CN108765876A - Driving fatigue depth analysis early warning system based on multimode signal and method - Google Patents

Driving fatigue depth analysis early warning system based on multimode signal and method Download PDF

Info

Publication number
CN108765876A
CN108765876A CN201810552524.XA CN201810552524A CN108765876A CN 108765876 A CN108765876 A CN 108765876A CN 201810552524 A CN201810552524 A CN 201810552524A CN 108765876 A CN108765876 A CN 108765876A
Authority
CN
China
Prior art keywords
steering wheel
module
driver
signal
fatigue
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
Application number
CN201810552524.XA
Other languages
Chinese (zh)
Inventor
王红菊
吴承阳
朱超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Northeastern University China
Original Assignee
Northeastern University China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Northeastern University China filed Critical Northeastern University China
Priority to CN201810552524.XA priority Critical patent/CN108765876A/en
Publication of CN108765876A publication Critical patent/CN108765876A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • 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
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • 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
    • A61B5/389—Electromyography [EMG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
    • A61B5/6893—Cars
    • 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
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • 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
    • A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • 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
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
    • 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

Abstract

The present invention provides a kind of driving fatigue depth analysis early warning system and method based on multimode signal, is related to fatigue driving technical field.The system includes more physiological signal collection modules, steering wheel angle data acquisition module, data transmission module, high in the clouds depth analysis module and safe early warning module；More physiological signal collection modules and steering wheel angle data acquisition module are each attached in vehicle steering wheel, and output end is connected with the input terminal of data transmission module；The output end of the data transmission module is connected with the input terminal of high in the clouds depth analysis module, and the output end of high in the clouds depth analysis module is connected with the input terminal of safe early warning module.Driving fatigue depth analysis early warning system and method provided by the invention based on multimode signal, the fatigue state of driver can be more accurately obtained by the physiologic information of driver itself and the behavioural information of driver, the high in the clouds depth analysis system built using deep learning, can obtain more accurate analysis result.

Description

Driving fatigue depth analysis early warning system based on multimode signal and method
Technical field
The present invention relates to fatigue driving technical field more particularly to a kind of driving fatigue depth analysis based on multimode signal Early warning system and method.
Background technology
In recent years, as the rapid development of Modern Traffic transport service, people's life income level step up, automobile is As transport facility mostly important in people's daily life.However, bring people it is quick, convenient, comfortable while, Traffic accident has become serious social concern, has been acknowledged as the first grand duke that the world today endangers human life's safety Evil.The statistics of China's road traffic accident shows to account for 90% or so mainly due to accident caused by driver, in these events In, driving fatigue occupies sizable ratio as risk factor again.Fatigue driving is to lead to the weight of China's traffic accident always Reason is wanted, it is because many people do not recognize the harm of fatigue driving, therefore pass through the tired shape to driver to trace it to its cause State is monitored in real time, is given driver's prompting in time, is avoided driver tired driving, to reduce traffic accident with important Meaning.
With the development of science and technology, occurring the product of many monitoring driver tired drivings, such as wearable intelligence on the market Equipment, eye tracker, brain electrical detection device etc..Such as：The utility model patent of Patent No. 201220441791.8 " is based on physiology The eyes that driver is acquired by the sensor being placed on glasses in the fatigue driving detecting and controlling system of signal acquisition " blink Number and brain wave frequency acquisition Driver physiological data analyze driver fatigue situation；Patent No. 201010286754.X Patent of invention " the fatigue of automobile driver monitoring method based on physiology signal " in pass through the heart on safety belt Rate acquires Variation of Drivers ' Heart Rate and breath signal with respiration transducer and is located in the pulse transducer acquisition pulse wave letter of hand Number, analyze driver fatigue state.But since the wearing product of the similar above patent is easy to make in driving procedure to driver It is not high at reasons popularizations such as inconvenient or valuable products.
Invention content
In view of the drawbacks of the prior art, the present invention provides a kind of driving fatigue depth analysis early warning system based on multimode signal System and method monitor driver's fatigue state in driving procedure, and are reminded in real time driver in real time, to reduce traffic thing Therefore generation.
On the one hand, the present invention provides a kind of driving fatigue depth analysis early warning system based on multimode signal, including mostly raw Manage signal acquisition module, steering wheel angle data acquisition module, data transmission module, high in the clouds depth analysis module and safe early warning Module；More physiological signal collection modules and steering wheel angle data acquisition module are each attached on steering wheel, and output end It is connected with the input terminal of data transmission module；The input of the output end and high in the clouds depth analysis module of the data transmission module End is connected, and the output end of high in the clouds depth analysis module is connected with the input terminal of safe early warning module.
Preferably, more physiological signal collection modules include pulse wave acquisition module, ecg signal acquiring module and flesh Electrical signal collection module；The pulse wave acquisition module, ecg signal acquiring module and electromyographic signal collection module are each attached to On steering wheel, and output end is connected with data transmission module.
Preferably, the steering wheel angle data acquisition module is mounted on using steering wheel accelerator on steering wheel shaft, For detection direction disk rotational frequency and corner size, output end is connected with data transmission module.
Preferably, the data transmission module, including sequentially connected micro-control unit MCU, amplifier, A/D converter, Bluetooth and intelligent terminal, to from more physiological signal collection modules and steering wheel angle data collecting module collected to signal carry out Amplification, pretreatment, A/D conversions and transmission.
Preferably, the high in the clouds depth analysis module, including steering wheel angle data analysis module and the more physiology letters of human body Number analysis module；The steering wheel angle data analysis module is connected with data transmission module, receives steering wheel angle data letter Breath, and the frequency of steering wheel rotation when being driven to driver, corner size these data are analyzed and extract feature, calculating side To the mean and variance of disk corner；The more physiological signal analysis modules of human body are connected with data transmission module, receive more physiology Physiological driver's signal of signal acquisition module acquisition carries out the electrocardiosignal, pulse wave signal and electromyography signal of driver Feature extraction；And signature analysis is carried out by deep neural network, obtain driver's fatigue degree.
Preferably, the safe early warning module is connected with high in the clouds depth analysis module, will be obtained from high in the clouds depth analysis module The driver's driving condition analysis result obtained is timely feedbacked to driver, reminds whether driver is in fatigue driving state, and Provide suggestion appropriate.
Preferably, the pulse collection module, using semiconductor pressure resistance sensor, the pulse wave for detecting driver； The ecg signal acquiring module, using textile electrode, the electrocardiosignal for detecting driver；The myoelectricity acquisition module, Equally use textile electrode, the electromyography signal for detecting driver.
On the other hand, the driving fatigue depth analysis early warning system that the present invention also provides a kind of using above-mentioned based on multimode signal The method that system carries out analysis and early warning, includes the following steps：
Step 1：In driving procedure, more physiological signal collection modules contact steering wheel by driver's both hands and adopt driver Collect a variety of physiological signals of human body of driver, including：Electrocardiosignal, electromyography signal and pulse wave signal；Meanwhile steering wheel turns By driver, the steering wheel rotation when driving acquires steering wheel angle data to angular data acquisition module；
Step 2：The more physiological signals of driver's human body and steering wheel angle number that step 1 is acquired by data transmission module It is handled according to being transmitted, specific method is：
Step 2.1：Data transmission module pre-processes collected pulse wave signal；Pulse wave signal is mainly floated by baseline It moves, the influence of Hz noise and High-frequency Interference；Pulse wave signal is pre-processed using mathematical morphology, recycles small echo Transformation carries out main heavy wave crest feature extraction to pulse signal, and the real-time blood of driver is calculated according to the main heavy wave crest of the pulse wave of extraction Pressure value；The amplitude of the main heavy wave crest of the pulse wave extracted and position feature are uploaded into high in the clouds depth analysis module, carry out fatigue State analysis；
Step 2.2：Collected electrocardiosignal pre-processes electrocardiosignal using wavelet transformation first, removal is made an uproar Sound；The noise of the electrocardiosignal includes industrial frequency noise, baseline drift noise and myoelectricity interference noise；Again to the heart of removal noise Electric signal extracts magnetic resonance angiography (magnetic resonance angiography, i.e. QRS) wave group of electrocardiosignal, Heart rate variability (Heart Rate are finally analyzed in time domain and in frequency domain to extracting the electrocardiosignal of R waves Variability, i.e. HRV)；
It is described extraction electrocardiosignal QRS wave group specific method be：
To passing through the pretreated electrocardiosignal of Wavelet Denoising Method first according to the waveform change rate of R waves an ecg wave form week Interim is this feature extraction R waves of steepest, and carrying out single order forward difference to electrocardiosignal compares, if a difference is more than a certain Occurs a failing edge after the rising edge of threshold value Tr again, and the difference of failing edge is more than this threshold value, then it is assumed that occur one Maximum point, these maximum points are the R peak points given tacit consent to；Flase drop is carried out to R waves again and missing inspection excludes；After R waves determine, with Centered on each R wave crest point, respectively in front and back specific time window, the detection of Q waves and S waves is carried out, is believed for personal electrocardio Breath judgement；
Step 2.3：Collected electromyography signal is pre-processed, electromyography signal is transformed by frequency by Fast Fourier Transform (FFT) Frequency spectrum in domain or power spectrum extract electromyography signal feature, obtain the frequency of average power of electromyography signal power spectrum；And it will extraction The feature arrived uploads high in the clouds fatigue depth analysis system, analyzes driver fatigue state in real time；
Step 2.4：Discretization and normalization are carried out to collected steering wheel angle data, extraction steering wheel operation is special Sign calculates steering wheel angle variance and mean value；The control ability of steering wheel is declined when human body is in fatigue state, the side of causing Become larger to disk amplitude of fluctuation, therefore steering wheel angle variance is larger when fatigue and steering wheel times of revision is less；
Step 3：High in the clouds fatigue depth analysis system is built, specific method is：
Step 3.1：The personal more physiological signal data libraries of structure, driver personal essential information is inputted by intelligent terminal, Such as name, height, weight, it is preprocessed in driving procedure by harvester to collect a variety of physiological signals of the driver And personal more physiological signal data libraries are uploaded to after feature extraction；Since everyone physiological signal can be poor with others It is different, as everyone electrocardiosignal be it is unique, QRS wave amplitude, wave group interval time, QT waves the parameters such as amplitude All there is personalization；Driver identity is effectively identified by personal more physiological signal data libraries；
Step 3.2：The fatigue characteristic extraction model based on multi-physiological-parameter is built, convolutional neural networks or cycle god are utilized Through network as feature learning method, using the feature learnt as the defeated of the final such as tired grader of softmax graders Enter；By after discretization and normalized steering wheel angle data and it is preprocessed and extraction feature after electrocardio, myoelectricity, A certain number of test samples, including awake sample, tired sample are chosen in input of the pulse wave physiological parameter as neural network Very tired sample carries out neural metwork training, establishes the fatigue characteristic extraction model based on convolutional neural networks；
Step 3.3：The tired identification model based on tired grader is built, it is tired by what is extracted from convolutional neural networks Input of the labor feature as tired grader characteristic model, merges multi-source information depth analysis fatigue characteristic, it is tired to obtain driver Labor degree is predicted；
Step 4：Safe early warning, high in the clouds fatigue depth analysis system is by the data analysis of acquisition and obtains as a result, will obtain To result provide by voice prompt driver and according to circumstances appropriate suggestion.
As shown from the above technical solution, the beneficial effects of the present invention are：Driving based on multimode signal provided by the invention Tired depth analysis early warning system and method are sailed, electrocardiosignal, electromyography signal and the pulse wave by monitoring driver in real time are believed Number obtain physiological driver's state；Meanwhile obtaining the instant behavior state of driver by acquiring steering wheel rotation situation in real time. The tired shape of driver can be more accurately obtained by the physiologic information of driver itself and the behavioural information of driver State, the high in the clouds depth analysis system built using deep learning, can obtain more accurate analysis result.
Description of the drawings
Fig. 1 is the structural frames of the driving fatigue depth analysis early warning system provided in an embodiment of the present invention based on multimode signal Figure；
Fig. 2 is the connection diagram of angle data acquisition module and steering wheel provided in an embodiment of the present invention；
Fig. 3 is the flow of the driving fatigue depth analysis method for early warning provided in an embodiment of the present invention based on multimode signal Figure；
Fig. 4 is the structure chart of constructed convolutional neural networks provided in an embodiment of the present invention.
In figure, 1, steering wheel accelerator；2, semiconductor pressure resistance sensor；3, textile electrode.
Specific implementation mode
With reference to the accompanying drawings and examples, the specific implementation mode of the present invention is described in further detail.Implement below Example is not limited to the scope of the present invention for illustrating the present invention.
Driving fatigue depth analysis early warning system based on multimode signal, as shown in Figure 1, including more physiological signal collection moulds Block, steering wheel angle data acquisition module, data transmission module, high in the clouds depth analysis module and safe early warning module；
More physiological signal collection modules include pulse wave acquisition module, ecg signal acquiring module and electromyographic signal collection mould Block；Pulse collection module, using semiconductor pressure resistance sensor 2, the pulse wave for detecting driver；Ecg signal acquiring mould Block, using textile electrode 3, the electrocardiosignal for detecting driver；Myoelectricity acquisition module equally uses textile electrode, is used for Detect the electromyography signal of driver.Semiconductor pressure resistance sensor 2 and textile electrode 3 as shown in Fig. 2, be each attached on steering wheel, Output end is connected with data transmission module；
Steering wheel angle data acquisition module, using steering wheel accelerator 1, as shown in Fig. 2, on steering wheel shaft, For detection direction disk rotational frequency and corner size, output end is connected with data transmission module；
Data transmission module, including sequentially connected micro-control unit MCU, amplifier (such as ECG100C amplifiers, EMG100C amplifiers), A/D converter, bluetooth and intelligent terminal, to from more physiological signal collection modules and steering wheel angle number It is amplified, pre-processes according to the collected signal of acquisition module, A/D is converted and transmission；
High in the clouds depth analysis module, including steering wheel angle data analysis module and the more physiological signal analysis modules of human body； The steering wheel angle data analysis module is connected with data transmission module, receives steering wheel angle data information, and to driving Feature is analyzed and extracted to the frequency, corner size these data of steering wheel rotation when member drives, and calculates steering wheel angle Mean and variance；Driver is stronger to the control ability of automobile when awake, and the steering wheel angle amplitude that swings is smaller, tired Driver's control ability declines when labor, and steering wheel amplitude of fluctuation is caused to become larger, therefore steering wheel angle variance is larger when fatigue.People The more physiological signal analysis modules of body are connected with data transmission module, receive the physiological driver of more physiological signal collection module acquisitions Signal carries out feature extraction to the electrocardiosignal, pulse wave signal and electromyography signal of driver；And by deep neural network into Row signature analysis obtains driver's fatigue degree；When human body is in fatigue state, in heart rate variability time domain measurement index R -- R interval standard deviation has apparent ascendant trend, and with the intensification of degree of fatigue, heart rate becomes the trend that rises overally that presents, meanwhile, Surface myoelectric value rises, and myoelectricity average frequency declines.
Safe early warning module is connected with high in the clouds depth analysis module, and the driver obtained from high in the clouds depth analysis module is driven It sails state analysis result to timely feedback to driver, reminds whether driver is in fatigue driving state, and provide appropriate build View.
The method for carrying out analysis and early warning using the above-mentioned driving fatigue depth analysis early warning system based on multimode signal, such as schemes Shown in 3, include the following steps：
Step 1：In driving procedure, more physiological signal collection modules contact steering wheel by driver's both hands and adopt driver Collect a variety of physiological signals of human body of driver, including：Electrocardiosignal, electromyography signal and pulse wave signal；Meanwhile steering wheel turns By driver, the steering wheel rotation when driving acquires steering wheel angle data to angular data acquisition module；
Step 2：The more physiological signals of driver's human body and steering wheel angle number that step 1 is acquired by data transmission module It is handled according to being transmitted, specific method is：
Step 2.1：Data transmission module pre-processes collected pulse wave signal；Pulse wave signal is mainly floated by baseline It moves, the influence of Hz noise and High-frequency Interference；Pulse wave signal is pre-processed using mathematical morphology, recycles small echo Transformation carries out main heavy wave crest feature extraction to pulse signal, and the real-time blood of driver is calculated according to the main heavy wave crest of the pulse wave of extraction Pressure value；The amplitude of the main heavy wave crest of the pulse wave extracted and position feature are uploaded into high in the clouds depth analysis module, carry out fatigue State analysis；
Step 2.2：Collected electrocardiosignal pre-processes electrocardiosignal using wavelet transformation first, removal is made an uproar Sound；The noise of electrocardiosignal includes industrial frequency noise, baseline drift noise and myoelectricity interference noise；The electrocardio for removing noise is believed again Number extraction electrocardiosignal magnetic resonance angiography (magnetic resonance angiography, i.e. QRS) wave group, finally Analyze to extracting the electrocardiosignal of R waves in time domain and in frequency domain heart rate variability (Heart Rate Variability, i.e., HRV)；
Extraction electrocardiosignal QRS wave group specific method be：
To passing through the pretreated electrocardiosignal of Wavelet Denoising Method first according to the waveform change rate of R waves an ecg wave form week Interim is this feature extraction R waves of steepest, and carrying out single order forward difference to electrocardiosignal compares, if a difference is more than a certain Occurs a failing edge after the rising edge of threshold value Tr again, and the difference of failing edge is more than this threshold value, then it is assumed that occur one Maximum point, these maximum points are the R peak points given tacit consent to；Flase drop is carried out to R waves again and missing inspection excludes；After R waves determine, with Centered on each R wave crest point, respectively in front and back specific time window, the detection of Q waves and S waves is carried out, is believed for personal electrocardio Breath judgement.
Electrocardiosignal to extracting R waves analyzes heart rate variability HRV in time domain, and common time-domain analysis index includes： Standard deviation (SDNN), average value standard deviation (SDANN) and coefficient of variation (CV) etc..
In present embodiment, selection criteria is poor, average value standard deviation, R -- R interval average value and the coefficient of variation become as heart rate Specific analysis index.
Electrocardiosignal to extracting R waves calculates R -- R interval standard deviation (SDNN), shown in following formula：
Wherein, N is R -- R interval number, RRiFor i-th of R -- R interval, i=1,2 ..., N, RRmeanFor the flat of N number of R -- R interval Mean value.
Electrocardiosignal to extracting R waves calculates average value standard deviation (SDANN), shown in following formula：
Wherein, it is the number of stages of a period, RR per 5min in chronological order that m, which is the R -- R interval that will all record,jFor The R -- R interval of j-th of 5min, j=1,2 ..., m.
Electrocardiosignal to extracting R waves calculates R -- R interval average value, shown in following formula：
Wherein, RRkFor the length between adjacent two R waves, k=1,2 ..., N.
To extracting the electrocardiosignals of the R waves analysis of HRV in time domain, coefficient of variation CV is calculated, shown in following formula：
To extracting the electrocardiosignals of the R waves analysis of HRV in frequency domain, Fourier transformation is carried out to electrocardiosignal and obtains frequency spectrum Figure, analyzes the heart rate variability of electrocardiosignal in frequency domain, and common frequency-domain analysis index includes：Low frequency power (LF), high frequency work( Rate (HF), general power (TF) and reflection sympathetic nerve and the ratio between the balanced low frequency power of vagus nerve and high frequency power LF/ HF etc..
By will the time and frequency parameter of acquisition be uploaded high in the clouds fatigue depth analysis system in real time, analysis drives present embodiment Whether member is in fatigue state.
Step 2.3：Collected electromyography signal is pre-processed, electromyography signal is transformed by frequency by Fast Fourier Transform (FFT) Frequency spectrum in domain or power spectrum extract electromyography signal feature, obtain the frequency of average power of electromyography signal power spectrum；And it will extraction The feature arrived uploads high in the clouds fatigue depth analysis system, analyzes driver fatigue state in real time；
Step 2.4：Discretization and normalization are carried out to collected steering wheel angle data, extraction steering wheel operation is special Sign calculates steering wheel angle variance and mean value；The control ability of steering wheel is declined when human body is in fatigue state, the side of causing Become larger to disk amplitude of fluctuation, therefore steering wheel angle variance is larger when fatigue and steering wheel times of revision is less.
Step 3：High in the clouds fatigue depth analysis system is built, specific method is：
Step 3.1：The personal more physiological signal data libraries of structure, driver personal essential information is inputted by intelligent terminal, Such as name, height, weight, it is preprocessed in driving procedure by harvester to collect a variety of physiological signals of the driver And personal more physiological signal data libraries are uploaded to after feature extraction；Since everyone physiological signal can be poor with others It is different, as everyone electrocardiosignal be it is unique, QRS wave amplitude, wave group interval time, QT waves the parameters such as amplitude All there is personalization；Driver identity is effectively identified by personal more physiological signal data libraries；
Step 3.2：The fatigue characteristic extraction model based on multi-physiological-parameter is built, convolutional neural networks or cycle god are utilized Through network as feature learning method, using the feature learnt as the defeated of the final such as tired grader of softmax graders Enter；By after discretization and normalized steering wheel angle data and it is preprocessed and extraction feature after electrocardio, myoelectricity, A certain number of test samples, including awake sample, tired sample are chosen in input of the pulse wave physiological parameter as neural network Very tired sample carries out neural metwork training, the fatigue characteristic extraction model based on convolutional neural networks is established, such as Fig. 4 institutes Show；
Step 3.3：The tired identification model based on tired grader is built, it is tired by what is extracted from convolutional neural networks Input of the labor feature as tired grader characteristic model, merges multi-source information depth analysis fatigue characteristic, it is tired to obtain driver Labor degree is predicted；In the present embodiment, driver's fatigue degree is divided into awake, tired and three kinds very tired.
Step 4：Safe early warning, high in the clouds fatigue depth analysis system is by the data analysis of acquisition and obtains as a result, will obtain To result provide by voice prompt driver and according to circumstances appropriate suggestion.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although Present invention has been described in detail with reference to the aforementioned embodiments, it will be understood by those of ordinary skill in the art that：It still may be used To modify to the technical solution recorded in previous embodiment, either which part or all technical features are equal It replaces；And these modifications or replacements, model defined by the claims in the present invention that it does not separate the essence of the corresponding technical solution It encloses.

Claims (10)

1. a kind of driving fatigue depth analysis early warning system based on multimode signal, it is characterised in that：It is adopted including more physiological signals Collect module, steering wheel angle data acquisition module, data transmission module, high in the clouds depth analysis module and safe early warning module；Institute It states more physiological signal collection modules and steering wheel angle data acquisition module is each attached on steering wheel, and output end is and data The input terminal of transmission module is connected；The output end of the data transmission module is connected with the input terminal of high in the clouds depth analysis module, The output end of high in the clouds depth analysis module is connected with the input terminal of safe early warning module.
2. a kind of driving fatigue depth analysis early warning system based on multimode signal according to claim 1, feature exist In：More physiological signal collection modules include pulse wave acquisition module, ecg signal acquiring module and electromyographic signal collection mould Block；The pulse wave acquisition module, ecg signal acquiring module and electromyographic signal collection module are each attached on steering wheel, and defeated Outlet is connected with data transmission module.
3. a kind of driving fatigue depth analysis early warning system based on multimode signal according to claim 1, feature exist In：The steering wheel angle data acquisition module is mounted in automobile steering dish axle, using steering wheel accelerator for detecting Steering wheel rotational frequency and corner size, output end are connected with data transmission module.
4. a kind of driving fatigue depth analysis early warning system based on multimode signal according to claim 1, feature exist In：The data transmission module, including sequentially connected micro-control unit MCU, amplifier, A/D converter, bluetooth and intelligence are eventually End, to from more physiological signal collection modules and steering wheel angle data collecting module collected to signal be amplified, pre-process, A/D is converted and transmission.
5. a kind of driving fatigue depth analysis early warning system based on multimode signal according to claim 1, feature exist In：The high in the clouds depth analysis module, including steering wheel angle data analysis module and the more physiological signal analysis modules of human body；Institute It states steering wheel angle data analysis module with data transmission module to be connected, receives steering wheel angle data information, and to driver Feature is analyzed and extracted to the frequency of steering wheel rotation when driving, corner size these data, calculates the equal of steering wheel angle Value and variance；The more physiological signal analysis modules of human body are connected with data transmission module, receive more physiological signal collection modules Physiological driver's signal of acquisition carries out feature extraction to the electrocardiosignal, pulse wave signal and electromyography signal of driver；And lead to It crosses deep neural network and carries out signature analysis, obtain driver's fatigue degree.
6. a kind of driving fatigue depth analysis early warning system based on multimode signal according to claim 1, feature exist In：The safe early warning module is connected with high in the clouds depth analysis module, and the driver obtained from high in the clouds depth analysis module is driven It sails state analysis result to timely feedback to driver, reminds whether driver is in fatigue driving state, and provide appropriate build View.
7. a kind of driving fatigue depth analysis early warning system based on multimode signal according to claim 1, feature exist In：The pulse collection module, using semiconductor pressure resistance sensor, the pulse wave for detecting driver；The electrocardiosignal Acquisition module, using textile electrode, the electrocardiosignal for detecting driver；The myoelectricity acquisition module equally uses fabric Electrode, the electromyography signal for detecting driver.
8. using a kind of driving fatigue depth analysis early warning system based on multimode signal described in claim 1 analyze pre- Alert method, it is characterised in that：Include the following steps：
Step 1：In driving procedure, more physiological signal collection modules contact steering wheel by driver's both hands and collect driver The a variety of physiological signals of human body of driver, including：Electrocardiosignal, electromyography signal and pulse wave signal；Meanwhile steering wheel angle number According to acquisition module, by driver, the steering wheel rotation when driving acquires steering wheel angle data；
Step 2：Step 1 is acquired by data transmission module more physiological signals of driver's human body and steering wheel angle data into Row transmission process；
Step 3：Build high in the clouds fatigue depth analysis system；
Step 4：Safe early warning, high in the clouds fatigue depth analysis system is by the data analysis of acquisition and obtains as a result, will get As a result appropriate suggestion is provided by voice prompt driver and according to circumstances.
9. a kind of driving fatigue depth analysis method for early warning based on multimode signal according to claim 8, feature exist In：The specific method of the step 2 is：
Step 2.1：Data transmission module pre-processes collected pulse wave signal；Pulse wave signal mainly by baseline drift, The influence of Hz noise and High-frequency Interference；Pulse wave signal is pre-processed using mathematical morphology, small echo is recycled to become It changes and main heavy wave crest feature extraction is carried out to pulse signal, the real-time blood pressure of driver is calculated according to the main heavy wave crest of the pulse wave of extraction Value；The amplitude of the main heavy wave crest of the pulse wave extracted and position feature are uploaded into high in the clouds depth analysis module, carry out tired shape State is analyzed；
Step 2.2：Collected electrocardiosignal pre-processes electrocardiosignal using wavelet transformation first, removes noise； The noise of the electrocardiosignal includes industrial frequency noise, baseline drift noise and myoelectricity interference noise；Again to the electrocardio of removal noise Signal extraction electrocardiosignal QRS wave group, finally analyzes heart rate variability to extracting the electrocardiosignal of R waves in time domain and in frequency domain Property (Heart Rate Variability, i.e. HRV)；
It is described extraction electrocardiosignal QRS wave group specific method be：
To passing through the pretreated electrocardiosignal of Wavelet Denoising Method first according to the waveform change rate of R waves in an ecg wave form period It is this feature extraction R waves of steepest, carrying out single order forward difference to electrocardiosignal compares, if a difference is more than a certain threshold value Occurs a failing edge after the rising edge of Tr again, and the difference of failing edge is more than this threshold value, then it is assumed that occur one greatly It is worth point, these maximum points are the R peak points given tacit consent to；Flase drop is carried out to R waves again and missing inspection excludes；After R waves determine, with each Centered on a R wave crest points, respectively in front and back specific time window, the detection of Q waves and S waves is carried out, is sentenced for personal ecg information It is fixed；
Step 2.3：Collected electromyography signal is pre-processed, electromyography signal is transformed into frequency domain by Fast Fourier Transform (FFT) Frequency spectrum or power spectrum, extract electromyography signal feature, obtain the frequency of average power of electromyography signal power spectrum；And it will extract Feature uploads high in the clouds fatigue depth analysis system, analyzes driver fatigue state in real time；
Step 2.4：Discretization and normalization are carried out to collected steering wheel angle data, extract steering wheel operation feature, meter Calculate steering wheel angle variance；The control ability of steering wheel is declined when human body is in fatigue state, leads to steering wheel amplitude of fluctuation Degree becomes larger, therefore steering wheel angle variance is larger when fatigue and steering wheel times of revision is less.
10. a kind of driving fatigue depth analysis method for early warning based on multimode signal according to claim 8, feature exist In：The specific method of the step 3 is：
Step 3.1：The personal more physiological signal data libraries of structure, driver personal essential information, such as surname are inputted by intelligent terminal Name, height, weight etc., it is preprocessed and special in driving procedure by harvester to collect a variety of physiological signals of the driver Personal more physiological signal data libraries are uploaded to after sign extraction；Due to everyone physiological signal can with others difference, such as Everyone electrocardiosignal be it is unique, QRS wave amplitude, wave group interval time, QT waves the parameters such as amplitude all have There is personalization；Driver identity is effectively identified by personal more physiological signal data libraries；
Step 3.2：The fatigue characteristic extraction model based on multi-physiological-parameter is built, convolutional neural networks or cycle nerve net are utilized Network is as feature learning method, using the feature learnt as the input of the final such as tired grader of softmax graders；It will The electrocardio after steering wheel angle data and preprocessed and extraction feature, myoelectricity, pulse after discretization and normalized Input of the wave physiological parameter as neural network, chooses a certain number of test samples, including awake sample, tired sample and non- Often fatigue sample carries out neural metwork training, establishes the fatigue characteristic extraction model based on convolutional neural networks；
Step 3.3：The tired identification model based on tired grader is built, the fatigue extracted from convolutional neural networks is special The input as tired grader characteristic model is levied, multi-source information depth analysis fatigue characteristic is merged, obtains driver fatigue journey Degree prediction.
CN201810552524.XA 2018-05-31 2018-05-31 Driving fatigue depth analysis early warning system based on multimode signal and method Pending CN108765876A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810552524.XA CN108765876A (en) 2018-05-31 2018-05-31 Driving fatigue depth analysis early warning system based on multimode signal and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810552524.XA CN108765876A (en) 2018-05-31 2018-05-31 Driving fatigue depth analysis early warning system based on multimode signal and method

Publications (1)

Publication Number Publication Date
CN108765876A true CN108765876A (en) 2018-11-06

Family

ID=64001511

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810552524.XA Pending CN108765876A (en) 2018-05-31 2018-05-31 Driving fatigue depth analysis early warning system based on multimode signal and method

Country Status (1)

Country Link
CN (1) CN108765876A (en)

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN109431498A (en) * 2018-11-14 2019-03-08 天津大学 Wearable multi-modal physiological driver's condition monitoring system
CN109559481A (en) * 2018-12-13 2019-04-02 平安科技（深圳）有限公司 Drive risk intelligent identification Method, device, computer equipment and storage medium
CN109591825A (en) * 2018-11-29 2019-04-09 北京新能源汽车股份有限公司 A kind of driving fatigue detection method, device and vehicle
CN109602403A (en) * 2018-12-05 2019-04-12 四川长虹电器股份有限公司 Fatigue driving detecting system and method
CN109884965A (en) * 2019-03-06 2019-06-14 扬州大学 Physiological driver's parameter monitoring and safe early warning cloud control system based on Internet of Things
CN109887239A (en) * 2019-03-16 2019-06-14 南京英诺微盛光学科技有限公司 It is a kind of for monitoring the wearable device and application method of fatigue driving
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
CN110196098A (en) * 2019-05-23 2019-09-03 山东理工大学 Vehicle sound quality evaluation method based on changes in heart rate
CN110491515A (en) * 2019-09-25 2019-11-22 江苏启润科技有限公司 Driving managing and control system and method based on vehicle-mounted human multi-parameter monitoring terminal
CN110638473A (en) * 2019-09-10 2020-01-03 中国平安财产保险股份有限公司 Method, device, electronic device and storage medium for determining fatigue driving
CN110796207A (en) * 2019-11-08 2020-02-14 中南大学 Fatigue driving detection method and system
CN110825232A (en) * 2019-11-07 2020-02-21 中国航天员科研训练中心 Gesture recognition man-machine interaction device based on medical insurance monitoring signals of astronaut
CN110909876A (en) * 2019-11-27 2020-03-24 上海交通大学 Sign information monitoring method and system based on multiple physiological parameters and CNN
CN111557673A (en) * 2020-04-22 2020-08-21 五邑大学 Automobile driving monitoring method, system and storage medium
CN111839506A (en) * 2019-04-30 2020-10-30 清华大学 Mental load detection method and device
CN111968341A (en) * 2020-08-21 2020-11-20 无锡威孚高科技集团股份有限公司 Fatigue driving detection system and method
CN112382053A (en) * 2020-10-29 2021-02-19 中国商用飞机有限责任公司 Method and system for monitoring the fatigue state of a crew member of an aircraft
CN112545530A (en) * 2020-06-18 2021-03-26 华南理工大学 Method for predicting drunk driving and fatigue driving based on HRV and countermeasure network
CN112572454A (en) * 2020-12-01 2021-03-30 浙江清华柔性电子技术研究院 Fatigue driving detection method and device and steering wheel equipment
CN112617772A (en) * 2021-01-05 2021-04-09 上海工程技术大学 Driving fatigue identification method and system based on pulse wave signals
CN112674721A (en) * 2020-12-25 2021-04-20 中科芯未来微电子科技成都有限公司 Multifunctional fatigue early warning and drunk driving detection steering wheel
CN113100776A (en) * 2021-04-20 2021-07-13 西北工业大学 Fatigue monitoring system and method fusing myoelectric signal and electrocardiosignal
CN113274029A (en) * 2021-05-25 2021-08-20 安徽安凯汽车股份有限公司 Passenger car driver vital sign information monitoring system
CN113555117A (en) * 2021-07-19 2021-10-26 江苏金海星导航科技有限公司 Driver health management system based on wearable device
CN114343661A (en) * 2022-03-07 2022-04-15 西南交通大学 Method, device and equipment for estimating reaction time of high-speed rail driver and readable storage medium
CN114454891A (en) * 2022-02-28 2022-05-10 奇瑞汽车股份有限公司 Automobile control method and device and computer storage medium
CN114613100A (en) * 2022-03-11 2022-06-10 北京悟空出行科技有限公司 Driver state monitoring method, device and system, electronic equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB0513488D0 (en) * 2004-07-01 2005-08-10 Mega Elektroniika Oy Method and device for measuring exercise level during exercise and for mearsuring tiredness
CN202995969U (en) * 2012-11-16 2013-06-12 西安众智惠泽光电科技有限公司 Automobile fatigue driving remote monitoring and real-time prompting system
CN103948394A (en) * 2014-04-04 2014-07-30 驻马店市金格尔电气设备有限公司 Fatigue driving detecting system and fatigue relief device
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
CN106073712A (en) * 2016-06-15 2016-11-09 南京理工大学 Driving based on heart physiological signal warning direction indicators cover device and signal detecting method
CN106691474A (en) * 2016-11-25 2017-05-24 中原电子技术研究所（中国电子科技集团公司第二十七研究所） Brain electrical signal and physiological signal fused fatigue detection system
CN107194346A (en) * 2017-05-19 2017-09-22 福建师范大学 A kind of fatigue drive of car Forecasting Methodology

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB0513488D0 (en) * 2004-07-01 2005-08-10 Mega Elektroniika Oy Method and device for measuring exercise level during exercise and for mearsuring tiredness
CN202995969U (en) * 2012-11-16 2013-06-12 西安众智惠泽光电科技有限公司 Automobile fatigue driving remote monitoring and real-time prompting system
CN103948394A (en) * 2014-04-04 2014-07-30 驻马店市金格尔电气设备有限公司 Fatigue driving detecting system and fatigue relief device
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
CN106073712A (en) * 2016-06-15 2016-11-09 南京理工大学 Driving based on heart physiological signal warning direction indicators cover device and signal detecting method
CN106691474A (en) * 2016-11-25 2017-05-24 中原电子技术研究所（中国电子科技集团公司第二十七研究所） Brain electrical signal and physiological signal fused fatigue detection system
CN107194346A (en) * 2017-05-19 2017-09-22 福建师范大学 A kind of fatigue drive of car Forecasting Methodology

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张驰: "基于脑/肌/眼电的疲劳驾驶检测技术的研究", 《工程科技Ⅱ辑》 *

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN109431498A (en) * 2018-11-14 2019-03-08 天津大学 Wearable multi-modal physiological driver's condition monitoring system
CN109591825A (en) * 2018-11-29 2019-04-09 北京新能源汽车股份有限公司 A kind of driving fatigue detection method, device and vehicle
CN109602403A (en) * 2018-12-05 2019-04-12 四川长虹电器股份有限公司 Fatigue driving detecting system and method
CN109559481A (en) * 2018-12-13 2019-04-02 平安科技（深圳）有限公司 Drive risk intelligent identification Method, device, computer equipment and storage medium
CN109884965A (en) * 2019-03-06 2019-06-14 扬州大学 Physiological driver's parameter monitoring and safe early warning cloud control system based on Internet of Things
CN109887239A (en) * 2019-03-16 2019-06-14 南京英诺微盛光学科技有限公司 It is a kind of for monitoring the wearable device and application method of fatigue driving
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
CN111839506A (en) * 2019-04-30 2020-10-30 清华大学 Mental load detection method and device
CN111839506B (en) * 2019-04-30 2021-10-12 清华大学 Mental load detection method and device
CN110196098A (en) * 2019-05-23 2019-09-03 山东理工大学 Vehicle sound quality evaluation method based on changes in heart rate
CN110638473A (en) * 2019-09-10 2020-01-03 中国平安财产保险股份有限公司 Method, device, electronic device and storage medium for determining fatigue driving
CN110491515A (en) * 2019-09-25 2019-11-22 江苏启润科技有限公司 Driving managing and control system and method based on vehicle-mounted human multi-parameter monitoring terminal
CN110825232A (en) * 2019-11-07 2020-02-21 中国航天员科研训练中心 Gesture recognition man-machine interaction device based on medical insurance monitoring signals of astronaut
CN110825232B (en) * 2019-11-07 2022-10-21 中国航天员科研训练中心 Gesture recognition man-machine interaction device based on medical insurance monitoring signals of astronaut
CN110796207B (en) * 2019-11-08 2023-05-30 中南大学 Fatigue driving detection method and system
CN110796207A (en) * 2019-11-08 2020-02-14 中南大学 Fatigue driving detection method and system
CN110909876A (en) * 2019-11-27 2020-03-24 上海交通大学 Sign information monitoring method and system based on multiple physiological parameters and CNN
CN111557673A (en) * 2020-04-22 2020-08-21 五邑大学 Automobile driving monitoring method, system and storage medium
CN112545530A (en) * 2020-06-18 2021-03-26 华南理工大学 Method for predicting drunk driving and fatigue driving based on HRV and countermeasure network
CN111968341A (en) * 2020-08-21 2020-11-20 无锡威孚高科技集团股份有限公司 Fatigue driving detection system and method
CN112382053B (en) * 2020-10-29 2022-06-14 中国商用飞机有限责任公司 Method and system for monitoring the fatigue state of a crew member of an aircraft
CN112382053A (en) * 2020-10-29 2021-02-19 中国商用飞机有限责任公司 Method and system for monitoring the fatigue state of a crew member of an aircraft
CN112572454A (en) * 2020-12-01 2021-03-30 浙江清华柔性电子技术研究院 Fatigue driving detection method and device and steering wheel equipment
CN112674721A (en) * 2020-12-25 2021-04-20 中科芯未来微电子科技成都有限公司 Multifunctional fatigue early warning and drunk driving detection steering wheel
CN112617772B (en) * 2021-01-05 2022-12-27 上海工程技术大学 Driving fatigue identification method and system based on pulse wave signals
CN112617772A (en) * 2021-01-05 2021-04-09 上海工程技术大学 Driving fatigue identification method and system based on pulse wave signals
CN113100776A (en) * 2021-04-20 2021-07-13 西北工业大学 Fatigue monitoring system and method fusing myoelectric signal and electrocardiosignal
CN113100776B (en) * 2021-04-20 2023-08-29 西北工业大学 Fatigue monitoring system and method for fusing myoelectricity and electrocardiosignal
CN113274029A (en) * 2021-05-25 2021-08-20 安徽安凯汽车股份有限公司 Passenger car driver vital sign information monitoring system
CN113555117A (en) * 2021-07-19 2021-10-26 江苏金海星导航科技有限公司 Driver health management system based on wearable device
CN114454891A (en) * 2022-02-28 2022-05-10 奇瑞汽车股份有限公司 Automobile control method and device and computer storage medium
CN114454891B (en) * 2022-02-28 2023-09-26 奇瑞汽车股份有限公司 Control method and device for automobile and computer storage medium
CN114343661A (en) * 2022-03-07 2022-04-15 西南交通大学 Method, device and equipment for estimating reaction time of high-speed rail driver and readable storage medium
CN114613100A (en) * 2022-03-11 2022-06-10 北京悟空出行科技有限公司 Driver state monitoring method, device and system, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN108765876A (en) Driving fatigue depth analysis early warning system based on multimode signal and method
US20200367800A1 (en) Method for identifying driving fatigue based on cnn-lstm deep learning model
CN102138789B (en) Dynamic electrocardiogram and motion recording and analyzing system
CN104952210B (en) A kind of fatigue driving state detecting system and method based on decision making level data fusion
CN108464839A (en) A kind of vehicle-mounted fatigue monitoring and early warning of driving system based on machine learning
CN110604565A (en) Brain health screening method based on portable EEG equipment
CN106691474A (en) Brain electrical signal and physiological signal fused fatigue detection system
CN204931634U (en) Based on the depression evaluating system of physiologic information
CN107080527B (en) Mental state monitoring method based on wearable vital sign monitoring device
CN105147248A (en) Physiological information-based depressive disorder evaluation system and evaluation method thereof
CN105595996A (en) Driving fatigue electroencephalogram monitoring method based on electrooculogram and electroencephalogram comprehensive determination
CN108392211A (en) A kind of fatigue detection method based on Multi-information acquisition
CN109953763A (en) A kind of vehicle carried driving behavioral value early warning system and method based on deep learning
CN102488512A (en) Automatic alarm system for electrocatdiogram monitoring and alarm method thereof
CN110123304B (en) Dynamic electrocardio noise filtering method based on multi-template matching and correlation coefficient matrix
CN114052744B (en) Electrocardiosignal classification method based on impulse neural network
CN106913333B (en) Method for selecting sensitivity characteristic index of continuous attention level
CN113288168A (en) Wearable fatigue monitoring of intelligence and early warning system
CN110367975A (en) A kind of fatigue driving detection method for early warning based on brain-computer interface
CN112057087B (en) Autonomic nerve function data processing method and device for high-risk schizophrenic people
CN106175754A (en) During sleep state is analyzed, waking state detects device
CN111297340A (en) Movement state monitoring method based on combination of GPS and heart rate
CN106618486B (en) Sleep state identification method and system in intelligent sleep assistance
CN106491118A (en) Real-time rate calculation system and method based on the electrocardiograph of Android system
CN204745287U (en) Therapeutical depression evaluation system of hypnotizeing based on rhythm of heart variability

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
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Xu Lisheng

Inventor after: Wang Hongju

Inventor after: Wu Chengyang

Inventor after: Zhu Chao

Inventor before: Wang Hongju

Inventor before: Wu Chengyang

Inventor before: Zhu Chao

WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20181106