Wearable brain fatigue analysis equipment based on BCG signal and brain fatigue monitoring method

Through the HRV parameters based on the heart impact signal, a brain fatigue model is established and real-time reminder function is provided, which solves the problems of complexity and electromagnetic interference of traditional electrical signal monitoring equipment, and realizes simple and accurate fatigue monitoring and reduces safety accidents.

CN119055241AInactive Publication Date: 2024-12-03NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411307821.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional fatigue monitoring methods are measured by electrical signals, the equipment is complex and has adverse effects on the operation of the operator, and it is difficult to collect signals in an electromagnetic interference environment.

Method used

Using heart rate variability (HRV) parameters based on cardiac impact signal (BCG), weak vibration signals are collected through wearable devices to establish association with brain fatigue states, and machine learning is used to establish fatigue models to provide real-time reminder functions.

Benefits of technology

It realizes simple and accurate fatigue monitoring without interfering with operation and reduces safety accidents caused by fatigue.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119055241A_ABST
    Figure CN119055241A_ABST
Patent Text Reader

Abstract

The invention provides wearable brain fatigue analysis equipment based on a BCG signal and a brain fatigue monitoring method. The wearable brain fatigue analysis equipment comprises a BCG signal acquisition module, a parameter extraction module, a fatigue analysis module and a display reminding module, wherein the BCG signal acquisition module is used for acquiring a BCG signal through a sensor; the parameter extraction module is used for calculating an HRV parameter of the BCG signal; the fatigue analysis module is used for generating a fatigue state index Ifeature of the user by utilizing a fatigue state model according to the HRV parameters; and the display reminding module is used for sending an alarm signal to a user according to the fatigue state index. The BCG signal measurement is accurate, the fatigue prediction effect is good, and the operation risk of an operator in a fatigue state is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of fatigue monitoring. Specifically, the present invention relates to a device and method for analyzing mental fatigue based on BCG signals. Background Art

[0002] Fatigue is an important factor leading to safety accidents. Fatigue monitoring of operators is helpful to reduce the occurrence of accidents. Traditional fatigue monitoring is mostly done through contact measurement of electroencephalogram (EEG), electrocardiogram (ECG), electrooculogram, electromyogram, etc. These methods are accurate and effective, but most of the measurements are electrical signals. The measuring equipment usually has multiple electrode patches and wires, and the measurement process is cumbersome. Using the measuring equipment for real-time monitoring during vehicle driving, aircraft operation, etc. will have an adverse effect on the operation of personnel, and various electromagnetic signals in the cockpit and other environments will have an adverse effect on the collection of electrical signals. Summary of the invention

[0003] In order to solve these problems in the prior art, the present invention provides a device and method for analyzing mental fatigue based on ballistic cardiomyopathy (BCG). The device for analyzing mental fatigue has simple detection and operation, can capture the weak vibration signal generated when the heart beats, calculate the heart rate variability (HRV) parameters through the BCG signal, and establish the association between the relevant parameters and the mental fatigue state, i.e., the fatigue model. On this basis, the fatigue state of a person is judged by the fatigue model, and the person can be reminded to rest in time, thereby avoiding accidents caused by fatigue, and the monitoring is accurate without hindering the person's operation.

[0004] The present invention provides a technical solution, including: a wearable mental fatigue analysis device based on BCG signals, including: a BCG signal acquisition module, a parameter extraction module, a fatigue analysis module, and a display reminder module; wherein the BCG signal acquisition module is used to collect BCG signals through a sensor;

[0005] Parameter extraction module, used to calculate HRV parameters of BCG signals;

[0006] The fatigue analysis module is used to generate the user's fatigue state index I based on the HRV parameters using the fatigue state model fatigue ;

[0007] The display reminder module is used to send an alarm signal to the user according to the fatigue status index.

[0008] Furthermore, the fatigue model module includes a fatigue state establishment method, in which the user collects BCG signals and mental fatigue parameters through fatigue-induced simulated driving experiments, and establishes a fatigue state model through machine learning with BCG signals as an input set and mental fatigue parameters as an output set.

[0009] Furthermore, the sensor is one of a piezoelectric film sensor, an optical fiber sensor, and a pressure sensor. The sensor can be placed on the headrest, on the chest, or above the radial artery of the arm. Depending on the different positions of the sensor, the analysis device can be designed as a helmet type, a vest type, or a wristband type.

[0010] Further, when the fatigue state index I fatigue ≤S1, the user is judged to be in a low fatigue state;

[0011] When S1 fatigue ≤S2, the user is judged to be in a medium fatigue state;

[0012] When I fatigue >S3, the user is judged to be in a high fatigue state;

[0013] Wherein S1 is the first threshold, S2 is the second threshold, and S3 is the third threshold.

[0014] A method for monitoring mental fatigue based on BCG signals, the method comprising the following steps:

[0015] Establish a fatigue status model based on BCG signals;

[0016] Collect users' BCG signals;

[0017] Calculate HRV parameters based on BCG signals;

[0018] According to HRV parameters, the fatigue state index I is calculated using the fatigue state model. fatigue ;

[0019] When the fatigue state index I fatigue ≤S1, the user is judged to be in a low fatigue state;

[0020] When S1 fatigue ≤S2, the user is judged to be in a medium fatigue state;

[0021] When I fatigue >S3, the user is judged to be in a high fatigue state;

[0022] Wherein S1 is the first threshold, S2 is the second threshold, S3 is the third threshold, and S1, S2, and S3 are fatigue state model parameters.

[0023] Furthermore, it also includes establishing a fatigue model. The user collects BCG signals and mental fatigue parameters through fatigue-induced simulated driving experiments, and uses the BCG signals as the input set and the mental fatigue parameters as the output set to train and establish a fatigue state model.

[0024] Furthermore, I fatigue ​​=f(VAI, VLI, MeanRR, HF, LF, …), where VAI represents the vector angle index calculated according to the Poincare diagram of the BCG signal, VLI represents the vector length index calculated according to the Poincare diagram of the BCG signal, HF represents the frequency parameter in the range of 0.15 Hz to 0.4 Hz, LF represents the frequency parameter in the range of 0.04 Hz to 0.15 Hz, and MeanRR represents the average value during the RR period.

[0025] Further,

[0026] In the formula, θ i is the angle between the horizontal coordinate and the line connecting the point and the coordinate origin.

[0027] Further,

[0028] In the formula, l i is the length of the line between the point in the scatter plot and the origin of the coordinate system, and L is the average length of all the lines.

[0029] BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the monitoring method flow of the present invention. DETAILED DESCRIPTION

[0031] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments.

[0032] To make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention.

[0033] The present invention provides a method for monitoring mental fatigue based on BCG signals. The method calculates heart rate variability (HRV) related parameters in real time based on BCG signals, including time domain, frequency domain and nonlinear domain parameters. When the related parameters meet certain conditions, a prompt is output to remind the operator that the operator has reached a fatigue state and recommends rest. This reduces user fatigue, prevents the operator from operating in a fatigued state, and reduces operational risks.

[0034] A wearable mental fatigue analysis device based on BCG signals, comprising: a BCG signal acquisition module, a parameter extraction module, a fatigue analysis module, and a display reminder module; wherein the BCG signal acquisition module is used to collect BCG signals through a sensor;

[0035] Parameter extraction module, used to calculate HRV parameters of BCG signals;

[0036] The fatigue analysis module is used to generate the user's fatigue state index I based on the HRV parameters using the fatigue state model fatigue ;

[0037] The display reminder module is used to send an alarm signal to the user according to the fatigue status index.

[0038] The BCG signal acquisition module is used to collect BCG signals through sensors. Ballistocardiogram (BCG) is a slight change in the external pressure on the human body surface caused by heart beats and blood circulation in the large arteries, and can be used for contactless heart activity detection. BCG signals can be used in heart rate detection, heart rate variability monitoring, heart contractility detection, and cardiac output change monitoring. The BCG signal is very weak. The sensor is placed on the body surface where the blood vessels can be touched, and the pressure signal is converted into a charge signal by the sensor. The sensor is connected to the amplifier and bandpass filter circuit, which is beneficial to improve the accuracy of BCG signal acquisition. For example: the sensor can be placed on the headrest, chest, or above the radial artery in the arm. Depending on the different positions of the sensor, the analysis equipment can be designed as a helmet, vest, or wristband.

[0039] In order to accurately describe the fatigue state, a fatigue model was established by setting up a fatigue induction experiment. In the experiment, BCG signals were collected, HRV-related parameters were obtained, and the mental fatigue state of the subjects was identified. Then, through machine learning and other methods, the corresponding relationship between BCG signal-related parameters and mental fatigue state was established as a criterion for mental fatigue state, namely, fatigue model.

[0040] The fatigue model module includes a fatigue state establishment method, in which the user collects BCG signals and mental fatigue parameters through fatigue-induced simulated driving experiments, and establishes a fatigue state model with BCG signals as input sets and mental fatigue parameters as output sets. In this method, fatigue-induced experiments include long-term simulated driving experiments, N-back experiments, task performance experiments, etc. HRV parameters calculated based on BCG include time domain, frequency domain, and nonlinear domain. The collection of operator mental fatigue parameters can be through but not limited to EEG analysis, subjective mental workload test scale (NASA-TLX), etc. The establishment of fatigue models can be through but not limited to machine learning and other methods. For example, through a simulated driving experiment of a long-term driving task, BCG signals and subjective fatigue test scale (NASA-TLX) parameters are collected in the experiment, and BCG signal-related parameters are used as input sets, and NASA-TLX scores are used as output sets to establish a fatigue mental fatigue model.

[0041] In order to further improve the accuracy of fatigue signal acquisition, BCG signal acquisition includes but is not limited to piezoelectric film sensors, optical fiber sensors, pressure sensors and other mechanical sensors. During driving, leg activities, vehicle vibrations, etc. will cause great interference to the acquisition. In order to reduce the interference of vibration on the driver's signal acquisition, the mechanical sensor uses a wristband device and is placed above the radial artery on the radial side of the user's arm. The pressure signal is converted into a charge signal by a mechanical sensor, connected to an amplifier and a bandpass filter circuit, and the BCG signal is acquired.

[0042] The parameter extraction module is used to calculate the HRV parameters of the BCG signal; by collecting the BCG signal of the user, the heart rate variability (HRV) parameters are calculated based on the collected BCG signal.

[0043] The time domain waveform of the BCG signal includes different peaks, and the amplitude of the waveform can indicate information such as the user's heart pumping intensity and blood flow acceleration, and the width of the waveform can indicate the duration of the user's heart diastole and systole. The BCG signal may include peaks such as H, I, J, K, L, M, and N, wherein the I, J, and K peaks may be generated during the heart systole, the L, M, and N peaks may be generated during the heart diastole, the J peak may be the largest amplitude point in each cycle of the BCG signal, a maximum value point adjacent to the J peak may be the H peak, and the two minimum value points adjacent to the J peak may be the I peak and the K peak, respectively. Therefore, when analyzing the morphology of the BCG signal, the H, I, J, K, L, M, and N peaks of the BCG signal may be detected. In this embodiment, after calculating the JJ interval by the time domain peak finding algorithm, the HRV parameters of the BCG signal are calculated, wherein the HRV parameters include time domain, frequency domain, and nonlinear domain parameters.

[0044] The fatigue analysis module is used to generate the user's fatigue state index I based on the HRV parameters using the fatigue state model fatigue ; When fatigue state index I fatigue ≤S1, the user is judged to be in a low fatigue state; when S1 fatigue ≤S2, the user is judged to be in a medium fatigue state; when I fatigue >S3, the user is judged to be in a high fatigue state; wherein S1 is the first threshold, S2 is the second threshold, and S3 is the third threshold.

[0045] The display reminder module is used to send an alarm signal to the user according to the fatigue state index. If the user is judged to be in a fatigue state, a reminder such as sound, vibration, or text is issued to remind the driver to take a rest and avoid fatigue driving.

[0046] like Figure 1 As shown, a method for monitoring mental fatigue based on BCG signals comprises the following steps:

[0047] Establish a fatigue status model based on BCG signals;

[0048] Collect users' BCG signals;

[0049] Calculate HRV parameters based on BCG signals;

[0050] According to HRV parameters, the fatigue state index I is calculated using the fatigue state model. fatigue ;

[0051] When the fatigue state index I fatigue ≤S1, the user is judged to be in a low fatigue state;

[0052] When S1 fatigue ≤S2, the user is judged to be in a medium fatigue state;

[0053] When I fatigue >S3, the user is judged to be in a high fatigue state;

[0054] Wherein S1 is the first threshold, S2 is the second threshold, S3 is the third threshold, and S1, S2, and S3 are fatigue state model parameters.

[0055] Furthermore, it also includes establishing a fatigue model. The user collects BCG signals and subjective fatigue test scale parameters through simulated driving experiments of long-term driving tasks, and uses the BCG signals as the input set and the subjective fatigue test scale scores as the output set to train and establish a fatigue state model.

[0056] Furthermore, I fatigue ​​=f(VAI, VLI, MeanRR, HF, LF, …), where VAI represents the vector angle index calculated according to the Poincare diagram of the BCG signal, VLI represents the vector length index calculated according to the Poincare diagram of the BCG signal, HF represents the frequency parameter in the range of 0.15 Hz to 0.4 Hz, LF represents the frequency parameter in the range of 0.04 Hz to 0.15 Hz, and MeanRR represents the average value during the RR period.

[0057] Further,

[0058] In the formula, θ i is the angle between the horizontal coordinate and the line connecting the point and the coordinate origin.

[0059] Further,

[0060] In the formula, l i is the length of the line between the point in the scatter plot and the origin of the coordinate system, and L is the average length of all the lines.

[0061] Further,

[0062] The above examples are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent changes or modifications made according to the spirit of the present invention should be included in the protection scope of the present invention.

Claims

1. A wearable mental fatigue analysis device based on BCG signals, Features: include: BCG signal acquisition module, parameter extraction module, fatigue analysis module, display reminder module; The BCG signal acquisition module is used to collect BCG signals through sensors; Parameter extraction module, used to calculate HRV parameters of BCG signals; The fatigue analysis module is used to generate the user's fatigue state index I based on the HRV parameters using the fatigue state model fatigue ; The display reminder module is used to send an alarm signal to the user according to the fatigue status index.

2. The wearable mental fatigue analysis device according to claim 1, Features: The fatigue analysis module includes a fatigue state establishment method, in which the user collects BCG signals and mental fatigue parameters through fatigue-induced simulated driving experiments, takes BCG signals as the input set and mental fatigue parameters as the output set, and establishes a fatigue state model through machine learning methods.

3. The wearable mental fatigue analysis device according to claim 2, Features: The sensor is a mechanical sensor, which is placed on the body surface where the blood vessel pulsation can be touched. Depending on the different locations where the sensor is placed, the sensor can be designed as a helmet type, a wristband type, or a vest type.

4. The wearable mental fatigue analysis device according to claim 3, Features: When the fatigue state index I fatigue ≤S1, the user is judged to be in a low fatigue state; When S1 fatigue ≤S2, the user is judged to be in a medium fatigue state;​ When I fatigue >S3, the user is judged to be in a high fatigue state; Wherein S1 is the first threshold, S2 is the second threshold, and S3 is the third threshold.

5. A method for monitoring mental fatigue based on BCG signals, Features: The method comprises the following steps: Establish a fatigue status model based on BCG signals; Collect users' BCG signals; Calculate HRV parameters based on BCG signals; According to HRV parameters, the fatigue state index I is calculated using the fatigue state model. fatigue ; When the fatigue state index I fatigue ≤S1, the user is judged to be in a low fatigue state; When S1 fatigue ≤S2, the user is judged to be in a medium fatigue state;​ When I fatigue >S3, the user is judged to be in a high fatigue state; Wherein S1 is the first threshold, S2 is the second threshold, S3 is the third threshold, and S1, S2, and S3 are fatigue state model parameters.

6. The method for monitoring mental fatigue according to claim 5, Features: It also includes establishing a fatigue model. Users collect BCG signals and mental fatigue parameters through fatigue-induced simulated driving experiments. The BCG signal is used as the input set and the mental fatigue parameters are used as the output set. The fatigue status model is established through training using machine learning methods.

7. The method for monitoring mental fatigue according to claim 5, Features: I fatigue =f(VAI, VLI, MeanRR, HF, LF, …), where VAI represents the vector angle index calculated according to the Poincare diagram of the BCG signal, VLI represents the vector length index calculated according to the Poincare diagram of the BCG signal, HF represents the frequency parameter in the range of 0.15 Hz to 0.4 Hz, LF represents the frequency parameter in the range of 0.04 Hz to 0.15 Hz, and MeanRR represents the average value during the RR period.

8. The method for monitoring mental fatigue according to claim 7, Features: In the formula, θ i is the angle between the horizontal coordinate and the line connecting the point and the coordinate origin.

9. The method for monitoring mental fatigue according to claim 8, Features: In the formula, l i is the length of the line between the point in the scatter plot and the origin of the coordinate system, and L is the average length of all the lines.

10. The method for monitoring mental fatigue according to claim 9, Features:

Citation Information

Patent Citations

  • Method and application for acquiring HRV based on piezoelectric sensor

    CN107569226A

  • Back cushion for detecting emotional stress in non-contact mode based on heart rate variability

    CN107595274A

  • Fatigue driving detection method and detection equipment

    CN107693031A

  • Intelligent health monitoring and improvement system for automobile driver

    CN111493897A

  • Fatigue state determination method and device, intelligent mattress and medium

    CN116784852A