Wearable physiological monitoring system and anti-fatigue data analysis method thereof

Abstract

The invention discloses a wearable physiological monitoring system and an anti-fatigue data analysis method thereof, and relates to the technical field of data analysis, a physiological data acquisition system is arranged in a wearable device of a user, an ECG signal of the user is acquired as a first ECG signal, and the motion state of the user is judged; setting different sampling modes and motion artifact removal modes for the ECG signal of the user according to the motion state of the user to obtain a second ECG signal of the user; determining whether artifacts of the ECG signal of the user are removed and qualified or not, and if yes, performing anti-fatigue data analysis; and if the second ECG signal is not qualified, motion artifact removal of the first ECG signal is carried out on the second ECG signal again until the second ECG signal is qualified. In this way, motion artifact removal can be carried out on the collected physiological data of the user, and adverse effects generated in the anti-fatigue data analysis process of the user are reduced; it is ensured that the electrocardiogram signal of the user is not distorted, the fatigue state evaluation is accurate, and wrong health early warning cannot be caused.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and particularly to a wearable physiological monitoring system and an anti-fatigue data analysis method thereof. Background Art

[0002] With the continuous growth of the demand for health management, wearable physiological monitoring systems (such as smart watches, health bracelets, etc.) have become important health monitoring tools in people's daily lives. These devices can collect users' physiological data and motion states in real time by integrating multiple sensors, such as electrocardiogram (ECG), heart rate monitoring, accelerometers, gyroscopes, etc. In particular, electrocardiogram (ECG) and heart rate monitoring can provide key data on users' heart health and fatigue status. In addition, wearing devices can also monitor information such as users' exercise intensity, activity patterns, and sleep quality, providing comprehensive data support for health management.

[0003] Currently, anti-fatigue data analysis methods based on wearable devices are gradually attracting the attention of researchers and developers; using physiological data collected from wearable devices, such as heart rate variability (HRV), electrocardiogram signals, etc., combined with users' motion states and environmental conditions, researchers have proposed some anti-fatigue analysis models. These models can judge users' fatigue levels by analyzing indicators such as heart rate changes, exercise intensity, and recovery status, and then provide personalized health advice. Many smart devices can now adjust monitoring strategies in real time based on this data and provide warnings according to users' fatigue conditions.

[0004] Although existing anti-fatigue data analysis methods based on wearable physiological monitoring systems have achieved certain success to some extent, there are still some significant challenges in practical applications, especially in eliminating motion artifacts and ensuring signal accuracy. Signal interference (such as ECG baseline drift, electromyogram (EMG) artifacts) caused by motion (such as running, jumping, etc.) will have an adverse impact on the data collection and analysis process; these motion artifacts will cause distortion of electrocardiogram signals, making the assessment of fatigue status inaccurate and even possibly leading to incorrect health warnings. Summary of the Invention

[0005] The object of the present invention is to solve the above-mentioned problems, and provide a wearable physiological monitoring system and an anti-fatigue data analysis method thereof.

[0006] In the first aspect of the implementation of the present invention, a wearable physiological monitoring system is first proposed, and the system includes:

[0007] A data acquisition module: Set up a physiological data acquisition system on the user's wearable device, collect the user's ECG signal as the first ECG signal according to the physiological data acquisition system, and judge the user's motion state;

[0008] Artifact removal module: Set different sampling methods and motion artifact removal methods for the user's ECG signal according to the user's motion state, and obtain the user's second ECG signal;

[0009] First analysis module: Determine whether the artifacts in the user's ECG signal are removed qualified according to the first ECG signal and the second ECG signal. If qualified, use the second ECG signal as the user's final ECG signal for anti-fatigue data analysis;

[0010] Second analysis module: If not qualified, perform motion artifact removal of the first ECG signal on the second ECG signal again until the second ECG signal is qualified.

[0011] Optionally, the physiological data acquisition system in the user's wearable device includes:

[0012] The physiological data acquisition system is applied to the user's wearable device, and the physiological data acquisition system includes an accelerometer, an ECG sensor, and a PPG sensor;

[0013] The ECG sensor is used to collect the user's ECG signal; the accelerometer is used to determine the user's current motion state, and the motion state includes static, walking, and strenuous exercise; the PPG sensor is used to detect the user's blood oxygen saturation and heart rate, and perform anti-fatigue data analysis on the user in combination with the ECG signal.

[0014] Optionally, the accelerometer is used to determine the user's current motion state, including:

[0015] Collect the user's current acceleration amplitude and acceleration change frequency; if the acceleration amplitude is low and close to the gravitational acceleration value of 9.8m / s 2 , and there is no obvious change in the acceleration change frequency, then the user's current motion state is a static state;

[0016] If the acceleration amplitude has a certain change, but the change frequency is low and the periodicity is strong, then the user's current motion state is a walking state;

[0017] If the acceleration amplitude is large and the change frequency is also large, then the user's current motion state is a strenuous exercise state.

