CN104952210A - Fatigue driving state detecting system and method based on decision-making level data integration - Google Patents
Fatigue driving state detecting system and method based on decision-making level data integration Download PDFInfo
- Publication number
- CN104952210A CN104952210A CN201510249302.7A CN201510249302A CN104952210A CN 104952210 A CN104952210 A CN 104952210A CN 201510249302 A CN201510249302 A CN 201510249302A CN 104952210 A CN104952210 A CN 104952210A
- Authority
- CN
- China
- Prior art keywords
- pulse
- driving state
- driver
- acceleration information
- data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 87
- 230000010354 integration Effects 0.000 title abstract 4
- 230000001133 acceleration Effects 0.000 claims abstract description 103
- 238000001514 detection method Methods 0.000 claims abstract description 46
- 230000033001 locomotion Effects 0.000 claims abstract description 31
- 230000004927 fusion Effects 0.000 claims description 38
- 230000008569 process Effects 0.000 claims description 28
- 230000008859 change Effects 0.000 claims description 22
- 238000009499 grossing Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 8
- 210000002321 radial artery Anatomy 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000009661 fatigue test Methods 0.000 claims description 6
- 210000000707 wrist Anatomy 0.000 claims description 6
- 238000005315 distribution function Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000007717 exclusion Effects 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000013519 translation Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 3
- 230000004044 response Effects 0.000 abstract description 2
- 230000035790 physiological processes and functions Effects 0.000 abstract 1
- 206010016256 fatigue Diseases 0.000 description 66
- 230000006870 function Effects 0.000 description 18
- 239000008280 blood Substances 0.000 description 13
- 210000004369 blood Anatomy 0.000 description 13
- 230000007423 decrease Effects 0.000 description 11
- 210000000709 aorta Anatomy 0.000 description 8
- 230000000737 periodic effect Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 210000001367 artery Anatomy 0.000 description 4
- 230000001174 ascending effect Effects 0.000 description 4
- 230000017531 blood circulation Effects 0.000 description 4
- 230000000747 cardiac effect Effects 0.000 description 4
- 210000005240 left ventricle Anatomy 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000008602 contraction Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000001932 seasonal effect Effects 0.000 description 3
- 238000010009 beating Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 210000003017 ductus arteriosus Anatomy 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 230000010247 heart contraction Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000036581 peripheral resistance Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000007958 sleep Effects 0.000 description 2
- 230000002861 ventricular Effects 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 229940109239 creatinine Drugs 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003205 diastolic effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000001361 intraarterial administration Methods 0.000 description 1
- 238000007914 intraventricular administration Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- ZRHANBBTXQZFSP-UHFFFAOYSA-M potassium;4-amino-3,5,6-trichloropyridine-2-carboxylate Chemical compound [K+].NC1=C(Cl)C(Cl)=NC(C([O-])=O)=C1Cl ZRHANBBTXQZFSP-UHFFFAOYSA-M 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009329 sexual behaviour Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
Landscapes
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a fatigue driving state detecting system and method based on decision-making level data integration. The fatigue driving state detecting system firstly uses an acceleration sensor to acquire motion acceleration of a steering wheel, judges motion states of the steering wheel based on dynamic acceleration threshold values, and primarily judges fatigue driving states of a driver based on 4s immobility theory. Detecting error tolerance is improved by setting errors of the steering wheel turning from left to right. Pulse time domain values of the driver can be acquired via a pulse sensor, and physiological states of the driver can be detected based on dynamic pulse threshold values. Integrated detecting results can be obtained by integrating two kinds of detecting results in decision making level. By the fatigue driving state detecting method based on decision-making level data integration, a fatigue driving state detecting prototype system is constructed. Compared with existing methods, the fatigue driving state detecting method based on decision-making level data integration has certain advantages in detection accuracy and perfect performance in response time, time complexity, memory occupation and the like of algorithms.
Description
Technical field
The present invention relates to driving condition detection method, particularly relate to a kind of fatigue driving state detection method, belong to the interleaving techniques application of mobile computing, sensing technology and data fusion.
Background technology
Fatigue driving (fatigue driving) refers generally to driver and cause the situation that its manipulation ability is not normal, serious harm traffic safety because tired change appears in health mechanism in startup procedure, has become the serious problems that the whole world faces.The report display of National Highway Traffic safety management office, the traffic hazard brought out because of driver tired driving account for the 20%-30% of traffic hazard sum.Such as, during 26 days 2 August in 2012 about 31 points, driver Chen drives night coach, knocks into the back with heavy pot type semi-trailer train, causes 36 people in motor bus to die instantly; According to vehicle-bone global positioning system (Global Position System, GPS) record, the continuous driving time of motor bus driver Chen reaches 4 hours 22 points, do not stop rest in midway, when fatigue driving causes driving, energy is not concentrated, and reaction and judgement decline, cause accident to occur.
Detect driver tired driving state efficiently and carry out in time feeding back the generation that effectively can prevent similar traffic hazard.The blood sugar of driver under fatigue driving state, plasma wrea and creatinine can be analyzed by the blood gathering driver, this a few category information of comprehensive analysis obtain one whether tired about driver, the method has higher Detection accuracy, experimental result can as the reference of additive method, but real-time is not good, and need the Medical Devices of specialty.At present, research and technician after deliberation and develop a series of achievement in research and product, are mainly divided three classes: the first kind is the detection technique based on physiological signal, mainly based on the change etc. of brain wave, heart rate, pulse and skin voltage; Equations of The Second Kind is based on driver's body physical state, mainly based on the inclined degree of head, the change of eye, the change of face and the dynamics etc. gripping bearing circle; The third is based on travel condition of vehicle, mainly based on the running orbit etc. of the characteristics of motion of bearing circle, the travel speed of vehicle, the acceleration of vehicle and vehicle.
At present, there is researchist to devise wearable electroencephalogram (Electroencephalograph, an EEG) detection system, the vigilant degree of driver to self driving behavior can be detected in real time, thus reflect the fatigue conditions of driver; Also have researchist under driver sleeps bereft situation, to gather cardiogram (Electrocardiogram, the ECG) data of driver, comprehensive heart rate and frequency of wink two indices, analyze the fatigue driving state of driver; Also having researchist by analyzing the EEG data of driver, obtaining the change information of driver in each frequency energy of fatigue stage, obtaining the tired variability in fatigue stage of driver.Also have researchist to propose a kind of mechanism of real-time detection driver tired driving state, utilize the EEG data of driver, ECG data and electromyographic signal to carry out the fatigue driving state of comprehensive descision driver; Also has researchist based on the principal component analysis (PCA) analysis design mothod sample of core; select suitable kernel function and correlation parameter effectively can isolate normal sample and tired sample; linear analysis is carried out to the ECG data of driver; obtain the experiment sample of driver's EEG data; analysis design mothod sample belongs to normal or belongs to tired sample, and then detects whether driver is in fatigue driving state.Fatigue state detection method based on EEG and ECG has good real-time and higher Detection accuracy, but hardware cost is higher, and wears not easily.
