Multi-mode-based brain fatigue detection system and method
Through a multimodal detection system, combined with EEG, near-infrared and eye movement data, the brain fatigue of staff is analyzed in real time, and the problems of misjudgment and misjudgment detection in the existing technology are solved, achieving more accurate and real-time brain fatigue Monitoring improves work efficiency and safety.
Patent Information
- Application Number
- CN202410960352.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-08
AI Technical Summary
The prior art is difficult to detect the mental fatigue of staff in human-machine systems in real time and accurately, and there are problems of misjudgment and misjudgment of single modal detection methods.
Using a multimodal detection system, combining EEG signals, near-infrared brain functional imaging and eye movement data, data is collected and analyzed in real time through electroencephalogram decoding unit, near-infrared analysis unit, eye movement data analysis unit and auditory button evaluation unit. Calculate the comprehensive fatigue score and grade the degree of brain fatigue.
Improve the accuracy and real-time nature of brain fatigue detection, avoid misjudgment and misjudgment of single modal detection, and provide a real-time brain fatigue monitoring system to help reasonably regulate the brain load of staff, improve work efficiency and safety. .
Smart Images

Figure CN118902455A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of mental fatigue detection, and in particular to a multimodal-based mental fatigue detection system and method. Background Art
[0002] With the advancement of science and technology and the continuous development of artificial intelligence, the human-machine system has experienced a development process from manual work to automated systems, which has reduced physical labor and increased mental labor in modern human-machine systems, and human labor has changed from operational operations to knowledge-based operations. Therefore, the proportion of mental labor in the labor structure is getting higher and higher, and the world's labor structure is also changing from physical labor to mental labor. In modern human-machine systems, people's role tends to be more advanced decision-making and monitoring. The complexity of human-machine systems and the complexity of the operating environment have caused a sharp increase in the amount of information that operators have to process, causing operators to often be at a high level of mental workload. Due to the fatigue-prone nature of the human brain, humans cannot perform long-term and high-intensity work. In some complex and safety-required human-machine systems, it is very important to evaluate the mental workload caused by long-term operation, monitor the mental workload in real time, and make feedback adjustments to reasonably control the task requirements in the human-machine system and adjust the level of human mental workload, which is of great significance to improving human work efficiency, the safety of human-machine system operation, and human physical and mental health. At present, the shortcomings of mental fatigue systems and technologies are: due to the high complexity and subjectivity of measuring human brain fatigue, the analysis of fatigue detection through a single modality is not accurate enough; and there is a lack of a system for real-time detection of mental fatigue of staff.
[0003] In summary, how to design a multimodal system that can detect the degree of mental fatigue in real time is an urgent problem to be solved by technical personnel in this field. Summary of the invention
[0004] The technical solution of the present invention to solve the above technical problems is to provide a multi-modal mental fatigue detection system, comprising:
[0005] A display, used for displaying a gaze information interface;
[0006] EEG signal collection cap, used to collect EEG data;
[0007] Eye tracker, used to collect eye movement data;
[0008] An EEG signal amplifier, the EEG signal amplifier is connected to the EEG signal collection cap;
[0009] A near-infrared brain function imager, the near-infrared brain function imager is electrically connected to the EEG signal acquisition cap;
[0010] The host computer is connected to the electroencephalogram signal amplifier, the near-infrared brain function imager and the eye tracker.
[0011] Furthermore, the host includes an electroencephalogram decoding unit, a near-infrared analysis unit, an eye movement data analysis unit, an auditory key evaluation unit, and a log recording unit.
[0012] Furthermore, the EEG decoding unit is used to analyze the EEG data, including waveform display, data recording and numerical calculation, to display the corresponding EEG waveform record in real time, and to calculate the power ratio R of the relevant frequency band in the time period, and to give a fatigue score S1.
[0013] Furthermore, the near-infrared analysis unit is used to analyze brain blood oxygen parameters in real time, including brain blood oxygen distribution topography and brain blood oxygen value calculation. The blood oxygen content distribution of each near-infrared light channel is represented by a 3D brain blood oxygen topography map, and the fatigue score S2 is given by calculating the change in local brain oxygen saturation (rSO2) in this time period.
[0014] Furthermore, the eye movement data analysis unit is used to analyze the eye movement data in real time, including the real-time position of the viewpoint and the calculation of the duration of scanning, fixation, eye closure and eye opening, and at the same time perform pupil diameter statistics and calculate the percentage of the time when the pupil is covered for more than 80% per unit time (PERCLOS for short), and give a fatigue score S3 for the time period.
[0015] Furthermore, the auditory keystroke evaluation unit is used to analyze the keystroke reaction time of the trainee in real time, including reaction time curve display and reaction time calculation, to judge the mental fatigue degree of the trainee, and to give a fatigue degree score S4 within the time period.
[0016] Furthermore, the host is used to combine the score S1, the score S2, the score S3 and the score S4, perform an average calculation, and obtain a score of a comprehensive fatigue degree F. According to the range of the F value, the fatigue degree is divided into four levels.
[0017] In order to solve the above technical problems, the present invention also proposes a multimodal mental fatigue detection method, comprising the following steps:
[0018] The EEG signal data is collected, the signal is amplified by the EEG signal amplifier, and the spectrum is analyzed by the EEG decoding unit. The power of each band is calculated by fast Fourier transform. The (α+β) / θ ratio R is calculated according to the power of α wave, β wave and θ wave to evaluate the degree of brain fatigue and give the fatigue score S1. The discrimination formula of fatigue score S1 is:
[0019] S1=0,R<1.15;
[0020] S1=1,1.15<R<1.35;
[0021] S1=2,R≥1.35;
[0022] The light intensity changes of the near-infrared detector are collected and converted into digital signals. The degree of mental fatigue of the trainees is evaluated by calculating the local brain oxygen saturation (rSO2) and a fatigue score S2 is given. The discrimination formula of the fatigue score S2 is:
[0023] Regional cerebral oxygen saturation (rSO2) = blood oxygen saturation (HBO2) concentration / (blood oxygen saturation (HBO2) concentration + hemoglobin (HB) concentration);
[0024] The formula for calculating the change in rSO2 is:
[0025] ΔrSO2 = (rSO2 initial value - rSO2 final value) × 100%;
[0026] S2=0,ΔrSO2≤2;
[0027] S2=1,2<ΔrSO2≤4;
[0028] S2=2,ΔrSO2>4;
[0029] Collect eye movement data, and evaluate the degree of brain fatigue of trainees by calculating the percentage of time that pupils are covered for more than 80% per unit time (P80 index), and give a fatigue score S3; the judgment formula of fatigue score S3 is:
[0030] S3=0,P80≤0.075;
[0031] S3=1,0.075<P80≤0.15;
[0032] S3=2,P80>0.15;
[0033] Collect the time tags of the audio playback moment and the time tags of the keyboard key presses (play short audio randomly multiple times, press any key on the keyboard as quickly as possible when the audio is heard, record the time tags of the audio playback moment and the time tags of the trainer pressing the keyboard key), calculate the time difference reaction time T (ms) of the two tags, evaluate the brain fatigue degree of the trainer according to the reaction time empirical distribution curve, and give the fatigue score S4; the discrimination formula of the fatigue score S4 is:
[0034] S4=0,T≤475;
[0035] S4=1,475<T≤997;
[0036] S4=2,T>997;
[0037] According to the scores S1, S2, S3 and S4, the comprehensive fatigue F score is calculated, and the calculation formula is: F = (S1 + S2 + S3 + S4) / 4; the comprehensive fatigue F rating is given, and the calculation formula is:
[0038] Level I, F≤0.5;
[0039] Level II, 0.5<F≤1;
[0040] Grade III, 1<F≤1.5;
[0041] Grade IV, 1.5<F≤2;
[0042] The degree of mental fatigue was measured according to the comprehensive fatigue F rating.
[0043] Compared with the prior art, this application has the following advantages:
[0044] (1) This application uses EEG spectrum feature decoding technology and combines it with near-infrared analysis technology, eye movement analysis technology and behavioral analysis technology for staff mental fatigue detection. It is a combination of behavioral, biomedical and artificial intelligence technologies, combined with a multi-modal comprehensive fatigue assessment method, which avoids misjudgment and missed judgment caused by using a single modality for fatigue assessment, and further improves the accuracy of fatigue judgment.
[0045] (2) The EEG signal monitoring and processing interface adopted in this application combines EEG analysis, spectrum analysis and mental fatigue estimation. It has a user-friendly interface, flexible operation and humanized design, which is conducive to the further promotion of EEG technology in the field of engineering applications.
[0046] (3) The eye movement signal monitoring and processing interface used in the present application displays the actual position of the viewpoint on the screen and gives a viewpoint coordinate waveform, which can intuitively analyze the eye dynamics of the trainee.
[0047] (4) The near-infrared signal monitoring and processing interface used in this application uses the brain blood oxygen distribution topography Figure 3 It can display the blood oxygen status and distribution of local brain tissue, which is convenient for analyzing the relationship between brain fatigue and brain blood oxygen, and is conducive to the further promotion of near-infrared technology in the field of engineering applications.
[0048] (5) The key signal monitoring and processing interface adopted in the present application directly represents the key pressing time point in the graph of the reaction time experience distribution curve, which is convenient for analyzing the individual reaction ability of the trainees and dividing the fatigue degree. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.
[0050] Figure 1 It is a structural block diagram of the multi-modal mental fatigue detection system of the present invention;
[0051] Figure 2 It is a schematic diagram of the overall system flow of the multi-modal mental fatigue detection system of the present invention;
[0052] Figure 3 It is a flowchart of the use of the multi-modal mental fatigue detection system of the present invention;
[0053] Figure 4 This is the interface diagram of the EEG decoding unit;
[0054] Figure 5 This is the interface diagram of the near infrared analysis unit;
[0055] Figure 6 This is the interface diagram of the eye movement data analysis unit;
[0056] Figure 7 This is the interface diagram of the key response analysis unit;
[0057] Figure 8 This is the interface diagram of the logging unit.
[0058] Description of Figure Numbers:
[0059] 1. Display; 2. EEG signal acquisition cap; 3. Eye tracker; 4. EEG signal amplifier; 5. Near-infrared brain function imager; 6. Host; 7. Keyboard. DETAILED DESCRIPTION
[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0061] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.
[0062] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "several" or "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0063] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0064] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.
[0065] The present invention proposes a multimodal mental fatigue detection system and method, aiming to design a multimodal mental fatigue detection method that combines EEG spectrum analysis, near-infrared cerebral blood oxygen parameter change analysis, eye movement parameter analysis, and behavioral analysis of auditory key press reaction time.
[0066] The specific structure of the multi-modal mental fatigue detection system proposed by the present invention will be described below in a specific embodiment:
[0067] Example 1
[0068] A multimodal mental fatigue detection system, such as Figure 1 As shown, including:
[0069] Display 1, used for displaying a gaze information interface;
[0070] An EEG signal collection cap 2, used for collecting EEG data;
[0071] Eye tracker 3, used to collect eye movement data;
[0072] An EEG signal amplifier 4, the EEG signal amplifier 4 is electrically connected to the EEG signal collection cap 2;
[0073] A near-infrared brain function imager 5, wherein the near-infrared brain function imager 5 is electrically connected to the EEG signal acquisition cap 2;
[0074] The host 6 is electrically connected to the EEG signal amplifier 4 , the near-infrared brain function imager 5 and the eye tracker 3 .
[0075] Understandably, if Figure 2 , Figure 3 As shown, the EEG signal acquisition cap 2 is connected to the input end of the EEG amplifier and the input end of the near-infrared brain function imager 5; the output end of the EEG amplifier, the output end of the near-infrared brain function imager 5 and the output end of the eye tracker 3 are connected to the host computer of the host 6; the host 6 includes a display 1, a keyboard 7, an EEG spectrum analysis unit, a near-infrared data analysis unit, an eye movement data analysis unit and a reaction time analysis unit. The display 1 displays the physiological data system interface of the personnel in real time. The personnel wears the signal acquisition cap and looks at the information interface through the display 1. After hearing the prompt tone, they immediately press any key on the keyboard; the eye tracker 3 is fixed horizontally in front of the screen of the display 1 to collect the user's eye movement data in real time; the system calculates the user's mental fatigue level as an evaluation index.
[0076] Furthermore, the host 6 includes an EEG decoding unit (including an EEG UI interface), a near-infrared analysis unit (including a near-infrared UI interface), an eye movement data analysis unit (including an eye movement UI interface), an auditory key evaluation unit, and a log recording unit.
[0077] It can be understood that the interface diagram of the log recording unit is as follows Figure 8 shown.
[0078] Furthermore, if Figure 4 As shown, the EEG decoding unit is used to analyze the EEG data, including waveform display, data recording and numerical calculation, real-time display of the corresponding EEG waveform record, and calculation of the power ratio R of the relevant frequency band in the time period to give a fatigue score S1.
[0079] Furthermore, if Figure 5 As shown, the near-infrared analysis unit is used to analyze brain blood oxygen parameters in real time, including brain blood oxygen distribution topography and numerical calculation. The blood oxygen content distribution of each near-infrared light channel is represented by a 3D brain topography map, and the fatigue score S2 is given by calculating the change in rSO2 during the time period.
[0080] Furthermore, if Figure 6As shown, the eye movement data analysis unit is used to analyze the eye movement data in real time, including the real-time position and numerical calculation of the viewpoint, and simultaneously perform pupil diameter statistics and calculate the PERCLOS value to provide a fatigue score S3 within the time period.
[0081] Furthermore, if Figure 7 As shown, the auditory key 7 evaluation unit is used to analyze the key 7 reaction time information in real time, including reaction time curve display and numerical calculation, judge the fatigue degree, and give a fatigue score S4 within the time period.
[0082] Furthermore, the host 6 is used to combine the score S1, the score S2, the score S3 and the score S4, perform an average calculation, and obtain a score of a comprehensive fatigue degree F, and divide the fatigue degree into 4 levels according to the range of the F value.
[0083] Working principle of a multimodal mental fatigue detection system:
[0084] The subject gazes at the display interface of the display 1, and the EEG electrodes on the EEG signal acquisition cap 2 collect the EEG signals of the trainee, which are amplified by the EEG signal amplifier 4 and transmitted to the EEG decoding unit in the host 6 for decoding. The decoding result is used to calculate the degree of mental fatigue of the person; at the same time, the EEG decoding unit performs spectrum analysis on the EEG and calculates the (α+β) / θ ratio R, and then gives a fatigue score S1; at the same time, the near-infrared transmitter on the EEG signal acquisition cap 2 emits near-infrared light, which enters the brain and then exits. The near-infrared detector transmits the received signal to the near-infrared analysis unit in the host 6, and evaluates brain fatigue by calculating rSO2 degree, and then give a fatigue score S2; at the same time, the eye tracker 3 collects pupil diameter data and transmits it to the eye movement data analysis unit, calculates the percentage of the time when the pupil is covered for more than 80% of the unit time, and then gives a fatigue score S3; during the training process, the host 6 randomly plays short audio multiple times, and the subject immediately presses any key 7 on the keyboard after hearing the audio. The host 6 calculates the reaction time T, and then gives a fatigue score S4; the system combines the scores S1, S2, S3 and S4 to calculate a comprehensive fatigue F score, and gives a comprehensive fatigue F rating to measure brain fatigue, and then remind the person of the current mental load level. This application provides a system for real-time detection of mental fatigue for people who need to engage in high-intensity mental work with high safety requirements.
[0085] Example 2
[0086] A multimodal mental fatigue detection method comprises the following steps:
[0087] The EEG signal data is collected, amplified by an EEG signal amplifier, and spectral analyzed by a decoding unit. The power of each band is obtained by fast Fourier transform. The (α+β) / θ ratio R is calculated based on the power of α, β and θ waves to evaluate the degree of brain fatigue and give a fatigue score S1. The discrimination formula of fatigue score S1 is:
[0088] S1=0,R<1.15;
[0089] S1=1,1.15<R<1.35;
[0090] S1=2,R≥1.35;
[0091] It can be understood that the subject wears an EEG signal collection cap and turns on the system's display. The subject looks at the display interface of the monitor, and the motor on the EEG signal collection cap collects the person's EEG signal data. The EEG signal data is amplified by an EEG signal amplifier and spectrally analyzed by a decoding unit. The power of each band is calculated through fast Fourier transform, and then the fatigue score S1 is calculated.
[0092] The changes in the light intensity of the near-infrared detector are collected and converted into digital signals. The degree of mental fatigue of the trainees is evaluated by calculating the local brain oxygen saturation and a fatigue score S2 is given. The discrimination formula of the fatigue score S2 is:
[0093] rSO2 = HbO2 concentration / (HbO2 concentration + Hb concentration);
[0094] The formula for calculating the change in rSO2 is:
[0095] ΔrSO2 = (rSO2 initial value - rSO2 final value) × 100%;
[0096] S2=0,ΔrSO2≤2;
[0097] S2=1,2<ΔrSO2≤4;
[0098] S2=2,ΔrSO2>4;
[0099] It can be understood that the infrared detector on the signal acquisition cap emits near-infrared light. Since HbO2 and Hb in brain tissue have different absorption spectra for near-infrared light, the near-infrared light enters the brain, is absorbed and attenuated by HbO2 and Hb in the brain tissue, and then is emitted. The near-infrared detector converts the change in the received light intensity into a digital signal and transmits it to the near-infrared analysis unit in the host computer. By calculating rSO2, the brain fatigue level of the trainees is preliminarily evaluated as an indicator for measuring the comprehensive fatigue index S2.
[0100] Collect eye movement data, and evaluate the degree of brain fatigue of trainees by calculating the percentage of time that pupils are covered for more than 80% per unit time (P80 index), and give a fatigue score S3; the judgment formula of fatigue score S3 is:
[0101] S3=0,P80≤0.075;
[0102] S3=1,0.075<P80≤0.15;
[0103] S3=2,P80>0.15;
[0104] It can be understood that the eye tracker collects the pupil diameter data of the subject and transmits it to the eye movement data analysis unit in the host computer. According to the P80 standard in the PERCLOS algorithm, that is, by calculating the percentage of the time when the pupil is covered for more than 80% per unit time, the brain fatigue level of the trainee is preliminarily evaluated as an indicator S3 for measuring the comprehensive fatigue index.
[0105] Collect the time tags of the audio playback moment and the time tags of the keyboard key presses (play short audio randomly multiple times, press any key on the keyboard as quickly as possible when the audio is heard, record the time tags of the audio playback moment and the time tags of the trainer pressing the keyboard key), calculate the time difference reaction time T (ms) of the two tags, evaluate the brain fatigue degree of the trainer according to the reaction time empirical distribution curve, and give the fatigue score S4; the discrimination formula of the fatigue score S4 is:
[0106] S4=0,T≤475;
[0107] S4=1,475<T≤997;
[0108] S4=2,T>997;
[0109] It can be understood that the host randomly plays short audio multiple times, and the subject needs to press any key on the keyboard as quickly as possible at the moment of hearing the audio. The auditory key evaluation unit in the host will record the time tag of the audio playback moment and the time tag of the trainee pressing the keyboard key, and calculate the time difference between the two tags to get the reaction time T ( / ms). According to the reaction time curve, the brain fatigue degree of the trainee is preliminarily evaluated as an indicator S4 for measuring the comprehensive fatigue index.
[0110] According to the scores S1, S2, S3 and S4, the comprehensive fatigue F score is calculated, and the calculation formula is: F = (S1 + S2 + S3 + S4) / 4; the comprehensive fatigue F rating is given, and the calculation formula is:
[0111] Level I, F≤0.5;
[0112] Level II, 0.5<F≤1;
[0113] Grade III, 1<F≤1.5;
[0114] Grade IV, 1.5<F≤2;
[0115] The degree of mental fatigue was measured according to the comprehensive fatigue F rating.
[0116] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. A multimodal mental fatigue detection system, characterized in that: include: A display, used for displaying a gaze information interface; EEG signal collection cap, used to collect EEG data; Eye tracker, used to collect eye movement data; An EEG signal amplifier, the EEG signal amplifier is electrically connected to the EEG signal collection cap; A near-infrared brain function imager, the near-infrared brain function imager is electrically connected to the EEG signal acquisition cap; A host computer is electrically connected to the electroencephalogram signal amplifier, the near-infrared brain function imager and the eye tracker.
2. The multimodal mental fatigue detection system according to claim 1, characterized in that: The host comprises an electroencephalogram decoding unit, a near infrared analysis unit, an eye movement data analysis unit, an auditory keystroke evaluation unit, and a log recording unit.
3. The multimodal mental fatigue detection system according to claim 2, characterized in that: The EEG decoding unit is used to analyze EEG data, including waveform display, data recording and numerical calculation, to display the corresponding EEG waveform record in real time, and to calculate the power ratio R of the relevant frequency band in the time period, and to give a fatigue score S1.
4. The multimodal mental fatigue detection system according to claim 3 is characterized in that: The near-infrared analysis unit is used to analyze brain blood oxygen parameters in real time, including brain blood oxygen distribution topography and numerical calculations. The blood oxygen content distribution of each near-infrared light channel is represented by a 3D brain topography map, and the fatigue score S2 is given by calculating the change in rSO2 during the time period.
5. The multimodal mental fatigue detection system according to claim 4, characterized in that: The eye movement data analysis unit is used to analyze the eye movement data in real time, including the real-time position and numerical calculation of the viewpoint, and simultaneously perform pupil diameter statistics and calculate the PERCLOS value to give a fatigue score S3 within the time period.
6. The multimodal mental fatigue detection system according to claim 5, characterized in that: The auditory keystroke evaluation unit is used to analyze keystroke reaction time information in real time, including reaction time curve display and numerical calculation, judge the fatigue degree, and give a fatigue degree score S4 within the time period.
7. The multimodal mental fatigue detection system according to claim 6, characterized in that: The host is used to combine the score S1, the score S2, the score S3 and the score S4, perform an average calculation, and obtain a score of a comprehensive fatigue degree F. According to the range of the F value, the fatigue degree is divided into four levels.
8. A multimodal mental fatigue detection method, characterized in that: The following steps are involved: The EEG signal data is collected, amplified by an EEG signal amplifier, and spectral analyzed by a decoding unit. The power of each band is obtained by fast Fourier transform. The (α+β) / θ ratio R is calculated based on the power of α, β and θ waves to evaluate the degree of brain fatigue and give a fatigue score S1. The discrimination formula of fatigue score S1 is: S1=0,R<1.15; S1=1,1.15<R<1.35; S1=2,R≥1.35; The changes in the light intensity of the near-infrared detector are collected and converted into digital signals. The degree of mental fatigue of the trainees is evaluated by calculating the local brain oxygen saturation and a fatigue score S2 is given. The discrimination formula of the fatigue score S2 is: rSO2 = HbO2 concentration / (HbO2 concentration + Hb concentration); The formula for calculating the change in rSO2 is: ΔrSO2 = (rSO2 initial value - rSO2 final value) × 100%; S2=0,ΔrSO2≤2; S2=1,2<ΔrSO2≤4; S2=2,ΔrSO2>4; Collect eye movement data, calculate the percentage of time that pupils are covered for more than 80% per unit time, evaluate the degree of brain fatigue of trainees, and give fatigue score S3; the judgment formula of fatigue score S3 is: S3=0,P80≤0.075; S3=1,0.075<P80≤0.15; S3=2,P80>0.15; Collect the time tags of the audio playback moment and the time tags of the keyboard key presses, calculate the time difference reaction time T (ms) of the two tags, evaluate the brain fatigue degree of the trainees according to the empirical distribution curve of the reaction time, and give the fatigue score S4; the judgment formula of the fatigue score S4 is: S4=0,T≤475; S4=1,475<T≤997; S4=2,T>997; According to the scores S1, S2, S3 and S4, the comprehensive fatigue F score is calculated, and the calculation formula is: F = (S1 + S2 + S3 + S4) / 4; the comprehensive fatigue F rating is given, and the calculation formula is: Level I, F≤0.5; Level II, 0.5<F≤1; Grade III, 1<F≤1.5; Grade IV, 1.5<F≤2; The degree of mental fatigue was measured according to the comprehensive fatigue F rating.
Citation Information
Patent Citations
Feedback type fatigue detecting system
CN101968918A
A Brain-Computer Adaptive System for Brain-Computer Interface System
CN109471528A
Target recognition training system and method based on EEG-NIRS
CN112130663A
RSVP target identification system fusing multi-modal fatigue monitoring and regulation and method thereof
CN114041793A
Apparatus for measuring 3D display-induced visual discomfort, apparatus for extracting 3D visual discomfort-inducing components automatically, and method thereof
KR1020120109160A
Cited By
Method for predicting and judging psychological fatigue of dispatcher based on physiology and response time indexes
CN120304830A
