CN105303771A - Fatigue judging system and method - Google Patents
Fatigue judging system and method Download PDFInfo
- Publication number
- CN105303771A CN105303771A CN201510590850.6A CN201510590850A CN105303771A CN 105303771 A CN105303771 A CN 105303771A CN 201510590850 A CN201510590850 A CN 201510590850A CN 105303771 A CN105303771 A CN 105303771A
- Authority
- CN
- China
- Prior art keywords
- parameter
- fatigue
- unit
- variable parameter
- result
- 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
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 invention provides a fatigue judging system and method to reduce erroneous judgment of fatigue driving. The system comprises a standard data set, an acquisition unit, a calculation unit, a judging unit and an alarm unit. Compared with the prior art, the system and the method have the advantages that a number of non-fatigued feature parameters are respectively acquired; the acquired feature parameters form the standard set; in a judging process, the state feature parameter of a detected person is acquired in unit time in real time, and at the same time the state feature parameter and the standard set are compared; whether the detected person is fatigue is comprehensively judged; the judgment accuracy of fatigue driving is improved; and a driver is timely reminded in a fatigue driving process to avoid traffic accidents.
Description
Technical field
The present invention relates to electronic system technology field, be specifically related to a kind of Fatigue Evaluating System and method.
Background technology
Fatigue driving detects the category belonged in active safety, and method for detecting fatigue driving is a lot of at present, as the open and-shut mode, steering wheel angle detection etc. of countenance, body action detection, muscle condition, eyes.Mainly can be divided into two class methods to the research of fatigue detecting system at present, a class is hardware based method, and another kind of is method based on computer vision.
Hardware based method relates to the research & design to physical hardware, as electroculogram, electromyogram, eeg measurement, although this method can obtain effect accurately to the judgement of fatigue, the hardware that these class methods use must contact human body, and operability is not strong in actual applications.Method based on computer vision obtains frontal one video to be checked by camera, processing terminal processes in real time to video image, extracting each organ characteristic of face, by analyzing the situation of change of the organ characteristic such as eyes, mouth, judging whether to be in fatigue state.Basis for estimation comprises that eyes open that degree reduces, pupil height diminishes, closed-eye time prolongation when blink, again and again to yawn the changes such as the mouth that causes opens.The method belongs to contactless detection method, checkout equipment is installed simple, workable, but this method all needs self-defined fatigue state Rule of judgment, and due to everyone nictation custom etc. all not identical, this just knows self-defining fatigue state Rule of judgment not necessarily mates each user, also just easily causes erroneous judgement.
Summary of the invention
The object of the invention is a kind of method proposing adaptive detection fatigue driving, the erroneous judgement of fatigue driving can be reduced.
The object of the invention, obtains by the following technical programs:
A kind of Fatigue Evaluating System, wherein,
Standard data set, obtains the characteristic parameter of detected person under non-fatigue state, and forms a standard set according to described characteristic parameter;
Collecting unit, the characteristic condition parameter of Real-time Collection detected person, and form a plurality of variable parameter;
Computing unit, according to described standard set and described variable parameter, forms result of calculation;
Judging unit, receives described result of calculation, and forms a judged result output according to described result of calculation,
Alarm unit, performs the operation matched with described judged result according to described judged result.
Preferably, above-mentioned Fatigue Evaluating System, wherein, described characteristic condition parameter comprises: the quantity implementing eye closing action in the unit interval; And/or in the unit interval, implement the quantity of action nictation; And/or in the unit interval, implement the quantity that lip opens maximum actuation; And/or in the unit interval, implement the quantity of nodding action; And/or the face-image frame number obtained in the unit interval; And/or in the unit interval, implement the quantity of continuous eye closing action.
Preferably, above-mentioned Fatigue Evaluating System, wherein, described collecting unit also comprises a conversion unit, and described conversion unit is in order to be converted into described variable parameter by described characteristic condition parameter.
Preferably, above-mentioned Fatigue Evaluating System, wherein, described characteristic condition parameter is converted into described variable parameter according to transfer functions by described conversion unit, with described variable parameter <1 and described variable parameter > 0, described transfer function is:
y＝kf(m(x-n))+c
Wherein, x is described characteristic condition parameter, and m is that described characteristic condition parameter is in the zoom ratio of horizontal direction; N be described characteristic condition parameter in the translational movement of horizontal direction, k is the first adjustment parameter, and k ∈ (0,1), c are the second adjustment parameter, and c ∈ (0,1), y is described variable parameter.
Preferably, above-mentioned Fatigue Evaluating System, wherein, described computing unit forms described result of calculation according to Sigmoid type excitation function in conjunction with described standard set and described variable parameter, and wherein, described Sigmoid type excitation function is:
Wherein, z is described result of calculation.
Preferably, above-mentioned Fatigue Evaluating System, wherein, described computing unit forms described result of calculation according to arctan function in conjunction with described standard set and described variable parameter, and wherein, described arctan function is:
z＝atan(y)+b
Wherein, z is described result of calculation, and a, b are constant.
A kind of tired determination methods, wherein,
Step S1, the characteristic parameter of acquisition detected person under non-fatigue state, and form a standard set according to described characteristic parameter;
The characteristic condition parameter of step S2, Real-time Collection detected person, and form a variable parameter;
Step S3, according to described standard set and described variable parameter, formed result of calculation;
Step S4, receive described result of calculation, and form a judged result according to described result of calculation and export.
Preferably, above-mentioned tired determination methods, wherein, step S5, alarm unit perform the action matched with described judged result under the effect of described judged result.
Preferably, above-mentioned tired determination methods, wherein, in described step S2, obtains described characteristic condition parameter by image acquiring device.
Preferably, above-mentioned tired determination methods, wherein, in described step S3, by a processing terminal according to described standard set and described variable parameter, forms result of calculation.
Preferably, above-mentioned tired determination methods, wherein, in described step S2, comprising:
The characteristic condition parameter of step S21, Real-time Collection detected person, and form a plurality of variable parameter;
Step S22, judge whether acquisition time reaches the schedule time;
Step S23, do not reach the schedule time in described acquisition time state under, perform step 21, continue to gather characteristic condition parameter described in next frame;
The change total amount of step S24, each described characteristic condition parameter of the statistics schedule time, and form described variable parameter.
Preferably, above-mentioned tired determination methods, wherein, described standard set adopts fuzzy theory to be formed.
Compared with prior art, advantage of the present invention is:
Gather the characteristic parameter under multiple non-fatigue state respectively, standard set is formed according to the characteristic parameter obtained, in deterministic process, the characteristic condition parameter of detected person in the Real-time Collection unit interval, characteristic condition parameter and standard set compare simultaneously, and whether comprehensive descision detected person is in fatigue state, improve the judging nicety rate of fatigue driving, remind in time in fatigue driving process simultaneously, avoid occurring traffic hazard.
Accompanying drawing explanation
Fig. 1 is the structural representation of a kind of Fatigue Evaluating System in the present invention;
Fig. 2 is Sigmoid type excitation function schematic diagram;
Fig. 3 is arctan function schematic diagram;
Fig. 4 is the schematic flow sheet of the present invention's a kind of tired determination methods;
Fig. 5 is the schematic flow sheet based on the fatigue state determination methods of fuzzy theory in the present invention.
Embodiment
Contrast accompanying drawing below, by the description to embodiment, the effect and principle of work etc. of the specific embodiment of the present invention as the mutual alignment between the shape of involved each component, structure, each several part and annexation, each several part are described in further detail.
As shown in Figure 1, a kind of structural representation of Fatigue Evaluating System, wherein, comprise standard data set, collecting unit, computing unit, judging unit, alarm unit, standard data set, collecting unit all connect the input end of computing unit, the input end of the output terminal connection judgment unit of computing unit, the output terminal of judging unit connects alarm unit.
Standard data set, obtains the characteristic parameter of detected person under non-fatigue state, and forms a standard set according to described characteristic parameter.Described characteristic condition parameter can comprise the quantity implementing eye closing action in the unit interval; The quantity of action nictation is implemented in unit interval; The quantity that lip opens maximum actuation is implemented in unit interval; The quantity of nodding action is implemented in unit interval; The face-image frame number obtained in unit interval; The quantity of continuous eye closing action is implemented in unit interval.
Collecting unit, the characteristic condition parameter of Real-time Collection detected person, and form a variable parameter; Further, described characteristic condition parameter is converted into described variable parameter according to transfer functions by described conversion unit, with described variable parameter < 1 and described variable parameter > 0, described transfer function is: described collecting unit also comprises a conversion unit, and described conversion unit is in order to be converted into described variable parameter y by described characteristic condition parameter
i;
y
i＝k
if(m(x
i-n))+c
i
Wherein, y
ifor variable parameter, y
i∈ [0,1], x
ifor described characteristic condition parameter, m is that described characteristic condition parameter is in the zoom ratio of horizontal direction; N be described characteristic condition parameter in the translational movement of horizontal direction, k
ibe the first adjustment parameter, k
i> 0, c
ibe the second adjustment parameter, c
i> 0, y is described variable parameter, and i is natural number.
In the present invention, characteristic condition parameter can comprise the quantity implementing eye closing action in the unit interval; The quantity of action nictation is implemented in unit interval; The quantity that lip opens maximum actuation is implemented in unit interval; The quantity of nodding action is implemented in unit interval; The face-image frame number obtained in unit interval; The quantity of continuous eye closing action is implemented in unit interval.The then corresponding characteristic condition parameter comprising enforcement eye closing action in the unit interval, with X
1represent, implement the characteristic condition parameter of action nictation in the unit interval, with X
2represent; The characteristic condition parameter that lip opens maximum actuation is implemented, with X in unit interval
3represent; The characteristic condition parameter of nodding action is implemented, with X in unit interval
4represent; The characteristic condition parameter of the face-image frame obtained in the unit interval, with X
5represent; The characteristic condition parameter of continuous eye closing action is implemented, with X in unit interval
6represent.
Described X
1variable parameter be: y
1=k
1f (m (x
1-n))+c
1;
Described X
2variable parameter be: y
2=k
2f (m (x
2-n))+c
2;
Described X
3variable parameter be: y
3=k
3f (m (x
3-n))+c
3;
Described X
4variable parameter be: y
4=k
4f (m (x
4-n))+c
4;
Described X
5variable parameter be: y
5=k
5f (m (x
5-n))+c
5;
Described X
6variable parameter be: y
6=k
6f (m (x
6-n))+c
6;
Computing unit, according to above-mentioned plurality of standard collection and above-mentioned a plurality of variable parameters, forms result of calculation;
As shown in Figure 2, Sigmoid type excitation function schematic diagram, when independent variable is far smaller than zero, infinite approach minimum value-1, when independent variable is far longer than zero, infinite approach maximal value 1, and when independent variable equals zero, slope is maximum, its behavioral trait just meets the demand that degree of fatigue is weighed, the impact of any one state parameter all changes in a limited scope, and has a Rapid Variable Design district being equivalent to threshold value.Described computing unit forms described result of calculation according to Sigmoid type excitation function in conjunction with described standard set and described variable parameter, wherein, and described Sigmoid type excitation function Z
ifor:
Wherein, Z
ifor the fatigue strength that described variable parameter is corresponding.
Specifically comprise:
Z
1for implementing the fatigue strength corresponding to eye closing action in the unit time;
Z
2for implementing the fatigue strength corresponding to action nictation in the unit time;
Z
3for enforcement lip opens the fatigue strength corresponding to maximum actuation;
Z
4for implementing the fatigue strength corresponding to nodding action in the unit time;
Z
5fatigue strength corresponding to the face-image frame number that obtains in the unit time;
Z
6for implementing the fatigue strength corresponding to 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, when independent variable is far longer than zero, infinite approach maximal value 1.5, and when independent variable equals zero, slope is maximum, its behavioral trait just meets the demand that degree of fatigue is weighed, the impact of any one state parameter all changes in a limited scope, and has a Rapid Variable Design district being equivalent to threshold value.Described computing unit forms described result of calculation according to arctan function in conjunction with described standard set and described variable parameter, and wherein, described arctan function is:
z
i＝atan(y
i)+b
Wherein, Z
ifor the fatigue strength that described variable parameter is corresponding, a, b are constant.
Specifically comprise:
z
1＝atan(y
1)+b
Z
1for implementing the fatigue strength corresponding to eye closing action in the unit time;
z
2＝atan(y
2)+b
Z
2for implementing the fatigue strength corresponding to action nictation in the unit time;
z
3＝atan(y
3)+b
Z
3for enforcement lip opens the fatigue strength corresponding to maximum actuation;
z
4＝atan(y
4)+b
Z
4for implementing the fatigue strength corresponding to nodding action in the unit time;
z
5＝atan(y
5)+b
Z
5fatigue strength corresponding to the face-image frame number that obtains in the unit time;
z
6＝atan(y
6)+b
Z
6for implementing the fatigue strength corresponding to continuous eye closing action in the unit time.
Judging unit, receives described result of calculation (fatigue strength that namely above-mentioned all variable parameters are corresponding), and forms a judged result output according to described result of calculation,
In the application, judged result the fatigue strength corresponding according to above-mentioned all variable parameters can obtain comprehensive fatigue strength, and the fatigue strength obtained for above-mentioned Sigmoid type excitation function, adopts every fatigue strength to obtain comprehensive fatigue strength S by weighting summation method, namely
S＝λ
1Z1+λ
2Z2+λ
3Z3+λ
4Z4+λ
5Z5+λ
6Z6；
Wherein, λ
i∈ [0,1], and in the Sigmoid type excitation function stated, k, c ∈ [0,1/ λ
i].
Alarm unit, the result of calculation according to described comprehensive fatigue strength S performs the operation matched with described judged result.Usual alarm unit is provided with fatigue threshold, and when comprehensive fatigue strength S does not mate fatigue threshold, alarm unit sends alarm operation, such as, thinks normal when S≤0.5; Think when 0.5<S≤0.8 for slight fatigue, now can carry out yellow card prompting; Can think as S>0.8 and occur major fatigue, now should carry out red card and remind.Once enter, alarm unit can also arrange separately the threshold range of plurality of states characteristic parameter, and when any one fatigue strength does not mate the threshold range of corresponding characteristic condition parameter, alarm unit sends corresponding alarm operation, to remind human pilot.
Pass through technique scheme, gather the characteristic parameter under multiple non-fatigue state respectively, standard set is formed according to the characteristic parameter obtained, in deterministic process, the characteristic condition parameter of detected person in the Real-time Collection unit interval, characteristic condition parameter and standard set compare simultaneously, and whether comprehensive descision detected person is in fatigue state, remind in time in fatigue driving process, avoid occurring traffic hazard.
As shown in Figure 4, the present invention is a kind of tired determination methods simultaneously, wherein,
Step S1, the characteristic parameter of acquisition detected person under non-fatigue state, and form a standard set according to described characteristic parameter;
The characteristic condition parameter of step S2, Real-time Collection detected person, and form a variable parameter; Described characteristic condition parameter is obtained by image acquiring device.Further, the characteristic condition parameter of Real-time Collection detected person, comprising:
The characteristic condition parameter of step S21, Real-time Collection detected person, and form a variable parameter;
Step S22, judge whether acquisition time reaches the schedule time;
Step S23, do not reach the schedule time in described acquisition time state under, perform step 21, continue to gather characteristic condition parameter described in next frame;
The change total amount of step S24, each described characteristic condition parameter of the statistics schedule time, and form described variable parameter.
Step S3, according to described standard set and described variable parameter, formed result of calculation; By a processing terminal according to described standard set and described variable parameter, form result of calculation.
Step S4, receive described result of calculation, and form a judged result according to described result of calculation and export.
A kind of tired determination methods, its principle of work is similar to the principle of work of above-mentioned a kind of Fatigue Evaluating System, does not repeat herein.
The application also can adopt the tired determination methods based on fuzzy theory, the degree of fatigue method of estimation based on neural network, degree of fatigue method of estimation based on cluster analysis.
As shown in Figure 5, based on the schematic flow sheet of the fatigue state determination methods of fuzzy theory, first, gather the measured data of a large amount of standard feature parameter, then, according to fuzzy subset and the subordinate function of each index amount of standard feature gain of parameter, fuzzy Judgment rule base/expert system is set up to fuzzy subset and subordinate function Fuzzy processing, gather real time data, by fuzzy Judgment rule base/expert system in conjunction with fuzzy set, fuzzy logic, fuzzy reasoning is carried out to measured data, finally judges corresponding fatigue state.Adopt this kind of mode, gradual perfection can be used according to reality in later stage or use procedure.
Based on the degree of fatigue measuring method of neural network, first one is designed with each index amount for input, take fatigue state as the artificial neural network exported, then, according to the measurement data of each index amount, designed neural network is trained, can by neural network to judge whether fatigue when practical application after having trained.
Cluster analysis refers to that the set by physics or abstract object is grouped into the analytic process of the multiple classes be made up of similar object.It is a kind of important human behavior.The target of cluster analysis is exactly collect data to classify on similar basis.Cluster comes from a lot of field, comprises mathematics, computer science, statistics, biology and economics.In different applications, a lot of clustering technique is obtained for development, and these technical methods are used as data of description, weighs the similarity between different pieces of information source, and data source is categorized in different bunches.
These are only preferred embodiment of the present invention; not thereby embodiments of the present invention and protection domain is limited; to those skilled in the art; should recognize and all should be included in the scheme that equivalent replacement done by all utilizations instructions of the present invention and diagramatic content and apparent change obtain in protection scope of the present invention.
Claims (10)
1. a Fatigue Evaluating System, is characterized in that,
Standard data set, obtains the characteristic parameter of detected person under non-fatigue state, and forms a standard set according to described characteristic parameter;
Collecting unit, the characteristic condition parameter of Real-time Collection detected person, and form a plurality of variable parameter;
Computing unit, according to described standard set and described variable parameter, forms result of calculation;
Judging unit, receives described result of calculation, and forms a judged result output according to described result of calculation,
Alarm unit, performs the operation matched with described judged result according to described judged result.
2. Fatigue Evaluating System according to claim 1, is characterized in that, described characteristic condition parameter comprises: the quantity implementing eye closing action in the unit interval; And/or in the unit interval, implement the quantity of action nictation; And/or in the unit interval, implement the quantity that lip opens maximum actuation; And/or in the unit interval, implement the quantity of nodding action; And/or the face-image frame number obtained in the unit interval; And/or in the unit interval, implement the quantity of continuous eye closing action.
3. Fatigue Evaluating System according to claim 1, is characterized in that, described collecting unit also comprises a conversion unit, and described conversion unit is in order to be converted into described variable parameter by described characteristic condition parameter.
4. Fatigue Evaluating System according to claim 3, it is characterized in that, described characteristic condition parameter is converted into described variable parameter according to transfer functions by described conversion unit, with described variable parameter < 1 and described variable parameter > 0, described transfer function is:
y＝kf(m(x-n))+c
Wherein, x is described characteristic condition parameter, and m is that described characteristic condition parameter is in the zoom ratio of horizontal direction; N be described characteristic condition parameter in the translational movement of horizontal direction, k is the first adjustment parameter, and k ∈ (0,1), c are the second adjustment parameter, and c ∈ (0,1), y is described variable parameter.
5. Fatigue Evaluating System according to claim 4, is characterized in that, described computing unit forms described result of calculation according to Sigmoid type excitation function in conjunction with described standard set and described variable parameter, and wherein, described Sigmoid type excitation function is:
Wherein, z is fatigue strength corresponding to described variable parameter.
6. Fatigue Evaluating System according to claim 4, is characterized in that, described computing unit forms described result of calculation according to arctan function in conjunction with described standard set and described variable parameter, and wherein, described arctan function is:
z＝atan(y)+b
Wherein, z is fatigue strength corresponding to described variable parameter, and a, b are constant.
7. a tired determination methods, is characterized in that,
Step S1, the characteristic parameter of acquisition detected person under non-fatigue state, and form a standard set according to described characteristic parameter;
The characteristic condition parameter of step S2, Real-time Collection detected person, and form a plurality of variable parameter;
Step S3, according to described standard set and described variable parameter, formed result of calculation;
Step S4, receive described result of calculation, and form a judged result according to described result of calculation and export.
8. tired determination methods according to claim 7, is characterized in that, in described step S3, by a processing terminal according to described standard set and described variable parameter, forms result of calculation.
9. tired determination methods according to claim 7, is characterized in that, in described step S2, comprising:
The characteristic condition parameter of step S21, Real-time Collection detected person, and form a variable parameter;
Step S22, judge whether acquisition time reaches the schedule time;
Step S23, do not reach the schedule time in described acquisition time state under, perform step 21, continue to gather characteristic condition parameter described in next frame;
The change total amount of step S24, each described characteristic condition parameter of the statistics schedule time, and form described variable parameter.
10. tired determination methods according to claim 7, is characterized in that, described standard set adopts fuzzy theory to be formed.
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 true CN105303771A (en) | 2016-02-03 |
| CN105303771B 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) |
Cited By (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 |
| CN110245574A (en) * | 2019-05-21 | 2019-09-17 | 平安科技（深圳）有限公司 | A kind of human fatigue state identification method, device and terminal device |
| CN112836275A (en) * | 2021-02-08 | 2021-05-25 | 哈尔滨工业大学 | Stadium emergency evacuation sign readability evaluation system based on fuzzy theory and control method thereof |
| 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 |
| 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 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470935A (en) * | 2007-12-26 | 2009-07-01 | 南京理工大学 | Key post attending personnel state monitoring and information reminding method and its implementing apparatus |
| CN101639894A (en) * | 2009-08-31 | 2010-02-03 | 华南理工大学 | Method for detecting train driver behavior and fatigue state on line and detection system thereof |
| CN101746269A (en) * | 2010-01-08 | 2010-06-23 | 东南大学 | Fatigue driving fusion detection method based on soft computing |
| US20140125474A1 (en) * | 2012-11-02 | 2014-05-08 | Toyota Motor Eng. & Mtfg. North America | Adaptive actuator interface for active driver warning |
| CN103824420A (en) * | 2013-12-26 | 2014-05-28 | 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 measuring |
-
2015
- 2015-09-15 CN CN201510590850.6A patent/CN105303771B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470935A (en) * | 2007-12-26 | 2009-07-01 | 南京理工大学 | Key post attending personnel state monitoring and information reminding method and its implementing apparatus |
| CN101639894A (en) * | 2009-08-31 | 2010-02-03 | 华南理工大学 | Method for detecting train driver behavior and fatigue state on line and detection system thereof |
| CN101746269A (en) * | 2010-01-08 | 2010-06-23 | 东南大学 | Fatigue driving fusion detection method based on soft computing |
| US20140125474A1 (en) * | 2012-11-02 | 2014-05-08 | Toyota Motor Eng. & Mtfg. North America | Adaptive actuator interface for active driver warning |
| CN103824420A (en) * | 2013-12-26 | 2014-05-28 | 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 measuring |
Cited By (7)
| 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 |
| CN110245574A (en) * | 2019-05-21 | 2019-09-17 | 平安科技（深圳）有限公司 | A kind of human fatigue state identification method, device and terminal device |
| WO2020232893A1 (en) * | 2019-05-21 | 2020-11-26 | 平安科技（深圳）有限公司 | User fatigue state recognition method, apparatus, terminal device and medium |
| 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 |
| 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 |
| CN112836275A (en) * | 2021-02-08 | 2021-05-25 | 哈尔滨工业大学 | Stadium emergency evacuation sign readability evaluation system based on fuzzy theory and control method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105303771B (en) | 2018-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105303771A (en) | Fatigue judging system and method | |
| Zhang et al. | Driver fatigue detection based on eye state recognition | |
| CN106108894A (en) | A kind of emotion electroencephalogramrecognition recognition method improving Emotion identification model time robustness | |
| CN103886341A (en) | Gait behavior recognition method based on feature combination | |
| CN105005765A (en) | Facial expression identification method based on Gabor wavelet and gray-level co-occurrence matrix | |
| CN106580282A (en) | Human body health monitoring device, system and method | |
| CN106128032A (en) | A kind of fatigue state monitoring and method for early warning and system thereof | |
| CN104274191A (en) | Psychological assessment method and psychological assessment system | |
| CN107169462A (en) | A kind of two sorting techniques of the EEG signals tagsort based on step analysis | |
| Zhao et al. | Research on fatigue detection based on visual features | |
| CN111259949A (en) | Fault identification model construction method, model and identification method for aircraft environmental control system | |
| Jahidin et al. | Classification of intelligence quotient using EEG sub-band power ratio and ANN during mental task | |
| CN105306438B (en) | Network security situation evaluating method based on fuzzy coarse central | |
| Qu et al. | Improved perception-based spiking neuron learning rule for real-time user authentication | |
| CN109567832A (en) | A kind of method and system of the angry driving condition of detection based on Intelligent bracelet | |
| Ramakrishnan et al. | Epileptic eeg signal classification using multi-class convolutional neural network | |
| Sun et al. | Blink number forecasting based on improved Bayesian fusion algorithm for fatigue driving detection | |
| Xiong et al. | Predicting separation errors of air traffic controllers through integrated sequence analysis of multimodal behaviour indicators | |
| CN114424941A (en) | Fatigue detection model construction method, fatigue detection method, device and equipment | |
| Tarafder et al. | Drowsiness detection using ocular indices from EEG signal | |
| Liu et al. | A novel fatigue driving state recognition and warning method based on EEG and EOG signals | |
| CN113116363A (en) | Method for judging hand fatigue degree based on surface electromyographic signals | |
| Li et al. | Novel multi-view Takagi–Sugeno–Kang fuzzy system for epilepsy EEG detection | |
| Chen et al. | Deep learning approach for detection of unfavorable driving state based on multiple phase synchronization between multi-channel EEG signals | |
| CN110134090A (en) | Merge the industrial robot control system reliability estimation method of multi-source information |
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 |