection with
And passive HF filters two parts.Because human body has electrostatic under special circumstances, so needing to set overvoltage protection electricity
Road, for protecting AD conversion chip.Overvoltage protection is made up of two diodes, limits the input voltage of A/D chip.Due to
The frequency distribution of EEG signals mainly in below 40Hz, can design low-pass filter circuit, the workload for further part.
Step 12：Brain electric analoging signal A/D is changed, and the core conversion chip of the part is ADS1299, is by TI companies
A chip dedicated for eeg signal acquisition of research and development, the built-in chip type function such as electrode detection and AF panel, and
Have the advantages that conversion accuracy is high and stability is good.Sample frequency can be set in acquisition chip ADS1299, is set in the present invention
Brain electricity sample frequency be 250Hz, every time gather 4 leads brain electricity data signal.
Step 13：By being wirelessly transferred for step 2 brain electricity data signal, it is wirelessly transferred part and is preferably transmitted by Bluetooth protocol
To brain electricity analytical subsystem, using HC-06 bluetooth serial ports transparent transmission modules, this wireless module is low in energy consumption, and need not apply for frequency range,
With higher transmission efficiency.Serial port protocol between brain wave acquisition equipment and brain electricity analytical system is：Baud rate 115200bps,
Data bit, check bit, header, telegram end.Wherein, CH1, CH2, CH3 and CH4 are respectively intended to transmit FP1, FP2, T3 and T4 passage
Analog-to-digital conversion after signal.CH5-CH8 is reserved place.
Midbrain electricity collecting device of the present invention is a kind of wearable EEG signals acquisition device.Relative to other brain wave acquisitions
Equipment, the present invention are significantly improved in many aspects such as portability, stability and securities.First, in portability side
Face, collecting device have the advantages that small volume, in light weight and comfortable wearing.Outward appearance process aspect meets anthroposomatology design, uses
Telescopic type wears structure, and uses the dry electrode of software sponge, ensure that comfort level during wearing.Secondly, in stability side
Face, using hardware signal modulate circuit, EEG signals are carried out with basic pretreatment, alleviates the pressure of software algorithm.Most
Afterwards, in terms of security, equipment uses the dry cell power supply of low-voltage, ensure that the personal safety of subject.
The circuit design of brain wave acquisition subsystem mainly includes Acquisition Circuit, pretreatment module and wireless transport module.
Because EEG signals are very faint, and with the contact noise of serious Hz noise, electrode and skin, so collection electricity
The design on road is using the ADS1299 of TI companies as core, and integrated chip biasing eliminates and the function such as electrode detection, effectively
Ground reduces the volume of pcb board, meets the design concept of wearable device.Pretreatment module uses STM32 series microprocessors, this
Processor cost is relatively low, and application is quite varied, and its stability is secure, and technology is very ripe, contributes to other work(
The expansion of energy.Eeg data is sent to brain electricity analytical system by wireless transport module, and the module has transmission rate soon and packet loss
The low advantage of rate.
Step 2, the core that brain electricity analytical subsystem is system, the brain electricity number using brain electricity analytical subsystem to reception
Word signal carries out feature extraction and analysis, and analysis gained brain electricity data signal is carried out into time domain waveform and shown；It is more using SVM
Analysis gained brain electricity data signal is identified classification and identification algorithm, obtains and transmits as the driving condition residing for driver
The classification results of scattered grade.Its operating procedure mainly includes：Graphic software platform, algorithm classification identification and data transfer three
Step.Detailed process is as follows：
Step 21：Graphic software platform, by being assisted between brain wave acquisition subsystem and brain electricity analytical system by serial ports transparent transmission
View carries out data interaction, and brain electricity analytical subsystem obtains data by reading serial ports buffer area first, and data pass through protocol analysis
The feature of the computer numeral signal of each lead is obtained, the brain electricity data signal progress time domain waveform of four leads is shown, used
Family can manually adjust the height of shown waveform.After brain wave patterns stabilization, it can just start formal brain
Electricity pays attention to force estimation.
Step 22：Analysis gained brain electricity data signal is identified using SVM more classification and identification algorithms, obtains and transmits
Disperse the classification results of grade as the driving condition residing for driver, obtain current notice grade and to notice grade
Realtime graphic is carried out to show.