At present, researchist is also had to analyze based on driver's face behavioural characteristic the fatigue driving state judging driver.As the fatigue driving state of the inclined degree comprehensive descision driver of: comprehensive utilization driver's eyes closure time number percent, degree that face opens and head; By the position of comprehensive utilization frame difference method, template matching method and Kalman's method location human eye, and then location human eye open the state of closing, the fatigue driving state of driver is detected based on eyes closed percentage of time (Percentage of Eyelid Closure, PERCLOS) eigenwert.Driver tired driving condition detection method real-time based on eye behavior is better, and Detection accuracy is higher, but these class methods are confined to the good situation of pilothouse light, cannot be applied to the situation of driving at night, have larger limitation.
The bearing circle pick-up unit SAM of Electronic Safety Products company development and production is a kind of devices that can detect the improper motion of vehicle steering, when bearing circle is when running well, sensor can not give the alarm, but when pilot control bearing circle 4 second is motionless, sensor device will give the alarm remind driver, until bearing circle by driver control get back to ordinary running condition under.The driver tired driving condition detection method that a kind of corner based on bearing circle also having researchist to propose changes, angle displacement sensor and GPS module are embedded on bearing circle, the angle change application pattern recognition theory collected is judged whether driver is in fatigue driving state, judges the transport condition of vehicle simultaneously by GPS module.Researchist is also had to devise a kind of method based on steering wheel angle input driver tired driving state, this algorithm is realized by the mode of the multiple linear regression model setting up rotating of steering wheel signal correction variable and physiological signal, make use of forward direction Sexual behavior mode method establishment regression model, driver can be analyzed by this regression model and whether be in fatigue driving state.These class methods have good real-time, and expense is less, but Detection accuracy is relatively low.
In a word, current achievement in research ubiquity that Detection accuracy is not high, hardware cost is higher, equipment is worn not easily, by defects such as such environmental effects are larger.And the present invention can solve problem above well.
Summary of the invention
The object of the invention is to propose a kind of fatigue driving state detection system based on decision making level data fusion, this system efficiently can detect driver fatigue state easily, first this system gathers the moving acceleration data of bearing circle by acceleration transducer, gather driver's pulse data by pulse transducer; Respectively pre-service is carried out to these two kinds of data, respectively dynamic threshold is calculated to pretreated two kinds of data, obtain the Preliminary detection result whether being in fatigue state about driver; By carrying out decision level fusion to two kinds of testing results, obtain the testing result after merging more accurately.
The present invention solves the technical scheme that its technical matters takes: a kind of fatigue driving state detection system based on decision making level data fusion, described system comprises acceleration information acquisition module, acceleration information transmission and pretreatment module, acceleration information dynamic threshold training module, the algorithm application module of driver tired driving state is detected based on acceleration information, pulse data acquisition module, pulse data stores and pretreatment module, pulse data dynamic threshold training module, the algorithm application module of driver tired driving state is detected based on pulse data, data fusion module etc., the comprehensive utilization acceleration of motion collateral information of bearing circle and the pulse direct information of driver, described system utilizes acceleration information acquisition module to collect recent movement acceleration information based on acceleration transducer, utilizes acceleration information to transmit with pretreatment module the smoothing process of these raw data application methods of moving average, the algorithm application module detecting driver tired driving state based on acceleration information adopts the motionless theory of bearing circle 4s, tentatively judges the testing result of fatigue driving state, meanwhile, pulse data acquisition module is utilized to collect the pulse data in driver process based on pulse transducer, utilize pulse data to store the pulse data that first storage of collected arrives with pretreatment module, the threshold method then based on wavelet transformation removes pulse signal noise, re-uses the method for weighted moving average to the smoothing process of data, utilize the training module analysis of pulse data dynamic threshold and calculate driver pulse frequency change, set up the threshold value of corresponding abnormal driving state for different individualities, detect the algorithm application module of driver tired driving state based on pulse data by judging that whether the current driver's pulse frequency obtained is normal with comparing of this normality threshold, and then judge whether driver is in fatigue driving state, data fusion module carries out decision level fusion, by obtaining based on the fatigue driving state detection algorithm of decision making level data fusion the testing result whether driver is in fatigue driving state to these two kinds of recognition result application evidence theories.
The function of acceleration information acquisition module is: utilize acceleration transducer to gather recent movement acceleration information.
Acceleration information transmission with the function of pretreatment module is: to gathering the smoothing process of the recent movement acceleration raw data application method of weighted moving average with acceleration transducer.
The function of acceleration information dynamic threshold training module is: to the data calculating mean value again through acceleration information transmission and pretreatment module process, obtaining the dynamic threshold of driver at current road segment, then obtaining the waving interval of bearing circle by comparing acceleration information.
The function detecting the algorithm application module of driver tired driving state based on acceleration information is: adopt the motionless theory of bearing circle 4s, tentatively judges the testing result of fatigue driving state.
The function of pulse data acquisition module is: the pulse transducer based on the wrist radial artery place being fixed on human body gathers the pulse data in driver process.
Pulse data stores and with the function of pretreatment module is: the pulse data that storage of collected arrives, and the threshold method then based on wavelet transformation removes pulse signal noise, re-uses the method for weighted moving average to the smoothing process of data.
The function of pulse data dynamic threshold training module is: analyze and calculate driver pulse frequency change, set up the threshold value of corresponding abnormal driving state for different individualities.
The function detecting the algorithm application module of driver tired driving state based on pulse data is: judge that whether the current driver's pulse frequency obtained is normal by comparing with the threshold value of abnormal driving state, and then judge whether driver is in fatigue driving state.
The function of data fusion module is: to detecting the algorithm application module of driver tired driving state based on acceleration information and carrying out decision level fusion, by obtaining based on the fatigue driving state detection algorithm of decision making level data fusion the testing result whether driver is in fatigue driving state based on the recognition result application evidence theory of the algorithm application module of pulse data detection driver tired driving state.
System driver of the present invention is in the process of steering vehicle, and the acceleration of steering wheel for vehicle motion and angle change information are the important informations of the driving condition analyzing driver, indirectly can react the driving condition of driver to a certain extent.On the normal road travelled, if continuous more than 4s is motionless for bearing circle, so driver is probably in fatigue driving state, if but driver travel on straight highway and around vehicle little, at this moment when the continuous 4s of bearing circle is motionless, cannot judge whether driver is in fatigue driving state, therefore the movable information of bearing circle only can reflect the driving condition of driver to a certain extent indirectly.The pulse change of people can demonstrate the physiological statuss such as the fatigue of people, and the pulse change in driver process, the especially change of pulse frequency is the direct reflection to driver state.
System of the present invention is the fatigue driving state detection method based on decision making level data fusion, the comprehensive utilization acceleration of motion collateral information of bearing circle and the pulse direct information of driver, effectively can improve the Detection accuracy of fatigue driving state: utilize acceleration transducer to collect recent movement acceleration information, to the smoothing process of these raw data application methods of weighted moving average, based on the motionless theory of bearing circle 4s, tentatively judge the testing result of fatigue driving state; Simultaneously, pulse transducer is utilized to collect pulse data in driver process, analyze and calculate driver pulse frequency change, the threshold value of corresponding abnormal driving state is set up for different individualities, by judging that whether the current driver's pulse frequency obtained is normal with comparing of this normality threshold, and then can judge whether driver is in fatigue driving state; Decision level fusion is carried out to these two kinds of recognition result application evidence theories, obtains the testing result whether being in fatigue driving state more accurately about driver.
