Physiological signal motion interference suppression method based on human factor intelligence and electronic device

Abstract

The application provides a physiological signal motion interference suppression method and device based on human factor intelligence, an electronic device and a storage medium. The method comprises the following steps: acquiring a first physiological signal and a motion signal, wherein the first physiological signal is used for representing a physiological signal subjected to motion interference; screening the motion signal based on the correlation between the first physiological signal and the motion signal; and performing adaptive filtering on the screened motion signal and the first physiological signal by using an adaptive filtering algorithm to obtain a second physiological signal, wherein the second physiological signal is used for representing a physiological signal after motion interference is suppressed. The method provided by the application can effectively suppress the motion interference in the physiological signal and restore a relatively accurate original physiological signal.

Description

Technical Field

[0001] This application relates to the field of signal processing technology, and in particular to a method, device, electronic device, and storage medium for suppressing motion interference of physiological signals based on human-centric intelligence. Background Technology

[0002] When using smart wearable devices to collect physiological signals, they are very susceptible to motion interference, which causes the collected physiological signals to be superimposed with motion interference noise, making it impossible to obtain accurate original physiological signals and causing significant deviations in the subsequent analysis of physiological signals to obtain other features.

[0003] The motion interference suppression methods used in related technologies involve inputting the acquired motion signal into an adaptive filter to suppress motion interference. However, these methods are not very effective at suppressing motion interference, and their goal is to recover a specific feature of the physiological signal, rather than the original physiological signal itself. Therefore, other features cannot be obtained from the physiological signal. Taking photoplethysmography (PPG) as an example, the motion interference suppression methods used in related technologies aim to recover a specific feature of the PPG signal (such as heart rate), rather than the original PPG signal itself. Therefore, other features (such as HRV, Heart Rate Variability) cannot be obtained from the PPG signal. Summary of the Invention

[0004] This application provides a method, device, electronic device, and storage medium for suppressing motion interference in physiological signals based on human-centric intelligence, which can effectively suppress motion interference in physiological signals and recover relatively accurate original physiological signals.

[0005] Firstly, this application provides a method for suppressing physiological signal motion interference based on human-centric intelligence, including:

[0006] Acquire a first physiological signal and a motion signal. The first physiological signal is used to characterize the physiological signal affected by motion disturbance.

[0007] Motion signals are filtered based on the correlation between the first physiological signal and the motion signal;

[0008] An adaptive filtering algorithm is used to adaptively filter the filtered motion signal and the first physiological signal to obtain the second physiological signal, which is used to characterize the physiological signal after motion interference is suppressed.

[0009] In one possible implementation, the physiological signal is at least one of PPG signal, electroencephalogram (EEG) signal, electrocardiogram (ECG) signal, or electromyogram (EMG) signal.

[0010] In one possible implementation, the physiological signal is a PPG signal, the first physiological signal is a PPG1 signal, and the second physiological signal is a PPG2 signal.

[0011] In one possible implementation,

[0012] The motion signal comprises M channels. The motion signal is filtered based on the correlation between the first physiological signal and the motion signal, including:

[0013] Calculate the Pearson correlation coefficients between the M channel signals and the PPG1 signal respectively;

[0014] From the M channel signals, the channel signals corresponding to those whose absolute value of the Pearson correlation coefficient is less than a preset threshold are removed, resulting in N channel signals, where N≤M.

[0015] In one possible implementation, an adaptive filtering algorithm is used to adaptively filter the filtered motion signal and the first physiological signal to obtain the second physiological signal, including:

[0016] In N channel signals, the channel signals with a Pearson correlation coefficient greater than 0 are classified as positive signals, and the channel signals with a Pearson correlation coefficient less than 0 are classified as negative signals.

[0017] Based on the grouping results, an adaptive filtering algorithm is used to adaptively filter the grouped motion signal and PPG1 signal to obtain the PPG2 signal.

[0018] In one possible implementation, the adaptive filtering algorithm includes a least mean square adaptive filtering algorithm. Based on the grouping results, the grouped motion signal and PPG1 signal are adaptively filtered using the adaptive filtering algorithm to obtain the PPG2 signal, including:

[0019] If all N channel signals are divided into positive or negative groups, then the summation of the N channel signals is used to obtain the first reference signal.

[0020] The first reference signal and the PPG1 signal are input into the minimum mean square adaptive filter for adaptive filtering to obtain the PPG3 signal. The PPG3 signal is used to characterize the PPG signal after adaptive filtering.

[0021] The PPG2 signal is obtained by aligning the phase of the PPG3 signal with the PPG1 signal.

[0022] One possible implementation involves phase alignment of the PPG3 signal based on the PPG1 signal, including:

[0023] Perform convolution calculation on PPG1 and PPG3 signals;

[0024] The PPG3 signal is shifted along the time axis based on the target phase offset corresponding to the maximum value in the convolution calculation result.

[0025] In one possible implementation, the adaptive filtering algorithm includes a least mean square adaptive filtering algorithm. Based on the grouping results, the grouped motion signal and PPG1 signal are adaptively filtered using the adaptive filtering algorithm to obtain the PPG2 signal, including:

[0026] If N channel signals are divided into positive and negative groups, then the positive and negative groups are sorted into signal groups to obtain the first and second groups of signals. The absolute value of the sum of the Pearson correlation coefficients of the first group of signals is greater than the absolute value of the sum of the Pearson correlation coefficients of the second group of signals.

[0027] The channel signals in the first group of signals are summed to obtain the second reference signal;

[0028] The second reference signal and the PPG1 signal are input into the minimum mean square adaptive filter for the first adaptive filtering to obtain the PPG4 signal. The PPG4 signal is used to characterize the PPG signal after the first adaptive filtering.

[0029] PPG4 signal is phase-aligned based on PPG1 signal to obtain PPG5 signal;

[0030] The channel signals in the second group of signals are summed to obtain the third reference signal;

[0031] The third reference signal and the PPG5 signal are input into the minimum mean square adaptive filter for a second adaptive filtering to obtain the PPG6 signal. The PPG6 signal is used to characterize the PPG signal after the second adaptive filtering.

[0032] The PPG2 signal is obtained by aligning the phase of the PPG6 signal with the PPG1 signal.

[0033] In one possible implementation, before filtering the motion signal based on the correlation between the first physiological signal and the motion signal, the method further includes:

[0034] The PPG1 signal and motion signal are filtered.

[0035] Secondly, this application provides a physiological signal motion interference suppression device based on human-centric intelligence, comprising:

[0036] The acquisition module is used to acquire a first physiological signal and a motion signal, wherein the first physiological signal is used to characterize the physiological signal affected by motion interference;

[0037] The filtering module is used to filter motion signals based on the correlation between the first physiological signal and the motion signal;

[0038] The adaptive filtering module is used to adaptively filter the selected motion signal and the first physiological signal using an adaptive filtering algorithm to obtain the second physiological signal, which is used to characterize the physiological signal after suppressing motion interference.

[0039] Thirdly, this application provides an electronic device, including: a processor and a memory, wherein the memory is used to store a computer program; and the processor is used to run the computer program to implement the human-based intelligent physiological signal motion interference suppression method as described in the first aspect.

[0040] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to implement the human-based intelligent physiological signal motion interference suppression method of the first aspect.

[0041] Compared with the prior art, this application has at least the following technical effects:

[0042] This application provides a method, device, electronic device, and storage medium for suppressing motion interference in physiological signals based on human-centric intelligence. By analyzing the correlation between the motion-interfered physiological signal and the motion signal, i.e., analyzing the degree of influence of the motion signal on the physiological signal, the motion signal is screened, and the motion signal with less influence on the physiological signal is removed. Then, an adaptive filtering algorithm is used to adaptively filter the screened motion signal and the motion-interfered physiological signal to obtain the physiological signal after suppressing motion interference. This avoids the addition of motion signals with less influence on the physiological signal to the adaptive filter, which would generate new noise and lead to the inability to effectively suppress motion interference in the physiological signal and recover the relatively accurate original physiological signal. Attached Figure Description

[0043] Figure 1 The figure shows the results of the signal motion interference suppression method of related technologies;

[0044] Figure 2 This application provides an architecture diagram for specific application scenarios.

[0045] Figure 3 A flowchart illustrating the method for suppressing motion interference in physiological signals based on human-centric intelligence provided in this application embodiment;

[0046] Figure 4 Here is a diagram of the LMS adaptive filter.

[0047] Figures 5(a) and 5(b) are the results of the physiological signal motion interference suppression method based on human intelligence provided in the embodiments of this application;

[0048] Figure 6 A schematic diagram of the structure of the physiological signal motion interference suppression device based on human-centric intelligence provided in this application embodiment;

[0049] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0050] In this embodiment of the application, unless otherwise stated, the character " / " indicates that the preceding and following objects are in an OR relationship. For example, A / B can represent A or B. "AND / OR" describes the relationship between the associated objects, indicating that three relationships can exist. For example, A AND / OR B can represent: A existing alone, A and B existing simultaneously, and B existing alone.

[0051] It should be noted that the terms "first" and "second" used in the embodiments of this application are used only for distinguishing descriptive purposes and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated, nor should they be construed as indicating or implying order.

[0052] In the embodiments of this application, "at least one" means one or more, and "more than one" means two or more. Furthermore, "at least one of the following" or similar expressions refer to any combination of these items, which may include any combination of a single item or a plurality of items. For example, at least one of A, B, or C can represent: A, B, C, A and B, A and C, B and C, or A, B, and C. Each of A, B, and C can be an element itself or a set containing one or more elements.

[0053] In this application, terms such as "exemplary," "in some embodiments," and "in another embodiment" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the term "exemplary" is intended to present the concept in a concrete manner.

[0054] In the embodiments of this application, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction, their meanings are consistent. Similarly, in the embodiments of this application, "communication" and "transmission" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction, their meanings are consistent. For example, transmission can include sending and / or receiving, and can be a noun or a verb.

[0055] In the embodiments of this application, the term "equal to" can be used in conjunction with "greater than" to apply to technical solutions employing the condition of "greater than", and can also be used in conjunction with "less than" to apply to technical solutions employing the condition of "less than". It should be noted that when "equal to" is used with "greater than", it cannot be used with "less than"; and when "equal to" is used with "less than", it cannot be used with "greater than".

[0056] When using smart wearable devices to collect physiological signals, they are very susceptible to motion interference, which causes the collected physiological signals to be superimposed with motion interference noise, making it impossible to obtain accurate original physiological signals and causing significant deviations in the subsequent analysis of physiological signals to obtain other features.

[0057] Most motion interference suppression methods used in related technologies employ a three-axis gyroscope to record motion and input the acquired motion signal into an adaptive filter to suppress motion interference. However, research on the input noise handling methods is limited. Common input methods include averaging the three-axis gyroscope signal and inputting it into the filter, or cascading three adaptive filters, with each stage inputting one dimension of the three-axis gyroscope signal. However, not all motion affects the signal, and such filtering methods introduce new noise. Furthermore, the goal of this method is to recover a specific feature of the physiological signal, rather than the original physiological signal itself; therefore, it cannot utilize the physiological signal to obtain other features.

[0058] like Figure 1 As shown, Figure 1 The image shows the results of signal motion interference suppression methods based on related technologies, using PPG signals as an example of physiological signals. Figure 1 The first row shows the PPG signal without motion interference, the second row shows the PPG signal with motion interference, the third row shows the result of cascaded adaptive filtering using the gyroscope signals from the two channels, and the fourth row shows the gyroscope signals from the two channels. Figure 1 As can be seen from the part highlighted in the middle, the gyroscope signal in the 4th row fluctuates significantly due to motion, but it has almost no effect on the PPG signal in the 2nd row that contains motion interference. The PPG signal after adaptive filtering has obvious distortion, that is, the deviation between the PPG signal after adaptive filtering and the original PPG signal (the PPG signal in the 1st row) is increased.

[0059] Furthermore, PPG signals can reflect certain specific states of a person, and HRV characteristics based on waveform (RR interval) play an important role in reflecting a person's state. However, the signal motion interference suppression methods used in related technologies can usually only recover a certain feature of the original signal, such as suppressing motion interference on PPG signals to obtain an accurate heart rate, rather than obtaining the signal itself after suppressing motion interference. Therefore, it is impossible to obtain other features (such as HRV) from PPG signals.

[0060] Based on the above problems, this application proposes a method for suppressing motion interference in physiological signals based on human-centric intelligence, which can effectively suppress motion interference in physiological signals and recover relatively accurate original physiological signals.

[0061] Now combined Figure 2 Figure 5 illustrates the method for suppressing motion interference of physiological signals based on human factors intelligence provided in the embodiments of this application.

[0062] Figure 2 This is an application scenario architecture diagram provided for embodiments of this application. (For example...) Figure 2 As shown, the above application scenarios include physiological signal acquisition devices, motion signal acquisition devices, and electronic devices. The physiological signal acquisition devices can be PPG signal acquisition devices (such as PPG sensors) used to collect the PPG signals of the subject; they can also be EEG (Electroencephalogram) brainwave signal acquisition devices, ECG (Electrocardiogram) electrocardiogram signal acquisition devices, EMG (Electromyogram) electromyogram signal acquisition devices, etc. The motion signal acquisition devices can be gyroscope sensors, accelerometers, inertial measurement units, etc., used to detect and quantify the subject's body movements, such as rotation and tilting, to obtain motion signals. The physiological signal acquisition devices and motion signal acquisition devices transmit the acquired signals to the electronic devices wirelessly or via wired means, and the electronic devices implement the human-centric intelligence-based physiological signal motion interference suppression method provided in this application embodiment. It should be noted that this application embodiment does not limit the type of electronic device; the electronic device can be a desktop computer, tablet computer, laptop computer, etc.

[0063] Figure 3 The flowchart of the physiological signal motion interference suppression method based on human-factor intelligence provided in this application embodiment specifically includes the following steps:

[0064] Step S31: Obtain the first physiological signal and motion signal.

[0065] Specifically, physiological signals of the subject are collected using a physiological signal acquisition device (which can be a portable bioinformatics acquisition device) to obtain a first physiological signal. This first physiological signal characterizes physiological signals affected by motion interference. The first physiological signal contains both genuine physiological signals and physiological signals corresponding to motion artifacts. The objective of this embodiment is to remove the physiological signals corresponding to motion artifacts and obtain genuine physiological signals, i.e., to restore the original physiological signals. Motion signals of the subject are collected using a motion signal acquisition device (which can be a portable bioinformatics acquisition device), such as a sensor combining a three-axis gyroscope and a three-axis accelerometer to collect information from the subject's moving parts (e.g., arms, elbows, etc.), obtaining six channels of motion signals, which are then used... express.

[0066] Optionally, the physiological signal can be any one of the following: PPG signal, electroencephalogram (EEG) signal, electrocardiogram (ECG) signal, electromyogram (EMG) signal, electrooculogram (EOG) signal, blood oxygen saturation, respiratory signal, blood pressure, etc.

[0067] The following embodiments use PPG signals as physiological signals, PPG1 signals as the first physiological signal, and PPG2 signals as the second physiological signal to illustrate the human-centric intelligence-based physiological signal motion interference suppression method of this application. It is understood that other physiological signals, such as electroencephalogram (EEG) signals, electrocardiogram (ECG) signals, and electromyogram (EMG) signals, are also applicable to the method provided in this application.

[0068] Step S32: Filter the motion signal based on the correlation between the first physiological signal and the motion signal.

[0069] Specifically, the motion signal includes M channel signals. The Pearson correlation coefficient between the M channel signals and the PPG1 signal is calculated. Among the M channel signals, the channel signals whose absolute value of the Pearson correlation coefficient is less than a preset threshold are removed, resulting in N channel signals, where N≤M.

[0070] This application performs Pearson correlation analysis on motion signals and PPG1 signals to obtain the Pearson correlation coefficient, which can effectively measure the degree of correlation between motion signals and PPG signals containing motion interference, and quantify the influence of motion signals on PPG1 signals.

[0071] Taking the motion signals of the above six channels as an example, the Pearson correlation coefficients between the six channels and the PPG1 signal are calculated respectively, and the correlation coefficients are obtained. The correlation coefficient ranges from -1 to 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no linear correlation. If the absolute value of the correlation coefficient of a certain channel signal in the motion signal is close to 1, it indicates that there is a strong correlation between the channel signal and the PPG1 signal, suggesting that the channel signal may be the main source of motion artifacts in the PPG signal and has the most significant interference with the PPG signal.

[0072] Next, among the six channel signals, channel signals with absolute Pearson correlation coefficients less than a preset threshold are removed. The preset threshold ranges from [0,1]. For example, channel signals with absolute Pearson correlation coefficients less than 0.1 are removed. This process filters the six channel signals, removing those with minimal impact on the PPG1 signal and selecting those with a significant impact. This avoids introducing new noise into the adaptive filter after adding motion signals with minimal impact on the PPG signal, which would otherwise result in significant distortion of the PPG signal and affect the motion interference suppression effect.

[0073] It should be noted that, in addition to the Pearson correlation coefficient, Spearman correlation coefficient, Kendall rank correlation coefficient, etc. can also be used to analyze the correlation between the PPG1 signal and the motion signal, and signals with weak correlation with the PPG1 signal in the motion signal can be removed to avoid generating new noise in the adaptive filtering process and affecting the motion interference suppression effect.

[0074] In some optional embodiments, the PPG1 signal and motion signal can be filtered before step S32. Specifically, since the effective frequency band of the real PPG signal is [0.5, 8] Hz, and signals in other frequency bands are mostly noise, the acquired PPG1 signal is bandpass filtered at [0.5, 8] Hz. Motion signal Similarly, filtering needs to be performed based on the motion characteristics (such as motion frequency). For example, when the motion frequency is high, a bandpass filter of [10, 15] Hz can be used, while when the motion frequency is low, a bandpass filter of [1, 2] Hz can be used. Typically, a bandpass filter of [1, 4] Hz is chosen to filter the motion signal, which can remove high-frequency motion artifacts while retaining the low-frequency components related to the PPG signal.

[0075] By filtering the PPG1 signal and the motion signal, the effective frequency band information in the PPG1 signal is preserved, while the frequency components in the motion signal that are related to the PPG signal are also preserved. This increases the accuracy of the correlation analysis when performing correlation analysis on the PPG1 signal and the motion signal.

[0076] Step S33: Adaptive filtering algorithm is used to adaptively filter the filtered motion signal and the first physiological signal to obtain the second physiological signal.

[0077] Specifically, among the N channel signals obtained after filtering, the channel signals corresponding to Pearson correlation coefficients greater than 0 are classified as positive group signals, and the channel signals corresponding to Pearson correlation coefficients less than 0 are classified as negative group signals. Based on the grouping results, an adaptive filtering algorithm is used to adaptively filter the grouped motion signal and PPG1 signal to obtain the PPG2 signal. The adaptive filtering algorithm can be Least Mean Square (LMS), Recursive Least Squares (RLS), Normalized Least Mean Squares (NLMS), etc. This application uses the LMS adaptive filtering algorithm as an example for explanation. Figure 4 As shown, Figure 4 This is a block diagram of an LMS adaptive filter. The LMS adaptive filter has two inputs: a noisy signal and a reference signal.

[0078] In one embodiment, if all N channel signals are divided into positive or negative groups, the N channel signals are summed to obtain a first reference signal; the first reference signal and the PPG1 signal are input to a minimum mean square adaptive filter for adaptive filtering to obtain a PPG3 signal, which is used to characterize the PPG signal after adaptive filtering; the PPG3 signal is phase-aligned with the PPG1 signal to obtain a PPG2 signal.

[0079] With the above 6 channels Taking motion signals as an example, through screening, the Pearson correlation coefficients of the 6 channels were analyzed. The absolute values ​​of all values ​​are greater than or equal to the preset threshold, and If all values ​​are greater than 0, then the 6 channels form a positive signal group. ,Right now Contains [ The least mean square adaptive filter requires two inputs: the observed signal containing noise and the reference signal as the target. The PPG1 signal is used as the noisy signal. The six channel signals in the group are summed to form the first reference signal. The first reference signal and the PPG1 signal are then input into the minimum mean square adaptive filter for adaptive filtering to obtain the PPG3 signal. The PPG3 signal is used to characterize the PPG signal after adaptive filtering.

[0080] Because the filter shifts the phase of signals at different frequencies differently during the filtering process, the output signal will have a certain phase shift. To ensure that the PPG3 signal is phase-aligned with the original PPG signal and to avoid deviation, the adaptively filtered PPG signal needs to be phase-aligned. Specifically, convolving the PPG1 and PPG3 signals yields a signal representing the similarity between the two signals, with the maximum value corresponding to the point of greatest similarity between the two signals.

[0081] The calculation formula is as follows:

[0082]

[0083] Where t represents time and τ represents phase offset.

[0084] Based on the target phase offset τ corresponding to the maximum value in the convolution calculation result, the PPG3 signal is shifted along the time axis to align PPG3 and PPG1 on the time axis. Specifically, when τ > 0, the PPG3 signal data is shifted to the left (i.e., moved in the negative direction of the time axis), and when τ < 0, the PPG3 signal data is shifted to the right (i.e., moved in the positive direction of the time axis). If the shift causes insufficient data length in the PPG3 signal (i.e., missing data at the beginning or end of the PPG3 signal after the shift), these missing parts are filled with 0, and the PPG2 signal is finally obtained after phase alignment. Phase alignment improves the accuracy of subsequent analysis of the PPG2 signal and extraction of certain features (such as heart rate, HRV, etc.).

[0085] In another embodiment, if the N channel signals are divided into positive and negative groups, the positive and negative groups are sorted to obtain a first group and a second group of signals. The absolute value of the sum of the Pearson correlation coefficients corresponding to the first group of signals is greater than the absolute value of the sum of the Pearson correlation coefficients corresponding to the second group of signals. The channel signals in the first group are summed to obtain a second reference signal. The second reference signal and the PPG1 signal are input to a minimum mean square adaptive filter for the first adaptive filtering to obtain a PPG4 signal, which is used to characterize the PPG signal after the first adaptive filtering. The PPG4 signal is phase-aligned according to the PPG1 signal to obtain a PPG5 signal. The channel signals in the second group are summed to obtain a third reference signal. The third reference signal and the PPG5 signal are input to a minimum mean square adaptive filter for the second adaptive filtering to obtain a PPG6 signal, which is used to characterize the PPG signal after the second adaptive filtering. The PPG6 signal is phase-aligned according to the PPG1 signal to obtain a PPG2 signal.

[0086] Similarly, using the above 6 channels Taking motion signals as an example, through screening, the Pearson correlation coefficients of the 6 channels were analyzed. The absolute values ​​of all values ​​are greater than or equal to the preset threshold, and If it is greater than 0, then Forming a positive group signal ,Right now Contains [ ]; If less than 0, then Forming negative group signals ,Right now Contains [ Next, the positive group signal. and negative group signal The Pearson correlation coefficients in the equation are summed, and then the absolute value is calculated. ,as well as The group with the largest absolute value is designated as the first group of signals. The other group is designated as the second group of signals. Based on the calculation results, the first set of signals was obtained. for The second set of signals for .

[0087] right Channel signals within the group The summation is performed to obtain the second reference signal. The second reference signal and the PPG1 signal are then input into the minimum mean square adaptive filter for the first adaptive filtering to obtain the PPG4 signal. The PPG4 signal is used to characterize the PPG signal after the first adaptive filtering. The motion signal within the group is phase-aligned with the PPG1 signal to ensure that the PPG4 signal is in phase with... The alignment of motion signals within a group requires phase alignment of the PPG4 signal based on the PPG1 signal. This involves convolving the PPG4 and PP1 signals, and then shifting the PPG4 signal along the time axis based on the target phase offset corresponding to the maximum value in the convolution result to obtain the PPG5 signal. The specific implementation principle is detailed in the steps described above for phase alignment of the PPG3 signal with the original PPG signal, and will not be repeated here.

[0088] Next, regarding Channel signals within the group The summation yields the third reference signal. This third reference signal and the PPG5 signal are then input into a minimum mean square adaptive filter for a second adaptive filtering process, resulting in the PPG6 signal. The PPG6 signal characterizes the PPG signal after the second adaptive filtering. Following the same logic, to ensure the PPG6 signal is phase-aligned with the original PPG signal and avoid deviations, phase alignment of the adaptively filtered PPG signal is required. This is done by performing a convolution calculation on the PPG6 and PPG1 signals. Based on the target phase offset corresponding to the maximum value in the convolution result, the PPG6 signal is shifted along the time axis to obtain the PPG2 signal, which is the final PPG signal after motion interference suppression. The specific implementation principle is detailed in the steps described above for aligning the phase of the PPG3 signal with the original PPG signal, and will not be repeated here.

[0089] The running signals after threshold filtering are grouped, with channel signals corresponding to Pearson correlation coefficients greater than 0 classified as positive signals and those corresponding to Pearson correlation coefficients less than 0 classified as negative signals. If the motion signals can be classified into either positive or negative groups, the motion signals and motion-interferenced PPG signals are input into an adaptive filter for one adaptive filtering and one phase alignment to obtain motion-interference-suppressed PPG signals. If the motion signals can be classified into positive and negative groups, the positive and negative groups need to be sorted, followed by two adaptive filtering and two phase alignments to obtain motion-interference-suppressed PPG signals. This method effectively suppresses motion interference in the signals.

[0090] In this application, the correlation between the motion-interferenced physiological signal and the motion signal is analyzed, i.e., the degree of influence of the motion signal on the physiological signal is analyzed. Pearson correlation coefficients are calculated for multiple channels of the motion signal and the motion-interferenced physiological signal. The motion signal is then filtered, and channel signals with absolute Pearson correlation coefficients less than a preset threshold are removed, i.e., channel signals with less influence on the physiological signal are eliminated. An adaptive filtering algorithm is then used to adaptively filter both the filtered motion signal and the motion-interferenced physiological signal to obtain a motion-interference-suppressed physiological signal. This avoids the addition of motion signals with less influence to the physiological signal, which could generate new noise after adaptive filtering, leading to ineffective suppression of motion interference in the physiological signal and the inability to recover a relatively accurate original physiological signal.

[0091] As shown in Figures 5(a) and 5(b), these figures represent the results of the human-centric intelligence-based physiological signal motion interference suppression method provided in this application. Taking PPG signals as an example, the first row in Figures 5(a) and 5(b) shows PPG signals without motion interference, the second row shows PPG signals with motion interference, and the third row shows PPG signals using two sets of motion signals (…). The results of cascaded adaptive filtering are shown in Figures 5(a) and 5(b). The fourth row contains two groups of motion signals. As can be seen from the results, the waveform of the filtered PPG signal in the third row is similar to that of the original PPG signal in the first row, with the same number of peaks. This indicates that the method provided in this embodiment can effectively suppress motion interference in the signal.

[0092] Following the same line of thought, this application also provides a physiological signal motion interference suppression device based on human-centric intelligence, such as... Figure 6 This is a schematic diagram of the structure of the human-centric intelligence-based physiological signal motion interference suppression device provided in this application embodiment. The human-centric intelligence-based physiological signal motion interference suppression device 60 mainly includes:

[0093] The acquisition module 61 is used to acquire a first physiological signal and a motion signal, wherein the first physiological signal is used to characterize the physiological signal affected by motion interference;

[0094] The filtering module 62 is used to filter the motion signal based on the correlation between the first physiological signal and the motion signal;

[0095] The adaptive filtering module 63 is used to adaptively filter the filtered motion signal and the first physiological signal using an adaptive filtering algorithm to obtain a second physiological signal, which is used to characterize the physiological signal after suppressing motion interference.

[0096] In one possible implementation, the physiological signal is at least one of PPG signal, electroencephalogram (EEG) signal, electrocardiogram (ECG) signal, or electromyogram (EMG) signal.

[0097] In one possible implementation, the physiological signal is a PPG signal, the first physiological signal is a PPG1 signal, and the second physiological signal is a PPG2 signal.

[0098] In one possible implementation, the motion signal includes M channels, and the upper filtering module 62 can also be used for:

[0099] Calculate the Pearson correlation coefficients between the M channel signals and the PPG1 signal respectively;

[0100] From the M channel signals, the channel signals corresponding to those whose absolute value of the Pearson correlation coefficient is less than a preset threshold are removed, resulting in N channel signals, where N≤M.

[0101] In one possible implementation, the adaptive filtering module 63 can also be used for:

[0102] In N channel signals, the channel signals with a Pearson correlation coefficient greater than 0 are classified as positive signals, and the channel signals with a Pearson correlation coefficient less than 0 are classified as negative signals.

[0103] Based on the grouping results, an adaptive filtering algorithm is used to adaptively filter the grouped motion signal and PPG1 signal to obtain the PPG2 signal.

[0104] In one possible implementation, the adaptive filtering algorithm includes a least mean square adaptive filtering algorithm, and the adaptive filtering module 63 can also be used for:

[0105] If all N channel signals are divided into positive or negative groups, then the summation of the N channel signals is used to obtain the first reference signal.

[0106] The first reference signal and the PPG1 signal are input into the minimum mean square adaptive filter for adaptive filtering to obtain the PPG3 signal. The PPG3 signal is used to characterize the PPG signal after adaptive filtering.

[0107] The PPG2 signal is obtained by aligning the phase of the PPG3 signal with the PPG1 signal.

[0108] One possible implementation involves phase alignment of the PPG3 signal based on the PPG1 signal, including:

[0109] Perform convolution calculation on PPG1 and PPG3 signals;

[0110] The PPG3 signal is shifted along the time axis based on the target phase offset corresponding to the maximum value in the convolution calculation result.

[0111] In one possible implementation, the adaptive filtering algorithm includes a least mean square adaptive filtering algorithm, and the adaptive filtering module 63 can also be used for:

[0112] If N channel signals are divided into positive and negative groups, then the positive and negative groups are sorted into signal groups to obtain the first and second groups of signals. The absolute value of the sum of the Pearson correlation coefficients of the first group of signals is greater than the absolute value of the sum of the Pearson correlation coefficients of the second group of signals.

[0113] The channel signals in the first group of signals are summed to obtain the second reference signal;

[0114] The second reference signal and the PPG1 signal are input into the minimum mean square adaptive filter for the first adaptive filtering to obtain the PPG4 signal. The PPG4 signal is used to characterize the PPG signal after the first adaptive filtering.

[0115] PPG4 signal is phase-aligned based on PPG1 signal to obtain PPG5 signal;

[0116] The channel signals in the second group of signals are summed to obtain the third reference signal;

[0117] The third reference signal and the PPG5 signal are input into the minimum mean square adaptive filter for a second adaptive filtering to obtain the PPG6 signal. The PPG6 signal is used to characterize the PPG signal after the second adaptive filtering.

[0118] The PPG2 signal is obtained by aligning the phase of the PPG6 signal with the PPG1 signal.

[0119] In one possible implementation, the device 60 further includes a filtering module for filtering the first physiological signal and the motion signal before filtering the motion signal based on the correlation between the first physiological signal and the motion signal.

[0120] Figure 6 The physiological signal motion interference suppression device 60 based on human-cause intelligence provided in the illustrated embodiment can be used to execute the technical solution of the method embodiment shown in this application. Its implementation principle and technical effects can be further referred to the relevant description in the method embodiment.

[0121] The above should be understood Figure 6 The division of the modules in the human-centric intelligence-based physiological signal motion interference suppression device 60 shown is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or physically separated. These modules can be implemented entirely in software via processing elements; entirely in hardware; or partially in software via processing elements and partially in hardware. For example, the acquisition module can be a separate processing element or integrated into a chip in an electronic device. The implementation of other modules is similar. Furthermore, these modules can be fully or partially integrated together or implemented independently. During implementation, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0122] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs). Alternatively, these modules can be integrated together as a system-on-a-chip (SOC).

[0123] In the above embodiments, the processor may include, for example, a CPU, DSP, microcontroller, or digital signal processor, and may also include a GPU, embedded neural network processing unit (NPU), and image signal processor (ISP). The processor may also include necessary hardware accelerators or logic processing hardware circuits, such as an ASIC, or one or more integrated circuits for controlling the execution of the program in this application. Furthermore, the processor may have the function of operating one or more software programs, which may be stored in a storage medium.

[0124] This application also provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the methods provided in the embodiments shown in this application.

[0125] The following is combined Figure 7 The exemplary electronic devices provided in the embodiments of this application are further described. Figure 7 A schematic diagram of the structure of electronic device 7000 is shown.

[0126] The electronic device 7000 may include: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions (such as computer programs) that can be executed by the processor, and the processor calls and executes the program instructions to implement the human-centric intelligence-based physiological signal motion interference suppression method provided in the embodiments of this application.

[0127] Figure 7 A block diagram is shown of an exemplary electronic device 7000 suitable for implementing embodiments of this application. Figure 7 The electronic device 7000 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0128] like Figure 7 As shown, the electronic device 7000 is presented in the form of a general-purpose computing device. The components of the electronic device 7000 may include, but are not limited to: one or more processors 7010, memory 7020, communication bus 7040 connecting different system components (including memory 7020 and processor 7010), and communication interface 7030.

[0129] The 7040 communication bus represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0130] Electronic devices 7000 typically include a variety of computer system-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, removable and non-removable media.

[0131] The memory 7020 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. Although Figure 7As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disc drive for reading and writing to a removable non-volatile optical disc (e.g., a compact disc read-only memory (CD-ROM), a digital video disc read-only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to the communication bus 7040 via one or more data media interfaces. The memory 7020 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0132] A program / utility having a set (at least one) of program modules can be stored in memory 7020. Such program modules include, but are not limited to, an operating system, one or more applications, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules typically perform the functions and / or methods described in the embodiments of this application.

[0133] Electronic device 7000 can also communicate with one or more external devices (e.g., keyboard, pointing device, display, etc.), and with one or more devices that enable a user to interact with the electronic device, and / or with any device that enables the electronic device to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through communication interface 7030. Furthermore, electronic device 7000 can also communicate through a network adapter (… Figure 7 (Not shown) communicates with one or more networks (e.g., Local Area Network (LAN), Wide Area Network (WAN), and / or public networks, such as the Internet). The aforementioned network adapter can communicate with other modules of the electronic device via the communication bus 7040. It should be understood that, although... Figure 7 As not shown, other hardware and / or software modules can be used in conjunction with the electronic device 7000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, Redundant Arrays of Independent Drives (RAID) systems, tape drives, and data backup storage systems.

[0134] The processor 7010 executes various functional applications and data processing by running programs stored in the memory 7020, such as implementing the methods provided in the embodiments of this application.

[0135] It is understood that the interface connection relationships between the modules illustrated in the embodiments of this application are merely illustrative and do not constitute a structural limitation on the electronic device 7000. In other embodiments of this application, the electronic device 7000 may also employ different interface connection methods or combinations of multiple interface connection methods as described in the above embodiments.

[0136] In the above embodiments, the processor may include, for example, a CPU (Central Processing Unit), a DSP (Digital Signal Processor), a microcontroller, and may also include a GPU (Graphics Processing Unit), an embedded neural network processing unit (NPU), and an image signal processor (ISP). The processor may also include necessary hardware accelerators or logic processing hardware circuits, such as an ASIC (Application-Specific Integrated Circuit), or one or more integrated circuits for controlling the execution of the program in this application. Furthermore, the processor may have the function of operating one or more software programs, which may be stored in a storage medium.

