Dynamic multi-modal physiological parameter wireless acquisition system

Abstract

The present application relates to the technical field of wireless acquisition of physiological parameters, and specifically to a dynamic multimodal wireless acquisition system for physiological parameters. The system includes: a physiological parameter acquisition module, and a physiological parameter signal modulation module including: a preamplifier, an electromyographic signal decomposition unit, which decomposes the electromyographic signal modality, constructs an extreme value distribution comparison sequence and a signal difference comparison sequence; a comparison eigenvalue unit, which is used to obtain the comparison eigenvalues ​​of each modal component; a consistency coefficient unit, which is used to determine the consistency coefficient of electromyographic signals at different positions; an electromyographic signal filtering unit, which is used to adjust the filtering window when filtering electromyographic signals; an electromyographic signal analog-to-digital conversion unit, a physiological parameter wireless communication module, and a power management module. The present application improves the accuracy of dynamic multimodal wireless acquisition of physiological parameters.

Description

Technical Field

[0001] The present application relates to the technical field of wireless collection of physiological parameters, and in particular to a dynamic multi-modal wireless collection system for physiological parameters. Background Art

[0002] Accurate collection and analysis of human physiological parameters are of great significance in the fields of medical diagnosis, rehabilitation therapy, sports science, etc. For example, by monitoring the electrical activity of muscles (such as surface electromyography signals), we can understand the functional state of muscles, including the degree of muscle recruitment, fatigue, spasm, and coordination between muscles, which is helpful for diagnosing neuromuscular diseases, evaluating the effect of rehabilitation training, and optimizing sports training programs.

[0003] In a multimodal physiological parameter acquisition system, since multiple sensors work simultaneously, interference between signals is likely to occur. For example, when electrical stimulation signals and ultrasound signals are running simultaneously in the same device, electromagnetic interference or ultrasonic interference may occur, causing signal distortion, affecting the accuracy of measurement and the stability of treatment effects. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a dynamic multi-modal physiological parameter wireless acquisition system, and the technical solutions adopted are as follows:

[0005] The present application proposes a dynamic multi-modal physiological parameter wireless acquisition system, the system comprising:

[0006] The physiological parameter acquisition module 10 is used to collect myoelectric signals of different positions of the user through various myoelectric sensors;

[0007] The physiological parameter signal modulation module 20 includes:

[0008] A preamplifier 21, used for amplifying the electromyographic signal;

[0009] The electromyographic signal decomposition unit 22 is used to perform modal decomposition of the electromyographic signal at different frequencies, and to fit the maximum and minimum values ​​in the modal components to obtain a first fitting curve and a second fitting curve, respectively, to construct an extreme value distribution comparison sequence of each modal component through the distribution of the first fitting curve and the second fitting curve, and to construct a signal difference comparison sequence of each modal component in combination with the signal difference degree between the first fitting curve and the second fitting curve;

[0010] A contrast eigenvalue unit 23 is used to analyze the difference of different modal components with respect to the extreme value distribution contrast sequence and the degree of difference with respect to the signal difference contrast sequence, and obtain the contrast eigenvalue of each modal component;

[0011] The consistency coefficient unit 24 is used to analyze the similarity of the contrast characteristic values ​​of the modal components of the electromyographic signals at different positions and the distance relationship between the electromyographic signal collection positions, and determine the consistency coefficients of the electromyographic signals at different positions;

[0012] The electromyographic signal filtering unit 25 is used to cluster all collected electromyographic signals according to the consistency coefficient, adjust the filtering window when filtering the electromyographic signals in the cluster according to the contrast characteristic value of each modal component of all the electromyographic signals in the cluster, and filter the electromyographic signals;

[0013] The electromyographic signal analog-to-digital conversion unit 26 is used to perform analog-to-digital conversion on the electromyographic signal after filtering;

[0014] A physiological parameter wireless communication module 30 is used to send the analog-to-digital converted data to a receiving end;

[0015] The power management module 40 is used to provide power for the wireless acquisition system.

[0016] The construction process of the extreme value distribution comparison sequence of each modal component is as follows:

[0017] For the first fitting curve and the second fitting curve of each modal component, a characteristic sequence of each peak in each fitting curve is constructed according to the peak information in each fitting curve, and the similarity between the characteristic sequence of each peak in the first fitting curve and the characteristic sequence of each peak in the second fitting curve is calculated. All the calculated similarities are combined into an extreme value distribution comparison sequence of the modal component.

[0018] The characteristic sequence of each peak consists of the peak width, peak value and peak position data of each peak.

[0019] The construction process of the signal difference comparison sequence of each modal component is as follows:

[0020] For the first fitting curve and the second fitting curve of each modal component, the myoelectric mean value, the integrated myoelectric value and the root mean square value of the first fitting curve and the second fitting curve are respectively counted;

[0021] The absolute value of the difference between the average electromyographic value, the absolute value of the difference between the integrated electromyographic value and the absolute value of the difference between the root mean square value corresponding to the first fitting curve and the second fitting curve are calculated respectively, and a sequence composed of three absolute values ​​is used as a signal difference comparison sequence of the modal component.

[0022] Wherein, the comparison characteristic value unit 23 is configured as follows:

[0023] Calculate the contrast eigenvalues ​​of each modal component: ;in, Indicates Comparison of eigenvalues ​​of modal components; Indicates and The Euclidean distance between the extreme value distribution comparison sequences of the modal components; Indicates and The Euclidean distance between the signal difference comparison sequences of the modal components.

[0024] Wherein, the consistency coefficient unit 24 is configured as follows:

[0025] For each electromyographic signal, the contrast eigenvalues ​​of all modal components of the electromyographic signal are arranged in descending order according to the frequencies corresponding to the modal components to form a contrast vector of the electromyographic signal;

[0026] The consistency coefficients of the electromyographic signals at different positions are calculated based on the similarity between the comparison vectors of the electromyographic signals collected at different positions and the distance relationship between the different positions.

[0027] The calculation formula of the consistency coefficient is specifically as follows: ;in, Indicates Position and The consistency coefficient of the electromyographic signals at each position; and Respectively represent and The contrast vector of the electromyographic signal at each position; represents cosine similarity; Indicates and The Euclidean distance between the EMG sensors at each location.

[0028] Wherein, the electromyographic signal filtering unit 25 is configured as follows:

[0029] The electromyographic signals collected at all positions are used as the input of the clustering algorithm, and the consistency coefficient of the electromyographic signals at different positions is used as the similarity measurement result in the clustering process. All electromyographic signals are clustered and divided through the clustering algorithm.

[0030] Wherein, the electromyographic signal filtering unit 25 is further configured as follows:

[0031] The filter window for adaptive filtering of all electromyographic signals in the cluster at each frequency is adjusted, and the adjusted filter window size is: , where To adjust the filter window size for adaptive filtering of all EMG signals in cluster p at frequency f, is the adjustment coefficient of the filter window when all the electromyographic signals in cluster p are adaptively filtered at frequency f, Indicates the preset initial filter window size.

[0032] Wherein, obtaining the adjustment coefficient further includes:

[0033] The average value of the contrast eigenvalues ​​at the same position in the contrast vector of all the electromyographic signals in the cluster is taken as the contrast response value of the corresponding modal component, and the normalized result of the contrast response value is taken as the adjustment coefficient of the filter window when the electromyographic signals in the cluster are adaptively filtered at the corresponding frequency of the modal component.

[0034] This application has the following beneficial effects:

[0035] The multimodal physiological parameter wireless acquisition system of the present application includes a sensor module, a signal modulation module, a microcontroller module, a wireless communication module and a power management module. Corresponding calibration and preprocessing are performed for different physiological parameters, and real-time optimization and adjustment processing is performed in combination with the contrast characteristics of weak and interference effects in the electromyographic signal acquisition process. The wireless acquisition system in the present application can accurately and dynamically acquire multimodal physiological parameter data, thereby improving the accuracy of dynamic multimodal physiological parameters acquired wirelessly. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 A block diagram of a dynamic multi-modal physiological parameter wireless acquisition system provided by an embodiment of the present application;

[0038] Figure 2 A schematic diagram of the composition of a physiological parameter signal modulation module provided in one embodiment of the present application;

[0039] Figure 3 A schematic diagram of the implementation process of filtering electromyographic signals provided in one embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of the dynamic multimodal physiological parameter wireless acquisition system proposed in the present application in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0041] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0042] The specific scheme of the dynamic multi-modal physiological parameter wireless acquisition system provided by the present application is described in detail below with reference to the accompanying drawings.

[0043] See also Figure 1 , which shows a block diagram of a dynamic multi-modal physiological parameter wireless acquisition system provided by an embodiment of the present application, the system comprising:

[0044] The physiological parameter acquisition module 10 is used to acquire myoelectric signals at different positions of the user through various myoelectric sensors.

[0045] The data is collected using an electromyographic sensor, wherein the electromyographic sensor electrodes are attached to the human skin according to the standard electrocardiographic electrode placement position, which is placed at the chest lead position in this embodiment, and during the data collection process, it is ensured that the electrodes are in good contact with the skin to obtain electromyographic signals.

[0046] The physiological parameter signal modulation module 20 includes a preamplifier 21 , an electromyographic signal decomposition unit 22 , a comparison eigenvalue unit 23 , a consistency coefficient unit 24 , an electromyographic signal filtering unit 25 , and an electromyographic signal analog-to-digital conversion unit 26 .

[0047] Specifically, in this embodiment, the composition diagram of the physiological parameter signal modulation module is as follows: Figure 2 shown.

[0048] Preamplifier 21: In view of the weak characteristics of electromyographic signals, their amplitude range is between 0 and 5000 μV; in order to enable the signal to be accurately identified and processed by the subsequent circuit, a preamplifier is set, wherein the gain of the preamplifier is between 100 and 1000 times, to ensure that the signal is not distorted after amplification, and at the same time, the preamplifier is biased so that the output signal is within the effective range of the subsequent analog-to-digital conversion; specifically, it is achieved by setting a bias resistor in the amplifier circuit or using an adjustable bias voltage source. By accurately measuring the DC component of the electromyographic signal and combining it with the input range requirements of the analog-to-digital converter (ADC), the bias voltage value is calculated so that the electromyographic signal after preamplification can fall completely within the effective conversion range of the ADC, avoiding the problem of signal truncation or excessive quantization error. It should be noted that the calculation of the bias voltage value and the amplification process of the signal by the preamplifier are both well-known technologies to those skilled in the art and will not be repeated.

[0049] The electromyographic signal decomposition unit 22 is used to perform modal decomposition of the electromyographic signal at different frequencies, and to fit the maximum and minimum values ​​in the modal components to obtain a first fitting curve and a second fitting curve, respectively. The extreme value distribution comparison sequence of each modal component is constructed through the distribution of the first fitting curve and the second fitting curve, and the signal difference comparison sequence of each modal component is constructed in combination with the signal difference degree between the first fitting curve and the second fitting curve.

[0050] The filter parameters are designed taking into account the frequency characteristics of the electromyographic signal and the frequency of the interference source; specifically, when collecting surface electromyographic signals, the collection environment is complex, and there are power frequency noise and peak amplitude interference, resulting in poor quality of the collected surface electromyographic signals, and traditional signal filtering methods are difficult to accurately handle the complex interference. Therefore, according to the interference characteristics presented in the electromyographic signal collection process, the filter parameters are optimized and adjusted in real time to improve the quality of the collected electromyographic signals. Specifically, in this embodiment, the optimization and adjustment steps for the collected electromyographic signal filtering process are as follows:

[0051] Normally, during the process of surface EMG signal acquisition, the surface EMG signal is usually weak. After being processed by an amplifier before signal processing, the interference characteristics of the EMG signal in different frequency ranges will be further highlighted. Therefore, the EMG signal collected by each EMG sensor is used as input, and the empirical mode decomposition algorithm is used to obtain the modal components of each EMG signal at different frequencies, which is used to analyze the degree of noise interference on the decomposed signals in different frequency ranges, as well as the prominent characteristics of noise interference on the modal components in different frequency ranges.

[0052] In order to further determine the peaks or longer-range stage-by-stage continuous influence characteristics that appear in the electromyographic signals affected by interference in different frequency ranges, for each modal component of each electromyographic signal, the minimum and maximum points in the modal component are obtained, all the minimum and maximum points are used as input, and the least squares method is used for curve fitting. The obtained fitting curves are used as the first fitting curve and the second fitting curve of the modal component, respectively.

[0053] Considering that the electromyographic signal exhibits symmetrical amplitude variation characteristics during the actual acquisition process, for each modal component, the first fitting curve and the second fitting curve are used as input respectively, and the findpeak function in MATLAB is used to obtain the peak width, peak value and peak position data of each peak in the fitting curve. The vector composed of the peak width, peak value and peak position of each peak in the fitting curve is used as the characteristic sequence of each peak.

[0054] Further, the similarity between the characteristic sequence of each peak in the first fitting curve and the characteristic sequence of each peak in the second fitting curve is calculated, and the similarity can be calculated by cosine similarity or dot product. In this embodiment, cosine similarity is used. A sequence composed of all similarities calculated based on the characteristic sequence of each peak in the first fitting curve and the characteristic sequence of each peak in the second fitting curve is used as the extreme value distribution comparison sequence of the corresponding modal component; the interference comparison sequence reflects the prominent symmetrical difference of the electromyographic signal caused by the peak or the staged interference in a longer time range during the signal acquisition process of the electromyographic signal at the frequency corresponding to the modal component.