In this algorithm, first to the single lead signals in brain electricity data signal, the work(of each ripple of wavelet decomposition acquisition is utilized
Rate and the feature extraction for calculating proportion, i.e. algorithm of each ripple in general power, for single lead signals, first with small wavelength-division
Solution, θ ripples, the power of β ripples and α ripples are obtained, θ ripples and proportion of the β ripples in general power is then calculated, is designated as R1, R2.
Then, characteristic parameter is determined according to the difference of specific gravity between the different lead signals of acquisition, and it is more as SVM
The input vector of classification and identification algorithm；It it is one group i.e. by FP1 and T3 points, remaining FP2 and T4 points is one group.Obtain FP1 with
And T3 power proportion FP1R1, FP1R2, T3R1, T3R2, obtain characteristic parameter E1=FP1R1/T3R2, E2=FP1R2/T3R1.
Characteristic parameter E3, E4 are similarly tried to achieve to another group.By this input vector of four power features values as SVM, for notice
Classification.
Secondly, the more classification and identification algorithms of SVM are established, more Classification and Identifications of algorithm, it is by the brain electricity numeral of input that it, which is acted on,
Signal is converted into notice grade label.The specific implementation of algorithm uses SVM multi-classification algorithms, and algorithm first passes through three samples
This study, just there is the function of identification.The target of study is in order to generate a discriminant function, by the sample in test set
Correctly classification as far as possible.
Kernel function of this algorithm picks RBF kernel functions as the algorithm, to the spy as low-dimensional sample space input vector
Sign Parameter Switch obtains the inner product value of high-dimensional feature space, and is worth to according to the inner product of gained high-dimensional feature space linear
Classification plane simultaneously carries out Classification and Identification, obtains the driving condition residing for driver and disperses grade.
The present invention, it is necessary to using kernel function by the input value of low-dimensional sample space, calculates higher-dimension using non-linear SVM algorithm
The inner product value of feature space.Different SVM kernel functions are used from identification process, are also had an impact to the result of identification.
The present invention have selected RBF kernel functions, shown in equation below：
The discriminant function finally given is：
SVM classifier construction SVM multi-classification algorithms are recycled, using the multicategory classification in LIBSVM, i.e., one-to-one method,
One-versus-one, abbreviation OVO SVMs.
Notice grade is divided into three classes, notice concentrates (A classes), and notice scatter light (B classes) and notice are serious
Scattered (C classes).In training, A, B are selected；A,C；B,C；Corresponding vector obtains three training results as training set.
Start to test again, Unknown worm vector is carried out to different tests three times respectively, one group of result is finally obtained using ballot form.
Than if any unknown vector X：
(A, B) classification is carried out, if A wins, A+1, otherwise B+1；
(A, C) classification is carried out, if A wins, A+1, otherwise C+1；
(B, C) classification is carried out, if B wins, B+1, otherwise C+1；
Final result is Max (A, B, C), and this method is no doubt good, but when classification is more, MODEL individual position is N* (N-
1)/2, cost is larger.And invent and there was only three classifications, just suitable for OVO SBMs.
According to above-mentioned a certain training process so that for single discriminant function, obtained result is 0 or 1.And for more points
Class algorithm, then by the superposition of category result, to determine notice classification.Because the result of svm classifier can only obtain 0 and 1,
If only two kinds of the notice classification in the system, is concentrated with not concentrating, the training with regard to only needing two class training sets of progress,
Can is concentrated or not concentrated to classifying for Unknown worm vector.And it is that there are 3 kinds of classification to tie in the present invention
Fruit, A class B classes and C classes.By the mutual combination of two of 3 classes, 3 training sets, i.e. 3 discriminant functions are obtained.One Unknown worm to
Amount obtains result, it is necessary to by 3 judgements further according to ballot.After training, by the characteristic parameter of brain electricity data signal
Classification and Identification is carried out as input, you can determines that the driving condition residing for driver disperses grade and has three class results, notice collection
In, notice scatter light and notice seriously disperse.
Step 23：It is wirelessly transferred, the step is that the driving condition residing for driver is disperseed into grade to be transferred to driving early warning
Subsystem.Transmitting terminal is bluetooth host, using one-to-many sending mode so that intelligent early-warning bracelet and onboard system obtain simultaneously
Obtain notice grade.Bluetooth communication modules use CC2540 as master chip, embed Bluetooth4.0 agreements, can directly with
Mobile communication.
In the present embodiment, brain electricity analytical subsystem has EEG Processing, graphic software platform, classification and identification algorithm, pre-
Several parts such as alert assessment form, the signal processing algorithm efficiency high in system, small volume, graphic interface simple and beautiful, operation
It is convenient, wherein to have that discrimination is high, recognition time is short, required learning data amount is smaller etc. excellent for embedded intelligent classification algorithm
Point.
The effect of brain electricity Digital Signal Processing is to obtain the data of required EEG signals and suppress Hz noise
And noise.Because brain electricity digital signal strength is that microvolt rank is extremely faint, and be highly prone to 50Hz industrial-frequency alternating current and
The influence of below 0.5Hz polarization signal.In order to ensure the accuracy of result, brain electricity data signal is pre-processed first,
Using the 1-30Hz frequency ranges of FIR digital filters extraction EEG signals, and check baseline drifts about.
During graphic software platform, analyzing subsystem can update the time domain waveform of EEG signals in real time, and pass through frequency domain
The means such as conversion and wavelet decomposition, clearly reflect spectrogram and energy spectrum of brain electricity etc..Most current human pilot at last
Notice intensity, it is clear by way of STEM figures and intuitively show.
Analyzing subsystem also has classification and identification algorithm, and specific EEG signals are converted to the different brackets of notice.
By machine learning, constantly improve recognizer, the stability and accuracy of identification will be improved.Finally tied further according to classification
Fruit, the driving condition residing for driver is disperseed into grade driving early warning was sent to by radio transmission apparatus in real time every three seconds
Subsystem.
Step 3, using drive early warning sub-device carry out early warning, it includes intelligent early-warning bracelet and vehicle mounted surveillance device, driven
The feedback fraction that early warning sub-device is system is sailed, the current driving condition of driver is prompted by the subsystem.
Wherein, the intelligent early-warning bracelet, for the driving condition according to residing for driver in the classification results received
Scattered grade is vibrated or the early warning of indicator lamp control；Specifically, intelligent early-warning bracelet is actively worn by driver, when going out
When existing notice concentrates label, bracelet does not send vibrations, and when there is notice scatter light label, bracelet, which will be sent, to be shaken
And warning light flicker, when there is notice seriously scattered label, bracelet is by continuous vibration and with warning light Chang Liang；
The communication protocol driven between early warning subsystem and brain electricity analytical subsystem is：Vibrate position, check bit, header, report
Tail.Wherein vibration position 0 represents not vibrate；1 represents intermittent control shaking；2 represent sustained vibration.Wherein X represents reserved place.
Step 31：The data receiver of bracelet, bracelet use bluetooth SOC as core component, concrete model CC2540F256,
So that data communication and peripheral hardware are controlled in one, PCB surface product is effectively reduced.
Step 32：As shown in Figure 3, bracelet is reminded, and there are the alarm set of bracelet vibrations to prompt two kinds of shapes with warning light
Formula.For bracelet under normal vibration, rated current is about 100mA.Because electric current is larger, set between core component SOC and peripheral hardware
Drive circuit is put, the circuit employs triode and is combined with metal-oxide-semiconductor, and controller is isolated with load, and has
There are small volume and outputting current steadily.
In system, the vehicle mounted surveillance device, disperse grade for the driving condition residing for driver and shown or language
The early warning control of sound.Specifically, onboard system is located on vehicle mounted surveillance screen, real-time display driver's driving condition, such as accompanying drawing 4
Shown, its display interface user can voluntarily be set as needed.In the present embodiment, the driving shape residing for driver will be shown
State disperses grade, and is parked in the current level status of station location marker using screen dolly.Concentrated when driver is in notice
When, dolly is in green runway in screen；When driver is in notice scatter light state, dolly is in Huang in screen
Color runway and voice reminder；When driver is in notice severe dispersity, dolly is in red runway and language in screen
Sound is reminded.The system can be with the driving condition residing for the current driver of reminding passengers, as driver's distraction state, passenger
Driver can be reminded to maintain vigilance.The part is realized by JAVA language, is carried out digital independent first, is entered by communication protocol
Row data parse.Data after parsing are embodied by the position of dolly, adjust position of the dolly on road to embody
Notice label.
To sum up, system of the invention, the brain electricity data signal gathered and analysis obtains is sent to brain electricity analytical subsystem
Feature extraction is carried out, the driving condition residing for driver is divided into notice using SVM more classification and identification algorithms concentrates, slightly
Classification results are transferred to portable intelligent early warning hand by scattered and serious scattered Three Estate eventually through Radio Transmission Technology
In ring and vehicle mounted surveillance device.When driver is in slight dispersity, bracelet is rendered as vibrating in short-term and light flash,
Vehicle mounted surveillance driver is in scatter light state, to remind driver to keep clear-headed；When driver is in serious dispersity
When, bracelet is rendered as sustained vibration and light Chang Liang, and vehicle mounted surveillance driver is in serious dispersity, to remind driver
It need to have a short interval, should not continue to drive a vehicle.In this, the present invention is truly realized a practical fatigue driving early warning subsystem, and
It judges precision height, and early warning is timely, easy to carry, easily operated, has higher practical value.
Embodiments of the present invention are explained in detail above in conjunction with accompanying drawing, but the present invention is not limited to above-mentioned implementation
Mode, can also be on the premise of present inventive concept not be departed from those of ordinary skill in the art's possessed knowledge
Make a variety of changes.
Claims (9)
- A kind of 1. driver fatigue monitor system based on electroencephalogramsignal signal analyzing, it is characterised in that including：Brain wave acquisition subsystem, brain electric analoging signal is obtained for gathering, and brain electrical analogue is believed according to the sample frequency of setting Number pretreatment obtain and transmission brain electricity data signal；Brain electricity analytical subsystem, for carrying out feature extraction and analysis to the brain electricity data signal of reception, and will analysis gained brain Electric data signal carries out time domain waveform and shown；Analysis gained brain electricity data signal is known using SVM more classification and identification algorithms , the classification results for being disperseed grade by the driving condition residing for driver and being formed are not obtained and transmit；Drive early warning sub-device, including intelligent early-warning bracelet and vehicle mounted surveillance device；The intelligent early-warning bracelet, for according to institute Driving condition in the classification results of reception residing for driver disperses grade and carries out early warning control；The vehicle mounted surveillance device, use Disperse grade in the driving condition according to residing for driver in the classification results received and carry out early warning control.
- 2. the driver fatigue monitor system based on electroencephalogramsignal signal analyzing according to claim 1, it is characterised in that：The brain electricity Acquisition subsystem includes capture setting in the brain electric analoging signal of the collection point of diverse location.
- 3. the driver fatigue monitor system based on electroencephalogramsignal signal analyzing according to claim 1, it is characterised in that：The brain electricity Acquisition subsystem is arranged on headgear.
- 4. the driver fatigue monitor system based on electroencephalogramsignal signal analyzing according to claim 1, it is characterised in that：The brain electricity Acquisition subsystem includes overvoltage protection and passive HF filtering process to the pretreatment of brain electric analoging signal.
- 5. the driver fatigue monitor system based on electroencephalogramsignal signal analyzing according to claim 1, it is characterised in that：The brain electricity Acquisition subsystem uses Bluetooth transmission mode by brain electricity digital data transmission.
- 6. the driver fatigue monitor system based on electroencephalogramsignal signal analyzing according to claim 1, it is characterised in that：The brain electricity Brain electricity data signal is identified using SVM more classification and identification algorithms for analyzing subsystem, is specifically included：Wavelet decomposition is carried out to the single lead signals in brain electricity data signal, the power of each ripple is obtained and calculates each ripple in total work Proportion in rate；Characteristic parameter is determined according to the difference of specific gravity between the different lead signals of acquisition, and as more points of SVM The input vector of class recognizer；Establish the more classification and identification algorithms of SVM and choose kernel function of the RBF kernel functions as the algorithm, to as low-dimensional sample space The characteristic parameter of input vector is converted to the inner product value of high-dimensional feature space, and the inner product value according to gained high-dimensional feature space Obtain linear classification plane and carry out Classification and Identification, obtain the driving condition residing for driver and disperse grade.
- 7. the driver fatigue monitor system based on electroencephalogramsignal signal analyzing according to claim 1, it is characterised in that：The brain electricity Driving condition obtained by analyzing subsystem residing for driver, which disperses grade, includes three scattered grades.
- 8. the driver fatigue monitor system based on electroencephalogramsignal signal analyzing according to claim 1, it is characterised in that：The intelligence Early warning bracelet carries out early warning using vibration or indicator lamp mode.
- 9. the driver fatigue monitor system based on electroencephalogramsignal signal analyzing according to claim 1, it is characterised in that：It is described vehicle-mounted Monitoring arrangement carries out early warning using display or voice mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710722181.2A CN107595306A (en) | 2017-08-22 | 2017-08-22 | A kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710722181.2A CN107595306A (en) | 2017-08-22 | 2017-08-22 | A kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107595306A true CN107595306A (en) | 2018-01-19 |
Family
ID=61065285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710722181.2A Pending CN107595306A (en) | 2017-08-22 | 2017-08-22 | A kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107595306A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108903958A (en) * | 2018-05-11 | 2018-11-30 | 南京邮电大学 | Driver attention evaluates early warning system and its implementation method |
| CN110327042A (en) * | 2019-07-17 | 2019-10-15 | 唐延智 | A kind of brain states monitoring device and its control method |
| CN110384478A (en) * | 2018-04-18 | 2019-10-29 | 丰田自动车株式会社 | Status predication device and trend prediction method |
| CN110464371A (en) * | 2019-08-29 | 2019-11-19 | 苏州中科先进技术研究院有限公司 | Method for detecting fatigue driving and system based on machine learning |
| CN110772249A (en) * | 2019-11-25 | 2020-02-11 | 华南脑控(广东)智能科技有限公司 | Attention feature identification method and application |
| CN111016914A (en) * | 2019-11-22 | 2020-04-17 | 华东交通大学 | Dangerous driving scene identification system based on portable terminal information and identification method thereof |
| CN111329497A (en) * | 2020-02-21 | 2020-06-26 | 华南理工大学 | Wearable fatigue driving monitoring system and method based on forehead electroencephalogram signals |
| CN112493995A (en) * | 2020-11-27 | 2021-03-16 | 燕山大学 | Anesthesia state evaluation system and method suitable for patients of different ages |
| CN114043992A (en) * | 2021-11-12 | 2022-02-15 | 东风柳州汽车有限公司 | Vehicle control method, device, equipment and storage medium |
| CN115782895A (en) * | 2022-12-29 | 2023-03-14 | 北京津发科技股份有限公司 | Intelligent driving assisting method, system and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103111020A (en) * | 2013-02-04 | 2013-05-22 | 东北大学 | System and method for detecting and relieving driving fatigue based on electrical acupoint stimulation |
| CN105869356A (en) * | 2016-06-15 | 2016-08-17 | 上海帝仪科技有限公司 | Railway driver work state evaluation intervening system and method |
| CN106963370A (en) * | 2017-03-27 | 2017-07-21 | 广州视源电子科技股份有限公司 | A kind of electric allowance recognition methods of the brain based on SVMs and device |
-
2017
- 2017-08-22 CN CN201710722181.2A patent/CN107595306A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103111020A (en) * | 2013-02-04 | 2013-05-22 | 东北大学 | System and method for detecting and relieving driving fatigue based on electrical acupoint stimulation |
| CN105869356A (en) * | 2016-06-15 | 2016-08-17 | 上海帝仪科技有限公司 | Railway driver work state evaluation intervening system and method |
| CN106963370A (en) * | 2017-03-27 | 2017-07-21 | 广州视源电子科技股份有限公司 | A kind of electric allowance recognition methods of the brain based on SVMs and device |
Non-Patent Citations (1)
| Title |
|---|
| 薛雷: "考虑驾驶员生物电信号的疲劳驾驶检测方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110384478A (en) * | 2018-04-18 | 2019-10-29 | 丰田自动车株式会社 | Status predication device and trend prediction method |
| CN110384478B (en) * | 2018-04-18 | 2022-04-19 | 丰田自动车株式会社 | State prediction device and state prediction method |
| CN108903958A (en) * | 2018-05-11 | 2018-11-30 | 南京邮电大学 | Driver attention evaluates early warning system and its implementation method |
| CN110327042A (en) * | 2019-07-17 | 2019-10-15 | 唐延智 | A kind of brain states monitoring device and its control method |
| CN110464371A (en) * | 2019-08-29 | 2019-11-19 | 苏州中科先进技术研究院有限公司 | Method for detecting fatigue driving and system based on machine learning |
| CN111016914B (en) * | 2019-11-22 | 2021-04-06 | 华东交通大学 | Dangerous driving scene identification system based on portable terminal information and identification method thereof |
| CN111016914A (en) * | 2019-11-22 | 2020-04-17 | 华东交通大学 | Dangerous driving scene identification system based on portable terminal information and identification method thereof |
| CN110772249A (en) * | 2019-11-25 | 2020-02-11 | 华南脑控(广东)智能科技有限公司 | Attention feature identification method and application |
| CN111329497A (en) * | 2020-02-21 | 2020-06-26 | 华南理工大学 | Wearable fatigue driving monitoring system and method based on forehead electroencephalogram signals |
| CN112493995B (en) * | 2020-11-27 | 2022-03-11 | 燕山大学 | Anesthesia state evaluation system and method suitable for patients of different ages |
| CN112493995A (en) * | 2020-11-27 | 2021-03-16 | 燕山大学 | Anesthesia state evaluation system and method suitable for patients of different ages |
| CN114043992A (en) * | 2021-11-12 | 2022-02-15 | 东风柳州汽车有限公司 | Vehicle control method, device, equipment and storage medium |
| CN115782895A (en) * | 2022-12-29 | 2023-03-14 | 北京津发科技股份有限公司 | Intelligent driving assisting method, system and device |
| CN115782895B (en) * | 2022-12-29 | 2024-02-06 | 北京津发科技股份有限公司 | Intelligent auxiliary driving method, system and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107595306A (en) | A kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing | |
| CN111329497A (en) | Wearable fatigue driving monitoring system and method based on forehead electroencephalogram signals | |
| CN106691443B (en) | Wearable driver fatigue-prevention intelligent monitoring and early warning system based on electroencephalogram | |
| CN105615878A (en) | Fatigue driving electroencephalographic monitoring method | |
| CN105022488B (en) | Wireless BCI input systems based on SSVEP brain electric potentials | |
| CN105595997B (en) | A kind of fatigue driving eeg monitoring method determined based on step fatigue | |
| CN106491104A (en) | Driver status intelligent real time monitoring system and method based on Intelligent worn device | |
| CN102331782B (en) | Automatic vehicle controlling method with multi-mode brain-computer interface | |
| CN108415565A (en) | The machine integrated intelligent control method of unmanned plane brain and technology | |
| CN101976495A (en) | System and method for detecting fatigue driving | |
| Shi et al. | A review on fatigue driving detection | |
| CN103479362A (en) | Motor function rehabilitation monitoring system based on wireless body area network | |
| CN104757954A (en) | Health monitoring and comfort adjusting system and method for vehicle | |
| CN105105773B (en) | A kind of fatigue driving eeg monitoring method compared based on multi-threshold | |
| CN104461007A (en) | Driver-car interactive system assisting driver based on electroencephalograms | |
| CN209220256U (en) | Fatigue driving based on pulse blood oxygen real-time monitoring monitors alarm set | |
| CN102697494A (en) | Wearable electroencephalogram signal collection equipment for high-speed train drivers | |
| CN110716578A (en) | Aircraft control system based on hybrid brain-computer interface and control method thereof | |
| CN203552404U (en) | Driver fatigue monitor system | |
| CN205340145U (en) | Telecontrolled aircraft based on brain wave and muscle electric control | |
| CN108903958A (en) | Driver attention evaluates early warning system and its implementation method | |
| CN205405809U (en) | Driver fatigue detection alarm system based on intelligence wrist -watch | |
| CN202716845U (en) | Equipment and safety belt for monitoring electrocardio | |
| CN114557708A (en) | Device and method for detecting somatosensory stimulation consciousness based on electroencephalogram dual-feature fusion | |
| CN206178667U (en) | Wear -type control system based on brain wave analytic technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180119 |