[0137] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0138] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0139] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0140] The above description is merely a specific embodiment of this application. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. The protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for suppressing motion interference in physiological signals based on human-centric intelligence, characterized in that, The method includes: Acquire a first physiological signal and a motion signal, wherein the first physiological signal is used to characterize the physiological signal affected by motion interference, and the motion signal includes M channel signals; Based on the correlation between the first physiological signal and the motion signal, the M channel signals are filtered into N channel signals, where N≤M; An adaptive filtering algorithm is used to adaptively filter the N channel signals and the first physiological signal to obtain a second physiological signal, which is used to characterize the physiological signal after suppressing motion interference. Wherein, the physiological signal is a PPG signal, the first physiological signal is a PPG1 signal, the second physiological signal is a PPG2 signal, and the adaptive filtering algorithm includes a least mean square adaptive filtering algorithm; The step of adaptively filtering the N channel signals and the first physiological signal using an adaptive filtering algorithm to obtain the second physiological signal includes: Among the N channel signals, motion signals with a Pearson correlation coefficient greater than 0 are classified as positive signals, and motion signals with a Pearson correlation coefficient less than 0 are classified as negative signals. If all N channel signals are divided into positive or negative groups, then the N channel signals are summed to obtain the first reference signal. The first reference signal and the PPG1 signal are input into the minimum mean square adaptive filter for adaptive filtering to obtain the PPG3 signal, which is used to characterize the PPG signal after adaptive filtering. Perform convolution calculation on the PPG1 signal and the PPG3 signal; The PPG3 signal is shifted along the time axis based on the target phase offset corresponding to the maximum value in the convolution calculation result to obtain the PPG2 signal; or If the N channel signals are divided into positive group signals and negative group signals, then the positive group signals and negative group signals are sorted into signal groups to obtain the first group signals and the second group signals. The absolute value of the sum of the Pearson correlation coefficients corresponding to the first group signals is greater than the absolute value of the sum of the Pearson correlation coefficients corresponding to the second group signals. The channel signals in the first group of signals are summed to obtain the second reference signal; The second reference signal and the PPG1 signal are input into the minimum mean square adaptive filter for the first adaptive filtering to obtain the PPG4 signal, which is used to characterize the PPG signal after the first adaptive filtering. The PPG4 signal is phase-aligned based on the PPG1 signal to obtain the PPG5 signal; The channel signals in the second group of signals are summed to obtain the third reference signal; The third reference signal and the PPG5 signal are input into the minimum mean square adaptive filter for a second adaptive filtering to obtain the PPG6 signal, which is used to characterize the PPG signal after the second adaptive filtering. The PPG6 signal is phase-aligned based on the PPG1 signal to obtain the PPG2 signal.

2. The method according to claim 1, characterized in that, The step of filtering the M channel signals into N channel signals based on the correlation between the first physiological signal and the motion signal includes: Calculate the Pearson correlation coefficients between the M channel signals and the PPG1 signal respectively; From the M channel signals, the channel signals corresponding to those whose absolute value of the Pearson correlation coefficient is less than a preset threshold are removed, resulting in the N channel signals.

3. The method according to claim 1 or 2, characterized in that, Before filtering the motion signal based on the correlation between the first physiological signal and the motion signal, the method further includes: The PPG1 signal and the motion signal are filtered.

4. A physiological signal motion interference suppression device based on human-centric intelligence, characterized in that, The device includes: An acquisition module is used to acquire a first physiological signal and a motion signal. The first physiological signal is used to characterize the physiological signal affected by motion interference. The motion signal includes M channel signals. The filtering module is used to filter the M channel signals into N channel signals, where N≤M, based on the correlation between the first physiological signal and the motion signal; An adaptive filtering module is used to adaptively filter the N channel signals and the first physiological signal using an adaptive filtering algorithm to obtain a second physiological signal, which is used to characterize the physiological signal after suppressing motion interference. Wherein, the physiological signal is a PPG signal, the first physiological signal is a PPG1 signal, the second physiological signal is a PPG2 signal, and the adaptive filtering algorithm includes a least mean square adaptive filtering algorithm; The adaptive filtering module is also used for: Among the N channel signals, motion signals with a Pearson correlation coefficient greater than 0 are classified as positive signals, and motion signals with a Pearson correlation coefficient less than 0 are classified as negative signals. If all N channel signals are divided into positive or negative groups, then the N channel signals are summed to obtain the first reference signal. The first reference signal and the PPG1 signal are input into the minimum mean square adaptive filter for adaptive filtering to obtain the PPG3 signal, which is used to characterize the PPG signal after adaptive filtering. Perform convolution calculation on the PPG1 signal and the PPG3 signal; The PPG3 signal is shifted along the time axis based on the target phase offset corresponding to the maximum value in the convolution calculation result to obtain the PPG2 signal; or If the N channel signals are divided into positive group signals and negative group signals, then the positive group signals and negative group signals are sorted into signal groups to obtain the first group signals and the second group signals. The absolute value of the sum of the Pearson correlation coefficients corresponding to the first group signals is greater than the absolute value of the sum of the Pearson correlation coefficients corresponding to the second group signals. The channel signals in the first group of signals are summed to obtain the second reference signal; The second reference signal and the PPG1 signal are input into the minimum mean square adaptive filter for the first adaptive filtering to obtain the PPG4 signal, which is used to characterize the PPG signal after the first adaptive filtering. The PPG4 signal is phase-aligned based on the PPG1 signal to obtain the PPG5 signal; The channel signals in the second group of signals are summed to obtain the third reference signal; The third reference signal and the PPG5 signal are input into the minimum mean square adaptive filter for a second adaptive filtering to obtain the PPG6 signal, which is used to characterize the PPG signal after the second adaptive filtering. The PPG6 signal is phase-aligned based on the PPG1 signal to obtain the PPG2 signal.

5. An electronic device, characterized in that, include: A processor and a memory, wherein the memory is used to store a computer program; the processor is used to run the computer program to implement the human-based intelligent physiological signal motion interference suppression method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when run on a computer, implements the human-centric intelligence-based method for suppressing physiological signal motion interference as described in any one of claims 1-3.

Images