[0055] In order to fully compare the symmetrical differences of electromyographic signals in different frequency ranges, the electromyographic average value, integrated electromyographic value and root mean square value of the first fitting curve and the second fitting curve are calculated respectively. The electromyographic average value, integrated electromyographic value and root mean square value of the fitting curve are well-known techniques for those skilled in the art to analyze the time domain signal of the electromyographic signal, and the specific calculation process will not be repeated. Further, the absolute value of the difference between the average electromyographic value, the absolute value of the difference between the integrated electromyographic value and the absolute value of the difference between the root mean square value corresponding to the first fitting curve and the second fitting curve are calculated respectively, and the sequence composed of the three absolute values ​​is used as the signal difference comparison sequence of the corresponding modal component; the signal difference comparison sequence reflects the overall symmetrical difference of the signal affected by interference in different frequency ranges.

[0056] The contrast eigenvalue unit 23 is used to analyze the difference of different modal components with respect to the extreme value distribution contrast sequence and the degree of difference with respect to the signal difference contrast sequence, and obtain the contrast eigenvalue of each modal component.

[0057] Furthermore, considering the influence of interference during the EMG signal acquisition process, there are large differences in the interference characteristics in different frequency ranges. If the symmetrical difference in the frequency range caused by the interference is larger, it means that the interference influence of the frequency in this range is larger. Therefore, based on the characteristics of the interference comparison between different frequency ranges, the interference comparison characteristic value of the EMG signal in each frequency range is calculated. , the specific calculation relationship is as follows:

[0058] ;in, Indicates The contrast eigenvalues ​​of the modal components; Indicates and The Euclidean distance between the extreme value distribution comparison sequences of the modal components; Indicates and The signal difference of each modal component is compared with the Euclidean distance between the sequences. It should be noted that the implementer can also use Manhattan distance and Flamenche distance to measure the difference between the sequences, which is not particularly limited in this embodiment; Indicates the number of modal components; the larger the calculated contrast eigenvalue is, the The frequency ranges corresponding to the modal components are greatly affected by interference.

[0059] The consistency coefficient unit 24 analyzes the similarity of the contrast characteristic values ​​of the modal components of the electromyographic signals at different positions and the distance relationship between the electromyographic signal collection positions to determine the consistency coefficients of the electromyographic signals at different positions.

[0060] Since signal data of multiple parts are usually collected during the electromyographic signal collection process, and the collection process is usually within the same environmental space, the data with similar interference characteristics are analyzed based on the interference influence characteristics of the data collected from different parts in the common space. For each electromyographic signal, a vector composed of the contrast eigenvalues ​​of all modal components arranged in descending order according to the frequencies corresponding to the modal components is used as the contrast vector of the electromyographic signal. Based on the similarity between the contrast vectors and the relative positions of the electromyographic signal collection, the consistency coefficients of the electromyographic signals at different positions are calculated. In this embodiment, the specific calculation relationship is:

[0061] ;in, Indicates Position and The consistency coefficient of the electromyographic signals at each position; and Respectively represent and The contrast vector of the electromyographic signal at each position; represents cosine similarity; Indicates and It can be understood that the larger the calculated consistency coefficient is, the greater the consistency of the interference effects of the myoelectric signals collected at different positions in different frequency ranges is when the distances are close.

[0062] The electromyographic signal filtering unit 25 is used to cluster all collected electromyographic signals according to the consistency coefficient, adjust the filtering window when filtering the electromyographic signals in the cluster according to the contrast characteristic values ​​of each modal component of all the electromyographic signals in the cluster, and filter the electromyographic signals.

[0063] Furthermore, all electromyographic signals are clustered and divided according to the consistency coefficients of electromyographic signals at different positions. Specifically, the electromyographic signals collected at all positions are taken as input, the consistency coefficients of electromyographic signals at different positions are taken as the similarity measurement results in the clustering process, and hierarchical clustering is used to obtain the division results of the electromyographic signals collected at all positions. It should be noted that the specific clustering division process of hierarchical clustering is a prior art and will not be repeated in this embodiment.

[0064] Furthermore, for each cluster in the division result, the average value of the contrast eigenvalues ​​at the same position in the contrast vector of all the electromyographic signals in the cluster is taken as the contrast response value of the corresponding modal component, all the contrast response values ​​are taken as input, and the Softmax function is used to obtain the normalized results of all the contrast response values, and the adjustment vector composed of all the normalized results is used as the adjustment coefficient of the filter window size when filtering all the electromyographic signals in the cluster, wherein the filter window for adaptive filtering of all electromyographic signals in the same cluster within the same frequency range is adjusted, and the formula for the adjusted filter window size is: , where To adjust the filter window size for adaptive filtering of all EMG signals in cluster p at frequency f, is the adjustment coefficient of the filter window when all the electromyographic signals in cluster p are adaptively filtered at frequency f, Indicates the preset initial filter window size, which is set to 5 times of the signal period in this embodiment. Through comprehensive judgment of the electromyographic signals with similar interference characteristics in the cluster, the greater the interference, the larger the filter window size required for more accurate filtering processing.

[0065] Specifically, the schematic diagram of the implementation process of filtering the electromyographic signal in this embodiment is as follows: Figure 3 shown.

[0066] The electromyographic signal analog-to-digital conversion unit 26 is used to perform analog-to-digital conversion on the electromyographic signal after filtering.

[0067] According to the requirements of data accuracy and sampling speed, select an analog-to-digital converter (ADC) chip with appropriate resolution and sampling frequency. Specifically, in this embodiment, for electromyographic signals, the sampling frequency is set to 2000Hz to meet the needs of signal analysis. Configure the ADC's operating mode and reference voltage parameters to ensure its normal operation. Connect the modulated analog signal to the input of the ADC, start the ADC conversion, and read the converted data in a timely manner.

[0068] The physiological parameter wireless communication module 30 is used to send the analog-to-digital converted data to the receiving end.

[0069] Initialize the wireless communication module and set the working parameters of the module according to the protocol specification of the selected wireless communication technology, including communication frequency, baud rate and device name. There are many existing wireless communication technologies, such as Bluetooth module and WiFi module.

[0070] Further, a connection with an external device is established. For the Bluetooth module, it enters the discoverable mode and waits for the external device to search and pair; for the WiFi module, it connects to a designated wireless network hotspot or is configured as an access point mode. In this embodiment, the Bluetooth module is used for connection.

[0071] The converted data is packaged in the format specified by the communication protocol and sent to the wireless communication module through the communication interface. For example, the data is encapsulated into a specific data packet structure, including the data header, data content and check bit information, to ensure the accuracy and integrity of data transmission.

[0072] Specifically, the data is packaged in the format specified by the Bluetooth protocol, and then the sending function of the Bluetooth driver is called to send the data to the Bluetooth module. After the Bluetooth module receives the data, it sends the data in the form of a wireless signal through the antenna. At the receiving end, such as a mobile phone and a computer, the terminal device in this embodiment is a computer, turn on the Bluetooth function and search for nearby Bluetooth devices, find the Bluetooth device of the collection system, and then pair and connect. After the pairing is successful, the receiving device can receive the data from the collection system.

[0073] The power management module 40 is used to provide power for the wireless acquisition system.

[0074] Choose the right capacity and type of battery based on the system's power consumption and battery life requirements. For example, for a low-power acquisition system, a small lithium battery can be used; for a system that needs to work continuously for a long time, a battery with a larger capacity can be selected.

[0075] Install the battery in the battery compartment of the device, making sure the battery is firmly installed and the positive and negative poles are connected correctly. For rechargeable batteries, you also need to consider the location and design of the charging port to facilitate battery charging.

[0076] It should be noted that the sequence of the above embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0078] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application should be included in the protection scope of the present application.

Claims

1. Dynamic multi-modal physiological parameter wireless acquisition system, characterized in that: The system comprises: A physiological parameter acquisition module (10) is used to acquire myoelectric signals at different positions of the user through various myoelectric sensors; The physiological parameter signal modulation module (20) comprises: A preamplifier (21), used for amplifying the electromyographic signal; The electromyographic signal decomposition unit (22) is used to perform modal decomposition of the electromyographic signal at different frequencies, respectively fit the maximum value and the minimum value in the modal component to obtain a first fitting curve and a second fitting curve, respectively construct a characteristic sequence of each peak in each fitting curve according to the peak information in each fitting curve for the first fitting curve and the second fitting curve of each modal component, calculate the similarity between the characteristic sequence of each peak in the first fitting curve and the characteristic sequence of each peak in the second fitting curve, and form all the calculated similarities into an extreme value distribution comparison sequence of the modal component; respectively count the electromyographic average value, the integrated electromyographic value and the root mean square value of the first fitting curve and the second fitting curve for each modal component, respectively calculate the absolute value of the difference between the average electromyographic value, the absolute value of the difference between the integrated electromyographic value and the absolute value of the difference between the root mean square value, and use the sequence composed of the three absolute values ​​as the signal difference comparison sequence of the modal component; and construct the signal difference comparison sequence of each modal component in combination with the signal difference degree between the first fitting curve and the second fitting curve; A contrast eigenvalue unit (23) is used to analyze the difference of different modal components with respect to the extreme value distribution contrast sequence and the degree of difference with respect to the signal difference contrast sequence, and obtain the contrast eigenvalue of each modal component; A consistency coefficient unit (24) is used to analyze the similarity of the contrast characteristic values ​​of the modal components of the electromyographic signals at different positions and the distance relationship between the electromyographic signal collection positions, and determine the consistency coefficients of the electromyographic signals at different positions; An electromyographic signal filtering unit (25) is used to cluster all collected electromyographic signals according to the consistency coefficient, and adjust the filtering window when filtering the electromyographic signals in the cluster according to the comparison characteristic values ​​of each modal component of all the electromyographic signals in the cluster, so as to filter the electromyographic signals; An electromyographic signal analog-to-digital conversion unit (26), used for performing analog-to-digital conversion on the electromyographic signal after filtering; A physiological parameter wireless communication module (30) is used to send the analog-to-digital converted data to a receiving end; The power management module (40) is used to provide power to the wireless acquisition system.

2. The dynamic multi-modal physiological parameter wireless acquisition system according to claim 1, characterized in that: The characteristic sequence of each peak consists of the peak width, peak value and peak position data of each peak.

3. The dynamic multi-modal physiological parameter wireless acquisition system according to claim 1, characterized in that: The comparison feature value unit (23) is configured as follows: Calculate the contrast eigenvalues ​​of each modal component: ;in, Indicates The contrast eigenvalues ​​of the modal components; Indicates and The Euclidean distance between the extreme value distribution comparison sequences of the modal components; Indicates and The Euclidean distance between the signal difference comparison sequences of the modal components.

4. The dynamic multi-modal physiological parameter wireless acquisition system according to claim 1, characterized in that: The consistency coefficient unit (24) is configured as follows: For each electromyographic signal, the contrast eigenvalues ​​of all modal components of the electromyographic signal are arranged in descending order according to the frequencies corresponding to the modal components to form a contrast vector of the electromyographic signal; The consistency coefficients of the electromyographic signals at different positions are calculated based on the similarity between the comparison vectors of the electromyographic signals collected at different positions and the distance relationship between the different positions.

5. The dynamic multi-modal physiological parameter wireless acquisition system according to claim 4, characterized in that: The calculation formula of the consistency coefficient is specifically: ;in, Indicates Position and The consistency coefficient of the electromyographic signals at each position; and Respectively represent and The contrast vector of the electromyographic signal at each position; represents cosine similarity; Indicates and The Euclidean distance between the EMG sensors at each location.

6. The dynamic multi-modal physiological parameter wireless acquisition system according to claim 1, characterized in that: The electromyographic signal filtering unit (25) is configured as follows: The electromyographic signals collected at all positions are used as the input of the clustering algorithm, and the consistency coefficient of the electromyographic signals at different positions is used as the similarity measurement result in the clustering process. All electromyographic signals are clustered and divided through the clustering algorithm.

7. The dynamic multi-modal physiological parameter wireless acquisition system according to claim 1, characterized in that: The electromyographic signal filtering unit (25) is further configured as follows: The filter window for adaptive filtering of all electromyographic signals in the cluster at each frequency is adjusted, and the adjusted filter window size is: , where To adjust the filter window size for adaptive filtering of all EMG signals in cluster p at frequency f, is the adjustment coefficient of the filter window when all the electromyographic signals in cluster p are adaptively filtered at frequency f, Indicates the preset initial filter window size.

8. The dynamic multi-modal physiological parameter wireless acquisition system according to claim 7, characterized in that: The acquisition of the adjustment coefficient further includes: The average value of the contrast eigenvalues ​​at the same position in the contrast vector of all the electromyographic signals in the cluster is taken as the contrast response value of the corresponding modal component, and the normalized result of the contrast response value is taken as the adjustment coefficient of the filter window when the electromyographic signals in the cluster are adaptively filtered at the corresponding frequency of the modal component.

Images