CN106781283A - A kind of method for detecting fatigue driving based on soft set - Google Patents
A kind of method for detecting fatigue driving based on soft set Download PDFInfo
- Publication number
- CN106781283A CN106781283A CN201611244964.6A CN201611244964A CN106781283A CN 106781283 A CN106781283 A CN 106781283A CN 201611244964 A CN201611244964 A CN 201611244964A CN 106781283 A CN106781283 A CN 106781283A
- Authority
- CN
- China
- Prior art keywords
- soft set
- fatigue driving
- surface electromyogram
- driver
- electromyogram signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- A61B5/24—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
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
- A61B2503/22—Motor vehicles operators, e.g. drivers, pilots, captains
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Emergency Management (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of method for detecting fatigue driving based on soft set, comprise the following steps：S1, gathers the surface electromyogram signal of the default muscle sites in predetermined time of driver；S2, extracts and analyzes the muscular states feature of the surface electromyogram signal；S3, the tired quantitative model based on soft set is set up according to the electromyographic signal for extracting；S4, fatigue driving decision content is calculated according to the tired quantitative model based on soft set.The present invention is by gathering driver's surface electromyogram signal, and after pretreatment is analyzed to surface electromyogram signal, abnormal data in signal Analysis, surface electromyogram signal to driver carries out Analysis of Policy Making, the degree of fatigue of each time period driver is drawn, so as to the tired decrease speed of driver can be analyzed；It is realized when ensureing that key message retains, and data is analyzed, is simplified and decision-making, can substantially reduce the knowledge representation space dimensionality of object.To the selection unrestriction of parameter.
Description
Technical field
The present invention relates to a kind of method for detecting fatigue driving based on soft set, belong to intelligent transportation field.
Background technology
As a kind of common, the physiological phenomenon of complexity will result directly in the alertness reduction of driver, reacts slow fatigue
It is slow, it is easy to cause traffic accident, the life security to driver causes very big threat.But, tired and non-fatigue
Separation is difficult to determine, can be described as to a certain extent uncertain, varies with each individual.From for this point, fatigue detecting
The problems such as recognizing problem such as Face datection than other classical modes is more difficult.In addition, degree of fatigue on earth how
It is difficult to determine so that fatigue state is difficult to classify and measures.
At present to the research of fatigue driving detection in, the change for being mainly all based on physiology signal under driving environment is entered
Capable, its main purpose is that the physiological status such as clear-headed, tired, sleepy of driver is measured.Surface electromyogram signal is people
Body move when neuron-muscular activity produce bioelectrical signals, can reflect to a certain extent human body physiological activity state and
Functional status.But, the difficult point of current fatigue-driving detection technology is：The signal for collecting have some it is uncertain because
Element, and current theory (such as probability theory, blind number theory, fuzzy set theory, rough set theory, interval mathematical theory etc. are all
For processing probabilistic mathematical tool) in for determine parameter instrument it is considerably less, cause quantity of parameters to determine, this
One problem is to use these theoretical bottlenecks.
The content of the invention
It is an object of the present invention to provide a kind of method for detecting fatigue driving based on soft set, he can solve currently
Problem present in technology, realizes, in the case where ensureing that key message retains, being analyzed data, simplifying and decision-making, energy
Enough substantially reduce the knowledge representation space dimensionality of object.To the selection unrestriction of parameter.
In order to solve the above technical problems, the present invention is adopted the following technical scheme that：A kind of fatigue driving based on soft set
Detection method, comprises the following steps：
S1, gathers the surface electromyogram signal of the default muscle sites in predetermined time of driver；
S2, extracts and analyzes the muscular states feature of the surface electromyogram signal；
S3, the tired quantitative model based on soft set is set up according to the electromyographic signal for extracting；
S4, fatigue driving decision content is calculated according to the tired quantitative model based on soft set.
Preferably, in the step S1, the default muscle sites include neck Superior trapezius, shoulder deltoid muscle, back
Latissimus dorsi, lower limb rectus femoris, musculus vastus lateralis and gastrocnemius.