[0018] Optionally, setting different sampling methods and motion artifact removal methods for the user's ECG signal according to the user's motion state includes:

[0019] When the user's motion state is a static state, the sampling frequency of the ECG signal is set not to be greater than 250Hz, and the first ECG signal passes through a low-pass filter set to remove low-frequency noise at 0.5 - 1Hz to remove motion artifacts; obtain the user's second ECG signal;

[0020] When the user's motion state is the walking state, the sampling frequency of the ECG signal is set to 500 Hz, and the first ECG signal passes through a high-pass filter set to 1 - 2 Hz to remove low-frequency noise, and the low-frequency noise-removed signal is subjected to wavelet transform to remove high-frequency noise and motion artifacts; the second ECG signal of the user is obtained;

[0021] When the user's motion state is the strenuous exercise state, the sampling frequency of the ECG signal is set to 1000 Hz, and the first ECG signal uses the blind source separation technology to separate the mixed signal composed of motion artifacts and the ECG signal, extracts the ECG signal, and the extracted ECG signal is subjected to wavelet transform to remove high-frequency noise and motion artifacts; the second ECG signal of the user is obtained.

[0022] Optionally, the steps to determine whether the artifacts of the user's ECG signal are removed qualified according to the first ECG signal and the second ECG signal are:

[0023] Perform low-pass filtering on the second ECG signal to remove high-frequency components and retain low-frequency baseline information;

[0024] Use the least squares method to fit the baseline of the ECG signal to obtain the fitted baseline, and calculate the baseline drift coefficient according to the baseline of the ECG signal and the second ECG signal. The calculation formula is:

[0025]

[0026] In the formula, GH is the baseline drift coefficient, ECG(t) is the value of the second ECG signal at time point t, the fitted baseline(t) is at time point t of the fitted baseline, and T is the signal duration;

[0027] Calculate the artifact removal qualification coefficient according to the baseline drift coefficient and the waveform of the second ECG signal, and judge whether the artifacts of the user's ECG signal are removed qualified according to the artifact removal qualification coefficient.

[0028] Optionally, the steps to calculate the artifact removal qualification coefficient according to the baseline drift coefficient and the waveform of the second ECG signal are:

[0029] Use the Pan-Tompkins algorithm to extract the P wave, QRS complex, and T wave from the second ECG signal;

[0030] Compare the extracted P wave, QRS complex, and T wave with the corresponding normal waveforms respectively, calculate the similarity of the amplitude, shape, and duration of each waveform, and use the average similarity as the similarity of the corresponding waveform; add the similarities of all waveforms and divide by 3 to obtain the waveform integrity coefficient of the second ECG signal;

[0031] The baseline drift coefficient and the waveform integrity coefficient are weighted and summed to obtain an artifact removal qualification coefficient.

[0032] Optionally, the steps for determining whether the artifacts in the user's ECG signal are removed qualified according to the artifact removal qualification coefficient are as follows:

[0033] Compare the artifact removal qualification coefficient with a preset artifact removal qualification coefficient threshold. If the artifact removal qualification coefficient is not less than the preset artifact removal qualification coefficient threshold, it means that the artifacts in the user's ECG signal are removed qualified, and then the second ECG signal is used as the final user's ECG signal for anti-fatigue data analysis;

[0034] If the artifact removal qualification coefficient is less than the preset artifact removal qualification coefficient threshold, it means that the artifacts in the user's ECG signal are not removed qualified, and then the second ECG signal is subjected to motion artifact removal of the first ECG signal again until the second ECG signal is qualified, and the second ECG signal is used as the final user's ECG signal for anti-fatigue data analysis.

[0035] In the second aspect of the implementation of the present invention, an anti-fatigue data analysis method is proposed, and the method includes:

[0036] Extract the heart rate variability and QT interval from the second ECG signal;

[0037] Obtain the user's blood oxygen saturation data through a PPG sensor, and the blood oxygen saturation data includes the average blood oxygen saturation, the fluctuation amplitude, and the hypoxic threshold;

[0038] Obtain the user's heart rate data through a PPG sensor, and the heart rate data includes heart rate fluctuations and recovery time;

[0039] Form a comprehensive physiological feature vector with the heart rate variability, QT interval, average blood oxygen saturation, fluctuation amplitude, hypoxic threshold, heart rate fluctuations and recovery time, input it into a machine learning model for fatigue assessment, output the user's fatigue level, and issue a rest alarm according to the fatigue level.

[0040] The beneficial effects of the present invention:

[0041] The present invention provides a wearable physiological monitoring system and an anti-fatigue data analysis method therefor. By setting a physiological data acquisition system in the user's wearable device, the user's ECG signal is collected by the physiological data acquisition system as the first ECG signal, and the user's motion state is judged; according to the user's motion state, different sampling methods and motion artifact removal methods are set for the user's ECG signal to obtain the user's second ECG signal; according to the first ECG signal and the second ECG signal, it is determined whether the artifact of the user's ECG signal is removed qualified. If qualified, the second ECG signal is used as the final user's ECG signal for anti-fatigue data analysis; if not qualified, the motion artifact of the first ECG signal is removed from the second ECG signal again until the second ECG signal is qualified. In this way, the motion artifact of the collected user's physiological data can be removed, reducing the adverse impact on the process of anti-fatigue data analysis of the user; ensuring that the user's electrocardiogram signal will not be distorted, making the fatigue state assessment accurate and not resulting in false health warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention will be further described below with reference to the accompanying drawings.

