Wearable multi-parameter physiological information monitoring system

Abstract

The invention relates to the technical field of medical care informatics, in particular to a wearable multi-parameter physiological information monitoring system. The system comprises a wearing detection module and a data analysis module. The wearing detection module is provided with an electrocardio sensor and a thoracic piezoelectric sensor; the electrocardio sensor and the thoracic piezoelectric sensor are used for collecting initial electrocardio signals and thoracic motion signals of a user respectively. And the data analysis module is used for performing noise filtering on the initial electrocardiosignal according to the thoracic motion signal. As the EMG signal is difficult to collect and has many interferences, when the adaptive filter is designed, the EMG signal is prevented from being directly collected as a noise source, and a piezoelectric signal caused by thoracic motion is used as the noise source, so that the signal output by the filter is closer to an ideal state. In the filtering process, the electric signals with the myoelectricity characteristics are deleted after the initial electrocardiosignals, so that the initial electrocardiosignals without myoelectricity interference can output a more accurate electrocardiogram.

Description

Technical Field

[0001] The present application relates to the technical field of medical care informatics, and in particular to a wearable multi-parameter physiological information monitoring system. Background Art

[0002] Wearable physiological monitoring devices are medical devices that integrate biosensors, signal acquisition and processing, data communication and other modules. They can monitor multiple physiological indicators or perform physiological treatments during daily wear.

[0003] In existing physiological monitoring systems, ECG signals are generally collected by sticking electrode patches on the body surface. The voltage amplitude of the ECG signal (i.e., electrocardiogram signal) detected by the electrode patch is a few millivolts, so there are inevitably interferences from various noise sources during collection, such as power frequency signals, myoelectric interference, etc.

[0004] In the existing initial ECG signal processing method, in order to eliminate noise, filtering is usually performed based on the frequency characteristics of the noise, such as a bandpass filter. The existing filter has a good filtering effect on interference with frequency characteristics that are significantly different from the ECG signal, but the filtering effect on EMG signals (i.e., electromyographic signals) is not good. The frequency of power frequency interference is generally around 50HZ, that is, there is a significant difference between the frequency characteristics of power frequency interference and bioelectric signals. By setting a bandpass filter, the interference signal in this frequency band can be filtered out.

[0005] However, for EMG signals, which are also bioelectric signals, their frequency characteristics are irregular depending on the body's condition, resulting in the inability of existing filters to effectively filter EMG signals.

[0006] At present, the ECG signals collected by the electrode patch solution are inevitably mixed with the EMG signals, because the electrode patches on the body surface will be interfered by the electrical signals generated by chest breathing.

[0007] In order to filter myoelectric noise signals when monitoring electrocardiogram signals, the present application provides a wearable multi-parameter physiological information monitoring system. Summary of the invention

[0008] In order to overcome the problems existing in the related art, the present application provides a wearable multi-parameter physiological information monitoring system, including: a wear detection module and a data analysis module;

[0009] The wear detection module is communicatively connected to the data analysis module;

[0010] The wear detection module is worn on the user, and is provided with an electrocardiogram sensor and a chest piezoelectric sensor;

[0011] The electrocardiogram sensor and the chest piezoelectric sensor are used to collect the user's initial electrocardiogram signal and chest movement signal respectively;

[0012] The initial electrocardiogram signal is a clutter signal mixed with an EMG signal and an ECG signal; the chest piezoelectric sensor is in contact with and fixed to the chest of the user, and the chest piezoelectric sensor is used to output the chest movement signal caused by chest movement;

[0013] The data analysis module is used to perform noise filtering on the initial electrocardiogram signal according to the chest movement signal.

[0014] In one embodiment, it also includes a monitoring vest; the wear detection module is fixed on the monitoring vest, the electrocardiogram sensor is arranged on the front of the monitoring vest, and the electrocardiogram sensor includes M electrode patches, and the electrode patches are attached to the user's body surface after being worn, and M is an integer greater than or equal to 2.

[0015] In one embodiment, the piezoelectric chest sensor is disposed on the back of the monitoring vest.

[0016] In one embodiment, the piezoelectric sensor for the chest includes an elastic band, a dielectric layer, and a lead wire;

[0017] The elastic band is arranged on the vest body around the middle of the thorax; the two ends of the elastic band are respectively connected to the two side surfaces of the dielectric layer, and the electrodes on the upper and lower surfaces of the dielectric layer are connected to the data analysis module through the lead wire communication.

[0018] In one embodiment, the dielectric layer is a dielectric elastomer; the dielectric elastomer is provided with a positive electrode and a negative electrode, and the positive electrode and the negative electrode are respectively connected to the data analysis module through lead wires.

[0019] In one implementation, the data analysis module is used to perform noise filtering on the initial ECG signal according to the chest motion signal, specifically including:

[0020] S1, build a noise canceller;

[0021] S2, collecting the initial ECG signal and the chest movement signal and inputting them into the noise canceller;

[0022] S3, iterating the noise canceller and updating the weight coefficient;

[0023] S4. Deploy the noise canceller after iteration in the data analysis module.

[0024] In one embodiment, the noise canceller includes a main signal input terminal, a noise input terminal, a noise filter unit and an output terminal;

[0025] S2 specifically includes:

[0026] Encoding the initial ECG signal into a main signal d(n) and inputting it into the main signal input terminal;

[0027] The thoracic motion signal is encoded into a noise signal v(n) and input into the noise input terminal.

[0028] In one embodiment, the noise canceller further comprises a noise processing unit;

[0029] Before encoding the thoracic motion signal into a noise signal v(n) and inputting the noise signal into the noise input terminal, the method further comprises:

[0030] S201, extracting features from the thorax motion signal;

[0031] S202, determining a scaling matrix and an offset;

[0032] S203: Perform an affine transformation on the thorax motion signal according to the scaling matrix and the offset to obtain a noise signal v(n).

[0033] In one implementation, the iterating and weight coefficient updating of the noise canceller specifically includes:

[0034] The noise canceller is iterated based on the LMS algorithm.

[0035] In one embodiment, in the noise filtering unit, its output signal is

[0036] y(n)=w T (n)v(n)

[0037] Among them, y(n) is v(n) after filtering, w T (n) is the coefficient vector of the noise filter unit, v(n) is the noise signal;

[0038] The coefficient vector update formula is defined as:

[0039] w(n)=w(n-1)+μe(n)v(n)

[0040] Among them, w(n) is the updated coefficient vector, w(n-1) is the coefficient vector before updating, μ is the step factor, e(n) is the error signal, and n represents the sampling time.

[0041] The technical solution provided by this application may have the following beneficial effects:

[0042] Before monitoring, the collected chest motion signal is converted into a noise source signal, and the noise source signal is used as a reference signal for the adaptive filter, and the adaptive filter is iterated. During monitoring, the initial ECG signal is filtered according to the reference signal, the EMG signal is eliminated, and the ECG signal is retained.

[0043] Since EMG signals are difficult to collect and there are many interferences, the embodiment of the present application avoids directly collecting EMG signals as noise sources when designing adaptive filters. The chest movement signal and EMG signal collected by the wear detection module of the embodiment of the present application are related in time sequence, so the piezoelectric signal caused by the chest movement is used as a noise source, so that the signal output by the filter is closer to the ideal state. During the filtering process, the electrical signal with electromyographic characteristics is deleted from the initial ECG signal, so that the initial ECG signal with electromyographic interference can output a more accurate ECG.

[0044] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0046] Figure 1 A network topology diagram of a wearable multi-parameter physiological information monitoring system shown in an embodiment of the present application;

[0047] Figure 2 for Figure 1 A three-dimensional diagram of a wear detection module of the system shown;

[0048] Figure 3 for Figure 1 A rear view of the wear detection module of the system shown;

[0049] Figure 4 for Figure 1 A schematic diagram of the algorithm steps involved in the data analysis module of the system shown;

[0050] Figure 5 A logical structure diagram of a data analysis module shown in an embodiment of the present application;

[0051] Figure 6 for Figure 4 A schematic diagram of the sub-steps of S2 in the algorithm steps shown;

[0052] Notes on the accompanying drawings: 100, wear detection module; 200, data analysis module; 1, vest body; 2, electrocardiogram sensor; 3, chest piezoelectric sensor; 30, elastic band; 31, dielectric layer. DETAILED DESCRIPTION

[0053] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0054] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0055] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0056] Embodiment 1

[0057] In existing physiological monitoring systems, ECG signals are generally collected by sticking electrode patches on the body surface. The voltage amplitude of the ECG signal (i.e., electrocardiogram signal) detected by the electrode patch is a few millivolts, so there are inevitably interferences from various noise sources during collection, such as power frequency signals, myoelectric interference, etc.

[0058] In the existing initial ECG signal processing methods, in order to eliminate noise, filtering is usually performed based on the frequency characteristics of the noise, such as a bandpass filter. The frequency of power frequency interference is generally around 50HZ, that is, there is a clear difference between the frequency characteristics of power frequency interference and bioelectric signals. By setting a bandpass filter, the interference signal in this frequency band can be filtered out.

[0059] Existing filters have good filtering effects on interference with significantly different frequency characteristics from ECG signals, but have poor filtering effects on EMG signals (i.e., electromyographic signals). Currently, the ECG signals collected by the electrode patch solution are inevitably mixed with the EMG signals, because the electrode patch on the body surface will be interfered by the electrical signals generated by chest breathing.

[0060] In order to filter out myoelectric noise signals when monitoring electrocardiogram signals, the present application embodiment provides a wearable multi-parameter physiological information monitoring system, such as Figure 1 As shown, it includes: a wearing detection module 100 and a data analysis module 200.

[0061] In the embodiment of the present application, the wearing detection module 100 is disposed on a monitoring vest. The monitoring vest can collect multiple physiological parameters when worn on the user.

[0062] like Figure 2 and Figure 3 As shown, the wear detection module 100 is provided with an electrocardiogram sensor 2 and a thoracic piezoelectric sensor 3. The electrocardiogram sensor 2 and the thoracic piezoelectric sensor 3 are used to collect the initial electrocardiogram signal and thoracic movement signal of the user, respectively.

[0063] It can be understood that the initial ECG signal is a clutter signal mixed with EMG signals and ECG signals, and the thoracic movement signal is an electrical signal generated by the user's thoracic movement. Specifically, the ECG sensor 2 is an electrode patch 21 that fits the skin on the heart area and can collect the user's initial ECG signal. Specifically, the thoracic piezoelectric sensor 3 is in contact with and fixed to the user's thorax, and thoracic movement can squeeze or stretch the thoracic piezoelectric sensor 3, and the thoracic piezoelectric sensor 3 outputs the thoracic movement signal caused by thoracic movement.

[0064] Further, such as Figure 1 As shown, the wear detection module 100 is communicatively connected to the data analysis module 200. The wear detection module 100 can send the collected initial ECG signal and chest movement signal to the data analysis module 200, and the data analysis module 200 performs noise filtering processing.

[0065] It should be noted that the wear detection module 100 and the data analysis module 200 can be communicated with each other through a circuit, or through a wireless communication module on the detection vest.

[0066] In another embodiment, the data analysis module 200 can be disposed on a monitoring vest, and the power module can supply power to the device on the monitoring vest. The executable code of the data analysis module 200 can also be mounted on a cloud computing device or an edge computing device.

[0067] The electrocardiogram sensor 2 collects voltage change signals on the user's body surface through the electrode patch 21. The initial voltage changes collected by the electrode patch 21 include ECG signals, EMG signals and other interfering electrical signals.

[0068] In order to reduce the calculation pressure of the data analysis module 200, for noise signals with obvious characteristics, the wear detection module 100 circuit is also provided with an analog filter, which is used to filter other interfering electrical signals and retain ECG signals and EMG signals.

[0069] Furthermore, in order to filter the EMG signal in the initial ECG signal, the data analysis module 200 of the embodiment of the present application is also provided with a digital filter, and the digital filter is used to filter the EMG signal, and then generate an electrocardiogram from the ECG signal obtained after filtering.

[0070] Specifically, the data analysis module 200 performs noise filtering on the initial ECG signal according to the chest movement signal. Different from the existing filter, the data analysis module 200 shown in the embodiment of the present application performs adaptive design of the digital filter by learning the correlation between chest movement and EMG.

[0071] Before monitoring, the collected chest motion signal is converted into a noise source signal, and the noise source signal is used as a reference signal for the adaptive filter, and the adaptive filter is iterated. During monitoring, the initial ECG signal is filtered according to the reference signal, the EMG signal is eliminated, and the ECG signal is retained.

[0072] Since EMG signals are difficult to collect and there are many interferences, the embodiment of the present application avoids directly collecting EMG signals as noise sources when designing adaptive filters. The chest movement signal and EMG signal collected by the wear detection module 100 of the embodiment of the present application are related in time sequence, so the piezoelectric signal caused by the chest movement is used as a noise source, so that the signal output by the filter is closer to the ideal state. During the filtering process, the electrical signal with electromyographic characteristics is deleted from the initial ECG signal, so that the initial ECG signal with electromyographic interference can output a more accurate ECG.

[0073] Embodiment 2

[0074] In order to clearly illustrate the structure of the monitoring vest of the first embodiment, a wearable multi-parameter physiological information monitoring system provided in the embodiment of the present application is provided as follows Figure 2 Monitoring vest shown.

[0075] Specifically, the monitoring vest includes a vest body 1 , and the electrocardiogram sensor 2 and the chest piezoelectric sensor 3 are fixed on the front and back of the vest body 1 .

[0076] Among them, Figure 2 As shown, the electrocardiogram sensor 2 is arranged on the front side 10 of the vest body 1. Figure 3 As shown, the chest piezoelectric sensor 3 is arranged on the back side 20 of the vest body 1.

[0077] Specifically, the electrocardiogram sensor 2 is composed of three electrode patches 21 and three lead wires. When in use, one side of the electrode patch 21 is fixed on the vest body 1, and the other side with adhesiveness is attached to the skin of the body. The three electrode patches 21 are arranged around the heart area on the skin of the body. The lead wires of the three electrode patches 21 are connected to the data analysis module for communication.

[0078] like Figure 3 As shown, the chest piezoelectric sensor 3 is composed of an elastic band 30, a dielectric layer 31 and a lead wire. The elastic band 30 is arranged on the vest body 1 around the middle of the chest; the two ends of the elastic band 30 are respectively connected to the two side surfaces of the dielectric layer 31, and the electrodes on the upper and lower surfaces of the dielectric layer 31 are connected to the data analysis module through the lead wire.

[0079] In the embodiment of the present application, in order to collect multiple physiological parameters of the user, the embodiment of the present application arranges sensors on the monitoring vest for real-time collection. In order to prevent the electrocardiogram sensor 2 from being electromagnetically interfered by the circuit of the piezoelectric sensor 3 of the thorax, the circuit structures of the electrocardiogram sensor 2 and the piezoelectric sensor 3 of the thorax are arranged on the front and back of the vest body 1, respectively, so as to achieve electromagnetic isolation.

[0080] Embodiment 3

[0081] Since the acquisition of bioelectric signals is done by collecting the voltage changes on the body surface through the electrode patch 21, the body surface voltage is very susceptible to interference from other electromagnetic signals. Therefore, the embodiment of the present application does not directly collect the EMG signal of the thorax area, but obtains the user's thorax movement signal through the thorax piezoelectric sensor 3, encodes the thorax movement signal, and uses it as a noise source to filter the initial electrocardiogram signal to obtain the ECG signal.

[0082] In the wearable multi-parameter physiological information monitoring system shown in the first and second embodiments, the algorithm steps involved in the data analysis module 200 are as follows: Figure 4 As shown, including:

[0083] S1, build a noise canceller;

[0084] S2, collecting the initial ECG signal and the chest movement signal and inputting them into the noise canceller;

[0085] S3, iterating the noise canceller and updating the weight coefficient;

[0086] S4. Deploy the noise canceller after iteration in the data analysis module 200.

[0087] In S1, the model structure of the noise canceller is as follows: Figure 5 As shown, the noise canceller includes a main signal input terminal, a noise input terminal, a noise filtering unit and an output terminal.

[0088] In S2, the initial electrocardiogram signal is encoded as a main signal d(n) and input into the main signal input terminal, and the chest movement signal is encoded as a noise signal v(n) and input into the noise input terminal.

[0089] It can be understood that the main signal d(n) is a mixed signal of the ECG signal s(n) and the EMG signal v0(n). Specifically, the ECG signal is an ideal electrocardiogram signal of the user, and the EMG signal is an electromyographic interference signal.

[0090] In the embodiment of the present application, the thoracic motion signal is related to the electromyographic signal. Therefore, before the thoracic motion signal is input into the noise input terminal, it needs to be converted into a noise signal v(n).

[0091] Furthermore, the noise canceller further comprises a noise processing unit, and the noise processing unit is used to perform the following steps:

[0092] S201, extracting features from the thorax motion signal;

[0093] S202, determining a scaling matrix and an offset;

[0094] S203: Perform affine transformation on the thorax motion signal according to the scaling matrix and the offset to obtain a noise signal.

[0095] Furthermore, the affine transformation formula is:

[0096] v(n)=Aq(n)+B

[0097] Wherein, v(n) is the noise signal, A is the scaling matrix, q(n) is the thorax motion signal, B is the offset, and n is the sampling time.

[0098] In order to eliminate the noise signal in the main signal, the embodiment of the present application filters the noise signal therein through the noise canceller.

[0099] In the embodiment of the present application, the main signal can be expressed as d(n)=s(n)+v0(n), where d(n) is the initial electrocardiogram signal, s(n) is the ECG signal, and v0(n) is the EMG signal.

[0100] Furthermore, S3 specifically includes: iterating the noise filtering unit based on the LMS algorithm.

[0101] Specifically, the error signal between the output signal y(n) of the noise filtering unit and the main signal is e(n)=s(n)+v0(n)-y(n).

[0102] In the noise filtering unit, the output signal is

[0103] y(n)=w T (n)v(n)

[0104] Among them, y(n) is v(n) after filtering, w T (n) is the coefficient vector of the noise filter unit, and v(n) is the noise signal.

[0105] In the embodiment of the present application, the coefficient vector of the noise filtering unit is updated using the gradient descent method, and the coefficient vector update formula is defined as:

[0106] w(n)=w(n-1)+μe(n)v(n)

[0107] Among them, w(n) is the updated coefficient vector, w(n-1) is the coefficient vector before updating, μ is the step factor, e(n) is the error signal, and n represents the sampling time.

[0108] When the preset number of iterations is reached or the error signal approaches the expected signal, the ECG signal is obtained by subtracting the filtered y(n) from the input main signal d(n).

[0109] In the embodiment of the present application, the output y(n) of the noise filtering unit approaches the noise signal v0(n) under the ideal state. After determining the output y(n), y(n) in the initial ECG signal is eliminated to obtain the ECG signal after noise reduction. Generating an electrocardiogram based on the ECG signal can avoid the interference of the electromyographic signal.

[0110] Regarding the device in the above embodiment, the specific way in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0111] The scheme of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. Those skilled in the art should also be aware that the actions and modules involved in the description are not necessarily required for the present application.

[0112] In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be combined, divided and deleted according to actual needs.

[0113] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0114] Alternatively, the present application can also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0115] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the application herein may be implemented as electronic hardware, computer software, or combinations of both.

[0116] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, a program segment or a code, and the part of the module, the program segment or the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or the flow chart, and the combination of the square boxes in the block diagram and / or the flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0117] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A wearable multi-parameter physiological information monitoring system, characterized in that: include: A wear detection module (100) and a data analysis module (200); The wear detection module (100) is communicatively connected to the data analysis module (200); The wear detection module (100) is worn on a user, and the wear detection module (100) is provided with an electrocardiogram sensor (2) and a chest piezoelectric sensor (3); The electrocardiogram sensor (2) and the chest piezoelectric sensor (3) are used to collect the user's initial electrocardiogram signal and chest movement signal respectively; The initial electrocardiogram signal is a clutter signal mixed with an EMG signal and an ECG signal; the chest piezoelectric sensor (3) is in contact with and fixed to the chest of the user, and the chest piezoelectric sensor (3) is used to output the chest movement signal caused by chest movement; The data analysis module (200) is used to perform noise filtering on the initial electrocardiogram signal according to the chest cage motion signal.

2. A wearable multi-parameter physiological information monitoring system according to claim 1, characterized in that: Also included are monitoring vests; The wear detection module (100) is fixed on the monitoring vest, the electrocardiogram sensor (2) is arranged on the front of the monitoring vest, and the electrocardiogram sensor (2) comprises M electrode patches (21). The electrode patches (21) are attached to the user's body surface after being worn, and M is an integer greater than or equal to 2.

3. A wearable multi-parameter physiological information monitoring system according to claim 2, characterized in that: The thoracic piezoelectric sensor (3) is arranged on the back of the monitoring vest.

4. A wearable multi-parameter physiological information monitoring system according to claim 3, characterized in that: The chest piezoelectric sensor (3) comprises an elastic band (30), a dielectric layer (31) and a lead wire; The elastic band (30) is arranged on the vest body (1) around the middle of the thorax; the two ends of the elastic band (30) are respectively connected to the two side surfaces of the dielectric layer (31); the electrodes on the upper and lower surfaces of the dielectric layer (31) are connected to the data analysis module through the lead wire communication.

5. A wearable multi-parameter physiological information monitoring system according to claim 4, characterized in that: The dielectric layer (31) is a dielectric elastomer.

6. A wearable multi-parameter physiological information monitoring system according to claim 1, characterized in that: The data analysis module (200) is used to filter the initial electrocardiogram signal for noise according to the chest movement signal, and specifically comprises: S1, build a noise canceller; S2, collecting the initial ECG signal and the chest movement signal and inputting them into the noise canceller; S3, iterating the noise canceller and updating the weight coefficient; S4. Deploy the iteratively completed noise canceller in the data analysis module (200).

7. A wearable multi-parameter physiological information monitoring system according to claim 6, characterized in that: The noise canceller includes a main signal input terminal, a noise input terminal, a noise filtering unit and an output terminal; S2 specifically includes: Encoding the initial ECG signal into a main signal d(n) and inputting it into the main signal input terminal; The thoracic motion signal is encoded into a noise signal v(n) and input into the noise input terminal.

8. A wearable multi-parameter physiological information monitoring system according to claim 7, characterized in that: The noise canceller also includes a noise processing unit; Before encoding the thoracic motion signal into a noise signal v(n) and inputting the noise signal into the noise input terminal, the method further comprises: S201, extracting features from the thorax motion signal; S202, determining a scaling matrix and an offset; S203: Perform affine transformation on the thorax motion signal according to the scaling matrix and the offset to obtain a noise signal v(n).

9. A wearable multi-parameter physiological information monitoring system according to claim 6, characterized in that: In iterating the noise canceller and updating the weight coefficient, the following steps are specifically included: The noise canceller is iterated based on the LMS algorithm.

10. A wearable multi-parameter physiological information monitoring system according to claim 9, characterized in that: In the noise filtering unit, the output signal is y(n)=w T (n)v(n) Among them, y(n) is v(n) after filtering, w T (n) is the coefficient vector of the noise filter unit, v(n) is the noise signal; The coefficient vector update formula is defined as: w(n)=w(n-1)+μe(n)v(n) Among them, w(n) is the updated coefficient vector, w(n-1) is the coefficient vector before updating, μ is the step factor, e(n) is the error signal, and n represents the sampling time.

Images