Preferably, in the step S1, using Wavelet noise-eliminating method and empirical mode decomposition Threshold Denoising Method to collection
To the surface electromyogram signal pre-processed, so as to remove during the collection of signal, pickup, conditioning because by extraneous
Noise jamming and the invalid information that produces.
Preferably, the step S2 includes：Using mean square root method, median frequency method or fuzzy approximation entropy algorithm to described
Surface electromyogram signal is analyzed, and obtains the muscular states feature of surface electromyogram signal.
Preferably, the step S3 includes：The fatigue state that the first soft set (F, E) characterizes driver is set, wherein, opinion
Domain U is set of the driver in muscular states feature not in the same time, i.e. U={ h1,h2,h3,h4...h25, E is parameter set, ginseng
Number is the fuzzy approximation entropy of the surface electromyogram signal, entropy algorithm statistics value stabilization, strong antijamming capability, to mixed signal
It is adaptable, and the change of result curve has preferable uniformity with body state change.
It is furthermore preferred that the step S3 also includes：The degree of correlation according to each parameter in E and body state is respectively provided with each ginseng
Several weights, weight and first soft set according to each parameter obtain the second soft set (T, E).
It is furthermore preferred that calculating the degree of correlation of each parameter and body state in E using line fitting method.
It is furthermore preferred that the step S3 also includes：Judge the abnormal data in second soft set (T, E), and to institute
Abnormal data is stated to be processed.
It is furthermore preferred that the formula for judging the abnormal data in second soft set (T, E) is：And make the abnormal data hij=*, obtains the 3rd soft set { T, E*, so as to avoid
Using some beyond the abnormal data of normal range (NR), cause the consequences such as incorrect decision or application error.
It is furthermore preferred that by the 3rd soft set { T, the E*In abnormal data before and after the average value of two groups of data enter
Row is replaced, and obtains the 4th soft set { G, E }, using the 4th soft set { G, E }, final decision content is obtained, so that using less
Data draw desired replacement values, simplify algorithm.
It is furthermore preferred that in the step S4：The circular of the decision content is：di=e1′+e2′+e3′+e4′+
e5′+e6', giving fatigue pre-warning threshold value is set according to the decision content, when decision content reaches the giving fatigue pre-warning threshold value, output alarm
Information, such that it is able to analyze body fatigue decline speed, it is proposed that driver rests in time, can be prevented effectively from traffic thing
Therefore generation.
Compared with prior art, it is of the invention by gathering six kinds of surface electromyogram signals of driver, and to surface electromyogram signal
After being analyzed pretreatment, using the abnormal data in soft set method signal Analysis, the surface electromyogram signal to driver enters
Row Analysis of Policy Making, draws the degree of fatigue of each time period driver, so as to the tired decrease speed of driver can be analyzed.It is real
Show in the case where ensureing that key message retains, data have been analyzed, are simplified and decision-making, knowing for object can have been substantially reduced
Know expression of space dimension；To the selection unrestriction of parameter, i.e., we detect that the parameter of fatigue driving can be arbitrary, embody
The a certain feature of object, six parameters that such as we select in the present invention, parameter value are not limited in form in the selection of parameter
It is a value for normalized of surface electromyogram signal, so that the means of detection can suitably be adjusted according to actual conditions, more
Various practicality.
Brief description of the drawings
Fig. 1 is the surface flesh schematic diagram measured by the embodiment of the present invention；
Fig. 2 is the fitting a straight line figure of latissimus dorsi provided in an embodiment of the present invention, rectus femoris and the Superior trapezius degree of correlation, its
Middle circular expression latissimus dorsi, five-pointed star represent that Superior trapezius, triangle represent latissimus dorsi；
Fig. 3 is the schematic flow sheet of the embodiment of the present invention；
Fig. 4 is human muscle's stress diagram in driving condition；
Fig. 5 is human muscle's force analysis schematic diagram in driving condition.
The present invention is further illustrated with reference to the accompanying drawings and detailed description.
