CN112401908B - Fatigue monitoring device, fatigue monitoring method, computing equipment and storage medium - Google Patents
Fatigue monitoring device, fatigue monitoring method, computing equipment and storage medium Download PDFInfo
- Publication number
- CN112401908B CN112401908B CN202011389592.2A CN202011389592A CN112401908B CN 112401908 B CN112401908 B CN 112401908B CN 202011389592 A CN202011389592 A CN 202011389592A CN 112401908 B CN112401908 B CN 112401908B
- Authority
- CN
- China
- Prior art keywords
- electroencephalogram
- fatigue
- blood oxygen
- fatigue monitoring
- data
- 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
- 238000012806 monitoring device Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012544 monitoring process Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 210000001061 forehead Anatomy 0.000 claims abstract description 15
- 239000000463 material Substances 0.000 claims abstract description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 86
- 239000008280 blood Substances 0.000 claims description 86
- 210000004369 blood Anatomy 0.000 claims description 86
- 229910052760 oxygen Inorganic materials 0.000 claims description 86
- 239000001301 oxygen Substances 0.000 claims description 86
- 238000012545 processing Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 11
- 230000015654 memory Effects 0.000 claims description 11
- 230000000638 stimulation Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000005312 nonlinear dynamic Methods 0.000 claims description 10
- 238000001228 spectrum Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000005452 bending Methods 0.000 claims description 7
- 230000005236 sound signal Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 229910021607 Silver chloride Inorganic materials 0.000 claims description 2
- HKZLPVFGJNLROG-UHFFFAOYSA-M silver monochloride Chemical compound [Cl-].[Ag+] HKZLPVFGJNLROG-UHFFFAOYSA-M 0.000 claims description 2
- 238000005245 sintering Methods 0.000 claims description 2
- 230000004936 stimulating effect Effects 0.000 claims description 2
- 206010016256 fatigue Diseases 0.000 description 125
- 210000004556 brain Anatomy 0.000 description 32
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 239000000741 silica gel Substances 0.000 description 4
- 229910002027 silica gel Inorganic materials 0.000 description 4
- 238000011282 treatment Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005389 magnetism Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000002496 oximetry Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 210000004761 scalp Anatomy 0.000 description 2
- 230000002269 spontaneous effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 208000019914 Mental Fatigue Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 206010041235 Snoring Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000499 gel Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
- 238000004073 vulcanization Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Optics & Photonics (AREA)
- Medical Informatics (AREA)
- Biophysics (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 fatigue monitoring device, comprising: the shell is made of flexible materials, and a through hole is formed in a first surface of the shell along a first direction; the FPC board is arranged in the shell, and a micro control unit is arranged on the FPC board; the electroencephalogram acquisition electrode passes through the through hole and is arranged on the first surface, the electroencephalogram acquisition electrode is electrically connected with the micro-control unit, and the electroencephalogram acquisition electrode is used for acquiring electroencephalogram signals of the forehead. By adopting the technical scheme, the fatigue monitoring device is convenient to use. The invention also discloses a fatigue monitoring method, a computing device and a storage medium.
Description
Technical Field
The present invention relates to the technical field of biomedical engineering and mechano-electronic engineering, and in particular, to a fatigue monitoring device, a fatigue monitoring method, a computing device, and a storage medium.
Background
Fatigue can have a significant impact on the cognitive, emotional and behavioral abilities of the body. During combat, when the pilot is in high load for a long time, the pilot is in mental fatigue risk increase and combat casualties are easily caused. In daily life, a doctor can last for tens of hours when performing a complex operation, accident reports of sudden fatigue of the doctor are frequent, and traffic accidents caused by fatigue driving of a driver are also endless. The fatigue state of a human body is judged through the spontaneous brain electricity (EEG) of the human body, and the human body is not dependent on subjective statement and active participation of a tested person and is currently recognized as a gold standard for fatigue monitoring.
Therefore, the existing fatigue monitoring device realizes fatigue judgment by collecting the electroencephalogram signals. Because the brain electrical signal is very weak signal, the amplitude of spontaneous brain electrical is about 5-200uV, the device is particularly easy to be interfered by environmental electromagnetic interference and the movement of a tested person, the existing fatigue monitoring device is connected with the exposed brain electrical acquisition electrode through a long connecting wire, the brain electrical acquisition electrode is arranged at a corresponding position to acquire the brain electrical signal after the tested person is subjected to scalp cleaning treatment, electrode conductive paste and the like, the monitoring process is always kept still as much as possible, the brain electrical acquisition electrode is prevented from being driven by the movement of the connecting wire and the like to deviate from the standard acquisition position, and the monitoring device is always only applicable to experimental environments such as hospitals and scientific research institutions and the tested controllable places.
Disclosure of Invention
The applicant has found that existing fatigue monitoring devices suffer from the problem of being complex to use. The applicant further researches and discovers that the whole device is large in size mainly because the traditional fatigue monitoring device is often connected with the data analysis equipment and the exposed acquisition electrode through a long connecting wire to acquire the electroencephalogram signals, and the analysis equipment and the acquisition electrode are required to be operated respectively when the device is used, so that the operation is complex.
The invention aims to solve the problem of complex use of a fatigue monitoring device in the prior art.
In order to solve the above technical problems, an embodiment of the present invention discloses a fatigue monitoring device, including: the shell is made of flexible materials, and a through hole is formed in a first surface of the shell along a first direction; the FPC board is arranged in the shell, and a micro control unit is arranged on the FPC board; the electroencephalogram acquisition electrode passes through the through hole and is arranged on the first surface, the electroencephalogram acquisition electrode is electrically connected with the micro-control unit, and the electroencephalogram acquisition electrode is used for acquiring electroencephalogram signals of the forehead; the first ear clip comprises a first magnetic attraction part which is symmetrically arranged, a bias acquisition electrode and a reference acquisition electrode are arranged on the first magnetic attraction part, and the bias acquisition electrode and the reference acquisition electrode are electrically connected with the micro-control unit; the second ear clip and the second connecting portion, second ear clip and casing are connected to second connecting portion, and first connecting portion and second connecting portion symmetry set up in the both ends of casing along the second direction, and the second ear clip is including the second magnetism portion of inhaling that the symmetry set up, is provided with blood oxygen collector in the second magnetism portion of inhaling, and blood oxygen collector is connected with little control unit electricity, and little control unit is connected with second magnetism portion electricity of inhaling.
By adopting the technical scheme, the fatigue monitoring device is convenient to use.
Optionally, the first ear clip and/or the second ear clip includes a symmetrically disposed bending portion, and the bending portion connects the first magnetic attraction portion and the first connection portion and/or connects the second magnetic attraction portion and the second connection portion.
Optionally, the number of the electroencephalogram collecting electrodes is multiple, the number of the through holes is the same as that of the electroencephalogram collecting electrodes, the electroencephalogram collecting electrodes are arranged at intervals along the second direction, and the distance between the electroencephalogram collecting electrodes at the two ends along the second direction is 60-100 mm.
Optionally, the fatigue monitoring device further comprises a binding band, wherein binding band holes are formed in two ends of the shell along the second direction, and the binding band penetrates through the binding band holes to be connected with the shell.
Optionally, the fatigue monitoring device further includes a key portion, the key portion is concavely disposed on the second surface of the housing along the first direction, and the key portion is electrically connected with the micro control unit.
Optionally, the fatigue monitoring device further comprises a status lamp, the status lamp is arranged on the second surface, and the status lamp is electrically connected with the micro-control unit.
Optionally, the fatigue monitoring device further comprises a power supply and a magnetic USB interface, the power supply is arranged in the shell, the power supply is electrically connected with the micro control unit and the magnetic USB interface, and the magnetic USB interface is concavely arranged on the second surface.
Optionally, a wireless transmission unit is further arranged on the FPC board, and the wireless transmission unit is electrically connected with the micro-control unit.
Optionally, the fatigue monitoring device further comprises a microphone, the microphone is arranged on the shell, the microphone is electrically connected with the micro-control unit, and the microphone is used for collecting sound signals.
Optionally, the fatigue monitoring device further comprises a speaker, the speaker is arranged on the shell, the speaker is electrically connected with the micro-control unit, and the speaker is used for outputting voice prompts.
Optionally, the micro-control unit comprises an active electrode conversion unit, a multistage filtering and amplifying unit, an analog-to-digital conversion unit and a microprocessor which are electrically connected in sequence, wherein the active electrode conversion unit is electrically connected with the electroencephalogram acquisition electrode.
The embodiment of the invention also discloses a fatigue monitoring method, which comprises the following steps: acquiring first electroencephalogram data and first blood oxygen data; processing the first electroencephalogram data and the first blood oxygen data respectively to obtain electroencephalogram characteristics and blood oxygen characteristics; and inputting the brain electrical characteristics and the blood oxygen characteristics into a classifier for fatigue judgment.
Optionally, before the step of processing the first electroencephalogram data and the first blood oxygen data to obtain the electroencephalogram feature and the blood oxygen feature, the method further includes the following steps: acquiring pre-sampled second electroencephalogram data; inputting the second electroencephalogram data into an identity recognition model for identity recognition; and if the identification fails, saving the second electroencephalogram data.
Optionally, the identification model is trained using a convolutional neural network.
Optionally, the fatigue monitoring method further comprises the steps of: and training and updating the identification model according to the second electroencephalogram data.
Optionally, inputting the electroencephalogram feature and the blood oxygen feature into a classifier for fatigue judgment, including: if the identification is successful, inputting the electroencephalogram characteristics and the blood oxygen characteristics into a specific classifier corresponding to the identified identification information to perform fatigue judgment; if the identification fails, the brain electrical characteristics and the blood oxygen characteristics are input into a general classifier to carry out fatigue judgment.
Optionally, the electroencephalographic features include functional connection features, nonlinear dynamics features, power spectrum features, and the oximetry features include oximetry variability features.
Optionally, the functional connection feature is mutual information values corresponding to theta waves, alpha waves, beta waves and gamma waves in the first electroencephalogram data, the nonlinear dynamics feature is approximate entropy corresponding to the theta waves, alpha waves, beta waves and gamma waves, and the power spectrum feature is a power ratio corresponding to the theta waves, alpha waves, beta waves and gamma waves.
Optionally, the fatigue monitoring method further comprises the steps of: acquiring pre-sampled second blood oxygen data, and calculating to obtain an average value P ref of blood oxygen saturation in the second blood oxygen data; and calculating according to the blood oxygen saturation value P of the first blood oxygen data, wherein the blood oxygen saturation variability is characterized by (P/P ref)4.
Optionally, before the step of calculating the variability of blood oxygen saturation characteristic (P/P ref)4), the method further comprises the step of processing the first blood oxygen data and the second blood oxygen data to remove outliers less than 85.
Optionally, the fatigue monitoring method further comprises the steps of: if the fatigue is judged, the electric stimulation is output.
Optionally, the fatigue monitoring method further comprises the steps of: and if the user is judged to be tired, playing a voice prompt.
Optionally, the fatigue monitoring method further comprises the steps of: if the identification fails and the user is judged to be tired, storing first electroencephalogram data; and training and generating a corresponding classifier according to the first electroencephalogram data and the second electroencephalogram data.
Embodiments of the invention also disclose a computing device comprising: a processor adapted to implement various instructions; a memory adapted to store a plurality of instructions adapted to be loaded by the processor and to perform any of the fatigue monitoring methods described above.
The embodiment of the invention also discloses a storage medium which stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the fatigue monitoring method.
Drawings
FIG. 1 illustrates a rear view of a fatigue monitoring device in an embodiment of the present invention;
FIG. 2 shows a top view of a fatigue monitoring device in accordance with yet another embodiment of the present invention;
FIG. 3 shows a front view of a fatigue monitoring device in another embodiment of the invention;
FIG. 4 shows a schematic block diagram of the connection of a micro-control unit in a further embodiment of the invention;
FIG. 5 is a flowchart showing steps of a fatigue monitoring method in an embodiment of the present invention;
Fig. 6 shows a flow chart of the steps of a fatigue monitoring method in a further embodiment of the invention.
Detailed Description
Further advantages and effects of the present invention will become apparent to those skilled in the art from the disclosure of the present specification, by describing the embodiments of the present invention with specific examples. While the description of the invention will be described in connection with the preferred embodiments, it is not intended to limit the inventive features to the implementation. Rather, the purpose of the invention described in connection with the embodiments is to cover other alternatives or modifications, which may be extended by the claims based on the invention. The following description contains many specific details for the purpose of providing a thorough understanding of the present invention. The invention may be practiced without these specific details. Furthermore, some specific details are omitted from the description in order to avoid obscuring the invention. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
It should be noted that in this specification, like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the embodiments of the present invention, it should be noted that, directions or positional relationships indicated by terms such as "upper", "lower", "inner", "bottom", etc., are directions or positional relationships based on those shown in the drawings, or those that are conventionally put in place when the inventive product is used, are merely for convenience in describing the present invention and simplifying the description, and are not indicative or implying that the apparatus or element to be referred to must have a specific direction, be configured and operated in a specific direction, and therefore should not be construed as limiting the present invention.
The terms "first," "second," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
Referring to fig. 1 and 2, an embodiment of the present invention provides a fatigue monitoring device, including: a housing 1, the housing 1 being of a flexible material, a first face 11 of the housing 1 in a first direction (X direction shown in fig. 2) being provided with a through hole 12; the FPC board 2, the FPC board 2 is set up in the body 1, there are micro-control units 21 on the FPC board 2; the electroencephalogram acquisition electrode 3 is arranged on the first surface 11 through the through hole 12, the electroencephalogram acquisition electrode 3 is electrically connected with the micro control unit 21, and the electroencephalogram acquisition electrode 3 is used for acquiring electroencephalogram signals of the forehead; the first ear clip 4 and the first connecting part 5, the first connecting part 5 connects the first ear clip 4 and the shell 1, the first ear clip 4 comprises a first magnetic attraction part 41 which is symmetrically arranged, a bias collection electrode (not shown in the figure) and a reference collection electrode (not shown in the figure) are arranged on the first magnetic attraction part 41, and the bias collection electrode and the reference collection electrode are electrically connected with the micro control unit 21; the second ear clip 6 and the second connecting part 7, the second connecting part 7 connects the second ear clip 6 and the housing 1, the first connecting part 5 and the second connecting part 7 are symmetrically arranged at two ends of the housing 1 along the second direction (Y direction shown in fig. 1), the second ear clip 6 comprises a second magnetic attraction part 61 which is symmetrically arranged, and a blood oxygen collector (not shown in the figure) is arranged on the second magnetic attraction part 61 and is electrically connected with the micro control unit 21; the micro control unit 21 is electrically connected to the second magnetic attraction portion 61.
In this embodiment, the housing 1 is made of a flexible material such as silica gel or rubber, and the first surface 11 of the housing 1 along the first direction is provided with a through hole 12, that is, the through hole 12 penetrates the first surface 11 to the inside of the housing 1, but does not penetrate the entire housing 1, and the through hole 12 is provided for the electroencephalogram acquisition electrode 3 to penetrate. The shell 1 is internally provided with an FPC board 2, namely a flexible circuit board (Flexible Printed Circuit), and the FPC is provided with a micro-control unit 21, and the micro-control unit 21 is electrically connected with the electroencephalogram acquisition electrode 3, so that acquired electroencephalogram signals can be processed. The electroencephalogram acquisition electrode 3 passes through the through hole 12 and is arranged on the first surface 11 of the shell 1, and the electroencephalogram acquisition electrode 3 is used for acquiring electroencephalogram signals of the forehead.
By adopting the technical scheme, the fatigue monitoring device is convenient to use. The fatigue monitoring device disclosed in this embodiment is characterized in that the electroencephalogram acquisition electrode 3 is directly arranged on the surface of the shell 1, and the micro control unit 21 arranged in the shell 1 performs signal processing, so that the fatigue monitoring device is different from the electroencephalogram acquisition electrode which is connected with data analysis equipment and exposed without a shell through a long connecting wire in the prior art, the whole device is miniaturized, is convenient to carry and use, and has wider use scene. When in use, the shell 1 is only required to be placed at the corresponding monitoring position for monitoring. And the micro control unit 21 is arranged in the shell 1, long connecting wires are not needed when the micro control unit 21 is electrically connected with the electroencephalogram acquisition electrode 3, and the electroencephalogram acquisition is more stable and reliable. Meanwhile, the shell and the circuit board in the embodiment are made of flexible materials, so that the device can be well attached to the forehead of a user according to the shape adaptability flexible deformation of the forehead of the user in the use process, is easier to fix, and further improves the accuracy of acquired brain electrical signals. Moreover, compared with a common PCB, the FPC board is adopted, the largest area of the circuit board can be lifted in the limited flexible shell space, and under the same number of circuit devices, the FPC board can enable the whole device to be miniaturized. In the same flexible shell space, more circuit devices than the PCB can be placed on the FPC board, so that the function expansion of the device is facilitated. And the FPC board is thinner, so that the thickness and weight of the device are reduced, and wearing comfort is enhanced. Preferably, the shell 1 is silica gel, so that the FPC is conveniently packaged through low-temperature silica gel vulcanization, circuit elements are prevented from being damaged by high temperature, the shell 1 is enabled to have better toughness, and the production efficiency, the yield and the comfort in use are improved. Preferably, one end of the electroencephalogram acquisition electrode 3 is fixedly arranged on the FPC board 2, and the other end of the electroencephalogram acquisition electrode passes through the through hole 12 and is fixedly arranged on the first surface 11, so that the volume is further reduced, and the stability of acquisition signals is improved.
In this embodiment, the bias collecting electrode and the reference collecting electrode can be stably and reliably fixed to the ear by the magnet through the magnetic first ear clip 4, and the collected electric signal is more stable. The offset collecting electrode and the reference collecting electrode are arranged on the symmetrical first magnetic attraction part 41, so that wearing is more comfortable, the electrode and the ear are ensured to be in more stable contact, the ear is closer to the forehead, and the first connecting part 5 is shorter in length and convenient to use. In one embodiment, the first magnetically attractable portion 41 secures the offset capture electrode and the reference capture electrode by magnet pack sintering the dry electrode. Preferably, the first connecting portion 5 is a shielding wire wrapped by silica gel, so that electrical stability of the collected electrical signals is improved. Preferably, the first connecting portion 5 is connected to an upper portion of the housing 1 when in use, so as to avoid interference with a user's vision when in use, and is suitable for various application scenarios.
In the present embodiment, the blood oxygen data of the user can be stably collected by providing the blood oxygen collector on the symmetrical second magnetic attraction part 61, and the fatigue monitoring and evaluation can be performed by integrating the blood oxygen data and the electroencephalogram data, so that the obtained fatigue monitoring result is more accurate. The blood oxygen collector is arranged on the ear clip which is different from the bias collecting electrode and the reference collecting electrode, so that the interference between circuits can be avoided, and the reliability and the accuracy of signal collection are improved. The blood oxygen collector may be a blood oxygen saturation sensor, or may be a transmission photodiode and an LED light emitting diode which are symmetrically arranged, which is not limited in this embodiment. By electrically connecting the micro control unit 21 and the second magnetic attraction portion 61, the magnetic attraction portion can not only play a role of fixation, but also use the magnet as a stimulating electrode. The complexity of the design of the stimulation portion can be effectively reduced, and thus the design of the housing 1 can be made very small. When the fatigue monitoring result is fatigue, the micro-control unit 21 sends an electric signal to the second magnetic attraction part 61 to perform electric needle stimulation, so that the structure is simple, fatigue intervention is timely and reliably completed, and safety accidents caused by fatigue of a user are avoided. The second magnetic part 61 outputs electric stimulation, so that interference on the acquisition of analog signals by the acquisition electrode on the first magnetic part 41 can be avoided, and the accuracy of signal acquisition is improved.
Referring to fig. 3, a further embodiment of the present invention provides a fatigue monitoring device, where the first ear clip 4 and/or the second ear clip 6 includes symmetrically arranged curved portions 8, and the curved portions 8 connect the first magnetic attraction portion 41 and the first connection portion 5, and/or connect the second magnetic attraction portion 61 and the second connection portion 7. Through setting up the equal outwards bending of symmetry flexion 8, can make the ear clamp adapt to the profile of ear better when using, flexion 8 can hold the ear edge, the pinch point degree of depth and the position of the regulation ear clamp of being convenient for.
Referring to fig. 1, another embodiment of the present invention provides a fatigue monitoring device, in which the number of electroencephalogram collecting electrodes 3 is plural, the number of through holes 12 is the same as that of the electroencephalogram collecting electrodes 3, the plural electroencephalogram collecting electrodes 3 are arranged at intervals along a second direction, and a distance between the electroencephalogram collecting electrodes 3 located at both ends along the second direction is 60mm-100mm. The electroencephalogram signals of a plurality of parts of the forehead can be collected by arranging a plurality of electroencephalogram collecting electrodes 3, and the accuracy of fatigue monitoring results is improved. Meanwhile, the distance between the electroencephalogram acquisition electrodes 3 at the two ends is 60mm-100mm, so that the applicant finds through a large number of experiments that the corresponding shell 1 at the distance can adapt to the forehead of most people, can accurately acquire the corresponding electroencephalogram signals, can improve the reliability of the device, and avoids overlong and easy bending damage. Preferably, the number of the electroencephalogram acquisition electrodes 3 is three, so that the accuracy of the monitoring result can be ensured, and the processing load of the micro control unit 21 is reduced. Preferably, the shell 1 between the electroencephalogram acquisition electrodes 3 is provided with grooves, so that on one hand, the appearance is improved, on the other hand, the contact area between the shell and the skin can be reduced, ventilation is realized, and perspiration of a user is reduced.
Referring to fig. 3, a further embodiment of the present invention provides a fatigue monitoring device, further comprising a strap (not shown), wherein strap holes 13 are provided at both ends of the housing 1 in the second direction (Y direction shown in fig. 3), and the strap is connected to the housing 1 through the strap holes 13. According to the embodiment, the shell 1 can be more stably and reliably fixed on the forehead of a user by arranging the binding bands, so that the use of the device in a scene where the user activities such as driving are frequent is facilitated.
Referring to fig. 2 and 3, another embodiment of the present invention provides a fatigue monitoring device, further comprising a key portion 15, wherein the key portion 15 is concavely disposed on the second surface 14 of the housing 1 along the first direction (X direction shown in fig. 2), and the key portion 15 is electrically connected to the micro-control unit 21. By arranging the key part 15 on the second surface 14 opposite to the electroencephalogram acquisition electrode 3, the operation in the use process of a user is facilitated. The recessed arrangement, i.e. the key part 15 is lower than the surrounding plane of the housing 1, can prevent the user from operating the fatigue monitoring device by mistake when wearing the device or sleeping.
Referring to fig. 3, a further embodiment of the present invention provides a fatigue monitoring device, further comprising a status light 16, wherein the status light 16 is disposed on the second surface 14, and the status light 16 is electrically connected to the micro-control unit 21. The status light 16 carries out light prompt according to the working state of the device, and the convenience of use is improved.
Referring to fig. 3, another embodiment of the present invention provides a fatigue monitoring device, further including a power source (not shown) and a magnetic-attraction type USB interface 17, wherein the power source is disposed in the housing 1, the power source is electrically connected with the micro control unit 21 and the magnetic-attraction type USB interface 17, and the magnetic-attraction type USB interface 17 is concavely disposed on the second face 14. In this embodiment, the power supply is arranged in the fatigue monitoring device, and the fatigue monitoring device can be a button cell or the like, and is convenient for daily use without external connection. The magnetic USB interface 17 is arranged to facilitate charging of a power supply, the size of the device can be reduced compared with a plug-in interface, waterproof treatment is facilitated on the interface, and false touch can be avoided due to concave arrangement. Preferably, the fatigue monitoring device further comprises a storage unit (not shown) for storing the collected brain electrical data, and the data stored in the storage unit can be transmitted through the magnetic USB interface 17, so that collection, analysis and processing of a large amount of data are facilitated.
A further embodiment of the present invention provides a fatigue monitoring device, wherein a wireless transmission unit (not shown) is further disposed on the FPC board 2, and the wireless transmission unit is electrically connected to the micro-control unit 21. In this embodiment, the wireless transmission unit is configured to wirelessly transmit collected computer data to a mobile terminal, a cloud server, etc., so as to facilitate a large amount of data analysis and processing, where a specific transmission mode may be WIFI, ZIGBEE, classical bluetooth, and BLE (bluetooth low energy). Preferably, the wireless transmission unit performs data transmission through BLE, so that the wireless transmission unit is suitable for being applied to an application scene of long-term monitoring, and the power consumption is smaller.
Referring to fig. 1 and 3, another embodiment of the present invention provides a fatigue monitoring device, further comprising a microphone 18, wherein the microphone 18 is disposed on the housing 1, the microphone 18 is electrically connected to the micro-control unit 21, and the microphone 18 is used for collecting sound signals. In the present embodiment, the microphone 18 is provided to collect the sound signal, and the micro control unit 21 analyzes the sound signal to find abnormality in time, for example, including snoring and whistling, thereby further improving safety in use. Preferably, the microphone 18 is provided with a waterproof and breathable film, so that water is prevented from entering during use, and stability is improved.
Referring to fig. 1 and 3, a further embodiment of the present invention provides a fatigue monitoring device, further comprising a speaker 19, wherein the speaker 19 is disposed on the housing 1, the speaker 19 is electrically connected to the micro-control unit 21, and the speaker 19 is configured to output a voice prompt. In this embodiment, by setting the speaker 19, when the fatigue monitoring result is fatigue, the voice prompt can be timely output to remind the user, and the use experience is improved.
Referring to fig. 4, another embodiment of the present invention provides a fatigue monitoring device, where the micro-control unit 21 includes an active electrode conversion unit 211, a multi-stage filtering and amplifying unit 212, an analog-to-digital conversion unit 213 and a microprocessor 214, which are electrically connected in sequence, and the active electrode conversion unit 211 is electrically connected to the electroencephalogram acquisition electrode 3. In this embodiment, by setting the active electrode conversion unit 211 and the multistage filtering and amplifying unit 212, weak electrical signals can be amplified, so that environmental interference is avoided, and because the electroencephalogram signal on the forehead is collected by the fatigue monitoring device, the electroencephalogram collection electrode 3 can be a gel electrode, a silver chloride sintered dry electrode or an electrocardiograph paste, and the like, and scalp cleaning treatment and conductive paste adding are not needed when the electroencephalogram collection electrode is used, and the electroencephalogram collection electrode is directly measurable and can be used for rapid monitoring of electroencephalogram. In one embodiment, the active electrode conversion unit 211 uses an operational amplifier as a voltage follower for level-keeping, provides a larger input impedance, and reduces interference to the collected electrical signal. Preferably, the active electrode conversion unit 211 adopts an input impedance of 50mΩ or more. At this time, even if the collecting electrode moves due to the movement of the user, the contact resistance generated when the collecting electrode moves changes by hundreds of ohms, and the impedance relative to 50MΩ ohms is negligible, so that the device has very low requirements on the user and wider application fields. Preferably, the multistage filtering and amplifying unit 212 mainly comprises an instrument amplifying and band-pass filtering circuit, wherein an intermediate signal amplified by the instrument is reversely output to a bias acquisition electrode through a bias circuit, and is similar to a right leg driving circuit for electrocardio acquisition. On one hand, the method is used for eliminating power frequency common mode interference, and on the other hand, the method is used for biasing an original signal to the vicinity of a 0 point position, so that the amplification and filtering of subsequent signals are facilitated.
Referring to fig. 5, an embodiment of the present invention provides a fatigue monitoring method, which includes the steps of: s1: acquiring first electroencephalogram data and first blood oxygen data; s2: processing the first electroencephalogram data and the first blood oxygen data respectively to obtain electroencephalogram characteristics and blood oxygen characteristics; s3: and inputting the brain electrical characteristics and the blood oxygen characteristics into a classifier for fatigue judgment.
In the present embodiment, by inputting the electroencephalogram data and the blood oxygen data together into the classifier to perform fatigue judgment, accuracy of the fatigue judgment result can be improved and erroneous judgment can be reduced as compared with a case where only the electroencephalogram data or only the blood oxygen data is used to perform single-dimensional judgment analysis. The device for acquiring the brain electrical data and the blood oxygen data can be selected correspondingly according to the needs, a plurality of devices can be respectively acquired, the same device can be used for acquiring, the structure of the device can be selected, and the embodiment is not limited to the method. In an embodiment, the fatigue monitoring method uses the fatigue monitoring device in any of the foregoing embodiments to collect electroencephalogram data and blood oxygen data, and performs fatigue judgment through the micro control unit 21, or may send the data to a mobile terminal, a cloud server, or the like to perform fatigue judgment. In other embodiments, other configurations of devices may be used to collect brain electrical data and blood oxygen data. The classifier may be a vector machine classifier or the like, and this embodiment is not limited thereto.
The invention further provides a fatigue monitoring method, which further comprises the following steps before the step S2 of processing the first electroencephalogram data and the first blood oxygen data to obtain the electroencephalogram characteristics and the blood oxygen characteristics respectively: acquiring pre-sampled second electroencephalogram data; inputting the second electroencephalogram data into an identity recognition model for identity recognition; and if the identification fails, saving the second electroencephalogram data.
In this embodiment, the second electroencephalogram data may be acquired simultaneously with the first electroencephalogram data, or may be acquired separately, and the order of the separate acquisitions is not limited. By means of identity recognition, different subsequent treatments are conveniently carried out according to whether a user is an existing person in the identity model, if the recognition fails, corresponding second electroencephalogram data are stored, the subsequent optimization model is conveniently carried out, and reliability and accuracy of the fatigue monitoring method are improved. In an embodiment, 300 pieces of electroencephalogram data of a user are collected and input into an identity recognition model, and when the recognition matching rate is lower than 90%, the recognition is judged to be failed, and at the moment, the recognition accuracy of the identity model is higher. In a preferred embodiment, the fatigue monitoring method uses the fatigue monitoring device in any of the foregoing embodiments to collect electroencephalogram data and blood oxygen data, where the fatigue monitoring device includes a communication unit, and sends the collected data to a cloud server in a wired or wireless manner, and the cloud server completes identity recognition and performs fatigue judgment. The cloud server can store more identity models, the operation efficiency is higher, and the universality of the fatigue monitoring method is improved. In other embodiments, other configurations of devices may be used to collect brain electrical data and blood oxygen data.
The invention further provides a fatigue monitoring method, and the identity recognition model is obtained by training a convolutional neural network. In the embodiment, the convolutional neural network is used for training the identity recognition model, so that the recognition accuracy of the identity recognition model can be improved. Preferably, a inceprtion network structure is added to the convolutional neural network, so that the accuracy of the identity recognition model is improved. In one embodiment, 300 pieces of electroencephalogram data of the user in a non-fatigue state are collected for training of the identification model, for example, the sampling frequency is 5 minutes, and the sampling frequency is 60 times/minute.
Still another embodiment of the present invention provides a fatigue monitoring method, further comprising the steps of: and training and updating the identification model according to the second electroencephalogram data. In this embodiment, the identification model is updated by the second electroencephalogram data, so that the operation efficiency can be improved when the device is used again. In this embodiment, the device for acquiring brain electrical data and blood oxygen data may be selected as needed, and this embodiment is not limited thereto. Preferably, the deep learning model, such as a convolutional neural network, is used for updating the identity recognition model, so that the updating efficiency can be improved.
The invention further provides a fatigue monitoring method, which inputs the brain electrical characteristics and the blood oxygen characteristics into a classifier to carry out fatigue judgment S3, and comprises the following steps: if the identification is successful, inputting the electroencephalogram characteristics and the blood oxygen characteristics into a specific classifier corresponding to the identified identification information to perform fatigue judgment; if the identification fails, the brain electrical characteristics and the blood oxygen characteristics are input into a general classifier to carry out fatigue judgment. In the embodiment, the fatigue classification accuracy is not high due to individual variability by using a method that a user uses a general fatigue classifier by one person, so that the accuracy of fatigue judgment is improved.
Yet another embodiment of the present invention provides a method for fatigue monitoring, wherein the electroencephalogram features include functional connection features, nonlinear dynamics features, power spectrum features, and blood oxygen features include blood oxygen saturation variability features. In the embodiment, by determining that the electroencephalogram characteristics are the functional connection characteristics, the nonlinear dynamics characteristics and the power spectrum characteristics, the electroencephalogram data is processed and analyzed from three different dimensions, so that the accuracy of fatigue judgment can be further improved. The functional connection characteristic, the nonlinear dynamics characteristic and the power spectrum characteristic can be obtained based on one or more of theta waves, alpha waves, beta waves and gamma waves corresponding to the acquired brain electrical data, and the blood oxygen saturation variability characteristic mainly comprises the step of evaluating whether blood oxygen saturation is abnormal or not, and can be whether the blood oxygen saturation exceeds a normal value or not.
In another embodiment of the present invention, a fatigue monitoring method is provided, where the functional connection feature is mutual information values corresponding to theta waves, alpha waves, beta waves and gamma waves in the first electroencephalogram data, the nonlinear dynamics feature is approximate entropy corresponding to the theta waves, alpha waves, beta waves and gamma waves, and the power spectrum feature is a power ratio corresponding to the theta waves, alpha waves, beta waves and gamma waves. In this embodiment, through a great deal of experimental study, the applicant finds that, in the first electroencephalogram data, mutual information values corresponding to the theta wave, the alpha wave, the beta wave and the gamma wave are used as functional connection features, approximate entropies corresponding to the theta wave, the alpha wave, the beta wave and the gamma wave are used as nonlinear dynamics features, and power ratios corresponding to the theta wave, the alpha wave, the beta wave and the gamma wave are used as power spectrum features, so that not only can the accuracy of fatigue judgment be ensured, but also the operation load is reduced. Preferably, the power spectral features include Ealpha/Ebeta、(Ealpha+Etheta)/Ebeta、(Ealpha+Etheta)/(Ebeta+Egamma)、Etheta/Ebeta, to further enhance the accuracy of the operation.
In one embodiment, a driving fatigue is induced by adopting a driving simulation task for 90 minutes, brain electrical signals of 24 leads of human brain electrical signals are collected, brain electrical data at the beginning of an experiment is selected as input data of identity recognition, and a convolutional neural network model is utilized to obtain the average identity recognition accuracy rate of 98.5 percent (96.3-100 percent) in 31 subjects. The sampling frequency of the brain electrical data is 60 times/min, and the brain electrical signals of 5 minutes corresponding to the lowest and highest reaction time in the experimental process are selected as brain electrical data of a awake state and a fatigue state. Preprocessing the electroencephalogram data, namely performing threshold drying, baseline drift removal, 4-40Hz filtering and the like on the acquired electroencephalogram data. The applicant finds out through a large number of experiments that the 4-40Hz filtering can keep the brain electrical signals of most people, filter clutter and reduce interference. Calculating the brain electrical characteristics, such as functional connection characteristics, of the preprocessed brain electrical data, wherein the brain electrical characteristics can be mutual information values corresponding to theta waves, alpha waves, beta waves and gamma waves, and the total number of the characteristics is 4; for example, the nonlinear dynamics features can be approximate entropy corresponding to theta waves, alpha waves, beta waves and gamma waves, and the total number of the features is 8; such as power spectrum characteristics, may be a total of 8 characteristics, such as Ealpha/Ebeta、(Ealpha+Etheta)/Ebeta、(Ealpha+Etheta)/(Ebeta+Egamma)、Etheta/Ebeta,, for two leads. In one embodiment, 20 features are selected by a recursive feature elimination-support vector machine feature selection algorithm and then used as input of a support vector machine classifier to calculate driving fatigue classification accuracy, wherein the accuracy in samples of the three lead pairs before ranking is 83.2%, 83.0% and 82.4% respectively, and the positions are located in forehead non-hair coverage areas; the electroencephalogram features extracted from the 3 leads which are not covered by the hair are re-classified as the input of the convolutional neural network, the accuracy of 96.0% is obtained in the sample, and the accuracy of 82.1% is obtained among the non-samples. Preferably, the fatigue monitoring method adopts the fatigue monitoring device in any one of the foregoing embodiments to collect brain electrical data and blood oxygen data, and three brain electrical collecting electrodes 3 are sequentially arranged on the first face 11 of the casing 1 of the fatigue monitoring device, and are used for collecting brain electrical data corresponding to three leads of the non-hair area on the front side of the forehead of the user. The distance between the electroencephalogram acquisition electrodes 3 at the two sides is 60mm-100mm, and the electroencephalogram signals at the FP1 and FP2 positions on the forehead of different people can be accurately acquired. The fatigue judgment accuracy rate can be up to 96.0% by acquiring the electroencephalogram data singly through the fatigue monitoring device, and the accuracy of fatigue judgment can be further improved by combining the blood oxygen data.
Still another embodiment of the present invention provides a fatigue monitoring method, further comprising the steps of: acquiring pre-sampled second blood oxygen data, and calculating to obtain an average value P ref of blood oxygen saturation in the second blood oxygen data; according to the blood oxygen saturation value P of the first blood oxygen data, the blood oxygen saturation variability characteristic is calculated (P/P ref)4. In the embodiment, the applicant finds that the average value of normal blood oxygen saturation in the pre-sampling is taken as a basis, the blood oxygen is set (P/P ref)4 is taken as the blood oxygen saturation variability characteristic, whether the blood oxygen is normal can be well judged, and the accuracy of fatigue judgment can be greatly improved after the blood oxygen is combined with the electroencephalogram characteristic.
In the embodiment, the obviously abnormal blood oxygen saturation value is removed, so that erroneous judgment can be avoided.
Referring to fig. 6, a further embodiment of the present invention provides a fatigue monitoring method, further comprising the steps of: s4: if the fatigue is judged, the electric stimulation is output. In the embodiment, fatigue early warning and intervention can be well carried out by the electric stimulation user, and compared with modes such as lamplight alarm, the electric stimulation is more direct and effective, and interference of lamp wire change on application scenes such as driving is avoided. In an embodiment, the fatigue monitoring method may adopt the fatigue monitoring device in any of the foregoing embodiments to perform data acquisition, as shown in fig. 3, and at this time, the electrical stimulation may be directly output through the second magnetic attraction portion 61, without setting an additional stimulation structure, so that the structure of the fatigue monitoring device is simplified, and the implementation of fatigue early warning and intervention is convenient.
Another embodiment of the present invention provides a fatigue monitoring method, further comprising the steps of: and if the user is judged to be tired, playing a voice prompt. In the embodiment, fatigue early warning and intervention can be timely and effectively completed through voice reminding.
Still another embodiment of the present invention provides a fatigue monitoring method, further comprising the steps of: if the identification fails and the user is judged to be tired, storing first electroencephalogram data; and training and generating a corresponding classifier according to the first electroencephalogram data and the second electroencephalogram data. In this embodiment, the fatigue electroencephalogram data, i.e., the first electroencephalogram data, and the non-fatigue electroencephalogram data, i.e., the second electroencephalogram data, of the new user are stored and then trained to generate the personal classifier corresponding to the new user. The method is convenient for accurately carrying out identity recognition when being used next time, and the corresponding personal classifier is used for improving the accuracy of fatigue judgment. Preferably, the training of the classifier is performed using a convolutional neural network. Preferably, the blood oxygen data of the new user in normal state and the blood oxygen data of the new user in fatigue state are simultaneously stored, and training of the classifier is completed together with the electroencephalogram data, so that the accuracy is further improved.
An embodiment of the present invention provides a computing device including: a processor adapted to implement various instructions; a memory adapted to store a plurality of instructions adapted to be loaded by the processor and to perform the fatigue monitoring method of any of the previous embodiments.
An embodiment of the present invention provides a storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the fatigue monitoring method of any of the previous embodiments.
Embodiments of the present disclosure may be implemented in hardware, software, firmware, or a combination of these implementations. Embodiments of the application may be implemented as a computer program or program code that is executed on a programmable system comprising at least one processor, a storage system (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device. Program code may be applied to input instructions to perform the functions described herein and generate output information. The output information may be applied to one or more output devices in a known manner. For the purposes of this application, a processing system includes any system having a processor such as, for example, a Digital Signal Processor (DSP), a microcontroller, an Application Specific Integrated Circuit (ASIC), or a microprocessor.
The program code may be implemented in a high level procedural or object oriented programming language to communicate with a processing system. Program code may also be implemented in assembly or machine language, if desired. Indeed, the mechanisms described in the present application are not limited in scope by any particular programming language. In either case, the language may be a compiled or interpreted language.
In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried by or stored on one or more transitory or non-transitory machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be distributed over a network or through other computer readable media. Thus, a machine-readable medium may include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer), including but not limited to floppy diskettes, optical disks, read-only memories (CD-ROMs), magneto-optical disks, read-only memories (ROMs), random Access Memories (RAMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), magnetic or optical cards, flash memory, or tangible machine-readable memory for transmitting information (e.g., carrier waves, infrared signal digital signals, etc.) in an electrical, optical, acoustical or other form of propagated signal using the internet. Thus, a machine-readable medium includes any type of machine-readable medium suitable for storing or transmitting electronic instructions or information in a form readable by a machine (e.g., a computer).
In the drawings, some structural or methodological features may be shown in a particular arrangement and/or order. However, it should be understood that such a particular arrangement and/or ordering may not be required. Rather, in some embodiments, these features may be arranged in a different manner and/or order than shown in the illustrative figures. Additionally, the inclusion of structural or methodological features in a particular figure is not meant to imply that such features are required in all embodiments, and in some embodiments, may not be included or may be combined with other features.
It should be noted that, in the embodiments of the present application, each module/unit mentioned in each device embodiment is a logic module/unit, and in physical terms, one logic module/unit may be one physical module/unit, or may be a part of one physical module/unit, or may be implemented by a combination of multiple physical modules/units, where the physical implementation manner of the logic module/unit itself is not the most important, and the combination of functions implemented by the logic module/unit is only a key for solving the technical problem posed by the present application. Furthermore, in order to highlight the innovative part of the present application, the above-described device embodiments of the present application do not introduce modules/units that are less closely related to solving the technical problems posed by the present application, which does not indicate that the above-described device embodiments do not have other modules/units.
While the invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that the foregoing is a further detailed description of the invention with reference to specific embodiments, and it is not intended to limit the practice of the invention to those descriptions. Various changes in form and detail may be made therein by those skilled in the art, including a few simple inferences or alternatives, without departing from the spirit and scope of the present invention.
Claims (23)
1. A fatigue monitoring device, comprising:
the shell is made of flexible materials, and a through hole is formed in a first surface of the shell along a first direction;
The FPC board is arranged in the shell, a micro control unit is arranged on the FPC board and is used for performing fatigue judgment or sending data to a mobile terminal, a cloud server and the like for performing fatigue judgment, and the micro control unit comprises an active electrode conversion unit, a multistage filtering and amplifying unit, an analog-digital conversion unit and a microprocessor which are electrically connected in sequence, wherein the active electrode conversion unit is electrically connected with an electroencephalogram acquisition electrode; the multistage filtering and amplifying unit comprises an instrument amplifying and band-pass filtering circuit;
The electroencephalogram acquisition electrode passes through the through hole and is arranged on the first surface, the electroencephalogram acquisition electrode is electrically connected with the micro control unit and is used for acquiring electroencephalogram signals of the forehead, and the electroencephalogram acquisition electrode is a gel electrode, a silver chloride sintered dry electrode or an electrocardio paste;
the first ear clip comprises a first magnetic attraction part which is symmetrically arranged, an offset acquisition electrode and a reference acquisition electrode are arranged on the first magnetic attraction part, the offset acquisition electrode and the reference acquisition electrode are electrically connected with the micro control unit, and the first magnetic attraction part is used for fixing the offset acquisition electrode and the reference acquisition electrode through a magnet package sintering dry electrode;
The first ear clip and the second ear clip are symmetrically arranged at two ends of the shell along a second direction, the second ear clip comprises a second magnetic attraction part which is symmetrically arranged, a blood oxygen collector is arranged on the second magnetic attraction part and is electrically connected with the micro-control unit, the micro-control unit is electrically connected with the second magnetic attraction part, a magnet of the second magnetic attraction part is used as a stimulating electrode, and when a fatigue monitoring result is fatigue, the micro-control unit sends an electric signal to the second magnetic attraction part to perform electric needle stimulation;
The first ear clip and/or the second ear clip comprise symmetrically arranged bending parts, the bending parts are connected with the first magnetic attraction part and the first connecting part and/or are connected with the second magnetic attraction part and the second connecting part, and the bending parts are outwards bent and are used for accommodating the edge of an ear and adjusting the depth and the position of a clamping point of the first ear clip and/or the second ear clip;
when fatigue judgment is carried out, the electroencephalogram characteristics of the acquired electroencephalogram data are adopted, wherein the electroencephalogram characteristics comprise mutual information values corresponding to theta waves, alpha waves, beta waves and gamma waves in the electroencephalogram data, approximate entropy corresponding to the theta waves, the alpha waves, the beta waves and the gamma waves, and power ratios corresponding to the theta waves, the alpha waves, the beta waves and the gamma waves.
2. The fatigue monitoring device according to claim 1, wherein the number of the electroencephalogram collecting electrodes is plural, the number of the through holes is the same as the number of the electroencephalogram collecting electrodes, the plural electroencephalogram collecting electrodes are arranged at intervals along the second direction, and a distance between the electroencephalogram collecting electrodes located at both ends along the second direction is 60mm-100mm.
3. The fatigue monitoring device of claim 1, further comprising a strap, wherein strap holes are provided at both ends of the housing in the second direction, the strap being connected to the housing through the strap holes.
4. The fatigue monitoring device of claim 1, further comprising a key portion recessed in the second face of the housing along the first direction, the key portion being electrically connected to the micro-control unit.
5. The fatigue monitoring device of claim 4, further comprising a status light disposed on the second face, the status light being electrically connected to the micro-control unit.
6. The fatigue monitoring device of claim 4, further comprising a power source and a magnetically attracted USB interface, wherein the power source is disposed in the housing, the power source is electrically connected to the micro-control unit and the magnetically attracted USB interface, and the magnetically attracted USB interface is recessed in the second face.
7. The fatigue monitoring device according to claim 1, wherein a wireless transmission unit is further provided on the FPC board, and the wireless transmission unit is electrically connected to the micro control unit.
8. The fatigue monitoring device of claim 1, further comprising a microphone disposed on the housing, the microphone electrically connected to the micro-control unit, the microphone configured to collect sound signals.
9. The fatigue monitoring device of claim 1, further comprising a speaker disposed on the housing, the speaker electrically connected to the micro-control unit, the speaker configured to output a voice prompt.
10. A fatigue monitoring method, characterized in that the fatigue monitoring is performed by using the fatigue monitoring device according to any one of claims 1-9, comprising the steps of:
acquiring first electroencephalogram data and first blood oxygen data;
processing the first electroencephalogram data and the first blood oxygen data respectively to obtain electroencephalogram characteristics and blood oxygen characteristics;
and inputting the electroencephalogram characteristics and the blood oxygen characteristics into a classifier to perform fatigue judgment.
11. The method of claim 10, wherein before the step of processing the first electroencephalogram data and the first blood oxygen data to obtain an electroencephalogram feature and a blood oxygen feature, respectively, further comprising the steps of:
acquiring pre-sampled second electroencephalogram data;
Inputting the second electroencephalogram data into an identity recognition model for identity recognition;
and if the identification fails, saving the second electroencephalogram data.
12. The fatigue monitoring method of claim 11, wherein the identification model is trained using a convolutional neural network.
13. The fatigue monitoring method of claim 11, further comprising the steps of:
and training and updating the identification model according to the second electroencephalogram data.
14. The method of claim 11, wherein the step of inputting the electroencephalogram feature and the blood oxygen feature into a classifier for fatigue determination comprises:
If the identification is successful, inputting the electroencephalogram characteristics and the blood oxygen characteristics into a specific classifier corresponding to the identified identification information to perform fatigue judgment;
If the identification fails, inputting the electroencephalogram characteristic and the blood oxygen characteristic into a general classifier for fatigue judgment.
15. The fatigue monitoring method of claim 10, wherein the electroencephalographic characteristic comprises a functional connection characteristic, a nonlinear dynamics characteristic, a power spectrum characteristic, and the blood oxygen characteristic comprises a blood oxygen saturation variability characteristic.
16. The method of claim 15, wherein the functional connection characteristic is mutual information values corresponding to theta waves, alpha waves, beta waves and gamma waves in the first electroencephalogram data, the nonlinear dynamics characteristic is approximate entropy corresponding to the theta waves, alpha waves, beta waves and gamma waves, and the power spectrum characteristic is a power ratio corresponding to the theta waves, alpha waves, beta waves and gamma waves.
17. The fatigue monitoring method of claim 16, further comprising the steps of:
acquiring pre-sampled second blood oxygen data, and calculating to obtain an average value P ref of blood oxygen saturation in the second blood oxygen data;
And calculating according to the blood oxygen saturation value P of the first blood oxygen data, wherein the blood oxygen saturation variability characteristic is (P/P ref)4.
18. The method of claim 17, further comprising, prior to the step of calculating the variability of blood oxygen saturation characterized by (P/P ref)4:
and processing the first blood oxygen data and the second blood oxygen data to remove abnormal values less than 85.
19. The fatigue monitoring method of claim 10, further comprising the steps of:
If the fatigue is judged, the electric stimulation is output.
20. The fatigue monitoring method of claim 10, further comprising the steps of:
And if the user is judged to be tired, playing a voice prompt.
21. The fatigue monitoring method of claim 13, further comprising the steps of:
If the identification fails and the identification is judged to be tired, the first electroencephalogram data is stored;
And training and generating a corresponding classifier according to the first electroencephalogram data and the second electroencephalogram data.
22. A computing device, comprising:
A processor adapted to implement various instructions;
A memory adapted to store a plurality of instructions adapted to be loaded by the processor and to perform the fatigue monitoring method according to any of claims 10-21.
23. A storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor and to carry out the fatigue monitoring method according to any of claims 10-21.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011389592.2A CN112401908B (en) | 2020-12-02 | 2020-12-02 | Fatigue monitoring device, fatigue monitoring method, computing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011389592.2A CN112401908B (en) | 2020-12-02 | 2020-12-02 | Fatigue monitoring device, fatigue monitoring method, computing equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112401908A CN112401908A (en) | 2021-02-26 |
| CN112401908B true CN112401908B (en) | 2024-07-19 |
Family
ID=74829544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011389592.2A Active CN112401908B (en) | 2020-12-02 | 2020-12-02 | Fatigue monitoring device, fatigue monitoring method, computing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112401908B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116035579B (en) * | 2023-03-06 | 2023-08-25 | 中国人民解放军海军特色医学中心 | Ship driver fatigue evaluation system and method |
| CN116439710B (en) * | 2023-04-11 | 2023-10-20 | 中国人民解放军海军特色医学中心 | Ship driver fatigue detection system and method based on physiological signals |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102520529A (en) * | 2011-12-31 | 2012-06-27 | 上海市七宝中学 | Glasses |
| CN104665790A (en) * | 2015-01-26 | 2015-06-03 | 周常安 | Ear-mounted physiological detector |
| CN111329474A (en) * | 2020-03-04 | 2020-06-26 | 西安电子科技大学 | Electroencephalogram identity recognition method and system based on deep learning and information updating method |
| CN213963394U (en) * | 2020-12-02 | 2021-08-17 | 中国人民解放军海军特色医学中心 | Fatigue monitoring device |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1037088A (en) * | 1988-04-28 | 1989-11-15 | 制铁化学工业株式会社 | Magnetic therapeutic device |
| JPH10259402A (en) * | 1997-03-21 | 1998-09-29 | Jatco Corp | Apparatus for molding sintered powder and molding method therefor |
| FI119172B (en) * | 2003-11-18 | 2008-08-29 | Nexstim Oy | Electrode construction for measuring electrical responses from a human body |
| CN2891967Y (en) * | 2006-04-21 | 2007-04-25 | 北京易飞华通科技开发有限公司 | Driver's fatigue driving monitoring and feedback stimulating instrument |
| CN201397365Y (en) * | 2009-05-11 | 2010-02-03 | 国家海洋技术中心 | Conductivity sensor with seven electrodes |
| CN104841057A (en) * | 2015-05-08 | 2015-08-19 | 山东大学 | Electroencephalogram brainwave alpha based infrasonic wave driving fatigue relieving method and device |
| CN205795687U (en) * | 2016-06-07 | 2016-12-14 | 汪子锋 | Brain electricity cap and brain signal harvester |
| CN105979614A (en) * | 2016-06-30 | 2016-09-28 | 张飞林 | Electric heater and electronic cigarette |
| CN205981306U (en) * | 2016-08-30 | 2017-02-22 | 辽阳文圣仪表有限公司 | Capacitance probe of whirling flow sensor |
| CA3038822A1 (en) * | 2016-09-29 | 2018-04-05 | Mindset Innovation, Inc. | Biosignal headphones |
| CN106683344A (en) * | 2017-01-22 | 2017-05-17 | 福州大学 | Anti-fatigue driving system and working method thereof |
| CN108175392A (en) * | 2018-01-13 | 2018-06-19 | 翟玉莲 | The fatigue driving monitoring based reminding method and device monitored in real time based on pulse blood oxygen |
| CN108784716A (en) * | 2018-03-29 | 2018-11-13 | 苏州中科先进技术研究院有限公司 | A kind of headset equipment and its pay attention to force estimation training method |
| CN209285530U (en) * | 2018-03-29 | 2019-08-23 | 苏州中科先进技术研究院有限公司 | A kind of headset equipment |
| CN210520970U (en) * | 2019-06-27 | 2020-05-15 | 唐延智 | Multi-lead brain wave acquisition equipment |
| CN110755089A (en) * | 2019-10-17 | 2020-02-07 | 浙江荷清柔性电子技术有限公司 | Blood oxygen detection method, blood oxygen detection device and terminal equipment |
-
2020
- 2020-12-02 CN CN202011389592.2A patent/CN112401908B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102520529A (en) * | 2011-12-31 | 2012-06-27 | 上海市七宝中学 | Glasses |
| CN104665790A (en) * | 2015-01-26 | 2015-06-03 | 周常安 | Ear-mounted physiological detector |
| CN111329474A (en) * | 2020-03-04 | 2020-06-26 | 西安电子科技大学 | Electroencephalogram identity recognition method and system based on deep learning and information updating method |
| CN213963394U (en) * | 2020-12-02 | 2021-08-17 | 中国人民解放军海军特色医学中心 | Fatigue monitoring device |
Non-Patent Citations (1)
| Title |
|---|
| 前额脑电与血氧信息融合的人—机交互装置研究;刘延刚;《中国优秀硕士学位论文全文数据库 (信息科技辑)》(第7期);第I138-1023页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112401908A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111417341B (en) | Electrocardiogram measuring equipment | |
| TWI602544B (en) | Biological signal measuring system, biological information measuring device and change method of biological information extraction algorithm | |
| US10092203B2 (en) | Using skin resistance measurements to determine timing of bio-telemetry measurements | |
| US9913591B2 (en) | Wrist-mounted device with integrated electronics | |
| CN112401908B (en) | Fatigue monitoring device, fatigue monitoring method, computing equipment and storage medium | |
| EP3220815B1 (en) | Apparatus for measuring bioelectrical signals | |
| US10368765B2 (en) | Wearable apparatus for ECG signal acquisition | |
| CN106999083A (en) | electrocardiogram device for clothes | |
| KR101258203B1 (en) | cradle device for sensing bio-electric signal and portable device for analyzing the bio-electric signal | |
| KR102057705B1 (en) | A smart hand device for gesture recognition and control method thereof | |
| JP7277970B2 (en) | Electrocardiogram measurement method and system using wearable device | |
| CN108451505A (en) | The In-Ear sleep stage system of light weight | |
| CN213963394U (en) | Fatigue monitoring device | |
| Paul et al. | Attention state classification with in-ear EEG | |
| Che et al. | Portable heart rate detector based on photoplethysmography with android programmable devices | |
| CN113243897B (en) | Health monitoring nursing medical system based on internet | |
| KR102389907B1 (en) | Method and system for measuring electrocardiogram using wearable device | |
| CN211460185U (en) | Intelligent physical examination cabin | |
| CN220001797U (en) | Digital stethoscope system based on piezoelectric film | |
| KR102720653B1 (en) | Electronic device for measuring biometric information and method of operating the same | |
| KR20220145456A (en) | Electronic device and method for providing health information based on electrocardiogram in the electronic device | |
| KR20220039929A (en) | Wearable Patch type Apparatus and its control method for measuring multi-bio signal using multi connection | |
| KR20240154417A (en) | A first wearable electronic device for obtaining a signal including a noise corresponding to a movement of a user, an electronic device for analyzing the signal and method for controlling thereof | |
| CN115040127A (en) | Wearable emotion monitoring method and system integrating electroencephalogram and functional near infrared |
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 |