[0043] Figure 1 It is a framework diagram of a wearable physiological monitoring system;

[0044] Figure 2 It is a flowchart of an anti-fatigue data analysis method. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] The embodiments of the present invention provide a wearable physiological monitoring system. Refer to Figure 1 , Figure 1 It is a framework diagram of a wearable physiological monitoring system provided by an embodiment of the present invention. The system includes:

[0048] Data acquisition module: A physiological data acquisition system is set in the user's wearable device, and the user's ECG signal is collected by the physiological data acquisition system as the first ECG signal, and the user's motion state is judged;

[0049] Artifact removal module: Set different sampling methods and motion artifact removal methods for the user's ECG signal according to the user's motion state, and obtain the user's second ECG signal;

[0050] First analysis module: Determine whether the artifacts in the user's ECG signal are removed qualified according to the first ECG signal and the second ECG signal. If qualified, use the second ECG signal as the final user's ECG signal for anti-fatigue data analysis;

[0051] Second analysis module: If not qualified, perform motion artifact removal of the first ECG signal on the second ECG signal again until the second ECG signal is qualified.

[0052] Based on a wearable physiological monitoring system provided by an embodiment of the present invention, in the above manner, motion artifacts can be removed from the collected physiological data of the user, reducing the adverse effects on the process of anti-fatigue data analysis of the user; ensuring that the user's electrocardiogram signal will not be distorted, making the fatigue state assessment accurate and not causing false health warnings.

[0053] In one embodiment, the physiological data acquisition system is applied to a user wearable device, and the physiological data acquisition system includes an accelerometer, an ECG sensor, and a PPG sensor;

[0054] The ECG sensor is used to collect the user's ECG signal; the accelerometer is used to determine the user's current motion state, and the motion state includes static, walking, and strenuous exercise; the PPG sensor is used to detect the user's blood oxygen saturation and heart rate, and perform anti-fatigue data analysis on the user in combination with the ECG signal.

[0055] It should be noted that

[0056] In this embodiment, the wearable device worn by the user is equipped with a set of physiological data acquisition system for real-time monitoring of the user's physiological state and anti-fatigue data analysis. It specifically includes the following components:

[0057] 1. Accelerometer function: The accelerometer is used to monitor the user's motion state. By detecting the acceleration amplitude and change frequency, the user's motion type is judged in real time.

[0058] Motion state judgment: Static state: If the acceleration amplitude is close to 9.8m / s 2 (Gravitational acceleration), and the acceleration change frequency has no obvious fluctuation, it is judged as the static state.

[0059] Walking state: If the acceleration amplitude changes moderately and the periodic change is strong, it is judged as the walking state.

[0060] Vigorous exercise state: If the acceleration amplitude changes significantly and the frequency fluctuates strongly, it is determined as the vigorous exercise state.

[0061] 2. ECG sensor function: The ECG sensor is used to collect the user's electrocardiogram signal (ECG). The ECG signal reflects the user's cardiac electrical activity and is an important data source for evaluating the cardiac health status and fatigue level.

[0062] Function of the ECG signal: Provide basic data for subsequent fatigue analysis to help judge the user's cardiac load and fatigue degree.

[0063] 3. PPG sensor function: The PPG sensor is used to monitor the user's blood oxygen saturation (SpO 2 ) and heart rate. PPG calculates the blood oxygen level and heart rate by analyzing the light absorption characteristics of blood flow in blood vessels.

[0064] Blood oxygen saturation (SpO 2 ): Monitor the blood oxygen level. Low blood oxygen levels are usually associated with excessive fatigue or lack of rest. Heart rate: Real-time detection of heart rate fluctuations. Abnormal heart rate may be an indication of fatigue.

[0065] 4. Correlation analysis between exercise state and signals

[0066] Accelerometer and exercise state recognition: The accelerometer is used to judge the user's exercise state, thereby providing exercise intensity information. According to different exercise states (stationary, walking, vigorous exercise), the system will adjust the signal acquisition and processing strategies to optimize the ECG signal quality and avoid artifacts.

[0067] In one implementation, the PPG is combined with the ECG signal: Combine the ECG signal and the blood oxygen saturation and heart rate data in the PPG signal to further enhance the accuracy of physiological data analysis and provide multi-dimensional support for fatigue state assessment.

[0068] In one embodiment, the accelerometer is used to determine the user's current exercise state, including:

[0069] Collect the user's current acceleration amplitude and acceleration change frequency; if the acceleration amplitude is low, close to the gravitational acceleration value of 9.8 m / s 2 , and there is no obvious change in the acceleration change frequency, then the user's current exercise state is the stationary state;

[0070] If the acceleration amplitude has a certain change, but the change frequency is low and the periodicity is strong, then the user's current exercise state is the walking state;

[0071] If the acceleration amplitude is large and the change frequency is also large, then the user's current exercise state is the vigorous exercise state.

[0072] It should be noted that the accelerometer determines the user's motion state in real time by collecting the user's acceleration amplitude and acceleration change frequency. Specifically, when the acceleration amplitude is close to the gravitational acceleration value of 9.8 m / s 2 , and there is no obvious fluctuation in the acceleration change frequency, it indicates that the user is in a stationary state. For example, when the user is sitting or standing, the acceleration signal of the device hardly changes and is mainly affected by the earth's gravity; if the acceleration amplitude changes, but the change frequency is low and the periodicity is strong, it indicates that the user is performing low-intensity activities such as walking. At this time, the acceleration signal shows relatively regular fluctuations, reflecting the ups and downs of the steps; and if the acceleration amplitude is large and the change frequency is also high, it means that the user is performing strenuous exercises such as running or fast cycling. At this time, the acceleration signal fluctuates frequently and has a large amplitude, reflecting relatively intense body movements. This method of judging the motion state based on acceleration changes can effectively distinguish different types of motion states and provide a reliable basis for subsequent physiological data collection and analysis, ensuring more accurate fatigue assessment of the user under different exercise conditions.

[0073] In one embodiment, setting different sampling methods and motion artifact removal methods for the user's ECG signal according to the user's motion state includes:

[0074] When the user's motion state is a stationary state, the sampling frequency of the ECG signal is set to not more than 250 Hz, and the first ECG signal passes through a low-pass filter set to 0.5 - 1 Hz to remove low-frequency noise and remove motion artifacts; the second ECG signal of the user is obtained;

[0075] When the user's motion state is a walking state, the sampling frequency of the ECG signal is set to 500 Hz, and the first ECG signal passes through a high-pass filter set to 1 - 2 Hz to remove low-frequency noise, and the low-frequency noise removal is subjected to wavelet transform to remove high-frequency noise and remove motion artifacts; the second ECG signal of the user is obtained;

[0076] When the user's motion state is a strenuous exercise state, the sampling frequency of the ECG signal is set to 1000 Hz, and the first ECG signal uses blind source separation technology to separate the mixed signal composed of motion artifacts and the ECG signal, extracts the ECG signal, and performs wavelet transform on the extracted ECG signal to remove high-frequency noise and remove motion artifacts; the second ECG signal of the user is obtained.

[0077] It should be noted that according to the different exercise states of users, the system will adopt adaptive sampling frequency settings and artifact removal strategies for ECG signals to ensure high-quality and accurate electrocardiogram signals under various exercise conditions. In the stationary state, the user has less movement and the changes in the ECG signal are relatively stable. Therefore, the system sets the sampling frequency to no more than 250 Hz, which is sufficient to capture the subtle changes in the electrocardiogram signal. At this time, a low-pass filter (0.5 - 1 Hz) is set to remove low-frequency noise and baseline drift, effectively removing artifacts caused by small skin vibrations or unstable device contacts during rest. For example, when the user sits on a chair and remains stationary for a long time, the signal fluctuations are small, and the low-pass filter can effectively remove these small fluctuations to ensure the stability of the ECG signal, thus obtaining a clear second ECG signal.

[0078] In the walking state, due to the ups and downs of the steps and the small movements of the body, obvious low-frequency noise and artifacts will be introduced into the ECG signal. Therefore, the system increases the sampling frequency to 500 Hz to more accurately capture the changes in the electrocardiogram. At the same time, a high-pass filter (1 - 2 Hz) is used to remove low-frequency noise and the low-frequency baseline drift caused by gait. In addition, the system also performs denoising processing on the ECG signal through wavelet transform to effectively remove the high-frequency noise generated during walking. For example, when the user is walking easily, the ECG signal fluctuates regularly, but the ups and downs of the steps will introduce periodic low-frequency noise. The high-pass filter can remove these low-frequency components, and wavelet transform can effectively filter out the high-frequency artifacts generated by gait to ensure that the signal quality is not affected.

[0079] In the state of strenuous exercise, the user has a large range of motion, especially when running or doing high-intensity exercises. More intense motion artifacts will appear in the ECG signal. At this time, a higher sampling frequency and more complex artifact removal strategies are required. The system sets the sampling frequency to 1000 Hz to ensure that it can capture the rapidly changing electrocardiogram signal. At the same time, the system uses blind source separation techniques (such as ICA) to separate the artifacts caused by motion and the real ECG signal from the mixed signal. This process can effectively separate the motion artifact part, remove it, and retain the signal of cardiac electrical activity. Then, the system performs denoising on the extracted ECG signal through wavelet transform to further remove high-frequency noise and motion artifacts. For example, when the user is running vigorously, due to the intense motion and muscle activity, the ECG signal will be affected by strong motion artifacts. The blind source separation technique can separate the artifacts and the real ECG waveform from it, ensuring that the system can obtain accurate electrocardiogram data, thus providing a reliable basis for subsequent anti-fatigue data analysis.

[0080] In one implementation method, by dynamically adjusting the sampling frequency and artifact removal strategy according to the motion state, the system can ensure accurate and clear ECG signals in various motion environments, greatly improving the accuracy and reliability of fatigue analysis. Whether the user is in a static, walking, or strenuous exercise state, the system can flexibly adjust the signal processing method according to the real-time motion situation, effectively removing motion artifacts and ensuring that the evaluation results of the fatigue state are not interfered by motion artifacts.

[0081] In one embodiment, the steps of determining whether the artifacts of the user's ECG signal are removed qualified according to the first ECG signal and the second ECG signal are as follows:

[0082] Perform low-pass filtering on the second ECG signal to remove high-frequency components and retain low-frequency baseline information;

[0083] Use the least squares method to fit the baseline of the ECG signal to obtain the fitted baseline, and calculate the baseline drift coefficient according to the baseline of the ECG signal and the second ECG signal. The calculation formula is:

[0084]

[0085] In the formula, GH is the baseline drift coefficient, ECG(t) is the value of the second ECG signal at time point t, the fitted baseline(t) is at time point t of the fitted baseline, and T is the signal duration;

[0086] Calculate the artifact removal qualified coefficient according to the baseline drift coefficient and the waveform of the second ECG signal, and judge whether the artifacts of the user's ECG signal are removed qualified according to the artifact removal qualified coefficient.

[0087] In one embodiment, the steps of calculating the artifact removal qualified coefficient according to the baseline drift coefficient and the waveform of the second ECG signal are as follows:

[0088] Use the Pan-Tompkins algorithm to extract the P wave, QRS complex, and T wave from the second ECG signal;

[0089] Compare the extracted P wave, QRS complex, and T wave with the corresponding normal waveforms respectively, calculate the similarity of the amplitude, shape, and duration of each waveform, and use the average similarity as the similarity of the corresponding waveform; add the similarities of all waveforms and divide by 3 to obtain the waveform integrity coefficient of the second ECG signal;

[0090] Perform weighted summation on the baseline drift coefficient and the waveform integrity coefficient to obtain the artifact removal qualified coefficient.

[0091] It should be noted that the second ECG signal is subjected to low-pass filtering to remove the high-frequency components in the signal. The cut-off frequency of the low-pass filter can be set appropriately (usually set between 50 Hz and 100 Hz), aiming to remove electrical interference and other high-frequency noises and retain the low-frequency baseline information in the ECG signal. Through this process, short-term noises caused by motion artifacts and the like can be removed, making the signal smoother.

[0092] It should be noted that the formula for obtaining the qualified artifact removal coefficient by weighted summation of the baseline drift coefficient and the waveform integrity coefficient is: GHY = a2×df - a1×fg, where GHY is the qualified artifact removal coefficient, fg and df are the baseline drift coefficient and the waveform integrity coefficient respectively, a1 and a2 are the preset proportionality coefficients of fg and df respectively, and both a1 and a2 are greater than 0;

[0093] It should be noted that a1 and a2 are set by professionals according to the actual situation. Generally, the sum of a1 and a2 is 1. For example, a1 and a2 can be 0.4 and 0.6 respectively, or other numbers, and there is no specific limitation; in addition, before the qualified artifact removal coefficient, the baseline drift coefficient and the waveform integrity coefficient need to be normalized. Common normalization methods include Min-Max normalization, Z-Score standardization, etc. The specific method is selected by professionals according to the actual situation and will not be specifically limited and elaborated here.

[0094] It should be noted that the baseline drift coefficient refers to the degree of deviation between the second ECG signal and the fitted baseline, reflecting whether the low-frequency components of the ECG signal are affected by motion artifacts. A larger baseline drift coefficient means that there are obvious baseline fluctuations in the signal, usually caused by motion-induced artifacts (such as the vibration of the arm during running causing the baseline drift of the ECG signal). The waveform integrity coefficient measures the similarity of the shapes, amplitudes, and durations of the P wave, QRS complex, and T wave in the second ECG signal to the normal waveform. The larger the waveform integrity coefficient, the closer these key waveforms are to the characteristics of a normal electrocardiogram, the smaller the influence of artifacts, and the higher the quality of the signal.

[0095] When the baseline drift coefficient is small, it means that the low-frequency noise and motion artifacts in the signal have been effectively removed, the baseline tends to be stable, and the signal response is more accurate; while a larger waveform integrity coefficient indicates that the shapes of the P wave, QRS complex, and T wave are closer to those of a normal electrocardiogram, indicating that the key features of the signal have not been distorted and these features can still be used to judge the heart health status. If both of these indicators are within the ideal range, it indicates that the ECG signal is not only not affected by artifacts, but also maintains high accuracy and reliability, so it can be safely used for subsequent anti-fatigue data analysis and health assessment.

[0096] For example: Suppose a user wears a smartwatch during intense exercise. The wrist vibrations generated during exercise may cause significant baseline drift in the ECG signal, resulting in violent fluctuations in the low-frequency part of the signal. At this time, the baseline drift coefficient is large, while the waveform integrity coefficient is small, indicating that the motion artifact has not been completely removed. After a series of filtering and denoising processes, the baseline drift coefficient drops to a low level, the waveform integrity coefficient increases, and the shapes of the P wave, QRS complex, and T wave of the second ECG signal are close to normal, and the artifact is effectively removed, and the signal resumes a high quality. At this time, this signal can be used as the user's valid ECG signal for subsequent anti-fatigue analysis, providing an accurate basis for judging the user's fatigue state and health condition.

[0097] In one implementation, the benefits of analyzing the baseline drift coefficient and the waveform integrity coefficient for determining whether the motion artifact in the user's ECG signal has been effectively removed and whether subsequent anti-fatigue data analysis of the user can be performed are as follows: Analyzing the baseline drift coefficient and the waveform integrity coefficient has significant advantages for determining whether the motion artifact in the user's ECG signal has been effectively removed and whether subsequent anti-fatigue data analysis can be performed. First, by quantitatively measuring the degree of low-frequency noise in the signal, the baseline drift coefficient can accurately evaluate the impact of motion artifacts on the ECG signal. If the baseline drift coefficient is small, it indicates that the low-frequency components in the signal have been effectively removed, and the quality of the signal is guaranteed, which can accurately reflect the true activities of the heart. In addition, the waveform integrity coefficient analyzes the morphology, amplitude, and duration of key waveforms such as the P wave, QRS complex, and T wave to ensure that the main physiological characteristics of the ECG signal are not distorted, which is crucial for judging the user's health status. The combination of the two can comprehensively evaluate the reliability of the ECG signal, avoid false appearances caused by motion artifacts, and ensure the authenticity and accuracy of the data. This method can continuously monitor and optimize the ECG signal during dynamic exercise, provide accurate data support for anti-fatigue analysis, reduce the risk of misjudgment caused by data errors, thereby improving the reliability of health management, and ensuring that there is no deviation in the cardiac health assessment of users in a fatigued state. Through this precise signal processing and analysis, the user's fatigue level can be better reflected, timely and effective health warnings can be provided, helping users take appropriate rest and recovery measures to avoid potential harm to health caused by over-fatigue.

[0098] In one embodiment, the steps for determining whether the artifact in the user's ECG signal has been removed qualified according to the artifact removal qualification coefficient are as follows:

[0099] Compare the artifact removal qualification coefficient with the preset artifact removal qualification coefficient threshold. If the artifact removal qualification coefficient is not less than the preset artifact removal qualification coefficient threshold, it indicates that the artifact in the user's ECG signal has been removed qualified, and then use the second ECG signal as the user's final ECG signal for anti-fatigue data analysis;

[0100] If the artifact removal qualification coefficient is less than the preset artifact removal qualification coefficient threshold, it indicates that the artifact removal of the user's ECG signal is unqualified. Then, the motion artifacts of the first ECG signal are removed from the second ECG signal again until the second ECG signal is qualified, and the second ECG signal is used as the final user's ECG signal for anti-fatigue data analysis.

[0101] It should be noted that the step of judging whether the artifacts of the user's ECG signal are removed qualified according to the artifact removal qualification coefficient is to judge whether the signal quality meets the standard by comparing the artifact removal qualification coefficient with the preset threshold. In this process, first, the baseline drift coefficient and waveform integrity coefficient of the second ECG signal are calculated to obtain the artifact removal qualification coefficient. If this coefficient is greater than or equal to the preset artifact removal qualification coefficient threshold, it indicates that the motion artifacts in the ECG signal have been effectively removed, and the signal quality meets the analysis requirements, and then it can be used as the final user's ECG signal for anti-fatigue data analysis. This step ensures the accuracy of the data and avoids analysis errors caused by the influence of motion artifacts. For example, when the user is doing strenuous exercise, due to unstable equipment wearing or violent muscle movement, large motion artifacts may be generated. After signal processing, if the artifact removal qualification coefficient meets the standard, it means that the artifacts have been successfully removed, and the signal has restored the true waveform of the electrocardiogram, so that effective fatigue assessment can be carried out.

[0102] On the contrary, if the artifact removal qualification coefficient is less than the preset threshold, it means that there are still obvious artifacts in the signal, resulting in the distortion of the ECG signal and being not suitable for further analysis. At this time, the system will start the motion artifact removal process again, and through further signal processing until the signal reaches the qualified standard. For example, assume that when a user is running, due to incomplete removal of motion artifacts, the waveforms of the P wave and T wave in the signal are significantly distorted, and the artifact removal qualification coefficient may be low. In this case, the system will re-adjust the signal processing method and perform denoising and filtering processing again until the artifact removal qualification coefficient meets the threshold requirement. Finally, the second ECG signal after multiple optimizations can provide accurate and reliable physiological data, ensuring that the subsequent anti-fatigue analysis can be based on the real and clear electrocardiogram signal, and avoiding incorrect health assessments caused by the influence of artifacts.

[0103] Based on the same inventive concept, the embodiment of the present invention also provides an anti-fatigue data analysis method. Refer to Figure 2 , Figure 2 which is a flowchart of an anti-fatigue data analysis method provided by the embodiment of the present invention. The method includes:

[0104] Extract the heart rate variability and QT interval from the second ECG signal;

[0105] Obtain the blood oxygen saturation data of the user through a PPG sensor. The blood oxygen saturation data includes the average blood oxygen saturation, the fluctuation amplitude, and the hypoxic threshold.

[0106] Obtain the heart rate data of the user through a PPG sensor. The heart rate data includes heart rate fluctuations and recovery time.

[0107] Form a comprehensive physiological feature vector from heart rate variability, QT interval, average blood oxygen saturation, fluctuation amplitude, hypoxic threshold, heart rate fluctuations, and recovery time, input it into a machine learning model for fatigue assessment, output the fatigue level of the user, and issue a rest alert according to the fatigue level.

[0108] It should be noted that heart rate variability (HRV) and QT interval are extracted from the second ECG signal. Heart rate variability reflects the ability of the heart to self-regulate, and usually, a decrease in heart rate variability occurs under a fatigued state. The QT interval represents the time interval in an electrocardiogram, which is normally related to the heart's health status. An overly long QT interval may be a sign of fatigue or overexertion.

[0109] Blood oxygen saturation data collection: Obtain the blood oxygen saturation data of the user through a PPG sensor, including: Average blood oxygen saturation: Reflects the overall oxygenation level of the user. Low blood oxygen may be a manifestation of physical fatigue or discomfort. Fluctuation amplitude: Reflects the fluctuation of blood oxygen saturation. A large fluctuation may mean abnormal blood oxygen changes during exercise or at rest, indicating potential signs of fatigue. Hypoxic threshold: Refers to the duration or number of times when the blood oxygen saturation is lower than a certain critical value. Prolonged hypoxia will affect the body's recovery and may be related to overfatigue or health problems.

[0110] Heart rate data collection. Obtain the heart rate data of the user through a PPG sensor, including:

[0111] Heart rate fluctuations: Represents the changes in heart rate at different time points. Large fluctuations may be related to fatigue, stress, or physical exertion.

[0112] Recovery time: Refers to the time required for the heart rate to return to the resting state after exercise. A long recovery time may indicate that the user's physical strength recovers slowly, suggesting a higher level of fatigue.

[0113] Construction of comprehensive physiological feature vector: Integrate the above-extracted physiological features (heart rate variability, QT interval, average blood oxygen saturation, fluctuation amplitude, hypoxic threshold, heart rate fluctuations, recovery time) into a comprehensive physiological feature vector, covering multi-dimensional information such as the user's heart health status, blood oxygen level, and heart rate changes.

[0114] Fatigue assessment using a machine learning model: The physiological feature vector is input into a trained machine learning model (such as a support vector machine, decision tree, neural network, etc.) for fatigue assessment. The model analyzes the user's current physiological state based on historical data and labeled fatigue levels, and outputs a fatigue level (such as low, medium, high fatigue levels).

[0115] Rest alert issued: According to the result of the fatigue level, if the model determines that the user's fatigue state reaches a certain threshold (for example, the fatigue level is "high"), the system will automatically issue a rest alert to prompt the user to rest, avoid overexertion, and reduce health risks.

[0116] For example: Suppose a user wears a wearable device after a day of work. The system extracts the heart rate variability and QT interval from the ECG signal, indicating a significant decrease in heart rate variability and an extension of the QT interval, suggesting a decline in the user's cardiac self-regulation ability, possibly due to accumulated fatigue. At the same time, the PPG sensor monitors that the average blood oxygen saturation of the user is slightly lower than the normal level, with a large fluctuation range and a high hypoxic threshold, indicating that the user's oxygenation level fluctuates, which may be a sign of fatigue caused by long-term work. Combining the heart rate fluctuation and recovery time, the user has a large heart rate fluctuation and a long recovery time, further confirming a decline in the user's physical recovery ability.

[0117] In one implementation, these physiological data are integrated into a feature vector. After being input into the machine learning model, the model determines that the user is in a relatively high fatigue level, thereby triggering the rest alert of the system to remind the user to rest in time to avoid damage to health caused by over-fatigue. Through the comprehensive analysis of such multi-dimensional data, the system can accurately assess the user's fatigue state and give a scientific health warning.

[0118] The above has described a specific embodiment of the present invention in detail, but the content described is only a preferred embodiment of the present invention and cannot be used to artificially limit the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the present invention application should still fall within the scope covered by the patent of the present invention.

Claims

1. A wearable physiological monitoring system, characterized in that: The system comprises: Data acquisition module: a physiological data acquisition system is set in the wearable device of the user, and the ECG signal of the user is collected as the first ECG signal according to the physiological data acquisition system, and the movement state of the user is determined; Artifact removal module: setting different sampling modes and motion artifact removal modes for the user's ECG signal according to the user's motion state to obtain the user's second ECG signal; The first analysis module: determines whether the artifact removal of the user's ECG signal is qualified according to the first ECG signal and the second ECG signal, and if qualified, uses the second ECG signal as the ECG signal of the final user for anti-fatigue data analysis; Second analysis module: If the signal fails to meet the requirements, the motion artifact removal of the first ECG signal is performed again on the second ECG signal until the second ECG signal meets the requirements.

2. A wearable physiological monitoring system according to claim 1, characterized in that: Setting up a physiological data collection system in a user's wearable device includes: The physiological data acquisition system is applied to a user's wearable device, and the physiological data acquisition system includes an accelerometer, an ECG sensor, and a PPG sensor; The ECG sensor is used to collect the user's ECG signal; the accelerometer is used to determine the user's current motion state, which includes stillness, walking and strenuous exercise; the PPG sensor is used to detect the user's blood oxygen saturation and heart rate, and perform anti-fatigue data analysis on the user in combination with the ECG signal.

3. A wearable physiological monitoring system according to claim 2, characterized in that: The accelerometer is used to determine the current motion state of the user including: Collect the user's current acceleration amplitude and acceleration change frequency; if the acceleration amplitude is low, close to the gravity acceleration value of 9.8m / s2, and the acceleration change frequency does not change significantly, the user's current motion state is static; If the acceleration amplitude changes to a certain extent, but the frequency of change is low and the periodicity is strong, the user's current motion state is walking; If the acceleration amplitude is large and the frequency of change is also large, the user's current exercise state is a strenuous exercise state.

4. A wearable physiological monitoring system according to claim 1, characterized in that: Different sampling methods and motion artifact removal methods are set for the user's ECG signal according to the user's motion state, including: When the user's motion state is static, the sampling frequency of the ECG signal is set to be no greater than 250 Hz, and the first ECG signal is filtered by a low-pass filter at 0.5-1 Hz to remove low-frequency noise and motion artifacts; and a second ECG signal of the user is obtained; When the user's motion state is walking, the sampling frequency of the ECG signal is set to 500 Hz, and the first ECG signal is filtered by a high-pass filter, set to 1-2 Hz to remove low-frequency noise, and the low-frequency noise is subjected to wavelet transformation to remove high-frequency noise and motion artifacts; the second ECG signal of the user is obtained; When the user's movement state is a strenuous exercise state, the sampling frequency of the ECG signal is set to 1000Hz, and the first ECG signal is separated from the mixed signal composed of motion artifacts and ECG signals by using blind source separation technology to extract the ECG signal, and the extracted ECG signal is subjected to wavelet transformation to remove high-frequency noise and motion artifacts; and the user's second ECG signal is obtained.

5. A wearable physiological monitoring system according to claim 1, characterized in that: The steps of determining whether the artifact removal of the user's ECG signal is qualified according to the first ECG signal and the second ECG signal are: Performing a low-pass filter on the second ECG signal to remove high-frequency components and retain low-frequency baseline information; The baseline of the ECG signal is fitted using the least squares method to obtain a fitted baseline, and the baseline drift coefficient is calculated based on the baseline of the ECG signal and the second ECG signal. The calculation formula is: Where GH is the baseline drift coefficient, ECG(t) is the value of the second ECG signal at time point t, fitted baseline(t) is the value of the fitted baseline at time point t, and T is the signal duration; An artifact removal qualification coefficient is calculated according to the baseline drift coefficient and the waveform of the second ECG signal, and whether the artifact removal of the user's ECG signal is qualified is determined according to the artifact removal qualification coefficient.

6. A wearable physiological monitoring system according to claim 1, characterized in that: The steps for calculating the artifact removal qualification coefficient based on the baseline drift coefficient and the waveform of the second ECG signal are: Using the Pan-Tompkins algorithm, extract the P wave, QRS complex and T wave from the second ECG signal; The extracted P wave, QRS complex and T wave are respectively compared with the corresponding normal waveforms, and the similarity of the amplitude, shape and duration of each waveform is calculated, and the mean of the similarity is used as the similarity of the corresponding waveform; the similarities of all waveforms are added and divided by 3 to obtain the waveform integrity coefficient of the second ECG signal; The baseline drift coefficient and the waveform integrity coefficient are weighted and summed to obtain the artifact removal qualified coefficient.

7. A wearable physiological monitoring system according to claim 5, characterized in that: The steps of judging whether the artifact removal of the user's ECG signal is qualified according to the artifact removal qualification coefficient are as follows: Compare the artifact removal qualified coefficient with the preset artifact removal qualified coefficient threshold, if the artifact removal qualified coefficient is not less than the preset artifact removal qualified coefficient threshold, it means that the artifact removal of the user's ECG signal is qualified, and the second ECG signal is used as the ECG signal of the final user for anti-fatigue data analysis; If the artifact removal qualification coefficient is less than the preset artifact removal qualification coefficient threshold, it means that the artifact removal of the user's ECG signal is unqualified, and the motion artifact removal of the first ECG signal is performed again on the second ECG signal until the second ECG signal is qualified, and the second ECG signal is used as the final user's ECG signal for anti-fatigue data analysis.

8. An anti-fatigue data analysis method, implemented by a wearable physiological monitoring system as claimed in claims 1-7, characterized in that: The method comprises: extracting heart rate variability and QT interval from the second ECG signal; The user's blood oxygen saturation data is obtained through the PPG sensor. The blood oxygen saturation data includes the average blood oxygen saturation value, fluctuation range and hypoxia threshold; Acquire the user's heart rate data through a PPG sensor, wherein the heart rate data includes heart rate fluctuation and recovery time; Heart rate variability, QT interval, average blood oxygen saturation, fluctuation amplitude and hypoxia threshold, heart rate fluctuation and recovery time are formed into a comprehensive physiological feature vector, which is input into the machine learning model for fatigue assessment, outputs the user's fatigue level, and issues a rest alarm based on the fatigue level.

Images