CN109567832A - A kind of method and system of the angry driving condition of detection based on Intelligent bracelet - Google Patents
A kind of method and system of the angry driving condition of detection based on Intelligent bracelet Download PDFInfo
- Publication number
- CN109567832A CN109567832A CN201811311656.XA CN201811311656A CN109567832A CN 109567832 A CN109567832 A CN 109567832A CN 201811311656 A CN201811311656 A CN 201811311656A CN 109567832 A CN109567832 A CN 109567832A
- Authority
- CN
- China
- Prior art keywords
- angry
- driver
- parameter
- driving condition
- layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- 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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Abstract
Present invention relates particularly to a kind of methods for detecting angry driving condition based on Intelligent bracelet, include the following steps: step 1: using Intelligent bracelet, acquiring electrocardiosignal；Step 2: electrocardiosignal being inputted into parameter processing module, exports ecg characteristics parameter and individual difference sexual factor parameter；Step 3: ecg characteristics parameter and individual difference sexual factor parameter being inputted to the learning evaluation model of angry driving condition, obtain the angry mood grade of driver；Step 4: utilizing warning module, driver is reminded.A kind of system detecting angry driving condition based on Intelligent bracelet, driver wears Intelligent bracelet and smart phone in system, is provided on the driven vehicle of driver and analyzes host and can communicate with Intelligent bracelet, smart phone.The input feature vector of neural network is added in individual difference index by the present invention, will not interfere the normal driving of driver, improves the accuracy rate of driver's indignation mood assessments, realizes the emotional state of real-time detection driver.
Description
Technical field
The invention belongs to the technical applications that intelligence auxiliary drives, and are related to abnormal driving condition detection method, specifically relate to
And a kind of method and system that angry driving condition is detected based on Intelligent bracelet.
Background technique
In recent years further seriously by " the road anger disease " unhealthy emotion, related with Driver's Factors in traffic accident to account for
90%, how accurately to identify the angry mood of driver, effectively prevents and avoid the road caused by angry driving mood
Road traffic accidents are the development trends of following driver's indignation mood research.
In traditional driver's indignation Emotion identification research, on the one hand, scholars mostly using physiologic information (brain electricity,
Electrocardio, breathing, pulse etc.) it is used as judging quota, but there is still a need for dress a large amount of electrode or sensing for the measurement of physiologic information
Device will affect the normal driving behavior of driver in practical applications, is not able to satisfy and drives this particular surroundings.On the other hand,
There is researcher to propose to detect angry state using the facial video image of driver or voice signal as research object, drives
The facial video image and voice signal of people is easier to obtain, and will not influence the normal driving of driver, still, due to driving
Rotary head viewing surrounding road condition, the behaviors such as adjustment sitting posture, and the shadow of the sound of surrounding traffic participant are often had during sailing
It rings, biggish noise can be generated, the loss and distortion of emotion information is caused, influence recognition result.Therefore, current related indignation is driven
The research for sailing testing mechanism is low in the prevalence of Detection accuracy, it is at high cost, equipment operation is complicated, it is affected by environment it is big etc. no
Foot.
Summary of the invention
Detection accuracy is low when driving detection for indignation of the existing technology, at high cost, equipment operation is complicated, by ring
Border influences the problems such as big, the method for the angry driving condition of the detection that the invention proposes a kind of based on Intelligent bracelet, including as follows
Step:
Step 1: using the heart rate sensor built in Intelligent bracelet, acquiring electrocardiosignal；
Step 2: the electrocardiosignal that step 1 is acquired inputs parameter processing module, exports ecg characteristics parameter and individual difference
Anisotropic factor parameter；
Step 3: the ecg characteristics parameter and individual difference sexual factor parameter that step 2 is obtained input angry driving condition
Learning evaluation model exports the angry state of driver；
Step 4: the angry state for the driver that step 3 is obtained inputs warning module, and the warning module is according to driving
The angry grade of member reminds driver；
The establishment process of the learning evaluation model of the angry driving condition includes:
Establish three layers of BP neural network model, including input layer, hidden layer and output layer, the heart that will be handled in smart phone
The input layer of electrical feature parameter and individual difference sexual factor parameter as model selects node in hidden layer and establishes input layer extremely
Hidden layer, hidden layer and output layer transmission function obtain output layer, and output layer is used to export the angry mood grade of driver,
Training is iterated to three layers of BP neural network model, finally obtains the learning evaluation model of angry driving condition；
The ecg characteristics parameter includes: the mark of time interval RR interphase between heartbeat twice, relevant RR interphase
Quasi- difference SDNN, the root mean square RMSSD of adjacent R R interphase difference, adjacent R R interphase number Zhan total sinus property heartbeat of the difference greater than 50ms
The change rate of the percentage PNN50 and SDNN of number；
The individual difference sexual factor parameter includes gender parameter and C.C.N；
The gender parameter is two kinds: male and female respectively correspond 0 and 1；The C.C.N is four kinds: more
Blood matter, the quality of bile, melancholy and mucilaginous substance, respectively correspond: 2,3,4 and 5.
Further, the parameter processing module first pre-processes the collected electrocardiosignal of heart rate sensor, so
Afterwards by ecg characteristics parameter is calculated, the pretreatment, which refers to, is smoothed original electrocardiosignal, rejecting abnormalities
Value.
Further, the foundation of the learning evaluation model of the angry driving condition includes the following steps:
Step 1: establishing three layers of BP neural network model, the ecg characteristics parameter and individual difference that parameter processing module is obtained
The standard deviation that seven nodes are respectively RR interphase, RR interphase is arranged in input layer of the anisotropic factor as model, the input layer
SDNN, SDNN change rate, the root mean square RMSSD of adjacent R R interphase difference, the difference of adjacent R R interphase are total greater than the number Zhan of 50ms
Percentage PNN50, gender and the character trait of sinus property heartbeat number；
Step 2: rule of thumb formulaNode in hidden layer is selected, N represents the node of hidden layer in formula
Number, n represent the number of input layer, and m represents the number of output node layer, and a is constant, and wherein n=7, m=3, a are positive
Integer；
Step 3: using Logsig function as hidden layer and output layer transmission function, expression formula is
Result is exported between [0,1], setting output node layer is 3, and the output format of output layer is set as 100,010,001, so that
100, the three grades of 010, the 001 angry mood for respectively corresponding driver it is tranquil, it is slight indignation, severe indignation, by reversed
Propagation algorithm repetitive exercise corrects the threshold value and weight of neural network model, finally obtains the learning evaluation of angry driving condition
Model.
Further, the warning module receives angry state grade locating for the driver transmitted in analysis host, if
Driver is judged for angry driving condition, and the APP on smart phone automatically turns on sound, with the mode of voice prompting, to driving
Member is reminded.
A kind of system of the angry driving condition of detection based on Intelligent bracelet, in the system driver wear Intelligent bracelet with
Smart phone is provided with analysis host on the driven vehicle of driver, and the Intelligent bracelet and smart phone can be with analysis hosts
It is communicated；
The Intelligent bracelet is built-in with heart rate sensor, for acquiring electrocardiosignal；
The smart phone is built-in with APP, including parameter processing module parameter processing module is used for heart rate sensor
Collected ECG's data compression is ecg characteristics parameter and obtains and handle individual difference sexual factor parameter,
The analysis host is built-in with the learning evaluation model of angry driving condition, the study of the indignation driving condition
Assessment models can detect angry state grade locating for driver；
The smart phone and Intelligent bracelet collectively constitutes warning module, and warning module is used for according to analysis host transmitting
Driver angry state and driver is reminded；
The establishment process of the learning evaluation model of the angry driving condition includes:
Establish three layers of BP neural network model, including input layer, hidden layer and output layer, the heart that will be handled in smart phone
The input layer of electrical feature parameter and individual difference sexual factor parameter as model, select node in hidden layer and establish hidden layer with
Output layer transmission function obtains output layer, and output layer is used to export the angry mood grade of driver, to three layers of BP neural network
Model is iterated training, finally obtains the learning evaluation model of angry driving condition.
This method have it is following the utility model has the advantages that
(1) electrocardiosignal of the method acquisition driver carries out feelings using the learning evaluation model of angry driving condition
Thread evaluation, realizes the emotional state of real-time detection driver, based on without intrusion index, will not influence the normal driving of driver,
Individual difference index (gender and character trait) is added to the input feature vector of neural network, is constantly learnt based on BP neural network
The evaluation index of driver greatly improves the accuracy rate of driver's indignation mood assessments.
(2) the present system response time is short, and the angry mood of real-time judge driver and timely early warning may be implemented, drop
Low traffic accident probability.
(3) using Intelligent bracelet and smart phone as medium is reminded, equipment operation is simple.
Detailed description of the invention
Fig. 1 is the flow chart of the abnormal driving state monitoring method based on Intelligent bracelet and system；
Fig. 2 is that indignation of the invention drives early warning work flow diagram；
Fig. 3 is neural network structure schematic diagram of the invention；
Fig. 4 is the pictorial diagram of the abnormal driving condition monitoring system based on Intelligent bracelet.
Specific embodiment
The following provides a specific embodiment of the present invention, it should be noted that the invention is not limited to implement in detail below
Example, all equivalent transformations made on the basis of the technical solutions of the present application each fall within protection scope of the present invention.
A kind of method of the angry driving condition of detection based on Intelligent bracelet includes the following steps:
Step 1: being built-in with heart rate sensor using Intelligent bracelet, acquire electrocardiosignal；
Step 2: the electrocardiosignal that step 1 is acquired inputs parameter processing module, obtains ecg characteristics parameter and individual difference
Anisotropic factor parameter；
Step 3: the ecg characteristics parameter and individual difference sexual factor parameter that step 2 is obtained input angry driving condition
Learning evaluation model exports the angry state of driver；
Step 4: the angry state for the driver that step 3 is obtained inputs warning module, and the warning module is according to driving
The angry grade of member reminds driver；
The establishment process of the learning evaluation model of the angry driving condition includes:
Establish three layers of BP neural network model, including input layer, hidden layer and output layer, the heart that will be handled in smart phone
The input layer of electrical feature parameter and individual difference sexual factor parameter as model, select node in hidden layer and establish input layer with
Hidden layer, hidden layer and output layer transmission function obtain output layer, and output layer is used to export the angry mood grade of driver,
Training is iterated to three layers of BP neural network model, finally obtains the learning evaluation model of angry driving condition；
The ecg characteristics parameter includes: the mark of time interval RR interphase between heartbeat twice, relevant RR interphase
Quasi- difference SDNN, the root mean square RMSSD of adjacent R R interphase difference, adjacent R R interphase number Zhan total sinus property heartbeat of the difference greater than 50ms
The change rate of the percentage PNN50 and SDNN of number；
The individual difference sexual factor parameter includes gender parameter and C.C.N；
The gender parameter is two kinds: male and female respectively correspond 0 and 1；The C.C.N is four kinds: more
Blood matter, the quality of bile, melancholy and mucilaginous substance, respectively correspond: 2,3,4 and 5.
The method acquires the electrocardiosignal of driver, carries out mood using the learning evaluation model of angry driving condition and comments
Valence realizes the emotional state of real-time detection driver, will not influence the normal driving of driver, by individual difference index (property
Other and character trait) input feature vector of neural network is added, based on the evaluation index of the continuous learner driver of BP neural network, pole
The earth improves the accuracy rate of driver's indignation mood assessments.
Specifically, needing first collecting sample when establishing three layers of BP neural network model, being utilized to each sample in sample set
Heart rate sensor built in Intelligent bracelet acquires electrocardiosignal of each sample under neutral emotional state and in angry mood shape
Electrocardiosignal under state, the electrocardiosignal are the heart rate (HR) and heart rate variability (HRV) of driver.
Preferably, the sample set is chosen to be 50 student enrollment, first acquires subject and is in tranquility
Electrocardiosignal under neutral emotional state induces the angry mood of subject by laboratory using video image data, leads to
It crosses after preliminary experiment assures success and induce angry mood, electrocardiosignal of the subject under angry emotional state is acquired, by two kinds of numbers
According to source as the data supporting for analyzing and building model.
Specifically, the electrocardiosignal to acquisition pre-processes, the pretreatment refer to original electrocardiosignal is carried out it is flat
Sliding processing, excluding outlier, carrying out pretreatment to electrocardiosignal can establish for the extraction of the statistical analysis characteristic index of later data
Fixed basis；Then it carries out characteristic index again to extract to obtain characteristic parameter, the characteristic parameter is chosen aobvious with driver's indignation mood
Relevant RR interphase, the standard deviation SDNN of RR interphase, the root mean square RMSSD of adjacent R R interphase difference, adjacent R R interphase difference
The change rate of the percentage PNN50 and SDNN of the total sinus property heartbeat number of number Zhan greater than 50ms.
Studies have shown that the cerebration state of heart rate and heart rate variability metrics and human body is closely bound up, in normally driving
It sails and the heart rate under angry driving condition and heart rate variability metrics has significant difference, utilize heart rate and heart rate variability metrics
It can differentiate whether driver is in angry driving condition.
Wherein, SDNN is calculated according to the numerical value of n continuous RR interphases, and meaning is part slowly varying in HRV,
If being that a unit is analyzed with 20s, its calculation formula is:
In formula 1, heartbeat number is indicated with n, RRiIt is i-th of RR, RRmeanIt is the mean value of n RR；
The change rate of SDNN is acquired according to the variation of SDNN value, its calculation formula is:
In formula 2, SDNNi SDNNi+1Indicate the adjacent S DNN value that step 1 acquires；
RMSSD indicates the root mean square of adjacent R R interphase difference, its calculation formula is:
PNN50 indicates the percentage of number Zhan total sinus property heartbeat number totalNN of the difference greater than 50ms of adjacent R R interphase,
Its calculation formula is:
By the method for paired sample T test, the present invention extracted RR interphase, the standard deviation (SDNN) of RR interphase,
SDNN change rate, the root mean square (RMSSD) of adjacent R R interphase difference, PNN50 and the significant relevant physiology of driver's indignation state
Index feature is extracted and the gender and character trait of the significant relevant reflection individual difference of angry mood by ANOVA；
Specifically, the gender parameter is two kinds: male and female respectively correspond 0 and 1；The C.C.N is
Four kinds: sanguine temperament, the quality of bile, melancholy and mucilaginous substance respectively correspond 2,3,4 and 5.
Specifically, the foundation of the learning evaluation model of the indignation driving condition includes the following steps:
Step 1: establishing three layers of BP neural network model, the ecg characteristics parameter and individual difference that parameter processing module is obtained
The standard deviation that seven nodes are respectively RR interphase, RR interphase is arranged in input layer of the anisotropic factor as model, the input layer
Root mean square, PNN50, gender and the character trait of SDNN, SDNN change rate, adjacent R R interphase difference, and initialized, it is described
Initialization includes carrying out random initializtion to the weight of input layer to hidden layer, hidden layer to output layer as the value in [- 1,1]；
Step 2: rule of thumb formulaNode in hidden layer is selected, N represents the node of hidden layer in formula
Number, n represent the number of input layer, and m represents the number of output node layer, and a is constant, and wherein n=7, m=3, a are positive
Integer；
Step 3: using Logsig function as hidden layer and output layer transmission function, expression formula isResult is exported between [0,1], setting output node layer is 3, and the output format of output layer is set as
100,010,001 so that 100,010,001 respectively correspond the angry mood of driver three grades it is tranquil, it is slight indignation, again
Degree indignation, by back-propagation algorithm repetitive exercise, corrects the threshold value and weight of neural network model, finally obtains angry driving
The learning evaluation model of state.
Since Trainlm is back-propagation algorithm fast convergence rate, selecting it is function used in training network, according to accidentally
The weight and threshold value of poor constantly correction model connection, the error are specially estimating angry grade and obtaining for output layer output
Error between target indignation grade.
Through experimental tests, the present invention are higher than the accuracy rate of traditional technology, have reached 86.4% accuracy rate.
Further, the warning module receives angry state grade locating for the driver transmitted in analysis host, if
Driver is judged for angry driving condition, and the APP on smart phone automatically turns on sound, with the mode of voice prompting, to driving
Member carries out early warning.
A kind of system of the angry driving condition of detection based on Intelligent bracelet, in the system driver wear Intelligent bracelet with
Smart phone is provided with analysis host on the driven vehicle of driver, and the Intelligent bracelet and smart phone can be with analysis hosts
It is communicated；
The Intelligent bracelet is built-in with heart rate sensor, for acquiring electrocardiosignal；
The smart phone is built-in with APP, including parameter processing module parameter processing module is used for heart rate sensor
Collected ECG's data compression is ecg characteristics parameter and obtains and handle individual difference sexual factor parameter,
The analysis host is built-in with the learning evaluation model of angry driving condition, the study of the indignation driving condition
Assessment models can detect which kind of angry state driver is in；
The smart phone and Intelligent bracelet collectively constitutes warning module, and warning module is used for according to analysis host transmitting
Driver angry state and driver is reminded；
The establishment process of the learning evaluation model of the angry driving condition includes:
Establish three layers of BP neural network model, including input layer, hidden layer and output layer, the heart that will be handled in smart phone
The input layer of electrical feature parameter and individual difference sexual factor parameter as model, select node in hidden layer and establish input layer with
Hidden layer, hidden layer and output layer transmission function obtain output layer, and output layer is used to export the angry mood grade of driver,
Training is iterated to three layers of BP neural network model, finally obtains the learning evaluation model of angry driving condition.
The workflow of the system of the angry driving condition of the detection based on Intelligent bracelet comprises the following steps:
Step 1: Intelligent bracelet is worn at the wrist of driver, acquires the electrocardiogram (ECG) data of driver；
Step 2: the collected electrocardiogram (ECG) data of step 1 being pre-processed, guarantees the reliability of data, reduces collection process
Middle error；
Step 3: smart phone carries out Data Management Analysis to according to the received electrocardiogram (ECG) data of step 2, obtains heart rate and anger
The significant relevant electrocardiosignal characteristic parameter index value of anger mood and individual difference factor index parameter value；
Step 4: heart rate, heart rate variability metrics and the input of individual difference factor index parameter value that step 3 is obtained
Angry emotional prediction model；
Step 5: grade classification being carried out to angry prediction result according to the output valve of angry prediction model, judges driver's
Angry grade；
Step 6: emotional state locating for driver being assessed in conjunction with status predication result angry in step 5, and root
Angry warning grade is divided into no early warning, slight early warning and severe early warning according to security situation, and passes through Intelligent bracelet and intelligent hand
Machine APP accurately takes different degrees of intervening measure, and driver is reminded to chill out, and prevents driver's indignation from driving, protection
Traffic safety.
Claims (8)
1. a kind of method of the angry driving condition of detection based on Intelligent bracelet, which comprises the steps of:
Step 1: using the heart rate sensor built in Intelligent bracelet, acquiring electrocardiosignal；
Step 2: the electrocardiosignal that step 1 is acquired inputs parameter processing module, exports ecg characteristics parameter and individual difference
Factor parameter；
Step 3: the ecg characteristics parameter and individual difference sexual factor parameter that step 2 is obtained input the study of angry driving condition
Assessment models export the angry mood grade of driver；
Step 4: the angry mood grade for the driver that step 3 is obtained inputs warning module, and the warning module is according to driving
The angry grade of member reminds driver；
The establishment process of the learning evaluation model of the angry driving condition includes:
Three layers of BP neural network model, including input layer, hidden layer and output layer are established, by the electrocardio handled in smart phone spy
Input layer as model of parameter and individual difference sexual factor parameter is levied, node in hidden layer is selected and establishes input layer to implying
Layer, hidden layer and output layer transmission function, output layer is used to export the angry mood grade of driver, to three layers of BP neural network
Model is iterated training, finally obtains the learning evaluation model of angry driving condition；
The ecg characteristics parameter includes: time interval RR interphase between heartbeat twice, the standard deviation SDNN of RR interphase, phase
The root mean square RMSSD of adjacent RR interphase difference, the difference of adjacent R R interphase are greater than the percentage of the total sinus property heartbeat number of number Zhan of 50ms
Than the change rate of PNN50 and SDNN；
The individual difference sexual factor parameter includes gender parameter and C.C.N；
The gender parameter is two kinds: male and female respectively correspond 0 and 1；
The C.C.N is four kinds: sanguine temperament, the quality of bile, melancholy and mucilaginous substance respectively correspond: 2,3,4 and 5.
2. the method for the angry driving condition of detection as described in claim 1 based on Intelligent bracelet, which is characterized in that the ginseng
Number processing module first pre-processes the collected electrocardiosignal of heart rate sensor, then by ecg characteristics ginseng is calculated
Number, the pretreatment, which refers to, is smoothed original electrocardiosignal, excluding outlier.
3. the method for the angry driving condition of detection as described in claim 1 based on Intelligent bracelet, which is characterized in that the anger
The foundation of the learning evaluation model of anger driving condition includes the following steps:
Step 1: establishing three layers of BP neural network model, the ecg characteristics parameter and individual difference that parameter processing module is obtained
Input layer of the factor as model, the input layer be arranged seven nodes be respectively RR interphase, RR interphase standard deviation SDNN,
SDNN change rate, the root mean square RMSSD of adjacent R R interphase difference, adjacent R R interphase difference be greater than 50ms the total Dou Xingxin of number Zhan
Percentage PNN50, gender and the character trait for number of fighting；
Step 2: rule of thumb formulaNode in hidden layer is selected, N represents the node number of hidden layer in formula,
N represents the number of input layer, and the number a that m represents output node layer is constant, and wherein n=7, m=3, a are positive integer；
Step 3: using Logsig function as hidden layer and output layer transmission function, expression formula isOutput
As a result between [0,1], setting output node layer is 3, and the output format of output layer is set as 100,010,001, so that 100,
010, the three grades of the 001 angry mood for respectively corresponding driver it is tranquil, it is slight indignation, severe indignation, pass through backpropagation
Algorithm iteration training, corrects the threshold value and weight of neural network model, finally obtains the learning evaluation model of angry driving condition.
4. the method for the angry driving condition of detection as described in claim 1 based on Intelligent bracelet, which is characterized in that described pre-
Alert module receives angry state grade locating for the driver for the prediction transmitted in analysis host, if judging, driver drives for indignation
State is sailed, the APP on smart phone automatically turns on sound and reminded with the mode of voice prompting driver.
5. a kind of system of the angry driving condition of detection based on Intelligent bracelet, which is characterized in that driver wears in the system
Intelligent bracelet and smart phone are provided with analysis host, the Intelligent bracelet and smart phone energy on the driven vehicle of driver
It is communicated with analysis host；
The Intelligent bracelet is built-in with heart rate sensor, for acquiring electrocardiosignal；
The smart phone is built-in with APP, including parameter processing module, and parameter processing module is for acquiring heart rate sensor
To ECG's data compression be ecg characteristics parameter and obtain and handle individual difference sexual factor parameter.
The analysis host is built-in with the learning evaluation model of angry driving condition, the learning evaluation of the indignation driving condition
Model can detect the angry mood grade of driver；
The smart phone and Intelligent bracelet collectively constitutes warning module, and warning module is used for driving according to analysis host transmitting
The angry state for the person of sailing and driver is reminded；
The establishment process of the learning evaluation model of the angry driving condition includes:
Three layers of BP neural network model, including input layer, hidden layer and output layer are established, by the electrocardio handled in smart phone spy
The input layer of parameter and individual difference sexual factor parameter as model is levied, node in hidden layer is selected and establishes input layer and implies
The transmission function of layer, hidden layer and output layer obtains output layer, and output layer is used to export the angry mood grade of driver, right
Three layers of BP neural network model are iterated training, finally obtain the learning evaluation model of angry driving condition.
The ecg characteristics parameter includes: time interval RR interphase, the standard deviation of relevant RR interphase between heartbeat twice
SDNN, the root mean square RMSSD of adjacent R R interphase difference, adjacent R R interphase difference be greater than 50ms the total sinus property heartbeat number of number Zhan
Percentage PNN50 and SDNN change rate；
The individual difference sexual factor parameter includes gender parameter and C.C.N；
The gender parameter is two kinds: male and female respectively correspond 0 and 1；
The C.C.N is four kinds: sanguine temperament, the quality of bile, melancholy and mucilaginous substance respectively correspond 2,3,4 and 5.
6. the system of the angry driving condition of detection as claimed in claim 5 based on Intelligent bracelet, which is characterized in that the ginseng
Number processing module first pre-processes the collected electrocardiosignal of heart rate sensor, then by ecg characteristics ginseng is calculated
Number, the pretreatment, which refers to, is smoothed original electrocardiosignal, excluding outlier.
7. the system of the angry driving condition of detection as claimed in claim 5 based on Intelligent bracelet, which is characterized in that the anger
The foundation of the learning evaluation model of anger driving condition includes the following steps:
Step 1: establishing three layers of BP neural network model, the ecg characteristics parameter and individual difference that parameter processing module is obtained
Input layer of the factor as model, the input layer be arranged seven nodes be respectively RR interphase, RR interphase standard deviation SDNN,
SDNN change rate, the root mean square RMSSD of adjacent R R interphase difference, adjacent R R interphase difference be greater than 50ms the total Dou Xingxin of number Zhan
Percentage PNN50, gender and the character trait for number of fighting；
Step 2: rule of thumb formulaNode in hidden layer is selected, N represents the node number of hidden layer in formula,
N represents the number of input layer, and the number a that m represents output node layer is constant, and wherein n=7, m=3, a are positive integer；
Step 3: using Logsig function as hidden layer and output layer transmission function, expression formula isOutput
As a result between [0,1], setting output node layer is 3, and the output format of output layer is set as 100,010,001, so that 100,
010, the three grades of the 001 angry mood for respectively corresponding driver it is tranquil, it is slight indignation, severe indignation, pass through backpropagation
Algorithm iteration training, corrects the threshold value and weight of neural network model, finally obtains the learning evaluation model of angry driving condition.
8. the system of the angry driving condition of detection as claimed in claim 5 based on Intelligent bracelet, which is characterized in that described pre-
Alert module receives angry state grade locating for the driver for the prediction transmitted in analysis host, if judging, driver drives for indignation
State is sailed, the APP on smart phone automatically turns on sound and reminded with the mode of voice prompting driver.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811311656.XA CN109567832A (en) | 2018-11-06 | 2018-11-06 | A kind of method and system of the angry driving condition of detection based on Intelligent bracelet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811311656.XA CN109567832A (en) | 2018-11-06 | 2018-11-06 | A kind of method and system of the angry driving condition of detection based on Intelligent bracelet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109567832A true CN109567832A (en) | 2019-04-05 |
Family
ID=65921560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811311656.XA Pending CN109567832A (en) | 2018-11-06 | 2018-11-06 | A kind of method and system of the angry driving condition of detection based on Intelligent bracelet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109567832A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112370037A (en) * | 2020-11-24 | 2021-02-19 | 惠州华阳通用电子有限公司 | Safe driving method and system based on emotion recognition |
| CN113303796A (en) * | 2021-04-22 | 2021-08-27 | 华中科技大学同济医学院附属协和医院 | Automatic psychological tester for tumor patients and testing method thereof |
| CN114098729A (en) * | 2020-08-27 | 2022-03-01 | 北京晶栈信息技术有限公司 | Emotional state objective measurement method based on cardiac interval |
| CN116453289A (en) * | 2022-01-06 | 2023-07-18 | 中国科学院心理研究所 | Bus driving safety early warning method and system based on electrocardiosignal |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6366207B1 (en) * | 2000-02-04 | 2002-04-02 | Michael Murphy | Device for modifying vehicle operator driving behavior |
| CN107235045A (en) * | 2017-06-29 | 2017-10-10 | 吉林大学 | Consider physiology and the vehicle-mounted identification interactive system of driver road anger state of manipulation information |
| CN107662611A (en) * | 2017-11-06 | 2018-02-06 | 吉林大学 | A kind of automatic driving mode switching system based on driver's Emotion identification |
-
2018
- 2018-11-06 CN CN201811311656.XA patent/CN109567832A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6366207B1 (en) * | 2000-02-04 | 2002-04-02 | Michael Murphy | Device for modifying vehicle operator driving behavior |
| CN107235045A (en) * | 2017-06-29 | 2017-10-10 | 吉林大学 | Consider physiology and the vehicle-mounted identification interactive system of driver road anger state of manipulation information |
| CN107662611A (en) * | 2017-11-06 | 2018-02-06 | 吉林大学 | A kind of automatic driving mode switching system based on driver's Emotion identification |
Non-Patent Citations (5)
| Title |
|---|
| 刘鲁蓉等: "《管理心理学》", 31 August 2017, 中国中医药出版社 * |
| 崔峻岭等: "《土壤水地下水联合管理技术》", 31 May 2016, 中国海洋大学出版社 * |
| 李英春等: "基于生理信号的情绪识别腕戴设备", 《测控技术与仪器仪表》 * |
| 汪小华等: "《心血管病护理学》", 30 March 2013, 苏州大学出版社 * |
| 郭双等: "驾驶员人格对驾驶愤怒的影响", 《中国健康心理学杂志》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114098729A (en) * | 2020-08-27 | 2022-03-01 | 北京晶栈信息技术有限公司 | Emotional state objective measurement method based on cardiac interval |
| CN114098729B (en) * | 2020-08-27 | 2023-11-10 | 中国科学院心理研究所 | Heart interval-based emotion state objective measurement method |
| CN112370037A (en) * | 2020-11-24 | 2021-02-19 | 惠州华阳通用电子有限公司 | Safe driving method and system based on emotion recognition |
| CN112370037B (en) * | 2020-11-24 | 2022-10-14 | 惠州华阳通用电子有限公司 | Safe driving method and system based on emotion recognition |
| CN113303796A (en) * | 2021-04-22 | 2021-08-27 | 华中科技大学同济医学院附属协和医院 | Automatic psychological tester for tumor patients and testing method thereof |
| CN116453289A (en) * | 2022-01-06 | 2023-07-18 | 中国科学院心理研究所 | Bus driving safety early warning method and system based on electrocardiosignal |
| CN116453289B (en) * | 2022-01-06 | 2024-02-20 | 中国科学院心理研究所 | Bus driving safety early warning method and system based on electrocardiosignal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109543526B (en) | True and false facial paralysis recognition system based on depth difference characteristics | |
| US11793406B2 (en) | Image processing method and corresponding system | |
| CN105877766B (en) | A kind of state of mind detection system and method based on the fusion of more physiological signals | |
| CN109567832A (en) | A kind of method and system of the angry driving condition of detection based on Intelligent bracelet | |
| CN106446811A (en) | Deep-learning-based driver's fatigue detection method and apparatus | |
| CN107979985B (en) | Vehicle-mounted healthy and safe driving auxiliary device | |
| CN111544015B (en) | Cognitive power-based control work efficiency analysis method, device and system | |
| CN105139029B (en) | A kind of Activity recognition method and device of prison prisoner | |
| CN104720796A (en) | Automatic detecting system and method for epileptic attack time period | |
| CN106128032A (en) | A kind of fatigue state monitoring and method for early warning and system thereof | |
| CN113095302B (en) | Depth model for arrhythmia classification, method and device using same | |
| CN110448281A (en) | A kind of wearable work fatigue detection system based on multisensor | |
| CN107609477A (en) | It is a kind of that detection method is fallen down with what Intelligent bracelet was combined based on deep learning | |
| CN109953763A (en) | A kind of vehicle carried driving behavioral value early warning system and method based on deep learning | |
| CN111466878A (en) | Real-time monitoring method and device for pain symptoms of bedridden patients based on expression recognition | |
| CN106667506A (en) | Method and device for detecting lies on basis of electrodermal response and pupil change | |
| CN114358194A (en) | Gesture tracking based detection method for abnormal limb behaviors of autism spectrum disorder | |
| CN109875583A (en) | A kind of fatigue driving detecting system and method based on AR technology | |
| CN105303771A (en) | Fatigue judging system and method | |
| Wang et al. | Detection of driver stress in real-world driving environment using physiological signals | |
| Mallol-Ragolta et al. | harAGE: a novel multimodal smartwatch-based dataset for human activity recognition | |
| CN112617772B (en) | Driving fatigue identification method and system based on pulse wave signals | |
| CN111281403B (en) | Fine-grained human body fatigue detection method and device based on embedded equipment | |
| CN112370058A (en) | Method for identifying and monitoring emotion of user based on mobile terminal | |
| CN109620263B (en) | Physical sign safety analysis method for post workers in enterprises and public institutions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190405 |