Specific embodiment
Embodiments of the invention：A kind of method for detecting fatigue driving based on soft set, as shown in figure 3, including following step
Suddenly：
S1, gathers the surface electromyogram signal of the default muscle sites in predetermined time of driver；Including neck Superior trapezius,
Shoulder deltoid muscle, back latissimus dorsi, lower limb rectus femoris, musculus vastus lateralis and gastrocnemius, and utilize Wavelet noise-eliminating method and Empirical Mode
State decomposition threshold denoising method is pre-processed to the surface electromyogram signal for collecting.In driving procedure, the head of people,
The weight of arm, neck and upper torso is born by the muscle of back protuberance, ischium position and its attachment, such as Fig. 4
With shown in Fig. 5.Buttocks muscles and femoral region are located at ischium lower section, and when driving, buttocks and thigh Surrounding muscles are due to being subject to
Static load pressure and deform, the nutrition input of the circulatory system and the exclusion of metabolin are affected, with the increasing of driving time
Plus lactic acid gathers, cause muscular fatigue and ache.In driving procedure, the motion of neck is the most frequent, the motility of neck and steady
Qualitatively maintain to be completed mainly by muscle and articular ligament, neck joint mainly plays a supportive role, therefore carries out musculi colli
Detection is extremely necessary.Deltoid muscle is located at the junction of shoulder and upper limbs, can make shoulder abduction, and its anterior muscle fibre is received
Contracting can make shoulder joint anteflexion and omit medial rotation；Rear portion muscle fibers contract is stretched and slightly outside rotation after can making shoulder joint.During driving, human body both arms
Abduction control direction disk, the deltoid muscle moment is in running order, and the degree of fatigue of deltoid muscle has larger shadow to the state of driver
Ring, so deltoid muscle is one of target site of sEMG collections.
The present embodiment chooses six muscle at strong correlation position for collection surface electromyographic signal altogether, respectively on neck tiltedly
Quadratus, shoulder deltoid muscle, back latissimus dorsi, lower limb rectus femoris, musculus vastus lateralis and gastrocnemius, muscle distribution situation are as shown in Figure 1.
By the method for fuse information, an integrality of human body, the more accurate reliability of conclusion for so drawing, it is not easy to receive are assessed
External environment influences, strong robustness.Due to surface electromyogram signal be it is a kind of it is non-linear it is unstable, with lot of complexity and nature
The signal of chaos.Denoising method based on wavelet decomposition can preferably keep the energy feature of original signal, and being set by threshold value can
To eliminate certain High-frequency Interference and low-frequency disturbance, but still there are many burrs, illustrate that high-frequency noise has certain residual.Experience
Fixed noise is eliminated after mode decomposition filtering, signal is more obvious to high-frequency noise denoising effect, but EMD (Empirical
Mode Decomposition empirical mode decompositions) there is certain mode mixing phenomenon.Two methods are used simultaneously, are carried out pre-
Treatment, while if, having filter effect to high and low frequency noise.It is exactly a kind of balance, is used in combination effect more preferable.
S2, extracts and analyzes the muscular states feature of the surface electromyogram signal, including：Using mean square root method, middle position frequently
Rate method or fuzzy approximation entropy algorithm are analyzed to the surface electromyogram signal, and the muscular states for obtaining surface electromyogram signal are special
Levy.
S3, the tired quantitative model based on soft set is set up according to the electromyographic signal for extracting, that is, set the first soft collection
The fatigue state that (F, E) characterizes driver is closed, wherein, domain U is set of the driver in muscular states feature not in the same time,
That is U={ h1,h2,h3,h4...h25, h1-h25It is to represent not in the same time, E is parameter set, parameter is the surface electromyogram signal
Fuzzy approximation entropy, the degree of correlation of each parameter and body state in E, each parameter and human body in E are calculated using line fitting method
The degree of correlation of state is respectively provided with the weight of each parameter, and weight and first soft set according to each parameter obtains
Two soft sets (T, E), and judge the abnormal data in second soft set (T, E), judge second soft set (T, E)
In the formula of abnormal data be：And make the abnormal data hij=*, obtains the 3rd
Soft set { T, E*, by the 3rd soft set { T, the E*In abnormal data before and after the average value of two groups of data replaced
Change, i.e. *ij=(hi-1,j+hi+1,j)/2, draw the 4th soft set { G, E }, final soft according to the 4th using soft set decision-making technique
Set { G, E }, obtains decision content.Abnormal data is a certain moment, and some muscle signals are beyond expected or collection data
Exception directly is occurred in that, is judged by certain method, processed as abnormal data.Judge that abnormal data is heavier
The step of wanting, it can allow result more reliable accurate, be replaced using the average value of front and rear two groups of data when replacing abnormal data
Change, only need to draw desired replacement values using less data, simplify algorithm.
S4, fatigue driving decision content, the decision content are calculated according to the tired quantitative model based on soft set
Circular be：di=e1′+e2′+e3′+e4′+e5′+e6', giving fatigue pre-warning threshold value is set according to the decision content, when
When decision content reaches the giving fatigue pre-warning threshold value, warning message is exported to driver.By The inventive method achieves in guarantor
In the case that card key message retains, data are analyzed, are simplified and decision-making, the knowledge representation that can substantially reduce object is empty
Between dimension；To the selection unrestriction of parameter, i.e., we detect that the parameter of fatigue driving can be arbitrary, be embodied in parameter
Selection is not limited to a certain feature of object in form, and six parameters that such as we select in the present invention, parameter value is surface flesh
One value of normalized of electric signal, so that the means of detection can suitably be adjusted according to actual conditions, more various practicality.
The present inventor has also done following work, and the present invention is demonstrated by another embodiment, specific as follows：
Measure deltoid muscle, latissimus dorsi, Superior trapezius, rectus femoris, six kinds of surface fleshes of musculus vastus lateralis and gastrocnemius of human body
Electric signal, using soft set method analysis surface electromyogram signal information not in the same time, so as to analyze the degree of fatigue of driver.
The collection of A1 surface electromyogram signals and treatment
(1) surface electromyogram signal acquisition：Using the physiological signal collection platform of Tianjin hair science and technology production, can simultaneously gather 16 and lead
Physiological signal, wirelessly receives and sending signal.This experiment chooses six muscle at position for collection surface altogether
Electromyographic signal, respectively neck Superior trapezius, shoulder deltoid muscle, back latissimus dorsi, lower limb rectus femoris, musculus vastus lateralis and sura
Flesh, muscle distribution situation is as shown in Figure 1.Because the quantity of human skeletal muscle is very more and is completely embedded, if electromyographic electrode
Placement location selection it is improper, it will the data for collecting is lost accuracy.Therefore, have by experimental measurement result
Pointedly determine electrode putting position to obtain the signal of reliable in quality.When measuring electrode is placed on into phase along muscle fibre direction
Close at the belly of muscle of muscle, reference electrode is placed on SEMG (surface electromyogram, surface electromyography) signal and compares
When at faint tendon, the SEMG signals of reliable in quality can be collected.
Surface electromyogram signal is by being attached to the faint bioelectrical signals that the electrode slice of skin surface is collected, in letter
Number collection, pickup, conditioning during be frequently subjected to the external world noise jamming so that the surface electromyogram signal for collecting is included
Some garbages, are pre-processed using two methods of Wavelet noise-eliminating method and empirical mode decomposition threshold denoising to signal.
(2) feature extraction：Time-domain analysis is carried out to surface electromyogram signal using mean square root method, is found with muscular fatigue journey
Degree increases, and root mean square amplitude declines, and frequency-domain analysis is carried out to surface electromyogram signal using median frequency method.Using fuzzy near
Linear Characteristics, the method statistics value stabilization, strong antijamming capability, to mixing are carried out to surface electromyogram signal like entropy algorithm
Signal it is adaptable be entropy algorithm advantage, the change of result curve has preferable uniformity with body state change.
(3) the theoretical application in fatigue-driving detection technology of soft set
The human body surface myoelectric signal faint complicated bioelectrical signals that each meat fiber is produced when being neuron-muscular activity,
It is comprehensive superposition of the electric field of many muscle fibres in room and time distribution, its state feature also has randomness, complexity
The characteristics of with being easily disturbed.Gathered and processed by the surface electromyogram signal to six positions of driver, then used
After the methods such as time-domain analysis, frequency-domain analysis are analyzed and extract to the muscular states feature at each position, the present invention establishes base
Human body multiple information is merged in the tired quantitative model of soft set, the abnormal information to occurring is processed, Ran Houjin
Row Comprehensive Evaluation.
A2 problems are described
Domain U is driver's not set of muscular states in the same time, i.e. U={ h1,h2,h3,h4...h25, E is parameter set,
Respectively the fuzzy approximation entropy of deltoid muscle, latissimus dorsi, Superior trapezius, rectus femoris, musculus vastus lateralis and gastrocnemius, i.e. E=
{e1,e2,e3,e4,e5,e6, setting Fuzzy Soft Sets close the fatigue state that (F, E) characterizes driver now, can obtain formula (1), its
In, the value of formula (1) is the surface electromyogram signal that will be collected, and after being processed by above-mentioned various preprocess methods, each position is fuzzy near
Like the result after entropy normalization.
{ F, E }={ (e1,{h1/0.8772,h2/1,h3/0.9908,h4/0.9931...h25/0.2687}),
(e2,{h1/1,h2/0.9230,h3/0.9136,h4/0.8144...h25/0.3031}),
(e3,{h1/0.8902,h2/1,h3/8498,h4/0.8197...h25/0.2917}),
(e4,{h1/0.9678,h2/0.9465,h3/0.9379,h4/1...h25/0.5071})
(e5,{h1/0.9634,h2/0.9241,h3/0.9501,h4/0.9526...h25/0.5283}),
(e6,{h1/0.9930,h2/1,h3/0.8998,h4/0.8244...h25/0.5171})} (1)
Soft set is represented with form, as shown in table 1.
The form of the soft set of table 1 (F, E)
A3. the determination of parameters weighting
From table 1 it follows that the fuzzy approximation entropy of leg muscle easily fluctuates, and increase over time, entropy
It is worth the speed for declining slower, and deltoid muscle and the very fast amplitude of latissimus dorsi decrease speed are larger.Due to this difference physiologically, I
Need to be adjusted different parameters, according to the weight of parameter and the degree of correlation arrange parameter of body state, so that as far as possible
Eliminate the interference that the difference between parameter is caused to the result of decision.
The calculating of the degree of correlation uses line fitting method, the absolute value with fitting a straight line slope as standard, with latissimus dorsi, stock
As shown in Fig. 2 wherein circular represent that latissimus dorsi, five-pointed star represent that Superior trapezius, triangle represent the back of the body as a example by rectus and Superior trapezius
Platysma.Represent the straight slope absolute value difference of deltoid muscle, musculus vastus lateralis, gastrocnemius, latissimus dorsi, rectus femoris and Superior trapezius
For：0.0325,0.0205,0.0198,0.0283,0.0237,0.0317.If slope is k, each parameters weighting is w, then weight is pressed
Formula (2) is calculated.
The weight for drawing respectively wi=[1.000,0.871,0.975,0.729,0.631,0.609].After weight is set
The form of soft set is as shown in table 2.
The form of the soft set (T, E) after the setting of the weight of table 2
A4. the treatment of abnormal data
In gatherer process is tested, often by various interference, cause the result after data processing beyond normal value
Scope, if directly removing analysis and decision using these abnormal datas, may obtain the result not corresponded with virtual condition, lead
Cause the consequences such as incorrect decision or application error.
First, it would be desirable to determine whether a data are abnormal data, because the collection of physiologic information is in time
Continuously, therefore, data change over time certain rule.If the gap mistake of a data and its former and later two data
Greatly, we are just seen as abnormal data, and because preceding 30 minutes human bodies are in excitatory state, data fluctuations are larger to belong to normal
Physiological phenomenon, therefore first three groups signal do not consider.The determination of abnormal data is according to formula (3)
Can regard the data in italics in table 2 as abnormal data by calculating, make abnormal data hij=*, has drawn not
Soft set { T, the E of complete information*, form is as shown in table 3.
We use front and rear two groups of average values of data for the filling of abnormal data, because, front and rear two groups of data time interval
It is identical, and data are in the trend of monotonic decreasing, therefore it may only be necessary to calculating average value just can preferably show data set
Essential characteristic and implicit rule.This method equally employs the thought of simplified algorithm, i.e., obtained using less data as far as possible
Go out desired replacement values, considered every possible angle rather than by all data.
Soft set { T, the E of the incomplete information of table 3*Form
By soft set { T, E*Abnormal data be replaced, draw the 4th soft set { G, E }, its form such as table 4
It is shown.The form of the soft set of table 4 (G, E)
Using table 4, judge value, wherein judge value d are obtainedi=e1′+e2′+e3′+e4′+e5′+e6', from table 4, it can be seen that
Increase over time, judge value is in monotonous decreasing trend, shows the change of driver's physical fatigue state, more tired, judge
Value is smaller.It is (such as in general continuous by setting a threshold value such that it is able to the speed that the fatigue for analyzing driver declines
Drive not above 4 hours, it is just relatively more tired more than 4 hours, danger is susceptible to, the flesh at multigroup four hours can be gathered
Electric signal draws average fatigue data, using this as threshold value of warning), judge the physical fatigue degree of driver, in time suggestion
Driver rests, and can be prevented effectively from the generation of traffic accident.
Claims (10)
1. a kind of method for detecting fatigue driving based on soft set, it is characterised in that comprise the following steps：
S1, gathers the surface electromyogram signal of the default muscle sites in predetermined time of driver；
S2, extracts and analyzes the muscular states feature of the surface electromyogram signal；
S3, the tired quantitative model based on soft set is set up according to the electromyographic signal for extracting；
S4, fatigue driving decision content is calculated according to the tired quantitative model based on soft set.
2. a kind of method for detecting fatigue driving based on soft set according to claim 1, it is characterised in that the step
In S1, the default muscle sites include neck Superior trapezius, shoulder deltoid muscle, back latissimus dorsi, lower limb rectus femoris, thigh lateral
Flesh and gastrocnemius.
3. a kind of method for detecting fatigue driving based on soft set according to claim 1 and 2, it is characterised in that described
In step S1, using Wavelet noise-eliminating method and empirical mode decomposition Threshold Denoising Method to the surface electromyogram signal that collects
Pre-processed.
4. a kind of method for detecting fatigue driving based on soft set according to claim 3, it is characterised in that the step
S2 includes：The surface electromyogram signal is analyzed using mean square root method, median frequency method or fuzzy approximation entropy algorithm, is obtained
To the muscular states feature of surface electromyogram signal.
5. a kind of method for detecting fatigue driving based on soft set according to claim 4, it is characterised in that the step
S3 includes：The fatigue state that the first soft set (F, E) characterizes driver is set, wherein, domain U is driver not in the same time
The set of muscular states feature, i.e. U={ h1,h2,h3,h4...h25, E is parameter set, and parameter is the surface electromyogram signal
Fuzzy approximation entropy.
6. a kind of method for detecting fatigue driving based on soft set according to claim 5, it is characterised in that the step
S3 also includes：The degree of correlation according to each parameter in E and body state is respectively provided with the weight of each parameter, according to each parameter
Weight and first soft set obtain the second soft set (T, E).
7. a kind of method for detecting fatigue driving based on soft set according to claim 6, it is characterised in that use straight line
Approximating method calculates the degree of correlation of each parameter and body state in E.
8. a kind of method for detecting fatigue driving based on soft set according to claim 6 or 7, it is characterised in that described
Step S3 also includes：Judge the abnormal data in second soft set (T, E), it judges that formula is specially：And the abnormal data is processed, make the abnormal data hij=*, obtains
Three soft set { T, E*}。
9. a kind of method for detecting fatigue driving based on soft set according to claim 8, it is characterised in that by described
Three soft set { T, E*In abnormal data before and after the average value of two groups of data be replaced, draw the 4th soft set G,
E }, its computational methods is *ij=(hi-1,j+hi+1,j)/2, and obtained according to the 4th soft set { G, E } using soft set decision-making technique
To final decision content.
10. a kind of method for detecting fatigue driving based on soft set according to any one of claim 9, it is characterised in that
In the step S4, the circular of decision content is：di=e1′+e2′+e3′+e4′+e5′+e6', according to the decision content
Giving fatigue pre-warning threshold value is set, when decision content reaches the giving fatigue pre-warning threshold value, warning message is exported to driver.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611244964.6A CN106781283B (en) | 2016-12-29 | 2016-12-29 | A kind of method for detecting fatigue driving based on soft set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611244964.6A CN106781283B (en) | 2016-12-29 | 2016-12-29 | A kind of method for detecting fatigue driving based on soft set |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106781283A true CN106781283A (en) | 2017-05-31 |
| CN106781283B CN106781283B (en) | 2019-04-05 |
Family
ID=58928697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611244964.6A Active CN106781283B (en) | 2016-12-29 | 2016-12-29 | A kind of method for detecting fatigue driving based on soft set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106781283B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133407A (en) * | 2017-12-21 | 2018-06-08 | 湘南学院 | A kind of e-commerce recommended technology and system based on soft collection Decision Rule Analysis |
| CN109431526A (en) * | 2018-12-25 | 2019-03-08 | 成都中昂科技有限公司 | Driving condition recognition methods and system based on WIFI |
| CN109993180A (en) * | 2017-12-29 | 2019-07-09 | 新华网股份有限公司 | Human biological electricity data processing method and device, storage medium and processor |
| CN110151203A (en) * | 2019-06-06 | 2019-08-23 | 常熟理工学院 | Fatigue driving recognition methods based on multistage avalanche type convolution Recursive Networks EEG analysis |
| CN110232976A (en) * | 2019-07-01 | 2019-09-13 | 上海电机学院 | A kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric |
| CN112006686A (en) * | 2020-07-09 | 2020-12-01 | 浙江大学 | Neck muscle fatigue analysis method and system |
| CN114081513A (en) * | 2021-12-13 | 2022-02-25 | 苏州大学 | Electromyographic signal-based abnormal driving behavior detection method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104599443A (en) * | 2015-01-12 | 2015-05-06 | 江苏省交通规划设计院股份有限公司 | Vehicle-mounted forewarning terminal for driving behaviors based on information fusion and forewarning method thereof |
| US20160090097A1 (en) * | 2014-09-29 | 2016-03-31 | The Boeing Company | System for fatigue detection using a suite of physiological measurement devices |
-
2016
- 2016-12-29 CN CN201611244964.6A patent/CN106781283B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160090097A1 (en) * | 2014-09-29 | 2016-03-31 | The Boeing Company | System for fatigue detection using a suite of physiological measurement devices |
| CN104599443A (en) * | 2015-01-12 | 2015-05-06 | 江苏省交通规划设计院股份有限公司 | Vehicle-mounted forewarning terminal for driving behaviors based on information fusion and forewarning method thereof |
Non-Patent Citations (8)
| Title |
|---|
| 付荣荣等: "基于无线体域网中多生理信号驾驶疲劳检测", 《东北大学学报》 * |
| 孙曙光等: "一种基于新型小波阈值去噪预处理的EEMD谐波检测方法", 《电力系统保护与控制》 * |
| 席旭刚等: "基于EEMD和二代小波变化的表面肌电信号消噪方法", 《传感技术学报》 * |
| 汪晨等: "基于模糊近似熵与辛几何的肌肉疲劳分析", 《现代仪器与医疗》 * |
| 洪智勇: "基于软集的不确定性分析方法及应用研究", 《中国博士学位论文全文数据库基础科学辑》 * |
| 缪彬: "基于软集合理论的不确定性多属性决策方法研究", 《中国博士学位论文全文数据库经济管理科学辑》 * |
| 赵永超等: "拖拉机驾驶员颈部疲劳肌电评价", 《农业工程学报》 * |
| 陈晓静等: "基于表面肌电的草原公路驾驶员局部肌肉疲劳试验研究", 《科学技术与工程》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133407A (en) * | 2017-12-21 | 2018-06-08 | 湘南学院 | A kind of e-commerce recommended technology and system based on soft collection Decision Rule Analysis |
| CN108133407B (en) * | 2017-12-21 | 2021-12-24 | 湘南学院 | E-commerce recommendation technology and system based on soft set decision rule analysis |
| CN109993180A (en) * | 2017-12-29 | 2019-07-09 | 新华网股份有限公司 | Human biological electricity data processing method and device, storage medium and processor |
| CN109431526A (en) * | 2018-12-25 | 2019-03-08 | 成都中昂科技有限公司 | Driving condition recognition methods and system based on WIFI |
| CN110151203A (en) * | 2019-06-06 | 2019-08-23 | 常熟理工学院 | Fatigue driving recognition methods based on multistage avalanche type convolution Recursive Networks EEG analysis |
| CN110151203B (en) * | 2019-06-06 | 2021-11-23 | 常熟理工学院 | Fatigue driving identification method based on multistage avalanche convolution recursive network EEG analysis |
| CN110232976A (en) * | 2019-07-01 | 2019-09-13 | 上海电机学院 | A kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric |
| CN112006686A (en) * | 2020-07-09 | 2020-12-01 | 浙江大学 | Neck muscle fatigue analysis method and system |
| CN114081513A (en) * | 2021-12-13 | 2022-02-25 | 苏州大学 | Electromyographic signal-based abnormal driving behavior detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106781283B (en) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106781283A (en) | A kind of method for detecting fatigue driving based on soft set | |
| CN108765876A (en) | Driving fatigue depth analysis early warning system based on multimode signal and method | |
| CN106691474A (en) | Brain electrical signal and physiological signal fused fatigue detection system | |
| CN103989485A (en) | Human body fatigue evaluation method based on brain waves | |
| Kumari et al. | Seizure detection in EEG using time frequency analysis and SVM | |
| CN105147248A (en) | Physiological information-based depressive disorder evaluation system and evaluation method thereof | |
| CN204931634U (en) | Based on the depression evaluating system of physiologic information | |
| CN104127181A (en) | Electromyographic signal tumble detection method based on WKFDA | |
| CN107832686A (en) | Merge the lower limb motion mode recognition methods of surface myoelectric and acceleration signal | |
| CN110974212A (en) | Electrocardio and myoelectric characteristic fused rehabilitation training motion state monitoring method and system | |
| CN114052744B (en) | Electrocardiosignal classification method based on impulse neural network | |
| CN108836328A (en) | A kind of equipment for being monitored for electromyography signal and generating corresponding electrical stimulation signal | |
| CN109691996A (en) | One kind is based on mixing binary-coded EEG signals feature preferably and classifier preferred method | |
| CN106175754A (en) | During sleep state is analyzed, waking state detects device | |
| CN115153984A (en) | Intelligent artificial limb control method, device, terminal and medium based on electromyographic signals | |
| Lei et al. | Study on driving fatigue evaluation system based on short time period ECG signal | |
| CN110097012A (en) | The fatigue detection method of eye movement parameter monitoring based on N-range image processing algorithm | |
| CN111671419B (en) | Electroencephalogram signal-based epilepsy early detection and identification method and system | |
| Zhang et al. | EEG signal classification method based on improved empirical mode decomposition and SVM | |
| CN110051351A (en) | It grits one's teeth the control method and device of signal acquiring method and electronic equipment | |
| CN106344008B (en) | Waking state detection method and system in sleep state analysis | |
| Fatmehsari et al. | Assessment of Parkinson's disease: Classification and complexity analysis | |
| Naseem et al. | Detection of sEMG muscle activation intervals using gaussian mixture model and ant colony classifier | |
| CN106983511A (en) | Recognition methods and identifying device of the muscular strength with Muscle tensility state mutation point | |
| CN106388812B (en) | The mask method and system of EEG signals data type under waking state |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |