Respiratory signal extraction methods and devices, electronic equipment, and storage media

By extracting low-frequency signals and screening respiratory signals using Hilbert vibration decomposition, the problems of inaccurate respiratory signal extraction and high computational load in existing technologies are solved, achieving efficient and accurate respiratory signal extraction.

CN118228014BActive Publication Date: 2026-11-17SHENZHEN COMEN MEDICAL INSTR
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410334661.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-20
Publication Date
2026-11-17
Estimated Expiration
2044-03-20

AI Technical Summary

Technical Problem

Existing technologies for extracting respiratory signals from electrocardiogram signals have low accuracy and robustness, require a large amount of computation, and inaccurate reference point positioning leads to unsatisfactory extraction results.

Method used

By acquiring the initial electrocardiogram signal, low-frequency signal extraction and Hilbert vibration decomposition are performed to determine the energy ratio of the signal components. Finally, the signal component with the largest energy is selected as the target respiratory signal.

Benefits of technology

It reduces the computational load of respiratory signal extraction, improves the accuracy and robustness of respiratory signals, avoids errors caused by inaccurate benchmark positioning, and enhances the quality of extraction results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118228014B_ABST
    Figure CN118228014B_ABST
Patent Text Reader

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for extracting respiratory signals, relating to the field of computer technology. The respiratory signal extraction method includes: acquiring a preset initial electrocardiogram (ECG) signal and determining a target ECG signal based on the initial ECG signal; performing low-frequency signal extraction on the target ECG signal to determine candidate respiratory signals within the target ECG signal; performing Hilbert oscillation decomposition on the candidate respiratory signals to determine multiple signal components corresponding to the candidate respiratory signals; determining the energy ratio of each signal component, and selecting the signal component with the largest energy ratio as the target respiratory signal. The technical solution of this disclosure can effectively reduce the computational load of extracting target respiratory signals from ECG signals, improving the accuracy and robustness of the extracted target respiratory signals.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a method for extracting respiratory signals, a device for extracting respiratory signals, an electronic device, and a computer-readable storage medium. Background Technology

[0002] Respiratory signals are important physiological signals for detecting the human body's respiratory status. They are also a vital marker of life, representing the body's respiratory information and allowing for the diagnosis of important diseases, such as sleep apnea syndrome, based on respiratory signals and other signals. An electrocardiogram (ECG) reflects the electrical activity of the heart, depicting its rhythm and underlying pathological conditions. Important respiratory information is contained within ECG signals. Breathing causes changes in the thoracic cavity; during inhalation, the thoracic cavity expands, and during exhalation, it contracts, thus providing respiratory information within the ECG signal.

[0003] Currently, existing methods for extracting respiratory signals from electrocardiogram (ECG) signals either involve morphological extraction, which requires the localization of a reference point (the latter being prone to errors if the reference point is not located correctly, resulting in spurious respiratory signals and low accuracy and robustness), or extraction through filter design. However, this method typically requires complex filter design, leading to high computational costs and low extraction efficiency.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide a respiratory signal extraction method, a respiratory signal extraction device, an electronic device, and a computer-readable storage medium, thereby reducing computational load and improving the accuracy and robustness of the extracted target respiratory signal.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to a first aspect of the present disclosure, a respiratory signal extraction method is provided, comprising: acquiring a preset initial electrocardiogram (ECG) signal, and determining a target ECG signal based on the initial ECG signal; performing low-frequency signal extraction on the target ECG signal to determine candidate respiratory signals in the target ECG signal; performing Hilbert vibration decomposition on the candidate respiratory signals to determine multiple signal components corresponding to the candidate respiratory signals; determining the energy ratio of each signal component, and taking the signal component with the largest energy ratio among the signal components as the target respiratory signal.

[0008] In some example embodiments of this disclosure, based on the foregoing scheme, the step of extracting low-frequency signals from the target ECG signal to determine candidate respiratory signals in the target ECG signal includes: demodulating the target ECG signal using an energy operator to obtain the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal; and determining candidate respiratory signals in the target ECG signal based on the instantaneous amplitude envelope and the instantaneous frequency.

[0009] In some example embodiments of this disclosure, based on the foregoing scheme, the step of demodulating the target ECG signal using an energy operator to obtain the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal includes: demodulating the target ECG signal using an energy operator to obtain a signal energy function and a signal differential energy function; determining the amplitude envelope and frequency corresponding to the target ECG signal based on the signal energy function and the signal differential energy function; performing low-pass filtering on the amplitude envelope and the frequency to obtain the instantaneous amplitude envelope and instantaneous frequency; determining the remaining signal components through the amplitude envelope and the instantaneous amplitude envelope; performing energy judgment on the remaining signal components; if it is determined that the ratio of the energy of the remaining signal components to the energy of the target ECG signal is greater than or equal to a preset threshold, then re-demodulating the target ECG signal using an energy operator until the ratio of the energy of the remaining signal components to the energy of the target ECG signal is less than the preset threshold, thus determining that the demodulation of the target ECG signal using an energy operator is complete, and the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal are obtained.

[0010] In some exemplary embodiments of this disclosure, based on the foregoing scheme, the step of demodulating the target ECG signal using an energy operator to obtain a signal energy function and a signal differential energy function includes: demodulating the target ECG signal using an energy operator through the following relationship to obtain the signal energy function:

[0011]

[0012] Where ψ(x) represents the signal energy function, and x(t) represents the target electrocardiogram signal. This represents the first-order differential signal corresponding to the target electrocardiogram signal. The second-order differential signal corresponding to the target ECG signal is represented by the following relationship: The first-order differential signal corresponding to the target ECG signal is demodulated using an energy operator to obtain the signal differential energy function:

[0013]

[0014] in, This represents the differential energy function of the signal. This represents the third-order differential signal corresponding to the target electrocardiogram signal.

[0015] In some exemplary embodiments of this disclosure, based on the foregoing scheme, determining the amplitude envelope and frequency corresponding to the target ECG signal according to the signal energy function and the signal differential energy function includes: determining the amplitude envelope corresponding to the target ECG signal through the following relationship:

[0016]

[0017] The frequency corresponding to the target electrocardiogram signal is determined by the following relationship:

[0018]

[0019] Where |a(t)| represents the amplitude envelope of the target ECG signal, ω(t) represents the frequency of the target ECG signal, and ψ(x) represents the signal energy function. This represents the differential energy function of the signal.

[0020] In some example embodiments of this disclosure, based on the foregoing scheme, determining the signal component energy ratio corresponding to each of the signal components and taking the signal component with the largest signal component energy ratio as the target respiratory signal includes: performing a Fourier transform on the signal components to obtain signal spectrum data; constructing the signal component energy ratio corresponding to the signal components based on the signal spectrum data, and taking the signal component with the largest signal component energy ratio as the target respiratory signal.

[0021] In some exemplary embodiments of this disclosure, based on the foregoing scheme, determining the target ECG signal according to the initial ECG signal includes: filtering interference from the initial ECG signal using a preset notch filter to obtain an interference-filtered initial ECG signal; eliminating P waves and QRS waves in the interference-filtered initial ECG signal using a preset first median filter to obtain an intermediate ECG signal; eliminating T waves in the intermediate ECG signal using a preset second median filter to obtain an ECG signal baseline; and determining the target ECG signal based on the interference-filtered initial ECG signal and the ECG signal baseline.

[0022] According to a second aspect of the present disclosure, a respiratory signal extraction device is provided, comprising: an electrocardiogram (ECG) signal preprocessing module for acquiring a preset initial ECG signal and determining a target ECG signal based on the initial ECG signal; a candidate respiratory signal extraction module for performing low-frequency signal extraction on the target ECG signal to determine candidate respiratory signals in the target ECG signal; a candidate respiratory signal decomposition module for performing Hilbert vibration decomposition on the candidate respiratory signal to determine multiple signal components corresponding to the candidate respiratory signal; and a target respiratory signal filtering module for determining the energy ratio of each signal component and selecting the signal component with the largest energy ratio as the target respiratory signal.

[0023] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory storing computer-readable instructions that, when executed by the processor, implement the respiratory signal extraction method of the first aspect.

[0024] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the respiratory signal extraction method of the first aspect.

[0025] The technical solutions provided in this disclosure can include the following beneficial effects:

[0026] The respiratory signal extraction method in the example embodiments of this disclosure can acquire a preset initial electrocardiogram (ECG) signal, determine a target ECG signal based on the initial ECG signal, extract low-frequency signals from the target ECG signal, and determine candidate respiratory signals in the target ECG signal; then, the candidate respiratory signals can be decomposed using Hilbert vibration decomposition to determine multiple signal components corresponding to the candidate respiratory signals, and then the energy ratio of each signal component can be determined, and the signal component with the largest energy ratio among the signal components is taken as the target respiratory signal. On the one hand, candidate respiratory signals can be extracted from the target ECG signal first, and then Hilbert vibration decomposition can be performed on the candidate respiratory signals to obtain signal components. The target respiratory signal can then be screened by the energy ratio of each signal component. Compared with related solutions that require the design of complex filters to extract respiratory signals, this method can effectively reduce the amount of computation required for respiratory signal extraction and ensure the quality of the extracted respiratory signals. On the other hand, by extracting candidate respiratory signals and performing Hilbert vibration decomposition on them, effective respiratory signals can be screened. Compared with related solutions that require the location of reference points in the ECG signal, this method can effectively avoid the problem of poor accuracy and robustness of respiratory signal extraction results due to inaccurate reference point location, thus improving the accuracy and robustness of the extracted respiratory signals.

[0027] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0028] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0029] Figure 1 The schematic diagram illustrates a flow chart of a respiratory signal extraction method according to some embodiments of the present disclosure.

[0030] Figure 2 The schematic diagram illustrates a flow chart of energy operator demodulation of a target electrocardiogram signal according to some embodiments of the present disclosure.

[0031] Figure 3 The illustration shows a flowchart of screening target respiratory signals according to some embodiments of the present disclosure.

[0032] Figure 4 A schematic diagram of a respiratory signal extraction device according to some embodiments of the present disclosure is shown.

[0033] Figure 5 The schematic diagram illustrates the structural schematic of a computer system of an electronic device according to some embodiments of the present disclosure.

[0034] Figure 6 A schematic diagram of a computer-readable storage medium according to some embodiments of the present disclosure is shown.

[0035] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0036] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed in the appended claims.

[0037] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” as used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0038] It should be understood that although the terms first, second, third, etc., may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0039] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0040] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0041] Furthermore, the accompanying drawings are for illustrative purposes only and are not necessarily drawn to scale. The block diagrams shown in the drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0042] In this example embodiment, a respiratory signal extraction method is first provided. This respiratory signal extraction method can be applied to terminal devices or servers. This example embodiment does not make any special limitations on it. The following description uses the execution of this method on a terminal device as an example. Figure 1 A schematic flowchart illustrating a respiratory signal extraction method according to some embodiments of the present disclosure is shown. (Reference) Figure 1 As shown, the respiratory signal extraction method may include the following steps:

[0043] Step S110: Obtain a preset initial electrocardiogram signal, and determine the target electrocardiogram signal based on the initial electrocardiogram signal;

[0044] Step S120: Extract low-frequency signals from the target electrocardiogram signal to determine candidate respiratory signals in the target electrocardiogram signal;

[0045] Step S130: Perform Hilbert vibration decomposition on the candidate respiratory signal to determine multiple signal components corresponding to the candidate respiratory signal;

[0046] Step S140: Determine the energy ratio of each signal component, and take the signal component with the largest energy ratio as the target respiratory signal.

[0047] According to the respiratory signal extraction method in this example embodiment, on the one hand, candidate respiratory signals can be extracted from the target electrocardiogram signal first, and then Hilbert vibration decomposition can be performed on the candidate respiratory signals to obtain signal components. The target respiratory signal can be screened by the energy ratio of the corresponding signal components. Compared with the related solutions that require the design of complex filters to extract respiratory signals, this method can effectively reduce the amount of computation required to extract respiratory signals and ensure the quality of the extracted respiratory signals. On the other hand, by extracting candidate respiratory signals and performing Hilbert vibration decomposition on the candidate respiratory signals, effective respiratory signals can be screened. Compared with the related solutions that require the location of reference points in the electrocardiogram signal, this method can effectively avoid the problem of poor accuracy and robustness of respiratory signal extraction results due to inaccurate reference point location, and improve the accuracy and robustness of the extracted respiratory signals.

[0048] The respiratory signal extraction method in this example embodiment will be further described below.

[0049] In step S110, a preset initial electrocardiogram signal is acquired, and a target electrocardiogram signal is determined based on the initial electrocardiogram signal.

[0050] In one example embodiment of this disclosure, the initial electrocardiogram (ECG) signal refers to signal data obtained by monitoring the electrical activity inside the heart to depict the heart rhythm and its underlying pathological conditions. For example, the initial ECG signal can be acquired by attaching electrodes to the chest. The human body can be viewed as a loop in a circuit. When inhaling, the chest cavity expands, and the resistance of the electrodes increases, causing a change in the measured surface potential amplitude. Similarly, during exhalation, the chest cavity shrinks, and the resistance of the electrodes decreases, resulting in a corresponding change in the measured surface potential. In summary, the chest impedance changes due to changes in lung volume. Of course, the initial ECG signal can also be obtained from the Fantasia database. This example embodiment does not impose any special limitations on the method of acquiring the initial ECG signal.

[0051] The target ECG signal refers to the pure ECG signal obtained by filtering from the initial ECG signal. For example, the target ECG signal can be the ECG signal obtained by removing the P wave, QRS complex, and T wave from the initial ECG signal; or it can be the ECG signal obtained by removing electric field interference from the initial ECG signal using a notch filter. This example embodiment does not impose any special limitations on the filtering method of the target ECG signal.

[0052] In step S120, low-frequency signal extraction is performed on the target electrocardiogram signal to determine candidate respiratory signals in the target electrocardiogram signal.

[0053] In one example embodiment of this disclosure, a candidate respiratory signal refers to signal data that may be a respiratory signal extracted from a target electrocardiogram (ECG) signal. This can be achieved by extracting low-frequency signals from the target ECG signal and using these low-frequency signals as candidate respiratory signals. For example, candidate respiratory signals can be extracted from the target ECG signal using the Teager energy operator or a low-pass filter. This example embodiment does not impose any special limitations on the method of extracting low-frequency signals from the target ECG signal.

[0054] In step S130, the candidate respiratory signal is subjected to Hilbert vibration decomposition to determine multiple signal components corresponding to the candidate respiratory signal.

[0055] In one example embodiment of this disclosure, Hilbert Vibration Decomposition (HVD) is a nonlinear and non-stationary signal analysis method used to decompose complex signals into a set of vibration modes with different natural frequencies. Multiple signal components corresponding to a candidate respiratory signal can be determined by performing Hilbert Vibration Decomposition on the candidate respiratory signal.

[0056] In step S140, the energy ratio of each signal component is determined, and the signal component with the largest energy ratio is taken as the target respiratory signal.

[0057] In one example embodiment of this disclosure, the signal component energy ratio refers to the ratio used to screen valid respiratory signals. It can be obtained by performing Fourier transform on each signal component to obtain spectral data, and then the signal component energy ratio corresponding to each signal component can be determined based on the spectral data of the signal components.

[0058] The target respiratory signal refers to the effective respiratory signal obtained through screening. The signal component with the largest energy ratio among the signal components can be used as the target respiratory signal.

[0059] The target respiratory signal is filtered by the energy ratio of each signal component. Compared with the complex filter design required for respiratory signal extraction in related schemes, this method can effectively reduce the computational load required for respiratory signal extraction and ensure the quality of the extracted respiratory signal. By extracting candidate respiratory signals and performing Hilbert oscillation decomposition on them, effective respiratory signals can be filtered. Compared with the method of locating a reference point in the electrocardiogram signal in related schemes, this method can effectively avoid the problem of poor accuracy and robustness of respiratory signal extraction results due to inaccurate reference point location, and improve the accuracy and robustness of the extracted respiratory signal.

[0060] The contents of steps S110 to S140 are described in detail below.

[0061] In one example embodiment of this disclosure, the determination of a target electrocardiogram (ECG) signal based on an initial ECG signal can be achieved through the following steps, specifically including:

[0062] The initial electrocardiogram (ECG) signal can be filtered out of interference using a preset notch filter to obtain an interference-filtered initial ECG signal. Then, the P wave and QRS wave in the interference-filtered initial ECG signal can be eliminated using a preset first median filter to obtain an intermediate ECG signal. The T wave in the intermediate ECG signal can be eliminated using a preset second median filter to obtain the ECG signal baseline. Finally, the target ECG signal can be determined based on the interference-filtered initial ECG signal and the ECG signal baseline.

[0063] The preset notch filter refers to a notch filter that is pre-set to remove power line interference in the initial electrocardiogram signal. For example, the preset notch filter can be a 60Hz notch filter. Of course, other specific frequencies of the preset notch filter can be customized according to the actual use. This example embodiment does not make any special limitations on this.

[0064] The first median filter and the second median filter refer to pre-set filters used to eliminate P waves, QRS waves and T waves in the initial electrocardiogram signal. For example, the first median filter can be a 200ms median filter and the second median filter can be a 600ms median filter. Of course, this is only an illustrative example. The specific median filters for eliminating P waves, QRS waves and T waves in the initial electrocardiogram signal can be customized according to the actual situation. This example embodiment does not impose any special limitations on this.

[0065] By using a preset notch filter, a first median filter, and a second median filter, interference data unrelated to the effective respiratory signal in the initial electrocardiogram (ECG) signal can be effectively removed, resulting in an ECG signal baseline. Then, the ECG signal baseline can be subtracted from the interference-filtered initial ECG signal to obtain a pure, interference-free target ECG signal, effectively reducing the influence of interference data and ensuring the accuracy of the extracted target respiratory signal.

[0066] In one example embodiment of this disclosure, low-frequency signal extraction of the target electrocardiogram (ECG) signal can be achieved through the following steps to determine candidate respiratory signals in the target ECG signal:

[0067] The target ECG signal can be demodulated using an energy operator to obtain the instantaneous amplitude envelope and instantaneous frequency of the target ECG signal. Based on the instantaneous amplitude envelope and instantaneous frequency, candidate respiratory signals in the target ECG signal can be determined.

[0068] Optionally, the energy operator demodulation of the target ECG signal can be achieved through the following steps to obtain the instantaneous amplitude envelope and instantaneous frequency of the target ECG signal, including:

[0069] The target ECG signal can be demodulated using energy operators, such as the Teager energy operator, to obtain the signal energy function and the signal differential energy function. Then, based on these functions, the amplitude envelope and frequency of the target ECG signal can be determined. The amplitude envelope and frequency are then low-pass filtered to obtain the instantaneous amplitude envelope and instantaneous frequency. The remaining signal components are determined using the amplitude envelope and instantaneous amplitude envelope. An energy decision is made on the remaining signal components. If the ratio of the energy of the remaining signal components to the energy of the target ECG signal is greater than or equal to a preset threshold, the target ECG signal is demodulated again using energy operators until the ratio is less than the preset threshold. This completes the demodulation of the target ECG signal using energy operators, yielding the instantaneous amplitude envelope and instantaneous frequency of the target ECG signal.

[0070] Optionally, the target ECG signal can be demodulated using an energy operator through relation (1) to obtain the signal energy function:

[0071]

[0072] Where ψ(x) can represent the signal energy function, and x(t) can represent the target electrocardiogram signal. It can represent the first-order differential signal corresponding to the target electrocardiogram signal. It can represent the second-order differential signal corresponding to the target electrocardiogram signal.

[0073] The energy operator demodulation of the first-order differential signal corresponding to the target electrocardiogram signal can be achieved through relation (2), resulting in the signal differential energy function:

[0074]

[0075] in, It can represent the differential energy function of the signal. It can represent the first-order differential signal corresponding to the target electrocardiogram signal. It can represent the second-order differential signal corresponding to the target electrocardiogram signal. It can represent the third-order differential signal corresponding to the target electrocardiogram signal.

[0076] Optionally, the calculated signal energy function ψ(x) and signal differential energy function can be... Zero-phase low-pass filtering is used to remove high-frequency error components, resulting in the signal energy function and signal differential energy function with the smallest error. The amplitude envelope corresponding to the target ECG signal can then be obtained through equation (3).

[0077]

[0078] The frequency corresponding to the target electrocardiogram signal can be determined by relation (4):

[0079]

[0080] Where |a(t)| can represent the amplitude envelope of the target ECG signal, ω(t) can represent the frequency of the target ECG signal, and ψ(x) can represent the signal energy function. It can represent the differential energy function of a signal.

[0081] Figure 2 The schematic diagram illustrates a flow chart of energy operator demodulation of a target electrocardiogram signal according to some embodiments of the present disclosure.

[0082] refer to Figure 2 As shown, in step S210, the target ECG signal is acquired; in step S220, the target ECG signal is demodulated using the Teager energy operator to obtain the signal energy function and the signal differential energy function. For example, the energy operator demodulation of the target ECG signal can be achieved using relation (1) and relation (2) to obtain the signal energy function and the signal differential energy function; in step S230, the signal energy function and the signal differential energy function are separated to obtain the amplitude envelope and the frequency corresponding to the target ECG signal. For example, the energy separation of the signal energy function and the signal differential energy function can be achieved using relation (3) and relation (4). Step S240: Low-pass filtering is performed on the amplitude envelope and frequency corresponding to the target ECG signal to obtain the instantaneous amplitude envelope and instantaneous frequency; Step S250: The amplitude envelope and instantaneous amplitude envelope are subtracted, i.e., the remaining signal components are determined by subtracting the instantaneous amplitude envelope from the amplitude envelope; Step S260: Energy determination is performed on the remaining signal components. If the ratio of the energy of the remaining signal components to the energy of the target ECG signal is greater than or equal to a preset threshold, the process returns to step S230 until the ratio of the energy of the remaining signal components to the energy of the target ECG signal is less than the preset threshold, thus confirming the completion of the Teager energy operator demodulation of the target ECG signal.

[0083] Optionally, after demodulating the target ECG signal using the energy operator, candidate respiratory signals can be determined from the instantaneous amplitude envelope and instantaneous frequency. For example, since respiratory signals are low-frequency signals, candidate respiratory signals can be extracted based on the initial iteration or a low-order iteration of the Teager energy operator demodulation. in, This can represent the extracted candidate respiratory signals, b j,k (t) can represent the instantaneous amplitude envelope obtained after k iterations, ω j,k (t) can represent the instantaneous frequency obtained after k iterations, where k can represent the number of iterations.

[0084] Optionally, after extracting the candidate respiratory signal from the target ECG signal, the candidate respiratory signal can be subjected to Hilbert vibration decomposition to determine multiple signal components corresponding to the candidate respiratory signal. For example, after performing Hilbert vibration decomposition on the candidate respiratory signal, a set of multiple slowly changing signal components can be obtained, i.e. in, It can represent multiple signal components corresponding to a candidate respiratory signal, b j,1 ω can represent the instantaneous amplitude envelope obtained after one iteration. j,k (dt) can represent the instantaneous amplitude envelope obtained after k iterations, and j can represent the signal component corresponding to the j-th maximum energy.

[0085] In one example embodiment of this disclosure, it can be achieved through Figure 3 The steps in the process determine the energy ratio of each signal component, referring to... Figure 3 As shown, it can specifically include:

[0086] Step S310: Perform Fourier transform on the signal components to obtain signal spectrum data;

[0087] Step S320: Construct the signal component energy ratio corresponding to the signal component based on the signal spectrum data, and take the signal component with the largest signal component energy ratio as the target respiratory signal.

[0088] The Fourier transform is a linear integral transform used to transform signals between the time (or spatial) domain and the frequency domain. By converting signal components to the frequency domain, accurate target respiratory signals can be effectively filtered out.

[0089] The signal components can be subjected to Fourier transform to obtain the signal spectrum data. Then, the energy ratio of the corresponding signal components can be constructed based on the signal spectrum data. For example, the energy ratio of the signal components can be expressed as the relationship (5):

[0090]

[0091] Among them, P j It can represent the ratio of the energy of the corresponding signal components. It can represent the signal spectrum data corresponding to each signal component.

[0092] The energy ratio of each signal component is calculated by formula (5). For example, the energy ratio of each signal component can be P1, P2, P3, P4, P5, ... Then the signal component corresponding to the maximum value of the energy ratio of each signal component, i.e. MAX(P1, P2, P3, P4, P5, ...), can be taken as the target respiratory signal.

[0093] Optionally, after the target respiratory signal is obtained through screening, it can be post-processed by a bandpass filter to obtain the final respiratory signal. For example, the target respiratory signal can be post-processed by a bandpass filter of 0.1-0.5Hz. Of course, other frequency bandpass filters can also be used. This example embodiment does not make any special limitation on this.

[0094] In summary, the respiratory signal extraction method of this disclosure can acquire a preset initial electrocardiogram (ECG) signal, determine a target ECG signal based on the initial ECG signal, extract low-frequency signals from the target ECG signal, and identify candidate respiratory signals in the target ECG signal. Then, the candidate respiratory signals can be decomposed using Hilbert vibration decomposition to determine multiple signal components corresponding to the candidate respiratory signals. Furthermore, the energy ratio of each signal component can be determined, and the signal component with the largest energy ratio among the signal components is taken as the target respiratory signal. On the one hand, candidate respiratory signals can be extracted from the target ECG signal first, and then Hilbert vibration decomposition can be performed on the candidate respiratory signals to obtain signal components. The target respiratory signal can then be screened by the energy ratio of each signal component. Compared with related solutions that require the design of complex filters to extract respiratory signals, this method can effectively reduce the amount of computation required for respiratory signal extraction and ensure the quality of the extracted respiratory signals. On the other hand, by extracting candidate respiratory signals and performing Hilbert vibration decomposition on them, effective respiratory signals can be screened. Compared with related solutions that require the location of reference points in the ECG signal, this method can effectively avoid the problem of poor accuracy and robustness of respiratory signal extraction results due to inaccurate reference point location, thus improving the accuracy and robustness of the extracted respiratory signals.

[0095] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0096] Furthermore, in this exemplary embodiment, a respiratory signal extraction device is also provided. (Refer to...) Figure 4 As shown, the respiratory signal extraction device 400 includes: an electrocardiogram signal preprocessing module 410, a candidate respiratory signal extraction module 420, a candidate respiratory signal decomposition module 430, and a target respiratory signal screening module 440. Wherein:

[0097] The electrocardiogram signal preprocessing module 410 is used to acquire a preset initial electrocardiogram signal and determine the target electrocardiogram signal based on the initial electrocardiogram signal.

[0098] The candidate respiratory signal extraction module 420 is used to extract low-frequency signals from the target electrocardiogram signal and determine candidate respiratory signals in the target electrocardiogram signal.

[0099] The candidate respiratory signal decomposition module 430 is used to perform Hilbert vibration decomposition on the candidate respiratory signal to determine multiple signal components corresponding to the candidate respiratory signal.

[0100] The target respiratory signal screening module 440 is used to determine the energy ratio of each signal component and to take the signal component with the largest energy ratio as the target respiratory signal.

[0101] In some example embodiments of this disclosure, based on the foregoing scheme, the candidate respiratory signal extraction module 420 can be used to: demodulate the target electrocardiogram signal using an energy operator to obtain the instantaneous amplitude envelope and instantaneous frequency corresponding to the target electrocardiogram signal; and determine the candidate respiratory signal in the target electrocardiogram signal based on the instantaneous amplitude envelope and the instantaneous frequency.

[0102] In some example embodiments of this disclosure, based on the foregoing scheme, the candidate respiratory signal extraction module 420 can be used to: demodulate the target ECG signal using an energy operator to obtain a signal energy function and a signal differential energy function; determine the amplitude envelope and frequency corresponding to the target ECG signal based on the signal energy function and the signal differential energy function; perform low-pass filtering on the amplitude envelope and the frequency to obtain an instantaneous amplitude envelope and an instantaneous frequency; determine the remaining signal components using the amplitude envelope and the instantaneous amplitude envelope; perform energy judgment on the remaining signal components; if it is determined that the ratio of the energy of the remaining signal components to the energy of the target ECG signal is greater than or equal to a preset threshold, then demodulate the target ECG signal again using an energy operator until the ratio of the energy of the remaining signal components to the energy of the target ECG signal is less than the preset threshold, and determine that the demodulation of the target ECG signal using an energy operator is completed, thereby obtaining the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal.

[0103] In some exemplary embodiments of this disclosure, based on the foregoing scheme, the candidate respiratory signal extraction module 420 can be used to: demodulate the target electrocardiogram signal using an energy operator through the following relationship to obtain a signal energy function:

[0104]

[0105] Where ψ(x) represents the signal energy function, and x(t) represents the target electrocardiogram signal. This represents the first-order differential signal corresponding to the target electrocardiogram signal. The second-order differential signal corresponding to the target ECG signal is represented by the following relationship: The first-order differential signal corresponding to the target ECG signal is demodulated using an energy operator to obtain the signal differential energy function:

[0106]

[0107] in, This represents the differential energy function of the signal. This represents the third-order differential signal corresponding to the target electrocardiogram signal.

[0108] In some example embodiments of this disclosure, based on the foregoing scheme, the candidate respiratory signal extraction module 420 can be used to: determine the amplitude envelope corresponding to the target electrocardiogram signal through the following relationship:

[0109]

[0110] The frequency corresponding to the target electrocardiogram signal is determined by the following relationship:

[0111]

[0112] Where |a(t)| represents the amplitude envelope of the target ECG signal, ω(t) represents the frequency of the target ECG signal, and ψ(x) represents the signal energy function. This represents the differential energy function of the signal.

[0113] In some example embodiments of this disclosure, based on the foregoing scheme, the target respiratory signal screening module 440 can be used to: perform Fourier transform on the signal components to obtain signal spectrum data; construct the signal component energy ratio corresponding to the signal components based on the signal spectrum data, and take the signal component with the largest signal component energy ratio as the target respiratory signal.

[0114] In some example embodiments of this disclosure, based on the foregoing scheme, the ECG signal preprocessing module 410 can be used to: filter interference from the initial ECG signal using a preset notch filter to obtain an interference-filtered initial ECG signal; eliminate the P wave and QRS wave in the interference-filtered initial ECG signal using a preset first median filter to obtain an intermediate ECG signal; eliminate the T wave in the intermediate ECG signal using a preset second median filter to obtain an ECG signal baseline; and determine the target ECG signal based on the interference-filtered initial ECG signal and the ECG signal baseline.

[0115] The specific details of each module of the respiratory signal extraction device mentioned above have been described in detail in the corresponding respiratory signal extraction methods, so they will not be repeated here.

[0116] It should be noted that although several modules or units of the respiratory signal extraction device have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0117] Furthermore, in an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described respiratory signal extraction method is also provided.

[0118] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be embodied in the following forms: a completely hardware embodiment, a completely software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0119] The following reference Figure 5 To describe an electronic device 500 according to such an embodiment of the present disclosure. Figure 5 The electronic device 500 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0120] like Figure 5 As shown, the electronic device 500 is manifested in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including storage unit 520 and processing unit 510), and a display unit 540.

[0121] The storage unit stores program code that can be executed by the processing unit 510, causing the processing unit 510 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 510 can perform actions such as... Figure 1 The steps shown in step S110 involve acquiring a preset initial electrocardiogram (ECG) signal and determining a target ECG signal based on the initial ECG signal; step S120 involves extracting low-frequency signals from the target ECG signal to determine candidate respiratory signals in the target ECG signal; step S130 involves performing Hilbert vibration decomposition on the candidate respiratory signals to determine multiple signal components corresponding to the candidate respiratory signals; and step S140 involves determining the energy ratio of each signal component and taking the signal component with the largest energy ratio as the target respiratory signal.

[0122] Storage unit 520 may include readable media in the form of volatile storage units, such as random access memory (RAM) 521 and / or cache memory 522, and may further include read-only memory (ROM) 523.

[0123] Storage unit 520 may also include a program / utility 524 having a set (at least one) program module 525, such program module 525 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0124] Bus 530 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0125] Electronic device 500 can also communicate with one or more external devices 570 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 500, and / or with any device that enables electronic device 500 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 550. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 560. As shown, network adapter 560 communicates with other modules of electronic device 500 via bus 530. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0126] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0127] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of this disclosure may also be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0128] refer to Figure 6 As shown, a program product 600 for implementing the above-described respiratory signal extraction method according to an embodiment of the present disclosure is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0129] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0130] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0131] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0132] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0133] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0134] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0135] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0136] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for extracting respiratory signals, characterized in that, include: Acquire a preset initial electrocardiogram (ECG) signal, and determine the target ECG signal based on the initial ECG signal; Low-frequency signal extraction is performed on the target electrocardiogram signal to determine candidate respiratory signals in the target electrocardiogram signal; The candidate respiratory signal is subjected to Hilbert vibration decomposition to determine multiple signal components corresponding to the candidate respiratory signal; Determine the energy ratio of each signal component, and take the signal component with the largest energy ratio as the target respiratory signal. The step of extracting low-frequency signals from the target electrocardiogram (ECG) signal to determine candidate respiratory signals within the target ECG signal includes: The target ECG signal is demodulated using an energy operator to obtain the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal; Based on the instantaneous amplitude envelope and the instantaneous frequency, candidate respiratory signals in the target electrocardiogram signal are determined; The step of demodulating the target ECG signal using an energy operator to obtain the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal includes: The target electrocardiogram signal is demodulated using an energy operator to obtain the signal energy function and the signal differential energy function; The amplitude envelope and frequency of the target electrocardiogram signal are determined based on the signal energy function and the signal differential energy function. The amplitude envelope and the frequency are low-pass filtered to obtain the instantaneous amplitude envelope and instantaneous frequency; The remaining signal components are determined using the amplitude envelope and the instantaneous amplitude envelope; Energy determination is performed on the remaining signal components. If it is determined that the ratio of the energy of the remaining signal components to the energy of the target ECG signal is greater than or equal to a preset threshold, the target ECG signal is demodulated again using the energy operator until the ratio of the energy of the remaining signal components to the energy of the target ECG signal is less than the preset threshold. It is then determined that the energy operator demodulation of the target ECG signal is complete, and the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal are obtained.

2. The respiratory signal extraction method according to claim 1, characterized in that, The step of demodulating the target electrocardiogram signal using an energy operator to obtain the signal energy function and the signal differential energy function includes: The target ECG signal is demodulated using an energy operator through the following relationship to obtain the signal energy function: in, This represents the signal energy function. This represents the target electrocardiogram signal. This represents the first-order differential signal corresponding to the target electrocardiogram signal. This represents the second-order differential signal corresponding to the target electrocardiogram signal; The energy operator demodulation of the first-order differential signal corresponding to the target electrocardiogram signal is performed using the following relationship to obtain the signal differential energy function: in, This represents the differential energy function of the signal. This represents the third-order differential signal corresponding to the target electrocardiogram signal.

3. The respiratory signal extraction method according to claim 1, characterized in that, The step of determining the amplitude envelope and frequency corresponding to the target electrocardiogram signal based on the signal energy function and the signal differential energy function includes: The amplitude envelope corresponding to the target electrocardiogram signal is determined by the following relationship: The frequency corresponding to the target electrocardiogram signal is determined by the following relationship: in, This represents the amplitude envelope corresponding to the target electrocardiogram signal. This indicates the frequency corresponding to the target electrocardiogram signal. This represents the signal energy function. This represents the differential energy function of the signal.

4. The respiratory signal extraction method according to claim 1, characterized in that, The step of determining the energy ratio of each signal component and taking the signal component with the largest energy ratio as the target respiratory signal includes: The signal components are subjected to Fourier transform to obtain the signal spectrum data; The energy ratio of the signal components corresponding to the signal components is constructed based on the signal spectrum data, and the signal component with the largest energy ratio among the signal components is taken as the target respiratory signal.

5. The respiratory signal extraction method according to claim 1, characterized in that, Determining the target electrocardiogram signal based on the initial electrocardiogram signal includes: The initial electrocardiogram signal is filtered out of interference by a preset notch filter to obtain the initial electrocardiogram signal after interference removal. The P wave and QRS wave in the initial electrocardiogram signal after interference filtering are eliminated by a preset first median filter to obtain an intermediate electrocardiogram signal. The T wave in the intermediate electrocardiogram signal is eliminated by a preset second median filter to obtain the baseline of the electrocardiogram signal; The target ECG signal is determined based on the initial ECG signal after interference filtering and the ECG signal baseline.

6. A respiratory signal extraction device, characterized in that, include: An electrocardiogram (ECG) signal preprocessing module is used to acquire a preset initial ECG signal and determine a target ECG signal based on the initial ECG signal. A candidate respiratory signal extraction module is used to extract low-frequency signals from the target electrocardiogram signal and determine candidate respiratory signals in the target electrocardiogram signal. The candidate respiratory signal decomposition module is used to perform Hilbert vibration decomposition on the candidate respiratory signal to determine multiple signal components corresponding to the candidate respiratory signal. The target respiratory signal screening module is used to determine the energy ratio of each signal component and to take the signal component with the largest energy ratio as the target respiratory signal. The candidate respiratory signal extraction module is used to extract low-frequency signals from the target electrocardiogram signal and determine candidate respiratory signals in the target electrocardiogram signal, including: The target ECG signal is demodulated using an energy operator to obtain the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal; Based on the instantaneous amplitude envelope and the instantaneous frequency, candidate respiratory signals in the target electrocardiogram signal are determined; The candidate respiratory signal extraction module is further configured to perform energy operator demodulation on the target ECG signal to obtain the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal, including: The target electrocardiogram signal is demodulated using an energy operator to obtain the signal energy function and the signal differential energy function; The amplitude envelope and frequency of the target electrocardiogram signal are determined based on the signal energy function and the signal differential energy function. The amplitude envelope and the frequency are low-pass filtered to obtain the instantaneous amplitude envelope and instantaneous frequency; The remaining signal components are determined using the amplitude envelope and the instantaneous amplitude envelope; Energy determination is performed on the remaining signal components. If it is determined that the ratio of the energy of the remaining signal components to the energy of the target ECG signal is greater than or equal to a preset threshold, the target ECG signal is demodulated again using the energy operator until the ratio of the energy of the remaining signal components to the energy of the target ECG signal is less than the preset threshold. It is then determined that the energy operator demodulation of the target ECG signal is complete, and the instantaneous amplitude envelope and instantaneous frequency corresponding to the target ECG signal are obtained.

7. An electronic device, comprising: processor; as well as A memory storing computer-readable instructions that, when executed by the processor, implement the respiratory signal extraction method as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the respiratory signal extraction method as described in any one of claims 1 to 5.

Citation Information

Patent Citations

  • Respiratory rate extraction method and device

    CN106725487A

  • Respiratory frequency estimation method and device, equipment and storage medium

    CN113642440A