Fatigue driving state detection model of the present invention comprises pulse data acquisition module, pulse data stores and to transmit with pretreatment module, pulse data dynamic threshold training module, the algorithm application module detecting driver tired driving state based on pulse data, acceleration information acquisition module, acceleration information and pretreatment module, acceleration information dynamic threshold training module, to detect the algorithm application module, data fusion module etc. of driver tired driving state based on acceleration information.
1, data acquisition and pre-service
(1) data acquisition
The advantage of recent movement acceleration is that changing features is obvious, the change embodying recent movement that can be real-time, and easily catches.First the present invention gathers the acceleration of motion of bearing circle by acceleration transducer, as judge driver driving condition according to one of.
For the collection of pulse data, pulse transducer is utilized to carry out.Pulse transducer is fixed on the wrist radial artery place of human body, because radial artery is the place that human pulse is the strongest.
(2) data prediction
Acceleration information and pulse data are all seasonal effect in time series data, there is noise in the data collected by sensor.The data ubiquity utilizing sensor to collect error, so need the data collected sensor to carry out basic data smoothing process.The present invention uses the method for weighted moving average to the smoothing process of data.Pulse signal has the feature that signal is weak, frequency is low and noise is strong, and noise may cause pulse signal distortion, can cause larger metrical error, carries out denoising before needing to carry out feature extraction to pulse signal.The pulse signal great majority of human body are distributed in low frequency region, and noise signal is generally evenly distributed in high-frequency region, and the Wavelet Component that amplitude is larger appears at sign mutation region usually.The threshold method that the present invention is based on wavelet transformation removes noise.
2, dynamic threshold training
(1) acceleration dynamic threshold
The present invention detects the method for driver fatigue state based on the motionless theory of bearing circle 4s, and improve on this basis, add the method for dynamic threshold, the change of removing bearing circle and car body angle, on the impact of testing result, judges the state of driver more accurately.
(2) pulse dynamic threshold
The present invention proposes a kind of method detecting driver tired driving state based on dynamic threshold, the degree of fatigue of driver is judged: a period of time that driver has just started to drive generally relatively regains consciousness according to the degree of Variation of Drivers ' Heart Rate cycle decline, detect the pulse data of driver during this period and calculate its corresponding heart rate periodic quantity, using this heart rate periodic quantity as the normal heart rate periodic quantity of driver, after having crossed this section of recovery time continuous detecting driver pulse and analyze the heart rate cycle, with normal heart rate period ratio comparatively, if decline degree has exceeded more than 10%, system judges that driver is in slight fatigue state, decline degree is more than 20%, system judges that driver is in fatigue state.
3, based on the fatigue driving state detection algorithm of decision making level data fusion
The present invention carries out decision level fusion by the driver fatigue testing result based on recent movement acceleration and the driver fatigue testing result based on pulse.
Present invention also offers a kind of based on decision making level data fusion fatigue state recognition method, the method comprises the steps:
Step 1 builds Basic probability assignment function, for acceleration and pulse two evidence bodies, calculates both probability distribution function f respectively, will guarantee to be independent of each other between these two evidence bodies simultaneously, separate.
The rule of combination that step 2 applies evidence theory obtains a new evidence body, this new evidence body is combined out by acceleration and these two evidence bodies of pulse, the basic probability assignment that new evidence body shows, more close to 1, shows the accuracy of proposition judgement higher.
Step 3 application decision rule, obtains the judgement result of decision about fatigue state and exports.
Step 3 of the present invention adopts the decision rule based on probability assignments, is expressed as the decision rule based on probability assignments: for arbitrary set M, if
Meet:
if there is f (S
1)-f (S
2) > θ
1, f (M) < θ
2, f (S
1) > f (M), then S
1the result of decision to event, wherein θ
1and θ
2the threshold value of representative setting.
Beneficial effect:
1, fatigue driving state Detection accuracy of the present invention is higher; Experiment shows that fatigue driving state Detection accuracy of the present invention then reaches 91.67%.
2, system response time of the present invention is short; Driver's indignation driving condition detection system has the delay of about 1s, and major expenses is on pulse data sample and transform.
3, Space-time Complexity of the present invention is low; Time complexity of the present invention is O (n); Installed System Memory consumes, and Installed System Memory consumption is between 50-70M.
Accompanying drawing explanation
Fig. 1 is fatigue driving state detection model figure of the present invention.
Fig. 2 is actual measurement one cycle pulse waveform figure.
Fig. 3 is decision making level data fusion illustraton of model of the present invention.
Fig. 4 is method flow diagram of the present invention.
Embodiment
Below in conjunction with Figure of description, the invention is further detailed.
The present invention is based on the fatigue driving state detection method comprehensive utilization acceleration of motion collateral information of bearing circle and the pulse direct information of driver of decision making level data fusion, effectively can improve the Detection accuracy of fatigue driving state: utilize acceleration transducer to collect recent movement acceleration information, to the smoothing process of these raw data application methods of weighted moving average, based on the motionless theory of bearing circle 4s, tentatively judge the testing result of fatigue driving state; Simultaneously, pulse transducer is utilized to collect pulse data in driver process, analyze and calculate driver pulse frequency change, the threshold value of corresponding abnormal driving state is set up for different individualities, by judging that whether the current driver's pulse frequency obtained is normal with comparing of this normality threshold, and then can judge whether driver is in fatigue driving state; Decision level fusion is carried out to these two kinds of recognition result application evidence theories, obtains the testing result whether being in fatigue driving state more accurately about driver.
As shown in Figure 1, system of the present invention comprises pulse data acquisition module, pulse data stores and to transmit with pretreatment module, pulse data dynamic threshold training module, the algorithm application module detecting driver tired driving state based on pulse data, acceleration information acquisition module, acceleration information and pretreatment module, acceleration information dynamic threshold training module, to detect the algorithm application module, data fusion module etc. of driver tired driving state based on acceleration information.
1, data acquisition and pre-service
(1) data acquisition
The advantage of recent movement acceleration is that changing features is obvious, the change embodying recent movement that can be real-time, and easily catches.First the present invention gathers the acceleration of motion of bearing circle by acceleration transducer, as judge driver driving condition according to one of.
Pulse wave (Pulse Wave) is the pressure wave that blood flow is formed when propagating from sustainer along arterial system, and blood flow to shrink just because of the ventricular cycle of heart and diastole causes aortal contraction and diastole in the propagation of arterial system.When each left ventricular contraction, penetrate blood and enter sustainer, aorta wall is expanded, and when LV Diastolic, aorta wall produces elastical retraction.Pulse is originated in beating of aortic root and propagates successively to each artery of whole body along ductus arteriosus wall.Pulse has reacted the cyclical upturn and downturn of endaortic pressure.With heart contraction and diastole, beating of one one, artery contracting.Under normal circumstances, pulse is consistent with heartbeat, and pulse is strong, and the rhythm and pace of moving things is even, and strong and weak consistent, interval is equal.The blood pumped by heart flows into sustainer, and cause again aortal contraction and diastole, blood flow is propagated from aortic root along arterial system with the form of pressure wave, defines pulse, and heart often shrinks diastole once can produce one-period pulse wave.Oscillogram shown in Fig. 2 is the cycle pulse wave intercepted in the cycle pulse waveform figure of system acquisition.
In fig. 2, horizontal ordinate T represents the time, ordinate P representative pressure value, and the waveform within the time [0, t] is a typical pulse cycle waveform, and t represents the one-period of pulse wave.H1 represents main wave amplitude, the height of main crest top to pulse wave figure baseline, h2 represents wave amplitude before dicrotic pulse, that dicrotic pulse prewave binds and arrives the height of pulse wave figure baseline, h3 represents dicrotic notch amplitude, the height of dicrotic notch the lowest point to pulse wave figure baseline, h4 represents dicrotic wave amplitude, for the height between the baseline parallel lines that dicrotic pulse crest top is done to dicrotic notch the lowest point, t1 represents the duration of pulse wave figure starting point to main wave crest point, the phase of maximum ejection of the corresponding left ventricle of t1, t2 represents the duration between pulse wave figure starting point to dicrotic notch, the systole phase of the corresponding left ventricle of t2, t2-t represents the duration between dicrotic notch to pulse wave figure terminating point during this period of time, the diastole of corresponding left ventricle, duration between the starting point that 0-t represents pulse wave figure to terminating point, t corresponds to a cardiac cycle of left ventricle, corresponding to pulse, also it is the cycle of a pulse.
In Fig. 2, the physiologic meaning of each Feature point correspondence is as follows:
P1 point: represent sustainer opening point, namely begin exit point.Be the minimum point of whole pulse waveform figure, indicate the beginning of heart phase of maximum ejection, the end of term endovascular pressure and volume are shunk in main reflection.
P2 point: aortic pressure peak.Be main ripple herein, be the maximal value of the upcurve of baseline to main crest top of oscillogram, summit reflection Intraarterial pressure and volume, form the ascending branch of main ripple, the fast rapid fire blood of reflection ventricle, angiosthenia rises rapidly, and tube wall is expanded suddenly.Its ascending velocity is mainly relevant with tube wall elasticity with cardiac output, Ve speed, Artery resistance, can represent with ascending branch slope.If cardiac output is more, penetrate blood speed, aorta elasticity reduces, then slope is comparatively large, and wave amplitude is higher; If cardiac output is less, penetrate blood speed comparatively slowly, aorta elasticity is comparatively large, then slope reduces, and wave amplitude is lower.
P4 point: the left heart penetrates blood halt, is tidal wave herein, is also dicrotic wave prewave.Be positioned at the decent of oscillogram, generally delay after main ripple, lower than main ripple, position is higher than dicrotic wave.It stops penetrating blood, asrteriectasia, blood pressure drops at later stage reduced ejection period ventricle, the reverse flow of artery inner blood and the reflection wave that formed, mainly relevant with the pace of change such as peripheral resistance, blood vessel elasticity and descending branch decline rate.
P5 point: dicrotic wave trough is the downward incisura ripple of waveform that main ripple decent and dicrotic wave ascending branch are formed.Its key reaction sustainer static pressure emptying time, is the separation of heart contraction and diastole, is subject to the impact of peripheral resistance and descending branch decline rate.
P6 point: aorta elasticity retraction ripple, i.e. dicrotic wave.Be be positioned at the outstanding small echo of after dicrotic wave trough one, its formation is that ventricle starts diastole after ventricle reduced ejection period, and intraventricular pressure is dropped rapidly to and is starkly lower than aortic pressure, and endaortic blood starts to backflow to ventricle direction.Because backflowing the impact of blood, aorta petal is closed suddenly, and the blood backflowed impinges upon on the aorta petal of suddenly closing and rebounded, and make aortic pressure again slightly increase, ductus arteriosus wall is also slightly expanded thereupon.Therefore, at the stage casing of decent formation one small echo upwards, i.e. dicrotic wave.It can react the function status of aorta petal, blood vessel elasticity and blood flow flow state.
For the collection of pulse data, pulse transducer is utilized to carry out.Pulse transducer is fixed on the wrist radial artery place of human body, because radial artery is the place that human pulse is the strongest, and the convenient pulse data obtaining human body accurately, and wear conveniently.
(2) data prediction
Acceleration information and pulse data are all seasonal effect in time series data, there is noise in the data collected by sensor.The data ubiquity utilizing sensor to collect error, so need the data collected sensor to carry out basic data smoothing process.First system of the present invention utilizes acceleration transducer to gather the acceleration of motion of bearing circle by acceleration information acquisition module, as judge driver driving condition according to one of; Utilize pulse transducer for the collection of pulse data by pulse data acquisition module, pulse transducer is fixed on the wrist radial artery place of human body; Acceleration information transmission stores with pretreatment module and pulse data and all uses the method for weighted moving average to the smoothing process of data with pretreatment module, point weights the closer to smooth window edge are less, the point entering smooth window is all little by little count in mean value, eliminates the impact on overall smoothness gradually:
In formula (1), s
irepresent the smooth value of i-th point; x
i+jrepresentative data point; w
jrepresent weights, comparatively large near middle weights, submarginal weights are less, and weights summation is 1.Obtain better data smoothing treatment effect for simplicity, the present invention selects the method for weighted moving average as the method for acceleration information smoothing processing, as used (1/4,1/2,1/4) as weights, for the recent movement acceleration information collected, adjacent three o'clock as a processing item, result after smoothing processing is updated to middle corresponding data item, and circular treatment, until process data.
Pulse signal has the feature that signal is weak, frequency is low and noise is strong, and the interference of body state and external environment all can produce larger impact to the collection of physiology signal.These noise may cause pulse signal distortion, can cause larger metrical error, carry out denoising before needing to carry out feature extraction to pulse signal.The pulse signal great majority of human body are distributed in low frequency region, and noise signal is generally evenly distributed in high-frequency region, and the Wavelet Component that amplitude is larger appears at sign mutation region usually.The threshold method that the present invention is based on wavelet transformation removes noise.
First, need to carry out wavelet transform to pulse signal.A typical wavelet is:
Suppose
be
fourier transform,
be called wavelet mother function.By to wavelet mother function
translation can obtain discrete wavelet race with flexible:
In formula (3), a is contraction-expansion factor, and b is shift factor.
Suppose that pulse signal is that signal (t), signal (t)=start (t)+noise (t), start (t) represents original pulse signal, noise (t) represents noise.Discrete sampling is carried out to pulse signal: signal (t), t=0,1,2 ..., N-1.
The coefficient of wavelet transformation is:
Through type (4) obtains wavelet coefficient W
signalafter (a, b), process by threshold value, determine the estimated value of wavelet coefficient
guarantee
value minimum, threshold value adopts generic threshold value choosing method:
In formula (5), med represents the intermediate value of high frequency orthogonal wavelet coefficient.
Obtain the estimated value of wavelet coefficient
with wavelet inverse transformation to wavelet reconstruction, obtain estimated signal
it is exactly the pulse signal after denoising.
2, dynamic threshold training
(1) acceleration dynamic threshold
The moving acceleration data of bearing circle is a kind of seasonal effect in time series data stream, the present invention is based on the acceleration of motion of sliding window model research direction dish.Sliding window model is the common model of processing time sequence data stream.The feature of sliding window model is that the data place window size that it processes is fixed, and the terminal of moving window is always current time, this restriction also ensure that the valid data of sliding window model process are the data in the most newly arrived window in data stream forever.
The present invention detects the method for driver fatigue state based on the motionless theory of bearing circle 4s, and improve on this basis, add the method for dynamic threshold, the change of removing bearing circle and car body angle, on the impact of testing result, judges the state of driver more accurately.
The situation on the road surface residing for the angle of bearing circle in actual conditions and vehicle is different, fixing threshold value can not be adopted as the foundation detecting steering wheel position, the present invention proposes a kind of method of dynamic training recent movement acceleration rate threshold: first analyze vehicle by the acceleration information of bearing circle and whether be in metastable transport condition, during this period of time monitoring direction is faced left the continuous time that right fluctuation is less than 15 degree, decile this continuous time is multiple continuous print time periods, obtains the weighted mean value of the acceleration information of bearing circle in these time periods; Then the mean value of these weighted mean values is got, obtain the dynamic threshold of driver at current road segment, obtaining the waving interval of bearing circle after obtaining threshold value by comparing acceleration information, the motionless theory of application direction dish 4s, judging that when the continuous 4s of bearing circle is motionless driver is in fatigue driving state.
(2) pulse dynamic threshold
Pulse and the heartbeat of normal person are consistent, are 60-100 time per minute, are generally 70-80 time per minute, on average 72 times about per minute.The elderly is comparatively slow, is 55 to 60 beats/min.Normal person's pulse frequency rule, there will not be the phenomenon that pulse interval time is different in size.Normal person's pulse is strong and weak impartial, there will not be the phenomenon that power replaces.The frequency of pulse by the impact of age and sex, in addition, motion and excited time pulse can be made to speed, and to have a rest, sleep and then make pulse slow down.
In order to obtain pulse frequency and tired relation, invention has been contrast experiment's test.Experimenter amounts to 12, and are all healthy adults, the age is between 23 to 26 years old.Experimenter measures 5 groups of pulse value when being in waking state; Experimenter measures 5 groups of pulse value when being in a some fatigue state again; Measurement 5 groups of pulse value are continued time experimenter is in more tired.According to the pulse value measured, calculate corresponding pulse frequency, count the pulse frequency situation of change of experimenter under different condition, as shown in table 1.
Table 1: the pulse frequency change of experimenter under different conditions
As shown in Table 1, the fatigue of pulse frequency and human body has relation closely.When experimenter has been in a some fatigue state, the amount of decrease of pulse frequency is between 8.57%-12.50%, and major part is more than 10%; When experimenter is in fatigue state, the amount of decrease of pulse frequency is between 19.44%-24.66, and major part is more than 20%.The conclusion experimentally drawn, the present invention proposes a kind of method detecting driver tired driving state based on dynamic threshold, the degree of fatigue of driver is judged: a period of time that driver has just started to drive generally relatively regains consciousness according to the degree of Variation of Drivers ' Heart Rate cycle decline, detect the pulse data of driver during this period and calculate its corresponding heart rate periodic quantity, using this heart rate periodic quantity as the normal heart rate periodic quantity of driver, after having crossed this section of recovery time continuous detecting driver pulse and analyze the heart rate cycle, with normal heart rate period ratio comparatively, if decline degree has exceeded more than 10%, system judges that driver is in slight fatigue state, decline degree is more than 20%, system judges that driver is in fatigue state.
3, based on the fatigue driving state detection algorithm of decision making level data fusion
The present invention carries out decision level fusion by the driver fatigue testing result based on recent movement acceleration and the driver fatigue testing result based on pulse.
The present invention is based on the theory of finite set Θ, what Θ represented is a framework of identification, and comprising the entire objects wanting system to detect, is the relation of mutual exclusion between object; Θ represents set that is tired and not tired two objects in the present invention.I.e. Θ={ tired, not tired }.
If the subset of θ is 2
θ, f is 2
θto the mapping function of [0,1], and meet f (Φ)=0, to arbitrary S ∈ 2
Θ, have f (s)>=0 and ∑ f (s)=1.F (s) represents the elementary probability value of an identification framework, reflects the size to s reliability.F
1() and f
2() represents two independently evidence source Basic probability assignment function of deriving, and corresponding in the present invention is the driver tired driving state gone out based on acceleration detection and these two the evidence bodies of driver tired driving state gone out based on pulse detection.Calculate a Basic probability assignment function, to reflect two coefficient fuse informations of evidence body:
Order
Then
The present invention adopts the decision rule based on probability assignments, can be expressed as follows for the decision rule based on probability assignments:
For arbitrary set M, if
Meet:
if there is f (S
1)-f (S
2) > θ
1, f (M) < θ
2, f (S
1) > f (M), then S
1the result of decision to event, wherein θ
1and θ
2the threshold value of representative setting.
As shown in Figure 4, the invention provides a kind of implementation method of the fatigue driving state detection system based on decision making level data fusion, the method comprises the steps:
Step 1 builds Basic probability assignment function, for acceleration and pulse two evidence bodies, calculates both probability distribution function f respectively, will guarantee to be independent of each other between these two evidence bodies simultaneously, separate.
The rule of combination that step 2 applies evidence theory obtains a new evidence body, this new evidence body is combined out by acceleration and these two evidence bodies of pulse, the basic probability assignment that new evidence body shows, more close to 1, shows the accuracy of proposition judgement higher.
Step 3 application decision rule, obtains the judgement result of decision about fatigue state and exports.
Claims (8)
1. the fatigue driving state detection system based on decision making level data fusion, it is characterized in that, described system comprises acceleration information acquisition module, acceleration information transmission stores with pretreatment module, acceleration information dynamic threshold training module, the algorithm application module detecting driver tired driving state based on acceleration information, pulse data acquisition module, pulse data and pretreatment module, pulse data dynamic threshold training module, detect algorithm application module, the data fusion module of driver tired driving state based on pulse data;
The function of acceleration information acquisition module is: utilize acceleration transducer to gather recent movement acceleration information;
Acceleration information transmission with the function of pretreatment module is: to gathering the smoothing process of the recent movement acceleration raw data application method of weighted moving average with acceleration transducer;
The function of acceleration information dynamic threshold training module is: to the data calculating mean value again through acceleration information transmission and pretreatment module process, obtaining the dynamic threshold of driver at current road segment, then obtaining the waving interval of bearing circle by comparing acceleration information;
The function detecting the algorithm application module of driver tired driving state based on acceleration information is: adopt the motionless theory of bearing circle 4s, tentatively judges the testing result of fatigue driving state;
The function of pulse data acquisition module is: the pulse transducer based on the wrist radial artery place being fixed on human body gathers the pulse data in driver process;
Pulse data stores and with the function of pretreatment module is: the pulse data that storage of collected arrives, and the threshold method then based on wavelet transformation removes pulse signal noise, re-uses the method for weighted moving average to the smoothing process of data;
The function of pulse data dynamic threshold training module is: analyze and calculate driver pulse frequency change, set up the threshold value of corresponding abnormal driving state for different individualities;
The function detecting the algorithm application module of driver tired driving state based on pulse data is: judge that whether the current driver's pulse frequency obtained is normal by comparing with the threshold value of abnormal driving state, and then judge whether driver is in fatigue driving state;
The function of data fusion module is: to detecting the algorithm application module of driver tired driving state based on acceleration information and carrying out decision level fusion, by obtaining based on the fatigue driving state detection algorithm of decision making level data fusion the testing result whether driver is in fatigue driving state based on the recognition result application evidence theory of the algorithm application module of pulse data detection driver tired driving state.
2. a kind of fatigue driving state detection system based on decision making level data fusion according to claim 1, it is characterized in that: first described system utilizes acceleration transducer to gather the acceleration of motion of bearing circle by acceleration information acquisition module, as judge driver driving condition according to one of; Utilize pulse transducer for the collection of pulse data by pulse data acquisition module, pulse transducer is fixed on the wrist radial artery place of human body; Acceleration information transmission stores with pretreatment module and pulse data and all uses the method for weighted moving average to the smoothing process of data with pretreatment module, point weights the closer to smooth window edge are less, the point entering smooth window is all little by little count in mean value, eliminates the impact on overall smoothness gradually:
In formula (1), s
irepresent the smooth value of i-th point; x
i+jrepresentative data point; w
jrepresent weights, comparatively large near middle weights, submarginal weights are less, and weights summation is 1; Select the method for weighted moving average as the method for acceleration information smoothing processing, for the recent movement acceleration information collected, within adjacent three o'clock, as a processing item, the result after smoothing processing is updated to middle corresponding data item, circular treatment, until process data.
3. a kind of fatigue driving state detection system based on decision making level data fusion according to claim 1, is characterized in that: described system removes pulse signal noise based on the threshold method of wavelet transformation, comprising:
First, need to carry out wavelet transform to pulse signal, wavelet is:
Suppose
be
fourier transform,
be called wavelet mother function, by wavelet mother function
translation can obtain discrete wavelet race with flexible:
In formula (3), a is contraction-expansion factor, and b is shift factor;
Suppose that pulse signal is signal (t), signal (t)=start (t)+noise (t), start (t) represents original pulse signal, noise (t) represents noise, carries out discrete sampling: signal (t), t=0 to pulse signal, 1,2 ..., N-1;
The coefficient of described wavelet transformation is:
Through type (4) obtains wavelet coefficient W
signalafter (a, b), process by threshold value, determine the estimated value of wavelet coefficient
guarantee
value minimum, threshold value adopts generic threshold value choosing method, comprising:
In formula (5), med represents the intermediate value of high frequency orthogonal wavelet coefficient;
Obtain the estimated value of wavelet coefficient
with wavelet inverse transformation to wavelet reconstruction, obtain estimated signal
it is exactly the pulse signal after denoising.
4. a kind of fatigue driving state detection system based on decision making level data fusion according to claim 1, it is characterized in that: first analyze vehicle by the acceleration information of the bearing circle collected by acceleration information acquisition module and whether be in metastable transport condition, during this period of time monitoring direction is faced left the continuous time that right fluctuation is less than 15 degree, decile this continuous time is multiple continuous print time periods, is transmitted the weighted mean value obtaining the acceleration information of bearing circle in these time periods with pretreatment module by acceleration information; Then the mean value of these weighted mean values is got by acceleration information dynamic threshold training module, obtain the dynamic threshold of driver at current road segment, obtain the waving interval of bearing circle by comparing acceleration information after obtaining threshold value, detect the algorithm application module of driver tired driving state according to the motionless theory of bearing circle 4s by based on acceleration information again, judge that when the continuous 4s of bearing circle is motionless driver is in fatigue driving state.
5. based on an implementation method for the fatigue driving state detection system of decision making level data fusion, it is characterized in that, described method comprises the steps:
Step 1: build Basic probability assignment function, for acceleration and pulse two evidence bodies, calculate both probability distribution function f respectively, guarantee to be independent of each other between these two evidence bodies simultaneously, separate;
Step 2: the rule of combination of application evidence theory obtains a new evidence body, this new evidence body is combined out by acceleration and these two evidence bodies of pulse, the basic probability assignment that new evidence body shows, more close to 1, shows the accuracy of proposition judgement higher;
Step 3: application decision rule, obtains the judgement result of decision about fatigue state and export.
6. the implementation method of a kind of fatigue driving state detection system based on decision making level data fusion according to claim 5, is characterized in that: described method carries out decision level fusion by the driver fatigue testing result based on recent movement acceleration and the driver fatigue testing result based on pulse.
7. the implementation method of a kind of fatigue driving state detection system based on decision making level data fusion according to claim 5, it is characterized in that: described method is based on the theory of finite set Θ, what Θ represented is a framework of identification, comprising the entire objects wanting system to detect, is the relation of mutual exclusion between object; Θ represents set that is tired and not tired two objects, i.e. Θ={ tired, not tired };
If the subset of θ is 2
θ, f is 2
θto the mapping function of [0,1], and meet f (Φ)=0, to arbitrary S ∈ 2
Θ, have f (s)>=0 and Σ f (s)=1, f (s) represents the elementary probability value of an identification framework, reflects the size to s reliability; f
1() and f
2() represents two independently evidence source Basic probability assignment function of deriving, the driver tired driving state that corresponding is goes out based on acceleration detection and these two the evidence bodies of driver tired driving state gone out based on pulse detection; Calculate a Basic probability assignment function, to reflect two coefficient fuse informations of evidence body, comprising:
Order
Then
8. the implementation method of a kind of fatigue driving state detection system based on decision making level data fusion according to claim 5, it is characterized in that: described step 3 adopts the decision rule based on probability assignments, decision rule based on probability assignments is expressed as: for arbitrary set M, if
meet:
and S
i≠ S
1; If there is f (S
1)-f (S
2) > θ
1, f (M) < θ
2, f (S
1) > f (M), then S
1the result of decision to event, wherein θ
1and θ
2the threshold value of representative setting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510249302.7A CN104952210B (en) | 2015-05-15 | 2015-05-15 | A kind of fatigue driving state detecting system and method based on decision making level data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510249302.7A CN104952210B (en) | 2015-05-15 | 2015-05-15 | A kind of fatigue driving state detecting system and method based on decision making level data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104952210A true CN104952210A (en) | 2015-09-30 |
| CN104952210B CN104952210B (en) | 2018-01-05 |
Family
ID=54166832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510249302.7A Expired - Fee Related CN104952210B (en) | 2015-05-15 | 2015-05-15 | A kind of fatigue driving state detecting system and method based on decision making level data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104952210B (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105261153A (en) * | 2015-11-03 | 2016-01-20 | 北京奇虎科技有限公司 | Vehicle running monitoring method and device |
| CN105405253A (en) * | 2015-12-18 | 2016-03-16 | 中交第一公路勘察设计研究院有限公司 | Method and apparatus for monitoring fatigue state of driver |
| CN105632103A (en) * | 2016-03-11 | 2016-06-01 | 张海涛 | Method and device for monitoring fatigue driving |
| CN106384129A (en) * | 2016-09-13 | 2017-02-08 | 西安科技大学 | Driver driving state recognition method based on closed loop driving model |
| CN106446849A (en) * | 2016-09-30 | 2017-02-22 | 防城港市港口区高创信息技术有限公司 | Fatigue driving detection method |
| CN106539581A (en) * | 2016-12-07 | 2017-03-29 | 中国民用航空总局第二研究所 | Controller's fatigue detection method and system based on probabilistic method |
| CN106548132A (en) * | 2016-10-16 | 2017-03-29 | 北海益生源农贸有限责任公司 | The method for detecting fatigue driving of fusion eye state and heart rate detection |
| CN106851478A (en) * | 2017-02-10 | 2017-06-13 | 深圳市笨笨机器人有限公司 | Multi-channel information processing method and system |
| CN106874900A (en) * | 2017-04-26 | 2017-06-20 | 桂林电子科技大学 | A kind of tired driver detection method and detection means based on steering wheel image |
| CN107212870A (en) * | 2017-06-28 | 2017-09-29 | 上海电力学院 | A kind of ear clip device for detecting driver status |
| CN107233103A (en) * | 2017-05-27 | 2017-10-10 | 西南交通大学 | High ferro dispatcher's fatigue state assessment method and system |
| CN107472130A (en) * | 2017-08-04 | 2017-12-15 | 山东理工大学 | A kind of method and system for monitoring driver's dangerous driving state |
| CN108682119A (en) * | 2018-05-29 | 2018-10-19 | 重庆大学 | Method for detecting fatigue state of driver based on smart mobile phone and smartwatch |
| CN108765876A (en) * | 2018-05-31 | 2018-11-06 | 东北大学 | Driving fatigue depth analysis early warning system based on multimode signal and method |
| US20180326990A1 (en) * | 2017-05-10 | 2018-11-15 | Honda Motor Co., Ltd. | Drive assist apparatus and drive assist method |
| CN108995531A (en) * | 2018-08-09 | 2018-12-14 | 爱驰汽车有限公司 | fatigue warning device and method for automobile |
| CN109389806A (en) * | 2018-11-08 | 2019-02-26 | 山东大学 | Fatigue driving detection method for early warning, system and medium based on multi-information fusion |
| CN109993119A (en) * | 2019-03-31 | 2019-07-09 | 广东乐之康医疗技术有限公司 | A kind of data collection and learning method based on wearable device |
| CN110101372A (en) * | 2019-04-24 | 2019-08-09 | 上海工程技术大学 | A kind of municipal rail train driver physiological status monitoring system |
| CN110334592A (en) * | 2019-05-27 | 2019-10-15 | 天津科技大学 | A kind of monitoring of driver's abnormal behaviour and safety control system and safety 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 |
| CN110476194A (en) * | 2017-03-28 | 2019-11-19 | 国立大学法人九州工业大学 | Driver status detection device |
| CN111344762A (en) * | 2017-11-21 | 2020-06-26 | 三菱电机株式会社 | Abnormality detection device and abnormality detection method |
| CN108926352B (en) * | 2017-05-22 | 2020-10-09 | 北京大学 | Driving fatigue detection method and system |
| CN112233276A (en) * | 2020-10-13 | 2021-01-15 | 重庆科技学院 | Steering wheel corner statistical characteristic fusion method for fatigue state recognition |
| CN113642522A (en) * | 2021-09-01 | 2021-11-12 | 中国科学院自动化研究所 | Audio and video based fatigue state detection method and device |
| CN114073513A (en) * | 2020-08-10 | 2022-02-22 | 安徽华米健康科技有限公司 | Detection method and device for getting up at night during sleep and intelligent wearable equipment |
| CN116382488A (en) * | 2023-06-01 | 2023-07-04 | 隽智生物医学研究实验室(佛山)有限公司 | Human-computer interaction intelligent regulation and control decision system and method based on human body state identification |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
| JP2011008457A (en) * | 2009-06-25 | 2011-01-13 | Hitachi Ltd | Automobile driver doze prevention device |
| CN102509418A (en) * | 2011-10-11 | 2012-06-20 | 东华大学 | Fatigue driving estimation and early-warning method and device of multi-sensor information fusion |
| CN203252643U (en) * | 2013-05-20 | 2013-10-30 | 江西理工大学 | Intelligent sleep prevention device by detecting driver pulse |
| CN103714660A (en) * | 2013-12-26 | 2014-04-09 | 苏州清研微视电子科技有限公司 | System for achieving fatigue driving judgment on basis of image processing and fusion between heart rate characteristic and expression characteristic |
| CN104112335A (en) * | 2014-07-25 | 2014-10-22 | 北京机械设备研究所 | Multi-information fusion based fatigue driving detecting method |
-
2015
- 2015-05-15 CN CN201510249302.7A patent/CN104952210B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
| JP2011008457A (en) * | 2009-06-25 | 2011-01-13 | Hitachi Ltd | Automobile driver doze prevention device |
| CN102509418A (en) * | 2011-10-11 | 2012-06-20 | 东华大学 | Fatigue driving estimation and early-warning method and device of multi-sensor information fusion |
| CN203252643U (en) * | 2013-05-20 | 2013-10-30 | 江西理工大学 | Intelligent sleep prevention device by detecting driver pulse |
| CN103714660A (en) * | 2013-12-26 | 2014-04-09 | 苏州清研微视电子科技有限公司 | System for achieving fatigue driving judgment on basis of image processing and fusion between heart rate characteristic and expression characteristic |
| CN104112335A (en) * | 2014-07-25 | 2014-10-22 | 北京机械设备研究所 | Multi-information fusion based fatigue driving detecting method |
Non-Patent Citations (1)
| Title |
|---|
| 李埃荣: "基于多传感器数据融合的驾驶状态监控研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105261153A (en) * | 2015-11-03 | 2016-01-20 | 北京奇虎科技有限公司 | Vehicle running monitoring method and device |
| CN105405253A (en) * | 2015-12-18 | 2016-03-16 | 中交第一公路勘察设计研究院有限公司 | Method and apparatus for monitoring fatigue state of driver |
| CN105405253B (en) * | 2015-12-18 | 2017-05-24 | 中交第一公路勘察设计研究院有限公司 | Method and apparatus for monitoring fatigue state of driver |
| CN105632103A (en) * | 2016-03-11 | 2016-06-01 | 张海涛 | Method and device for monitoring fatigue driving |
| CN106384129B (en) * | 2016-09-13 | 2018-07-20 | 西安科技大学 | A kind of driver's driving condition discrimination method based on closed loop driving model |
| CN106384129A (en) * | 2016-09-13 | 2017-02-08 | 西安科技大学 | Driver driving state recognition method based on closed loop driving model |
| CN106446849A (en) * | 2016-09-30 | 2017-02-22 | 防城港市港口区高创信息技术有限公司 | Fatigue driving detection method |
| CN106548132A (en) * | 2016-10-16 | 2017-03-29 | 北海益生源农贸有限责任公司 | The method for detecting fatigue driving of fusion eye state and heart rate detection |
| CN106539581A (en) * | 2016-12-07 | 2017-03-29 | 中国民用航空总局第二研究所 | Controller's fatigue detection method and system based on probabilistic method |
| CN106851478A (en) * | 2017-02-10 | 2017-06-13 | 深圳市笨笨机器人有限公司 | Multi-channel information processing method and system |
| CN110476194A (en) * | 2017-03-28 | 2019-11-19 | 国立大学法人九州工业大学 | Driver status detection device |
| CN106874900A (en) * | 2017-04-26 | 2017-06-20 | 桂林电子科技大学 | A kind of tired driver detection method and detection means based on steering wheel image |
| US20180326990A1 (en) * | 2017-05-10 | 2018-11-15 | Honda Motor Co., Ltd. | Drive assist apparatus and drive assist method |
| CN108926352B (en) * | 2017-05-22 | 2020-10-09 | 北京大学 | Driving fatigue detection method and system |
| CN107233103A (en) * | 2017-05-27 | 2017-10-10 | 西南交通大学 | High ferro dispatcher's fatigue state assessment method and system |
| CN107212870A (en) * | 2017-06-28 | 2017-09-29 | 上海电力学院 | A kind of ear clip device for detecting driver status |
| CN107472130A (en) * | 2017-08-04 | 2017-12-15 | 山东理工大学 | A kind of method and system for monitoring driver's dangerous driving state |
| CN111344762B (en) * | 2017-11-21 | 2022-03-01 | 三菱电机株式会社 | Abnormality detection device and abnormality detection method |
| CN111344762A (en) * | 2017-11-21 | 2020-06-26 | 三菱电机株式会社 | Abnormality detection device and abnormality detection method |
| CN108682119A (en) * | 2018-05-29 | 2018-10-19 | 重庆大学 | Method for detecting fatigue state of driver based on smart mobile phone and smartwatch |
| CN108765876A (en) * | 2018-05-31 | 2018-11-06 | 东北大学 | Driving fatigue depth analysis early warning system based on multimode signal and method |
| CN108995531A (en) * | 2018-08-09 | 2018-12-14 | 爱驰汽车有限公司 | fatigue warning device and method for automobile |
| CN109389806A (en) * | 2018-11-08 | 2019-02-26 | 山东大学 | Fatigue driving detection method for early warning, system and medium based on multi-information fusion |
| CN109993119A (en) * | 2019-03-31 | 2019-07-09 | 广东乐之康医疗技术有限公司 | A kind of data collection and learning method based on wearable device |
| CN110101372A (en) * | 2019-04-24 | 2019-08-09 | 上海工程技术大学 | A kind of municipal rail train driver physiological status monitoring system |
| CN110334592A (en) * | 2019-05-27 | 2019-10-15 | 天津科技大学 | A kind of monitoring of driver's abnormal behaviour and safety control system and safety 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 |
| CN114073513A (en) * | 2020-08-10 | 2022-02-22 | 安徽华米健康科技有限公司 | Detection method and device for getting up at night during sleep and intelligent wearable equipment |
| CN112233276A (en) * | 2020-10-13 | 2021-01-15 | 重庆科技学院 | Steering wheel corner statistical characteristic fusion method for fatigue state recognition |
| CN112233276B (en) * | 2020-10-13 | 2022-04-29 | 重庆科技学院 | Steering wheel corner statistical characteristic fusion method for fatigue state recognition |
| CN113642522A (en) * | 2021-09-01 | 2021-11-12 | 中国科学院自动化研究所 | Audio and video based fatigue state detection method and device |
| CN116382488A (en) * | 2023-06-01 | 2023-07-04 | 隽智生物医学研究实验室(佛山)有限公司 | Human-computer interaction intelligent regulation and control decision system and method based on human body state identification |
| CN116382488B (en) * | 2023-06-01 | 2023-10-27 | 隽智生物医学研究实验室(佛山)有限公司 | Human-computer interaction intelligent regulation and control decision system and method based on human body state identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104952210B (en) | 2018-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104952210A (en) | Fatigue driving state detecting system and method based on decision-making level data integration | |
| US11311201B2 (en) | Feature selection for cardiac arrhythmia classification and screening | |
| CN110742585B (en) | Sleep staging method based on BCG (BCG-broadcast) signals | |
| CN108765876A (en) | Driving fatigue depth analysis early warning system based on multimode signal and method | |
| Kampouraki et al. | Heartbeat time series classification with support vector machines | |
| Dewangan et al. | ECG arrhythmia classification using discrete wavelet transform and artificial neural network | |
| CN103020472B (en) | Based on physiological signal quality evaluation method and the system of restrained split-flow | |
| Singh et al. | An approach for real-time stress-trend detection using physiological signals in wearable computing systems for automotive drivers | |
| Pimentel et al. | Heart beat detection in multimodal physiological data using a hidden semi-Markov model and signal quality indices | |
| Bashar et al. | A machine learning approach for heart rate estimation from PPG signal using random forest regression algorithm | |
| Singh et al. | Assessment of driver stress from physiological signals collected under real-time semi-urban driving scenarios | |
| Singh et al. | Biosignal based on-road stress monitoring for automotive drivers | |
| Wang et al. | Temporal-framing adaptive network for heart sound segmentation without prior knowledge of state duration | |
| US20140378855A1 (en) | Apparatus and method for feature extraction and classification of fetal heart rate | |
| Zhao et al. | ECG identification based on matching pursuit | |
| Park et al. | Prediction of daily mental stress levels using a wearable photoplethysmography sensor | |
| Luguev et al. | Deep learning based affective sensing with remote photoplethysmography | |
| CN115486824B (en) | Cuff-free continuous blood pressure estimation system based on uncertainty measurement | |
| Lukoševičius et al. | Noninvasive fetal QRS detection using echo state network | |
| CN115474901A (en) | Non-contact living state monitoring method and system based on wireless radio frequency signals | |
| Radha et al. | LSTM knowledge transfer for HRV-based sleep staging | |
| Duraj et al. | Heartbeat detection in seismocardiograms with semantic segmentation | |
| Arya et al. | HRV and GSR as viable physiological markers for mental health recognition | |
| Chan et al. | Estimating heart rate from seismocardiogram signal using a novel deep dominant frequency regressor and domain adversarial training | |
| Fotoohinasab et al. | A graph-constrained changepoint detection approach for ECG segmentation |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20150930 Assignee: NUPT INSTITUTE OF BIG DATA RESEARCH AT YANCHENG Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS Contract record no.: X2020980007071 Denomination of invention: A fatigue driving state detection system and method based on decision level data fusion Granted publication date: 20180105 License type: Common License Record date: 20201026 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180105 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |