CN105303771B - A kind of Fatigue Evaluating System and method - Google Patents
A kind of Fatigue Evaluating System and method Download PDFInfo
- Publication number
- CN105303771B CN105303771B CN201510590850.6A CN201510590850A CN105303771B CN 105303771 B CN105303771 B CN 105303771B CN 201510590850 A CN201510590850 A CN 201510590850A CN 105303771 B CN105303771 B CN 105303771B
- Authority
- CN
- China
- Prior art keywords
- parameter
- fatigue
- unit
- characteristic
- implement
- 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.)
- Active
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
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention provides a kind of Fatigue Evaluating System and method, can reduce the erroneous judgement of fatigue driving, including standard data set, collecting unit, computing unit, judging unit, alarm unit, compared with prior art, it is an advantage of the invention that：The characteristic parameter under multiple non-fatigue states is gathered respectively, standard set is formed according to the characteristic parameter of acquisition, in deterministic process, the characteristic condition parameter of detected person in the real-time acquisition units time, characteristic condition parameter compares with standard set simultaneously, and whether comprehensive descision detected person is in fatigue state, improves the judging nicety rate of fatigue driving, reminded in time during fatigue driving simultaneously, avoid the occurrence of traffic accident.
Description
Technical field
The present invention relates to electronic system technology field, and in particular to a kind of Fatigue Evaluating System and method.
Background technology
The category that fatigue driving detection belongs in active safety, and method for detecting fatigue driving is many at present, such as face's table
Feelings, body action detection, muscle condition, the open and-shut mode of eyes, steering wheel angle detection etc..At present to fatigue detecting system
Research can be largely classified into two class methods, and one kind is hardware based method, and another kind of is the method based on computer vision.
Hardware based method is related to research and design to physical hardware, as electroculogram, electromyogram, electroencephalogram are surveyed
Amount, although judgement of this method to fatigue can obtain accurate effect, hardware used in this kind of method must reach over to people
Body, operability is not strong in actual applications.Method based on computer vision is that frontal faces to be checked are obtained by camera
Portion's video, processing terminal are handled video image in real time, each organ characteristic of face are extracted, by analyzing the devices such as eyes, mouth
The situation of change of official's feature, judge whether to be in fatigue state.Basis for estimation opens degree reduction including eyes, pupil highly becomes
It is small, blink when closed-eye time extend, again and again yawn caused by mouth open etc. change.This method belongs to contactless detection
Method, detection device installation is simple, workable, but this method is required for self-defined fatigue state Rule of judgment, and
Due to everyone blink be accustomed to etc. differ, this just know customized fatigue state Rule of judgment to each user not
Certain matching, is also easy for causing erroneous judgement.
The content of the invention
The purpose of the present invention is to propose to a kind of method of adaptive detection fatigue driving, the erroneous judgement of fatigue driving can be reduced
It is disconnected.
The object of the invention, obtain by the following technical programs：
A kind of Fatigue Evaluating System, wherein,
Standard data set, characteristic parameter of the detected person under non-fatigue state is obtained, and according to the characteristic parameter shape
Into a standard set；
Collecting unit, gathers the characteristic condition parameter of detected person in real time, and forms a plurality of variable parameters；
Computing unit, according to the standard set and the variable parameter, form result of calculation；
Judging unit, the result of calculation is received, and judged result output is formed according to the result of calculation,
Alarm unit, the operation to match with the judged result is performed according to the judged result.
Preferably, above-mentioned Fatigue Evaluating System, wherein, the characteristic condition parameter includes：Implement to close in unit interval
The quantity of eye action；And/or implement the quantity of blink action in the unit interval；And/or implement lip in the unit interval and open most
The quantity of big-movement；And/or implement the quantity of nodding action in the unit interval；And/or the face-image obtained in the unit interval
Frame number；And/or implement the quantity of continuous eye closing action in the unit interval.
Preferably, above-mentioned Fatigue Evaluating System, wherein, the collecting unit also includes a conversion unit, the conversion
Unit by the characteristic condition parameter being converted into the variable parameter.
Preferably, above-mentioned Fatigue Evaluating System, wherein, the conversion unit is according to conversion function by the state feature
Parameter is converted into the variable parameter, with the variable parameter<1 and the variable parameter ＞ 0, the transfer function be：
Y=kf (m (x-n))+c
Wherein, x is the characteristic condition parameter, and m is the characteristic condition parameter in the zoom ratio of horizontal direction；N is institute
Characteristic condition parameter is stated in the translational movement of horizontal direction, k is the first adjusting parameter, and k ∈ (0,1), c are the second adjusting parameter, c ∈
(0,1), y are the variable parameter.
Preferably, above-mentioned Fatigue Evaluating System, wherein, the computing unit combines according to Sigmoid types excitation function
The standard set and the variable parameter form the result of calculation, wherein, the Sigmoid types excitation function is：
Wherein, z is the result of calculation.
Preferably, above-mentioned Fatigue Evaluating System, wherein, the computing unit is according to arctan function with reference to the standard
Set and the variable parameter form the result of calculation, wherein, the arctan function is：
Z=atan (y)+b
Wherein, z is the result of calculation, and a, b are constant.
A kind of tired determination methods, wherein,
Step S1, characteristic parameter of the detected person under non-fatigue state is obtained, and one is formed according to the characteristic parameter
Standard set；
Step S2, the characteristic condition parameter of collection detected person, and form a variable parameter in real time；
Step S3, according to the standard set and the variable parameter, result of calculation is formed；
Step S4, the result of calculation is received, and judged result output is formed according to the result of calculation.
Preferably, above-mentioned tired determination methods, wherein, step S5, alarm unit is in the presence of the judged result
Perform the action to match with the judged result.
Preferably, above-mentioned tired determination methods, wherein, in the step S2, institute is obtained by image acquiring device
State characteristic condition parameter.
Preferably, above-mentioned tired determination methods, wherein, in the step S3, by a processing terminal according to
Standard set and the variable parameter, form result of calculation.
Preferably, above-mentioned tired determination methods, wherein, in the step S2, including：
Step S21, the characteristic condition parameter of collection detected person, and form a plurality of variable parameters in real time；
Step S22, judge whether acquisition time reaches the scheduled time；
Step S23, in the state of the acquisition time is not up to the scheduled time, step 21 is performed, continues to gather next
Characteristic condition parameter described in frame；
Step S24, the change total amount of each characteristic condition parameter of the scheduled time is counted, and forms the variable ginseng
Number.
Preferably, above-mentioned tired determination methods, wherein, the standard set is formed using fuzzy theory.
Compared with prior art, it is an advantage of the invention that：
The characteristic parameter under multiple non-fatigue states is gathered respectively, and standard set is formed according to the characteristic parameter of acquisition,
In deterministic process, the characteristic condition parameter of detected person in the real-time acquisition units time, while characteristic condition parameter and regular set
Conjunction compares, and whether comprehensive descision detected person is in fatigue state, improves the judging nicety rate of fatigue driving, while in fatigue
Reminded in time in driving procedure, avoid the occurrence of traffic accident.
Brief description of the drawings
Fig. 1 is a kind of structural representation of Fatigue Evaluating System in the present invention；
Fig. 2 is Sigmoid type excitation function schematic diagrames；
Fig. 3 is arctan function schematic diagram；
Fig. 4 is a kind of schematic flow sheet of tired determination methods of the present invention；
Fig. 5 is the schematic flow sheet of the fatigue state determination methods based on fuzzy theory in the present invention.
Embodiment
Below against accompanying drawing, by the description to embodiment, for example involved to the embodiment of the present invention is each
Mutual alignment and annexation, the effect of each several part and operation principle between the shape of component, construction, each several part etc. are made into one
The detailed description of step.
As shown in figure 1, a kind of structural representation of Fatigue Evaluating System, wherein, including standard data set, collecting unit,
Computing unit, judging unit, alarm unit, standard data set, collecting unit are all connected with the input of computing unit, computing unit
Output end connection judgment unit input, judging unit output end connection alarm unit.
Standard data set, characteristic parameter of the detected person under non-fatigue state is obtained, and according to the characteristic parameter shape
Into a standard set.The characteristic condition parameter may include the quantity for implementing eye closing action in the unit interval；It is real in unit interval
Apply the quantity of blink action；Implement the quantity that lip opens maximum actuation in unit interval；Implement nodding action in unit interval
Quantity；The face-image frame number obtained in unit interval；Implement the quantity of continuous eye closing action in unit interval.
Collecting unit, the characteristic condition parameter of detected person is gathered in real time, and form a variable parameter；Further, institute
State conversion unit and the characteristic condition parameter is converted into by the variable parameter according to conversion function, with the variable parameter ＜ 1
And the variable parameter ＞ 0, the transfer function are：The collecting unit also includes a conversion unit, and the conversion unit is used
So that the characteristic condition parameter is converted into the variable parameter yi；
yi=kif(m(xi-n))+ci
Wherein, yiFor variable parameter, yi∈ [0,1], xiFor the characteristic condition parameter, m be the characteristic condition parameter in
The zoom ratio of horizontal direction；N is the characteristic condition parameter in the translational movement of horizontal direction, kiFor the first adjusting parameter, ki＞ 0,
ciFor the second adjusting parameter, ci＞ 0, y are the variable parameter, and i is natural number.
In the present invention, characteristic condition parameter may include the quantity for implementing eye closing action in the unit interval；It is real in unit interval
Apply the quantity of blink action；Implement the quantity that lip opens maximum actuation in unit interval；Implement nodding action in unit interval
Quantity；The face-image frame number obtained in unit interval；Implement the quantity of continuous eye closing action in unit interval.Then phase therewith
That answers includes implementing in the unit interval characteristic condition parameter of eye closing action, with X1Represent, implement blink action in the unit interval
Characteristic condition parameter, with X2Represent；Implement the characteristic condition parameter that lip opens maximum actuation in unit interval, with X3Represent；
Implement the characteristic condition parameter of nodding action in unit interval, with X4Represent；The shape of the face-image frame obtained in unit interval
State characteristic parameter, with X5Represent；Implement the characteristic condition parameter of continuous eye closing action in unit interval, with X6Represent.
The X1Variable parameter be：y1=k1f(m(x1-n))+c1；
The X2Variable parameter be：y2=k2f(m(x2-n))+c2；
The X3Variable parameter be：y3=k3f(m(x3-n))+c3；
The X4Variable parameter be：y4=k4f(m(x4-n))+c4；
The X5Variable parameter be：y5=k5f(m(x5-n))+c5；
The X6Variable parameter be：y6=k6f(m(x6-n))+c6；
Computing unit, according to above-mentioned plurality of standard collection and above-mentioned a plurality of variable parameters, form result of calculation；
As shown in Fig. 2 Sigmoid type excitation function schematic diagrames, when independent variable is far smaller than zero, infinite approach minimum value-
1, when independent variable is far longer than zero, infinite approach maximum 1, and when independent variable is equal to zero, maximum slope, its behavioral trait
Just meeting the demand of degree of fatigue measurement, the influence of any one state parameter all changes in a limited scope, and
There is a quick variation zone equivalent to threshold value.The computing unit is according to Sigmoid types excitation function with reference to the regular set
Close and the variable parameter forms the result of calculation, wherein, the Sigmoid types excitation function ZiFor：
Wherein, ZiFor fatigue strength corresponding to the variable parameter.
Specifically include：
Z1To implement the corresponding fatigue strength of eye closing action in the unit time；
Z2To implement the corresponding fatigue strength of blink action in the unit time；
Z3To implement the fatigue strength corresponding to lip opening maximum actuation；
Z4To implement the fatigue strength corresponding to nodding action in the unit time；
Z5Fatigue strength corresponding to the face-image frame number that is obtained in the unit time；
Z6To implement the corresponding fatigue strength of continuous eye closing action in the unit time.
As shown in figure 3, arctan function schematic diagram, when independent variable is far smaller than zero, infinite approach minimum value -1.5, certainly
When variable is far longer than zero, infinite approach maximum 1.5, and when independent variable is equal to zero, maximum slope, its behavioral trait is just
Meet the demand of degree of fatigue measurement, the influence of any one state parameter all changes in a limited scope, and has one
The individual quick variation zone equivalent to threshold value.The computing unit is according to arctan function with reference to the standard set and the variable
Parameter forms the result of calculation, wherein, the arctan function is：
zi=atan (yi)+b
Wherein, ZiFor fatigue strength corresponding to the variable parameter, a, b are constant.
Specifically include：
z1=atan (y1)+b
Z1To implement the corresponding fatigue strength of eye closing action in the unit time；
z2=atan (y2)+b
Z2To implement the corresponding fatigue strength of blink action in the unit time；
z3=atan (y3)+b
Z3To implement the fatigue strength corresponding to lip opening maximum actuation；
z4=atan (y4)+b
Z4To implement the fatigue strength corresponding to nodding action in the unit time；
z5=atan (y5)+b
Z5Fatigue strength corresponding to the face-image frame number that is obtained in the unit time；
z6=atan (y6)+b
Z6To implement the corresponding fatigue strength of continuous eye closing action in the unit time.
Judging unit, the result of calculation (fatigue strength corresponding to i.e. above-mentioned all variable parameters) is received, and according to institute
State result of calculation and form judged result output,
In the application, judged result fatigue strength acquisition can integrate fatigue according to corresponding to above-mentioned all variable parameters
Degree, by taking the fatigue strength that above-mentioned Sigmoid types excitation function obtains as an example, obtained using every fatigue strength by weighting summation method
Comprehensive fatigue strength S, i.e.,
S=λ1Z1+λ2Z2+λ3Z3+λ4Z4+λ5Z5+λ6Z6；
Wherein, λi∈ [0,1], and in the Sigmoid type excitation functions stated, k, c ∈ [0,1/ λi]。
Alarm unit, the operation to match with the judged result is performed according to the result of calculation of the comprehensive fatigue strength S.
Usual alarm unit is provided with fatigue threshold, and when comprehensive fatigue strength S mismatches fatigue threshold, alarm unit sends alarm behaviour
Make, for example, thinking normal as S≤0.5；When 0.5<Think for slight fatigue, can now carry out yellow card prompting during S≤0.8；When
S>It can consider major fatigue occurred when 0.8, should now carry out famous prompting.Enter once, alarm unit can also be independent
The threshold range of plurality of states characteristic parameter is set, in the threshold value of characteristic condition parameter corresponding to any one fatigue strength mismatch
During scope, alarm unit sends corresponding alarm operation, to remind human pilot.
Pass through above-mentioned technical proposal, the characteristic parameter under multiple non-fatigue states is gathered respectively, joined according to the feature of acquisition
Number form is into standard set, in deterministic process, the characteristic condition parameter of detected person in the real-time acquisition units time, while state
Characteristic parameter compares with standard set, and whether comprehensive descision detected person is in fatigue state, during fatigue driving and
When remind, avoid the occurrence of traffic accident.
As shown in figure 4, of the invention while a kind of tired determination methods, wherein,
Step S1, characteristic parameter of the detected person under non-fatigue state is obtained, and one is formed according to the characteristic parameter
Standard set；
Step S2, the characteristic condition parameter of collection detected person, and form a variable parameter in real time；Obtained and filled by image
Put and obtain the characteristic condition parameter.Further, the characteristic condition parameter of detected person is gathered in real time, including：
Step S21, the characteristic condition parameter of collection detected person, and form a variable parameter in real time；
Step S22, judge whether acquisition time reaches the scheduled time；
Step S23, in the state of the acquisition time is not up to the scheduled time, step 21 is performed, continues to gather next
Characteristic condition parameter described in frame；
Step S24, the change total amount of each characteristic condition parameter of the scheduled time is counted, and forms the variable ginseng
Number.
Step S3, according to the standard set and the variable parameter, result of calculation is formed；By a processing terminal according to
The standard set and the variable parameter, form result of calculation.
Step S4, the result of calculation is received, and judged result output is formed according to the result of calculation.
A kind of tired determination methods, its operation principle is similar to a kind of operation principle of above-mentioned Fatigue Evaluating System, this
Place does not repeat.
The application can also use the tired determination methods based on fuzzy theory, the degree of fatigue estimation side based on neutral net
Method, the degree of fatigue method of estimation based on cluster analysis.
As shown in figure 5, the schematic flow sheet of the fatigue state determination methods based on fuzzy theory, first, gathers a large amount of marks
The measured data of quasi- characteristic parameter is then, right according to the fuzzy subset of each index amount of standard feature gain of parameter and membership function
Fuzzy subset and membership function Fuzzy processing establish fuzzy Judgment rule base/expert system, gather real time data, by fuzzy
Judgment rule storehouse/expert system combination fuzzy set, fuzzy logic, fuzzy reasoning is carried out to measured data, finally judged pair
The fatigue state answered., can be according to actual use gradual perfection during later stage or use using such a mode.
Degree of fatigue measuring method based on neutral net, one is designed first using each index amount as input, with tired shape
State is the artificial neural network of output, and then, designed neutral net is carried out according to the measurement data to each index amount
Training, can judge whether fatigue in practical application after the completion of training by neutral net.
Cluster analysis refers to the analysis that the set of physics or abstract object is grouped into the multiple classes being made up of similar object
Process.It is a kind of important human behavior.The target of cluster analysis is exactly that data are collected on the basis of similar to classify.It is poly-
Class comes from many fields, including mathematics, computer science, statistics, biology and economics.In different application fields, very
Multi-cluster technology is developed, and these technical methods are used as describing data, weigh the similitude between different data sources, with
And data source is categorized into different clusters.
Preferred embodiments of the present invention are these are only, not thereby limit embodiments of the present invention and protection domain, it is right
For those skilled in the art, it should can appreciate that and all be replaced with being equal made by description of the invention and diagramatic content
Change and obviously change resulting scheme, should be included in protection scope of the present invention.
Claims (9)
- A kind of 1. Fatigue Evaluating System, it is characterised in thatStandard data set, characteristic parameter of the detected person under non-fatigue state is obtained, and one is formed according to the characteristic parameter Standard set；Collecting unit, gathers the characteristic condition parameter of detected person in real time, and forms a plurality of variable parameters；Computing unit, according to the standard set and the variable parameter, form result of calculation；Judging unit, the result of calculation is received, and judged result output is formed according to the result of calculation,Alarm unit, the operation to match with the judged result is performed according to the judged result；The characteristic condition parameter includes：Implement the quantity of eye closing action in unit interval；And/or implement blink in the unit interval The quantity of action；And/or implement the quantity that lip opens maximum actuation in the unit interval；And/or implement the quantity of nodding action in the unit interval；And/or the face-image frame number obtained in the unit interval；And/or Implement the quantity of continuous eye closing action in unit interval.
- 2. Fatigue Evaluating System according to claim 1, it is characterised in that it is single that the collecting unit also includes a conversion Member, the conversion unit by the characteristic condition parameter being converted into the variable parameter.
- 3. Fatigue Evaluating System according to claim 2, it is characterised in that the conversion unit is according to conversion function by institute State characteristic condition parameter and be converted into the variable parameter, with the variable parameter ＜ 1 and the variable parameter ＞ 0, the conversion Function is：Y=kf (m (x-n))+cWherein, x is the characteristic condition parameter, and m is the characteristic condition parameter in the zoom ratio of horizontal direction；N is the shape For state characteristic parameter in the translational movement of horizontal direction, k is the first adjusting parameter, and k ∈ (0,1), c are the second adjusting parameter, c ∈ (0, 1), y is the variable parameter.
- 4. Fatigue Evaluating System according to claim 3, it is characterised in that the computing unit swashs according to Sigmoid types Encourage function and form the result of calculation with reference to the standard set and the variable parameter, wherein, the Sigmoid types encourage letter Number is：<mrow> <mi>Z</mi> <mo>=</mo> <mfrac> <mrow> <mn>1</mn> <mo>-</mo> <msup> <mi>e</mi> <mrow> <mo>-</mo> <mi>y</mi> </mrow> </msup> </mrow> <mrow> <mn>1</mn> <mo>+</mo> <msup> <mi>e</mi> <mrow> <mo>-</mo> <mi>y</mi> </mrow> </msup> </mrow> </mfrac> </mrow>Wherein, z is fatigue strength corresponding to the variable parameter.
- 5. Fatigue Evaluating System according to claim 3, it is characterised in that the computing unit is according to arctan function knot Close the standard set and the variable parameter forms the result of calculation, wherein, the arctan function is：Z=atan (y)+bWherein, z is fatigue strength corresponding to the variable parameter, and a, b are constant.
- A kind of 6. tired determination methods, it is characterised in thatStep S1, characteristic parameter of the detected person under non-fatigue state is obtained, and a standard is formed according to the characteristic parameter Set；Step S2, the characteristic condition parameter of collection detected person, and form a plurality of variable parameters in real time；Step S3, according to the standard set and the variable parameter, result of calculation is formed；Step S4, the result of calculation is received, and judged result output is formed according to the result of calculation；The characteristic condition parameter includes：Implement the quantity of eye closing action in unit interval；And/or implement blink in the unit interval The quantity of action；And/or implement the quantity that lip opens maximum actuation in the unit interval；And/or implement the quantity of nodding action in the unit interval；And/or the face-image frame number obtained in the unit interval；And/or Implement the quantity of continuous eye closing action in unit interval.
- 7. tired determination methods according to claim 6, it is characterised in that in the step S3, by a processing eventually End forms result of calculation according to the standard set and the variable parameter.
- 8. tired determination methods according to claim 6, it is characterised in that in the step S2, including：Step S21, the characteristic condition parameter of collection detected person, and form a plurality of variable parameters in real time；Step S22, judge whether acquisition time reaches the scheduled time；Step S23, in the state of the acquisition time is not up to the scheduled time, step S21 is performed, continues to gather next frame institute State characteristic condition parameter；Step S24, the change total amount of each characteristic condition parameter of the scheduled time is counted, and forms the variable parameter.
- 9. tired determination methods according to claim 6, it is characterised in that the standard set uses fuzzy theory shape Into.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510590850.6A CN105303771B (en) | 2015-09-15 | 2015-09-15 | A kind of Fatigue Evaluating System and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510590850.6A CN105303771B (en) | 2015-09-15 | 2015-09-15 | A kind of Fatigue Evaluating System and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105303771A CN105303771A (en) | 2016-02-03 |
| CN105303771B true CN105303771B (en) | 2018-02-23 |
Family
ID=55200976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510590850.6A Active CN105303771B (en) | 2015-09-15 | 2015-09-15 | A kind of Fatigue Evaluating System and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105303771B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107316532A (en) * | 2017-05-27 | 2017-11-03 | 西南交通大学 | The method of testing and system of dispatcher's inferential capability |
| CN109493567A (en) * | 2018-12-29 | 2019-03-19 | 汉腾汽车有限公司 | A kind of fatigue drive of car early warning system and method |
| CN110245574B (en) * | 2019-05-21 | 2024-07-05 | 平安科技（深圳）有限公司 | User fatigue state identification method and device and terminal equipment |
| TWI763435B (en) * | 2019-07-16 | 2022-05-01 | 國立陽明交通大學 | Physiological information detection device and physiological information detection method |
| TWI744666B (en) * | 2019-07-16 | 2021-11-01 | 國立陽明交通大學 | Physiological information detection device and physiological information detection method |
| CN112836275B (en) * | 2021-02-08 | 2023-03-14 | 哈尔滨工业大学 | Stadium emergency evacuation sign readability evaluation system based on fuzzy theory and control method thereof |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470935B (en) * | 2007-12-26 | 2010-11-03 | 南京理工大学 | Key post attending personnel state monitoring and information reminding method and its implementing apparatus |
| CN101639894B (en) * | 2009-08-31 | 2013-03-20 | 华南理工大学 | Method for detecting train driver behavior and fatigue state on line and detection system thereof |
| CN101746269B (en) * | 2010-01-08 | 2013-04-03 | 东南大学 | Fatigue driving fusion detection method based on soft computing |
| US9007198B2 (en) * | 2012-11-02 | 2015-04-14 | Toyota Motor Engineering & Manufacturing North America, Inc. | Adaptive Actuator interface for active driver warning |
| CN103824420B (en) * | 2013-12-26 | 2016-12-07 | 苏州清研微视电子科技有限公司 | Fatigue driving identification system based on heart rate variability non-contact measurement |
-
2015
- 2015-09-15 CN CN201510590850.6A patent/CN105303771B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105303771A (en) | 2016-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105303771B (en) | A kind of Fatigue Evaluating System and method | |
| Shen et al. | A detailed comparison of optimality and simplicity in perceptual decision making. | |
| CN108664947A (en) | A kind of fatigue driving method for early warning based on Expression Recognition | |
| Zheng et al. | Some novel double-scroll chaotic attractors in Hopfield networks | |
| US9824489B2 (en) | Grading and monitoring of a geographical region | |
| CN103955270B (en) | Character high-speed input method of brain-computer interface system based on P300 | |
| Das et al. | A self-regulated interval type-2 neuro-fuzzy inference system for handling nonstationarities in EEG signals for BCI | |
| CN109646022A (en) | Child attention assessment system and its method | |
| CN108200005A (en) | Electric power secondary system network flow abnormal detecting method based on unsupervised learning | |
| Begum et al. | Classification of physiological signals for wheel loader operators using multi-scale entropy analysis and case-based reasoning | |
| CN104537273B (en) | A kind of drowned pattern intelligent inference system and method | |
| CN108549834A (en) | A kind of human body sitting posture recognition methods and its system based on flexible sensor | |
| Zhong et al. | Neural mechanism of visual information degradation from retina to V1 area | |
| Sun et al. | Blink number forecasting based on improved Bayesian fusion algorithm for fatigue driving detection | |
| Ding et al. | DS evidential theory on sEMG signal recognition | |
| Shanmuga Sundari et al. | Neurological disease prediction using impaired gait analysis for foot position in cerebellar ataxia by ensemble approach | |
| CN112998657A (en) | Method and system for preventing skin allergy | |
| CN110598789A (en) | Human fatigue state prediction method and system based on fuzzy perceptron | |
| CN110134090A (en) | Merge the industrial robot control system reliability estimation method of multi-source information | |
| CN112370039B (en) | Classroom quality detection method and device based on intelligent classroom | |
| Lu et al. | Fatigue detection technology for online learning | |
| CN104123384A (en) | Method and device for screening pathogenic factors causing food poisoning | |
| Craven et al. | Cognitive workload gauge development: comparison of real-time classification methods | |
| CN112133405A (en) | Method and system for assessing children nutrition state of smart community | |
| Kaur et al. | Analysis of adaptive neuro-fuzzy based expert system for Parkinson's disease diagnosis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |