CN110464371A - Method for detecting fatigue driving and system based on machine learning - Google Patents
Method for detecting fatigue driving and system based on machine learning Download PDFInfo
- Publication number
- CN110464371A CN110464371A CN201910808132.XA CN201910808132A CN110464371A CN 110464371 A CN110464371 A CN 110464371A CN 201910808132 A CN201910808132 A CN 201910808132A CN 110464371 A CN110464371 A CN 110464371A
- Authority
- CN
- China
- Prior art keywords
- eeg
- driving
- eeg signals
- driving condition
- machine learning
- 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
Classifications
-
- 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
- A61B5/168—Evaluating attention deficit, hyperactivity
-
- 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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- 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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Psychology (AREA)
- Developmental Disabilities (AREA)
- Mathematical Physics (AREA)
- Social Psychology (AREA)
- General Physics & Mathematics (AREA)
- Hospice & Palliative Care (AREA)
- Child & Adolescent Psychology (AREA)
- Educational Technology (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Fuzzy Systems (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of method for detecting fatigue driving and system based on machine learning, the described method includes: S1, the eeg data under the different driving conditions of acquisition and the EEG signals for extracting different-waveband, obtain OVO SVMs disaggregated model according to driving condition and EEG signals training;S2, the real-time eeg data for acquiring driver to be detected;EEG signals in S3, extraction eeg data, and pass through the driving condition that OVO SVMs disaggregated model judges driver;S4, the driving condition for exporting driver to be detected.The present invention judges that the driving condition of driver, SVM algorithm ensure that the accuracy of classification results because the uniqueness of its algorithm is without generating overfitting problem using OVO SVMs disaggregated model.
Description
Technical field
The present invention relates to field of artificial intelligence, more particularly to a kind of fatigue driving detection side based on machine learning
Method and system.
Background technique
With the increase of automobile quantity, traffic accident amount caused by fatigue driving is also rising, thus effectively detection with it is pre-
Anti-fatigue-driving has become a serious social concern.Brain wave is some spontaneous rhythmic neural electrical activities, according to
EEG signals can be divided into the signal of five wave bands, i.e. δ wave (1-3Hz), θ wave (4-7Hz), α wave by different frequency ranges
(8-13Hz), β wave (14-30Hz), γ wave (30-50Hz).Studies have shown that people can generate δ wave in a sleep state, sleepy
When can generate θ wave, and the appearance of β wave generally means that brain is more excited.
Hooke flourish (2016) proposes method for detecting fatigue driving and process based on EEG signals in the prior art, is based on
The method for detecting fatigue driving of EEG signals comprising following steps:
S1: EEG signals of the acquisition driver when driving in real time, and it is removed blink artefact processing, obtain EEG brain
Wave signal;
S2: converting the EEG E.E.G of time-domain signal, be transformed into frequency domain, and then acquires each frequency range E.E.G in E.E.G
Energy value, determine degree of fatigue further according to the size of its relative energy;
S3: design BP neural network classifier carries out the characteristic signal of identification degree of fatigue;
S4: the estimation of fatigue exponent and degree of fatigue.
The prior art mainly passes through the degree of fatigue of BP neural network classifier identification vehicle driver, and neural network is divided
The accuracy of class depends on the depth of network, and network is deeper, and accuracy is higher, but deep-neural-network is generally meant that more
Neuron parameter, it is slack-off and generate over-fitting to will lead to the speed of service, takes into account the speed of service (real-time) and accuracy.
Therefore, in view of the above technical problems, it is necessary to provide a kind of method for detecting fatigue driving based on machine learning and
System.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of method for detecting fatigue driving based on machine learning and being
System.
To achieve the goals above, the technical solution that one embodiment of the invention provides is as follows:
A kind of method for detecting fatigue driving based on machine learning, which comprises
S1, the eeg data under the different driving conditions of acquisition and the EEG signals for extracting different-waveband, according to driving condition
OVO SVMs disaggregated model is obtained with EEG signals training;
S2, the real-time eeg data for acquiring driver to be detected;
EEG signals in S3, extraction eeg data, and pass through the driving shape that OVO SVMs disaggregated model judges driver
State;
S4, the driving condition for exporting driver to be detected.
As a further improvement of the present invention, the driving condition includes low excited, normal, sleepy, four kinds of states of sleep.
As a further improvement of the present invention, the EEG signals include δ wave, θ wave, α wave, β wave, γ wave.
As a further improvement of the present invention, the OVO SVMs disaggregated model includes several between any two classes sample
SVM classifier.
As a further improvement of the present invention, the OVO SVMs disaggregated model includes excited-normal, excited-sleepy, emerging
It puts forth energy-sleeps, normal-sleepy, normal-sleep, sleepy-corresponding six SVM classifiers of six groups of training set datas of sleep.
As a further improvement of the present invention, OVO SVMs disaggregated model judges the driving shape of driver in the step S3
State specifically:
Initialize driving condition;
EEG signals are substituted into each SVM classifier, SVM classifier throws the corresponding driving condition of EEG signals
Ticket;
Choose classification results of the highest driving condition as EEG signals of voting.
As a further improvement of the present invention, in the step S1 or step S3, the extraction of EEG signals specifically:
After acquiring eeg data, eeg data is analyzed using signal Fourier transformation method, first believes time domain
Number switch to frequency-region signal, a variety of EEG signals are then extracted according to the frequency distribution feature of different-waveband EEG signals respectively.
As a further improvement of the present invention, in the step S1 or step S3, the extraction of EEG signals specifically:
After acquiring eeg data, eeg data is analyzed using signal small wave converting method, first eeg data
Multi-resolution decomposition is carried out, interference signal is eliminated on several scales, then according to the frequency band of different-waveband EEG signals
Distribution characteristics extracts Ambulatory EEG signal.
As a further improvement of the present invention, the step S4 further include:
If it is detected that the driving condition of driver is default driving condition, alarm.
Another embodiment of the present invention provides technical solution it is as follows:
A kind of fatigue driving detecting system based on machine learning, the system comprises:
Preprocessing module, for acquiring the eeg data under different driving conditions and extracting the EEG signals of different-waveband,
OVO SVMs disaggregated model is obtained according to driving condition and EEG signals training;
Signal acquisition module, for acquiring the real-time eeg data of driver to be detected;
Signal processing module judges for extracting the EEG signals in eeg data, and by OVO SVMs disaggregated model
The driving condition of driver;
Display module is exported, for exporting the driving condition of driver to be detected.
The beneficial effects of the present invention are:
The present invention judges the driving condition of driver, uniqueness of the SVM algorithm because of its algorithm using OVO SVMs disaggregated model
Property ensure that the accuracy of classification results without generating overfitting problem;
Compared to deep-neural-network, the speed of service of SVM algorithm is very fast, is advantageously implemented the real-time inspection of fatigue driving
It surveys.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in invention, for those of ordinary skill in the art, without creative efforts,
It is also possible to obtain other drawings based on these drawings.
Fig. 1 is that the present invention is based on the flow diagrams of the method for detecting fatigue driving of machine learning;
Fig. 2 is that the present invention is based on the module diagrams of the fatigue driving detecting system of machine learning.
Specific embodiment
Technical solution in order to enable those skilled in the art to better understand the present invention, below in conjunction with of the invention real
The attached drawing in example is applied, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described implementation
Example is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without making creative work, all should belong to protection of the present invention
Range.
Join shown in Fig. 1, the invention discloses a kind of method for detecting fatigue driving based on machine learning, comprising:
S1, the eeg data under the different driving conditions of acquisition and the EEG signals for extracting different-waveband, according to driving condition
OVO SVMs disaggregated model is obtained with EEG signals training;
S2, the real-time eeg data for acquiring driver to be detected;
EEG signals in S3, extraction eeg data, and pass through the driving shape that OVO SVMs disaggregated model judges driver
State;
S4, the driving condition for exporting driver to be detected.
Join shown in Fig. 2, the invention also discloses a kind of fatigue driving detecting systems based on machine learning, comprising:
Preprocessing module 10, for acquiring the eeg data under different driving conditions and extracting the brain telecommunications of different-waveband
Number, OVO SVMs disaggregated model is obtained according to driving condition and EEG signals training;
Signal acquisition module 20, for acquiring the real-time eeg data of driver to be detected;
Signal processing module 30 is sentenced for extracting the EEG signals in eeg data, and by OVO SVMs disaggregated model
The driving condition of disconnected driver;
Display module 40 is exported, for exporting the driving condition of driver to be detected.
Below in conjunction with specific embodiment in the present invention based on machine learning method for detecting fatigue driving and system carry out
It is discussed in detail.
In a specific embodiment of the invention, the method for detecting fatigue driving based on machine learning includes pretreatment, letter
Number acquisition, signal processing and output display four steps.
Pretreatment:
The main training for realizing machine learning classification model;First through experiment acquisition subject under different driving conditions
The real-time eeg data of (excited, normal, sleepy, in sleep four state), then extracts EEG signals using wavelet transformation respectively
(including δ wave, θ wave, α wave, β wave, γ wave signal), and corresponding data label is stamped for it, finally by tagged brain electricity
Data are passed to OVO SVMs disaggregated model, carry out model training, and save the model finally trained.
Eeg data refers to brain wave (EEG) signal that brain wave acquisition equipment is directly obtained, it records brain activity
When electric wave variation, be overall reflection of the bioelectrical activity in cerebral cortex or scalp surface of cranial nerve cell.
After obtaining eeg data, the methods of signal Fourier transformation, wavelet transformation can be used, eeg data is divided
Analysis, and extract different EEG signals (δ wave, θ wave etc.).
Time-domain signal is switched to frequency-region signal first by Fourier transformation, then according to the frequency of different-waveband EEG signals point
Cloth feature extracts a variety of EEG signals respectively;
Eeg data is carried out multi-resolution decomposition first by wavelet transformation on it, is carried out on certain scales to interference signal
It eliminates, then according to the frequency band distribution feature extraction Ambulatory EEG signal of different-waveband EEG signals.
OVO SVMs is a kind of more classification methods based on SVM, and way is that one is designed between any two classes sample
SVM classifier, when classifying to a unknown sample, last who gets the most votes's classification is the classification of the unknown sample.
Assuming that there is tetra- class of A, B, C, D, I selects (A, B) when training;(A, C);(A, D);(B, C);(B, D);(C,
D the data corresponding to) obtain six classifiers as training set.
It sleeps as OVO SVMs disaggregated model includes excited in the present embodiment-normal, excitement-sleepy, excited-, is normal-tired
Tired, normal-sleep, sleepy-corresponding six SVM classifiers of six groups of training set datas of sleep.
Signal acquisition:
It mainly realizes the acquisition of eeg data, acquires the real-time brain of driver in the present embodiment in real time with brain wave acquisition equipment
Electric data.
Present invention eeg data collected is also possible to a certain region of brain either entire corticocerebral data
Data (such as prefrontal cortex).
Signal processing:
The main processing for realizing eeg data;EEG signals (δ wave, θ wave, α are extracted from collected real-time eeg data
Wave, β wave, γ wave signal), these data are then passed to OVO SVMs disaggregated model, the model parameter that combined training obtains is sentenced
The driving condition (excited, normal, sleepy, sleep) of disconnected driver, and export judging result.
When detection, corresponding data respectively test six classifiers, then take ballot form, most
After obtain one group of result.
Ballot is such that
A=B=C=D=0 is initialized, sample is substituted into respectively:
(A, B) SVM classifier, if classification results are A, A=A+1;Otherwise, B=B+1;
(A, C) SVM classifier, if classification results are A, A=A+1;Otherwise, C=C+1;
……
(C, D) SVM classifier, if classification results are C, C=C+1;Otherwise, D=D+1;
Finally, selecting the classification to score the most points in A, B, C, D as the classification results of the sample.
As in the present embodiment, OVO SVMs disaggregated model judges the driving condition of driver specifically:
Initialize driving condition (excited, normal, sleepy, sleep);
EEG signals are substituted into each SVM classifier, SVM classifier throws the corresponding driving condition of EEG signals
Ticket;
Choose classification results of the highest driving condition as EEG signals of voting.
The method that EEG signals are extracted from collected real-time eeg data is similar with the method in pre-treatment step, can
To use the methods of signal Fourier transformation, wavelet transformation, no longer repeated herein.
Output display:
The judging result of OVO SVMs disaggregated model is shown in equipment, output is respectively excited, normal, sleepy, sleeps
Four kinds of states of sleeping can start alarm if driver is in sleepy or sleep state immediately.
It should be understood that driving condition is divided into excited, normal, sleepy, four classifications of sleep in the present embodiment, at it
It can also be corresponded in his embodiment and increase or decrease classification.
As can be seen from the above technical solutions, the invention has the following beneficial effects:
The present invention judges the driving condition of driver, uniqueness of the SVM algorithm because of its algorithm using OVO SVMs disaggregated model
Property ensure that the accuracy of classification results without generating overfitting problem;
Compared to deep-neural-network, the speed of service of SVM algorithm is very fast, is advantageously implemented the real-time inspection of fatigue driving
It surveys.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (10)
1. a kind of method for detecting fatigue driving based on machine learning, which is characterized in that the described method includes:
S1, the eeg data under the different driving conditions of acquisition and the EEG signals for extracting different-waveband, according to driving condition and brain
Electric signal training obtains OVO SVMs disaggregated model;
S2, the real-time eeg data for acquiring driver to be detected;
EEG signals in S3, extraction eeg data, and pass through the driving condition that OVO SVMs disaggregated model judges driver;
S4, the driving condition for exporting driver to be detected.
2. the method for detecting fatigue driving according to claim 1 based on machine learning, which is characterized in that the driving shape
State includes low excited, normal, sleepy, four kinds of states of sleep.
3. the method for detecting fatigue driving according to claim 1 based on machine learning, which is characterized in that the brain telecommunications
Number include δ wave, θ wave, α wave, β wave, γ wave.
4. the method for detecting fatigue driving according to claim 1 based on machine learning, which is characterized in that the OVO
SVMs disaggregated model includes several SVM classifiers between any two classes sample.
5. the method for detecting fatigue driving according to claim 2 based on machine learning, which is characterized in that the OVO
SVMs disaggregated model includes excited-normal, excited-sleepy, excited-sleep, normal-sleepy, normal-sleep, sleepy-sleep six
Corresponding six SVM classifiers of group training set data.
6. the method for detecting fatigue driving according to claim 4 or 5 based on machine learning, which is characterized in that the step
OVO SVMs disaggregated model judges the driving condition of driver in rapid S3 specifically:
Initialize driving condition;
EEG signals are substituted into each SVM classifier, SVM classifier votes to the corresponding driving condition of EEG signals;
Choose classification results of the highest driving condition as EEG signals of voting.
7. the method for detecting fatigue driving according to claim 1 based on machine learning, which is characterized in that the step S1
Or in step S3, the extraction of EEG signals specifically:
After acquiring eeg data, eeg data is analyzed using signal Fourier transformation method, first turns time-domain signal
For frequency-region signal, a variety of EEG signals are then extracted according to the frequency distribution feature of different-waveband EEG signals respectively.
8. the method for detecting fatigue driving according to claim 1 based on machine learning, which is characterized in that the step S1
Or in step S3, the extraction of EEG signals specifically:
After acquiring eeg data, eeg data is analyzed using signal small wave converting method, eeg data is carried out first
Multi-resolution decomposition eliminates interference signal on several scales, then according to the frequency band distribution of different-waveband EEG signals
Feature extraction Ambulatory EEG signal.
9. the method for detecting fatigue driving according to claim 8 based on machine learning, which is characterized in that the step S4
Further include:
If it is detected that the driving condition of driver is default driving condition, alarm.
10. a kind of fatigue driving detecting system based on machine learning, which is characterized in that the system comprises:
Preprocessing module, for acquiring the eeg data under different driving conditions and extracting the EEG signals of different-waveband, according to
Driving condition and EEG signals training obtain OVO SVMs disaggregated model;
Signal acquisition module, for acquiring the real-time eeg data of driver to be detected;
Signal processing module drives for extracting the EEG signals in eeg data, and by the judgement of OVO SVMs disaggregated model
The driving condition of member;
Display module is exported, for exporting the driving condition of driver to be detected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910808132.XA CN110464371A (en) | 2019-08-29 | 2019-08-29 | Method for detecting fatigue driving and system based on machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910808132.XA CN110464371A (en) | 2019-08-29 | 2019-08-29 | Method for detecting fatigue driving and system based on machine learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110464371A true CN110464371A (en) | 2019-11-19 |
Family
ID=68514005
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910808132.XA Pending CN110464371A (en) | 2019-08-29 | 2019-08-29 | Method for detecting fatigue driving and system based on machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110464371A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112016504A (en) * | 2020-09-06 | 2020-12-01 | 天津大学 | Fatigue driving electroencephalogram signal regression analysis method based on ensemble learning |
CN114504329A (en) * | 2022-01-30 | 2022-05-17 | 天津大学 | Human brain fatigue state autonomous identification system based on 40-lead electroencephalogram acquisition equipment |
CN116746931A (en) * | 2023-06-15 | 2023-09-15 | 中南大学 | Incremental driver bad state detection method based on brain electricity |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102009022637A1 (en) * | 2009-05-26 | 2010-12-02 | Volkswagen Ag | Method for controlling headlight of motor vehicle, involves adjusting additional operating modes for controlling lighting device such that lighting device is partially operated with low luminous intensity |
CN102119857A (en) * | 2011-02-15 | 2011-07-13 | 陕西师范大学 | Electric detecting system and method for fatigue driving brain on basis of matching pursuit algorithm |
CN102274032A (en) * | 2011-05-10 | 2011-12-14 | 北京师范大学 | Driver fatigue detection system based on electroencephalographic (EEG) signals |
CN104952210A (en) * | 2015-05-15 | 2015-09-30 | 南京邮电大学 | Fatigue driving state detecting system and method based on decision-making level data integration |
CN105726046A (en) * | 2016-01-29 | 2016-07-06 | 西南交通大学 | Method for detecting vigilance state of driver |
CN107095671A (en) * | 2017-05-27 | 2017-08-29 | 西南交通大学 | Driving fatigue recognition methods and system |
CN107451651A (en) * | 2017-07-28 | 2017-12-08 | 杭州电子科技大学 | A kind of driving fatigue detection method of the H ELM based on particle group optimizing |
CN107595306A (en) * | 2017-08-22 | 2018-01-19 | 南京邮电大学 | A kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing |
US20180186234A1 (en) * | 2017-01-03 | 2018-07-05 | General Electric Company | Control system and method |
CN108464839A (en) * | 2018-03-22 | 2018-08-31 | 东华大学 | A kind of vehicle-mounted fatigue monitoring and early warning of driving system based on machine learning |
CN109480871A (en) * | 2018-10-30 | 2019-03-19 | 北京机械设备研究所 | A kind of fatigue detection method towards RSVP brain-computer interface |
CN109820525A (en) * | 2019-01-23 | 2019-05-31 | 五邑大学 | A kind of driving fatigue recognition methods based on CNN-LSTM deep learning model |
-
2019
- 2019-08-29 CN CN201910808132.XA patent/CN110464371A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102009022637A1 (en) * | 2009-05-26 | 2010-12-02 | Volkswagen Ag | Method for controlling headlight of motor vehicle, involves adjusting additional operating modes for controlling lighting device such that lighting device is partially operated with low luminous intensity |
CN102119857A (en) * | 2011-02-15 | 2011-07-13 | 陕西师范大学 | Electric detecting system and method for fatigue driving brain on basis of matching pursuit algorithm |
CN102274032A (en) * | 2011-05-10 | 2011-12-14 | 北京师范大学 | Driver fatigue detection system based on electroencephalographic (EEG) signals |
CN104952210A (en) * | 2015-05-15 | 2015-09-30 | 南京邮电大学 | Fatigue driving state detecting system and method based on decision-making level data integration |
CN105726046A (en) * | 2016-01-29 | 2016-07-06 | 西南交通大学 | Method for detecting vigilance state of driver |
US20180186234A1 (en) * | 2017-01-03 | 2018-07-05 | General Electric Company | Control system and method |
CN107095671A (en) * | 2017-05-27 | 2017-08-29 | 西南交通大学 | Driving fatigue recognition methods and system |
CN107451651A (en) * | 2017-07-28 | 2017-12-08 | 杭州电子科技大学 | A kind of driving fatigue detection method of the H ELM based on particle group optimizing |
CN107595306A (en) * | 2017-08-22 | 2018-01-19 | 南京邮电大学 | A kind of driver fatigue monitor system based on electroencephalogramsignal signal analyzing |
CN108464839A (en) * | 2018-03-22 | 2018-08-31 | 东华大学 | A kind of vehicle-mounted fatigue monitoring and early warning of driving system based on machine learning |
CN109480871A (en) * | 2018-10-30 | 2019-03-19 | 北京机械设备研究所 | A kind of fatigue detection method towards RSVP brain-computer interface |
CN109820525A (en) * | 2019-01-23 | 2019-05-31 | 五邑大学 | A kind of driving fatigue recognition methods based on CNN-LSTM deep learning model |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112016504A (en) * | 2020-09-06 | 2020-12-01 | 天津大学 | Fatigue driving electroencephalogram signal regression analysis method based on ensemble learning |
CN112016504B (en) * | 2020-09-06 | 2022-06-03 | 天津大学 | Fatigue driving electroencephalogram signal regression analysis method based on ensemble learning |
CN114504329A (en) * | 2022-01-30 | 2022-05-17 | 天津大学 | Human brain fatigue state autonomous identification system based on 40-lead electroencephalogram acquisition equipment |
CN114504329B (en) * | 2022-01-30 | 2023-09-22 | 天津大学 | Human brain fatigue state autonomous identification system based on 40-lead electroencephalogram acquisition equipment |
CN116746931A (en) * | 2023-06-15 | 2023-09-15 | 中南大学 | Incremental driver bad state detection method based on brain electricity |
CN116746931B (en) * | 2023-06-15 | 2024-03-19 | 中南大学 | Incremental driver bad state detection method based on brain electricity |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111329474B (en) | Electroencephalogram identity recognition method and system based on deep learning and information updating method | |
CN102499677B (en) | Emotional state identification method based on electroencephalogram nonlinear features | |
CN110464371A (en) | Method for detecting fatigue driving and system based on machine learning | |
CN104503580B (en) | A kind of recognition methods to Steady State Visual Evoked Potential brain-computer interface target | |
CN107007278A (en) | Sleep mode automatically based on multi-parameter Fusion Features method by stages | |
CN102200833B (en) | Speller brain-computer interface (SCI) system and control method thereof | |
CN104461007B (en) | A kind of driver assistance people's car mutual system based on EEG signals | |
Zou et al. | Constructing multi-scale entropy based on the empirical mode decomposition (EMD) and its application in recognizing driving fatigue | |
CN109512442A (en) | A kind of EEG fatigue state classification method based on LightGBM | |
CN102499676A (en) | Effective time sequence and electrode recombination based electroencephalograph signal categorizing system and method | |
Yger | A review of kernels on covariance matrices for BCI applications | |
CN103019383A (en) | Steady state visual evoked potential brain-computer interface signal identification method | |
CN106502410A (en) | Improve the transcranial electrical stimulation device of Mental imagery ability and method in brain-computer interface | |
CN110037693A (en) | A kind of mood classification method based on facial expression and EEG | |
Zhou et al. | Vigilance detection method for high‐speed rail using wireless wearable EEG collection technology based on low‐rank matrix decomposition | |
CN110390272A (en) | A kind of EEG signal feature dimension reduction method based on weighted principal component analyzing | |
CN109375776A (en) | EEG signals based on multitask RNN model act intension recognizing method | |
Zhao et al. | Deep convolutional neural network for drowsy student state detection | |
CN106963374A (en) | A kind of brain electro-detection method and device based on S-transformation and deep belief network | |
CN114081505A (en) | Electroencephalogram signal identification method based on Pearson correlation coefficient and convolutional neural network | |
CN110464368A (en) | Brain attention rate appraisal procedure and system based on machine learning | |
CN111671421A (en) | Electroencephalogram-based children demand sensing method | |
CN105787459B (en) | A kind of ERP Modulation recognition method based on the optimal sparse differentiation of scoring | |
CN114897071A (en) | Identity recognition method and device based on single-channel electroencephalogram | |
Shrivastava et al. | On the potential of EEG for biometrics: Combining power spectral density with a statistical test |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191119 |
|
RJ01 | Rejection of invention patent application after publication |