Integrated Wearable Electromyogram Monitoring and Electrical Stimulation Intervention Device

Abstract

The present invention discloses an integrated device for wearable electromyogram monitoring and electrical stimulation intervention, comprising: an integrated functional patch for collecting surface electromyogram signals during exercise and applying electrical stimulation to muscles; an electromyogram signal preprocessing module for preprocessing the surface electromyogram signal sequence; a muscle force generation period electromyogram signal processing module for extracting the signal subsequence of the muscle gait movement during the force generation period from the preprocessed surface electromyogram signal sequence; calculating the eigenvalue of each signal subsequence of the force generation period, and the eigenvalue of the signal subsequence of the force generation period reflects the deviation degree of each signal in the force generation period; a control module for creating an eigenvalue sequence based on the eigenvalue of each signal subsequence of the force generation period; generating an accumulated feature enhancement sequence based on the eigenvalue sequence; judging whether the selected element in the accumulated feature enhancement sequence is less than a preset contraction feature threshold; when it is less than the preset contraction feature threshold, continuing to generate therapeutic stimulation electrical pulses, otherwise, generating relaxation electrical pulses.

Description

Technical Field

[0001] The present invention relates to the technical field of electromyogram detection, and particularly to a wearable integrated device for electromyogram monitoring and electrical stimulation intervention. Background Art

[0002] Factors such as abnormal neuromuscular control or motor neuron lesions often lead to phenomena such as muscle atrophy, weakness, easy fatigue, and abnormal contraction patterns. Surface electromyogram can reflect the function of nerve control and muscle to a certain extent. Its essence is the superposition of motor unit action potentials (MUAPs) generated by the activation of multiple motor units (MUs) at the detection electrode. By collecting the surface electromyogram signals of the corresponding muscles and extracting features, the neuromuscular control status can be judged to a large extent. Therefore, electromyogram features are often used as evaluation indicators for neuromuscular control evaluation or the effectiveness evaluation of related intervention methods. Neuromuscular electrical stimulation (NMES), as a common method for neuromuscular control intervention, mainly performs medium and low-frequency electrical stimulation on the corresponding muscle (group) through prefabricated patterns, body positions or time sequences (such as gait cycles, etc.) to activate or inhibit nerve control, improve muscle atrophy, adjust the muscle contraction duration or amplitude, and then achieve the purpose of correcting the muscle contraction pattern within the gait movement cycle and improving neuromuscular control.

[0003] In the process of implementing the present invention, the inventors found the following technical problems: At present, when performing neuromuscular monitoring and intervention, it is often necessary to first collect electromyogram signals and extract features, and then match corresponding fixed electrical stimulation parameters for intervention treatment, which cannot achieve real-time adjustment. Even the existing relatively perfect monitoring and stimulation adaptive adjustment methods mainly perform adjustment and intervention based on the gait cycle time sequence or body position angle, resulting in a phenomenon that the basis of electrical stimulation intervention does not match the target parameters, leading to certain deviations in monitoring and intervention, making it difficult to achieve real-time and precise neuromuscular control intervention, and reducing the practical application effectiveness of rehabilitation such as walking learning or gait correction. Summary of the Invention

[0004] Embodiments of the present invention provide a wearable integrated device for electromyogram monitoring and electrical stimulation intervention to solve the technical problem that real-time adjustment cannot be achieved in the prior art for neuromuscular monitoring and intervention.

[0005] In view of this, embodiments of the present invention provide a wearable integrated device for electromyogram monitoring and electrical stimulation intervention, including:

[0006] An integrated functional patch for collecting surface electromyogram signals in a motion state and applying electrical stimulation to muscles;

[0007] An electromyogram signal preprocessing module, which is used to preprocess the surface electromyogram signal sequence collected by the integrated functional patch;

[0008] A muscle force generation period electromyogram signal processing module, which is used to extract the signal subsequence in the muscle gait movement during the muscle force generation period from the preprocessed surface electromyogram signal sequence; calculate the eigenvalue of each said signal subsequence in the muscle force generation period, and the eigenvalue of the signal subsequence in the muscle force generation period reflects the sum of the deviation degrees of each signal in the muscle force generation period;

[0009] A control module, which is used to create an eigenvalue sequence based on the eigenvalue of each signal subsequence in the muscle force generation period; generate an accumulated feature enhancement sequence based on the eigenvalue sequence; select a preset number of elements in the accumulated feature enhancement sequence in the order from back to front, and determine whether the selected elements are less than a preset contraction feature threshold; when less than the preset contraction feature threshold, control the integrated functional patch to continue generating therapeutic electrical pulses, otherwise, control the integrated functional patch to generate relaxation electrical pulses.

[0010] Further, the wearable integrated device for electromyogram monitoring and electrical stimulation intervention further includes:

[0011] A muscle contraction abnormality reference value generation module, which is used to generate a muscle contraction abnormality reference value according to the linear quantization estimation adjustment factor and the elements in the accumulated feature enhancement sequence;

[0012] A muscle contraction abnormality reference value output module, which is used to output the muscle contraction abnormality reference value generated by the muscle contraction abnormality reference value generation module for reference.

[0013] Further, the control module includes:

[0014] A stimulation electrical pulse intensity calculation unit, which is used to calculate the stimulation electrical pulse intensity according to the last element in the accumulated feature enhancement sequence, the fat layer and the skin thickness;

[0015] A relaxation electrical pulse intensity calculation unit, which is used to calculate the relaxation electrical pulse intensity according to the last element in the accumulated feature enhancement sequence, the fat layer and the skin thickness.

[0016] Further, the muscle force generation period electromyogram signal processing module includes:

[0017] A muscle force generation period electromyogram signal division unit, which is used to divide the muscle force generation period according to the smooth change degree of the collected surface electromyogram signal.

[0018] Further, the electromyogram signal preprocessing module includes:

[0019] A normalization processing unit, which is used to normalize the collected surface electromyogram signal sequence.

[0020] Further, the electromyogram signal preprocessing module further includes:

[0021] A denoising unit, configured to perform denoising processing on the surface electromyogram signal after normalization processing.

[0022] Furthermore, the denoising unit is used for:

[0023] Select a wavelet basis type and the level N of wavelet decomposition, perform N-layer wavelet decomposition on the noisy signal to obtain wavelet coefficients of each layer;

[0024] Threshold quantization of the high-frequency coefficients of wavelet decomposition, adopting a soft threshold quantization method, setting a threshold λ. When the wavelet coefficients converge to 0, the coefficients greater than λ are set to parameters related to λ, and for the wavelet coefficients less than λ, they are directly set to 0 to obtain a smoother denoised signal;

[0025] Reconstruct the processed signal to obtain a new denoised sequence.

[0026] The wearable electromyogram monitoring and electrical stimulation intervention integrated device provided by the embodiment of the present invention, by setting an integrated functional patch for collecting surface electromyogram signals in a motion state and applying electrical stimulation to muscles; an electromyogram signal preprocessing module for preprocessing the surface electromyogram signal sequence collected by the integrated functional patch; a power phase electromyogram signal processing module for extracting a power phase signal subsequence in the muscle gait movement from the preprocessed surface electromyogram signal sequence; calculating the eigenvalue of each power phase signal subsequence, and the eigenvalue of the power phase signal subsequence reflects the sum of the deviation degrees of each signal in the power phase; a control module for creating an eigenvalue sequence based on the eigenvalue of each power phase signal subsequence; generating an accumulated feature enhancement sequence based on the eigenvalue sequence; selecting a preset number of elements in the reverse order from the accumulated feature enhancement sequence, and determining whether the selected elements are less than a preset contraction feature threshold; when less than the preset contraction feature threshold, controlling the integrated functional patch to continue generating therapeutic electrical pulses, otherwise, controlling the integrated functional patch to generate relaxation electrical pulses. It can use the electromyogram detection integrated patch worn on the surface of the patient's muscle to collect muscle group signals in real time through electromyogram detection electrodes and transmit them to the signal processing module for preprocessing; then through the feature extraction module, digital filtering and dynamic electromyogram feature calculation are performed; the obtained electromyogram features are analyzed by the feature recognition unit and fed back to the main control, and the main control correspondingly outputs an electrical stimulation signal with a certain frequency and duty cycle, which is amplified and processed by the electrical stimulation circuit and applied to the patient's muscle part by the electrical stimulation electrode. It can realize real-time monitoring and real-time intervention according to the monitoring results. Description of the Drawings

[0027] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:

[0028] Figure 1 It is a schematic structural diagram of a computing device in the integrated wearable myoelectric monitoring and electrical stimulation intervention device provided by an embodiment of the present invention. Detailed implementation manners

[0029] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. Additionally, it should be noted that for the convenience of description, only parts related to the present invention rather than all structures are shown in the drawings.

[0030] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0031] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "center", "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. In addition, the terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first", "second", etc. may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise stated, the meaning of "a plurality" is two or more.

[0032] In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, the terms "mounted", "connected", "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood through specific situations.

[0033] Figure 1 is a schematic structural diagram of the integrated wearable myoelectric monitoring and electrical stimulation intervention device provided by an embodiment of the present invention. Refer to Figure 1 , the integrated wearable myoelectric monitoring and electrical stimulation intervention device includes:

[0034] Integrated functional patch, which can be realized by combining a wire cap, a flexible patch, a surface electromyography sensor, and an electrical stimulation therapy electrode. The flexible patch is attached to the surface of the user's muscle to collect the electromyography signals generated during the user's walking. And corresponding pulse signals can be generated through the electrical stimulation therapy electrode. The surface electromyography sensor adopts a multi-channel electrode system and can collect 6-8 channel signals. The electrode substrate uses a gel patch electrode, which is bipolar, and a reference electrode is inserted between the two electrodes to help reduce noise and improve the ability to suppress common-mode signals.

[0035] Correspondingly, the integrated device for wearable electromyography monitoring and electrical stimulation intervention may further include a main control system. The main control system can perform real-time processing on the collected surface electromyography signals to determine whether the current muscle is in an abnormal contraction state. And generate a control signal according to the judgment result, and use this control signal to control the electrical stimulation therapy electrode to switch between treatment and sending electrical pulses.

[0036] Exemplarily, the main control system may include:

[0037] An electromyography signal preprocessing module, which is used to preprocess the surface electromyography signal sequence collected by the integrated functional patch to meet the requirements for judging whether the current muscle is in an abnormal contraction state. Optionally, the electromyography signal preprocessing module can perform processing such as normalization and denoising. Exemplarily, analog-to-digital conversion can be performed through an AD module to form a digital sequence, and corresponding preprocessing can be performed on the digital sequence.

[0038] A power generation period electromyography signal processing module, which is used to extract the power generation period signal subsequence in the muscle gait movement from the preprocessed surface electromyography signal sequence; calculate the eigenvalue of each power generation period signal subsequence, and the eigenvalue of the power generation period signal subsequence reflects the sum of the deviation degrees of each signal in the power generation period.

[0039] First, according to the smoothness of the signals in the surface electromyography signal sequence obtained by the above electromyography signal preprocessing module, it can be determined whether it is the power generation period. Since the muscle movement in the power generation period is relatively more intensive and the electromyography signal intensity is greater. Therefore, the power generation period signal subsequence in the muscle gait movement can be extracted from the preprocessed surface electromyography signal sequence by using the smoothness.

[0040] After obtaining the power generation period signal subsequence, calculate the eigenvalue of each power generation period signal subsequence, and this eigenvalue is used to reflect the deviation degree of each signal in the power generation period. Exemplarily, the average value of each signal in the power generation period can be calculated, and the difference between each signal and the average value can be calculated, and then the deviation degree can be calculated. Or use the signal value at a certain action or moment in the power generation period of the user's movement gait as the standard value, and the standard value of each user is different. Use this standard value to calculate the eigenvalue.

[0041] In this embodiment, the following method is adopted to calculate the eigenvalue of each of the force application period signal subsequences:

[0042]

[0043] where S i represents the eigenvalue of the force application period in the i-th gait motion cycle in the EMG sequence X″′, and x i ″′(p) is the p-th EMG signal value in the force application period of the i-th gait motion cycle, p ∈ [1, m], i ∈ [1, q], and both m and q are positive integers.

[0044] Using this calculation method, the discrete degree of the signal volume in this force application period can be fully reflected, and the sequence structure and properties can be measured.

[0045] The control module is used to create an eigenvalue sequence based on the eigenvalues of each force application period signal subsequence; generate an accumulated feature enhancement sequence based on the eigenvalue sequence; select a preset number of elements in the reverse order from the accumulated feature enhancement sequence, and determine whether the selected elements are less than a preset contraction feature threshold; when less than the preset contraction feature threshold, control the integrated functional patch to continue generating therapeutic electrical pulses, otherwise, control the integrated functional patch to generate relaxation electrical pulses.

[0046] In this embodiment, the control module can continuously and real-time detect according to the force application period signal subsequences corresponding to the real-time collected signals. Exemplarily, an eigenvalue sequence can be created based on the eigenvalues of each force application period signal subsequence; an accumulated feature enhancement sequence can be generated based on the eigenvalue sequence.

[0047] Exemplarily, an eigenvalue sequence S = [S1, S2, ……, S i can be formed, where the number of elements in the eigenvalue sequence S is continuously increasing. Add adjacent two terms of the obtained eigenvalue sequence to form an accumulated feature enhancement sequence. That is, it is achieved through the following method:

[0048] I = [I1, I2, ……, Ij], j ∈ [1, i - 1], where I j = Sj + Sj +1 . Similar to the eigenvalue sequence, the number of elements in the accumulated feature enhancement sequence is also continuously increasing.

[0049] In this embodiment, the reason for using the elements in the cumulative feature enhancement sequence to evaluate the degree of muscle contraction instead of directly using eigenvalue calculation is mainly found in the actual operation process: Using the eigenvalue of a single force generation period alone is prone to misjudgment, that is, the eigenvalue is closely related to each force generation period, the walking environment, and the walking manner. Even if the EMG signal is preprocessed in the early stage, a large error will still occur. Experiments show that a single eigenvalue sequence has the disadvantages of disorder, non-linearity, and randomness, which is not conducive to judging the degree of fatigue. Through the method of processing the cumulative feature enhancement sequence, experiments have proved that it can be linear and ordered. It can better and more accurately reflect the degree of contraction.

[0050] Exemplarily, since the number of elements in the cumulative feature enhancement sequence increases continuously with the user's walking movement and real-time acquisition. Since the cumulative feature enhancement sequence corresponding to the EMG signal collected earlier has little reference significance, therefore, according to a preset number of elements in the reverse order from the back, where the last element is the newly generated one, it is judged whether the selected element is less than the preset contraction feature threshold.

[0051] For the analysis of abnormal muscle contraction, the following non-absolutely quantitative method can be used: When I j ≥α, the possibility of abnormal muscle contraction is negatively correlated with the magnitude of I j ; when I j <α, the muscle is in the stage of abnormal contraction, where α is the normal muscle contraction threshold, usually taking 0.00716.

[0052] Optionally, after obtaining the relevant cumulative sequence, the cumulative sequence signal is transmitted to the PC side in the form of Bluetooth, and the electrical stimulation instruction is transmitted back after a decision is made on the PC side.

[0053] An intervention signal in the form of a pulse is used, with the pulse frequency between 50 - 75 Hz and the duration of 200 - 400 μs. The pulse form signal is used to make the muscle better adapt to the current. The control module may include: a stimulating electric pulse intensity calculation unit for calculating the stimulating electric pulse intensity according to the last element in the cumulative feature enhancement sequence, the fat layer, and the skin thickness; a relaxing electric pulse intensity calculation unit for calculating the relaxing electric pulse intensity according to the last element in the cumulative feature enhancement sequence, the fat layer, and the skin thickness. Regarding real-time intensity adjustment, when I j ≥α, this unit applies a relaxing mode electric pulse corresponding to the I j value to the specified muscle, and the electric stimulation intensity is within the upper limit of the voltage amplitude of 5 V and the upper limit of the current amplitude of 100 mA; when I j <α, this unit applies an enhancing mode electric pulse corresponding to the I j value to the specified muscle. When I jWhen the electric pulse intensity γ = 10000×K1×(I j -α) mA when I ≥ α. When I j < α, the electric stimulation intensity γ = 10000×K2×(I j -α - I j ) mA. The values of K1 and K2 are determined by the fat layer and skin thickness of the person being tested. Generally, the value of K1 ranges from 0.23 to 0.30, and the value of K2 ranges from 0.46 to 0.54.

[0054] The wearable integrated device for myoelectric monitoring and electrical stimulation intervention may also be provided with a muscle contraction abnormality reference value generation module for generating a muscle contraction abnormality reference value according to the linearly quantified estimation adjustment factor and the elements in the cumulative feature enhancement sequence; a muscle contraction abnormality reference value output module for outputting the muscle contraction abnormality reference value generated by the muscle contraction abnormality reference value generation module for reference.

[0055] Exemplarily, the values of each element in the cumulative sequence are input into a specific calculation and comparison unit for evaluating the possibility of muscle contraction abnormality. The calculation method is as follows: ρ j = 1 - β×I j , where ρ j represents the possibility of muscle contraction abnormality in the j-th gait movement cycle during exercise. Among them, β can be a linearly quantified estimation parameter. Using the above evaluation results, it can provide reference for physicians or users. For physicians, targeted treatment can be carried out, and for users, the exercise mode and force application mode can be adjusted in time to avoid injury.

[0056] By setting an integrated functional patch for collecting surface electromyography signals during exercise and applying electrical stimulation to muscles; an electromyography signal preprocessing module for preprocessing the surface electromyography signal sequence collected by the integrated functional patch; a muscle force generation period electromyography signal processing module for extracting the muscle gait movement force generation period signal subsequence from the preprocessed surface electromyography signal sequence; calculating the eigenvalue of each said muscle force generation period signal subsequence, the eigenvalue of the muscle force generation period signal subsequence reflecting the sum of the deviation degrees of each signal in the muscle force generation period; a control module for creating an eigenvalue sequence based on the eigenvalue of each muscle force generation period signal subsequence; generating an accumulated feature enhancement sequence based on the eigenvalue sequence; selecting a preset number of elements in the reverse order from the accumulated feature enhancement sequence, and determining whether the selected elements are less than a preset real-time contraction feature threshold; when less than the preset contraction feature threshold, controlling the integrated functional patch to generate a stimulation electrical pulse, otherwise, controlling the integrated functional patch to generate a relaxation electrical pulse. The muscle group signals can be collected in real time through the electromyography detection electrodes of the electromyography detection integrated patch worn on the patient's muscle surface and transmitted to the signal processing module for preprocessing; then, through the feature extraction module, digital filtering and dynamic electromyography feature calculation are carried out; the obtained electromyography features are analyzed by the feature recognition unit and fed back to the main control, and the main control correspondingly outputs an electrical stimulation signal with a certain frequency and duty cycle, which is amplified and processed by the electrical stimulation circuit and then applied to the patient's muscle part by the electrical stimulation electrodes. Real-time monitoring can be realized and intervention can be carried out in real time according to the monitoring results.

[0057] In addition, in this embodiment, the electromyography signal preprocessing module includes: a normalization processing unit for normalizing the collected surface electromyography signal sequence. Exemplarily, first, the muscle electrical signals collected by the flexible circuit group are subjected to analog-to-digital conversion through the AD module, and a certain length of original signal x1, x2,..., x n , the signal length is determined according to the actual situation. Assume that the maximum value of the original signal during the detection of this section of signal is x t , that is, after x t , the size of the original electrical signal data drops significantly, and the judgment criterion is When , it is judged that this detection period is a valid period, otherwise it is regarded as noise signal filtering. When , it is determined that x n is the last electromyography data of this period.

[0058] Normalize the collected single-cycle electromyography signal. The normalization is calculated based on the following formula: Where X′ = x(n)′ ∈ [0, 1] is the normalized electromyogram signal sequence, n is the position of the element in the sequence, and X = x(n) is the electromyogram signal sequence before normalization. The purpose of normalization is that the existence of singular sample data will increase the data processing time, resulting in the main control processing timeout and the inability to achieve the real-time integration of detection and stimulation. At the same time, it may also cause the algorithm not to converge during training. Therefore, it is necessary to normalize the preprocessed data before data processing; if normalization is not performed, due to the large difference in the values of different features in the feature vector, it will lead to the lack of target function features. In this way, when performing gradient descent, the direction of the gradient will deviate from the direction of the minimum value, significantly affecting the efficiency of real-time electrical stimulation.

[0059] In addition, the electromyogram signal preprocessing module further includes: a denoising unit for denoising the surface electromyogram signal after normalization processing. The denoising unit is used to: select a wavelet basis type and the level N of wavelet decomposition, perform N-layer wavelet decomposition on the noisy signal to obtain wavelet coefficients of each layer; perform threshold quantization on the high-frequency coefficients of wavelet decomposition, adopt the soft threshold quantization method, set the threshold λ, when the wavelet coefficient converges to 0, the coefficient greater than λ is set to a parameter related to λ, and for the wavelet coefficient less than λ, it is directly set to 0 to obtain a smoother denoised signal; reconstruct the processed signal to obtain a new denoised sequence.

[0060] Exemplarily, the normalized electromyogram signal sequence can be wavelet denoised. The expression of the noisy signal is: x(t) = y(t) + n(t). Wavelet denoising is divided into three steps. The first step is the wavelet decomposition of the signal. Select a wavelet basis type and the level N of wavelet decomposition, perform N-layer wavelet decomposition on the noisy signal to obtain wavelet coefficients of each layer. The second step is the threshold quantization of the high-frequency coefficients of wavelet decomposition. Adopt the soft threshold quantization method and set a threshold MAD is the median absolute deviation, and n is the length of the signal. When the wavelet coefficient converges to 0, the coefficient greater than λ is set to sgn(W)(|W| - λ), and for the wavelet coefficient less than λ, it is directly set to 0, and a smoother denoised signal can be obtained. The third step is the wavelet signal reconstruction. Reconstruct the processed signal to obtain a new denoised sequence.

[0061] The purpose of wavelet denoising is that in the process of integrated detection and treatment, the detection of electromyogram signals is accompanied by the interference of electrical stimulation signals. The wavelet denoising algorithm is simple and clear, and the calculation speed is fast. If N is the length of the signal, its calculation speed is O(N). In addition, the electrical stimulation signal is controlled by the main control unit, which can be regarded as noise with a known frequency range and the frequency bands of the signal and noise are separated from each other, and the denoising effect is excellent.

[0062] By using the above means, effective preprocessing of the collected EMG signals can be achieved, thereby providing a judgment basis for subsequent real-time and accurate electrical stimulation intervention.

[0063] Note that the above is only the preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A wearable integrated device for electromyogram monitoring and electrical stimulation intervention, characterized in that, Including: An integrated functional patch for collecting surface electromyography signals during exercise and applying electrical stimulation to muscles; An electromyography signal preprocessing module for preprocessing the surface electromyography signal sequence collected by the integrated functional patch; A muscle force generation period electromyography signal processing module for extracting the muscle gait movement force generation period signal subsequence from the preprocessed surface electromyography signal sequence; Calculating the eigenvalue of each of the force generation period signal subsequences, including: Calculating the deviation degree by calculating the average value of each signal in the force generation period and calculating the difference between each signal and the average value; Or using the signal value at a certain action or moment in the muscle gait force generation period of the user as a standard value, and calculating the eigenvalue using this standard value; the eigenvalue of the force generation period signal subsequence reflects the deviation degree of each signal in the force generation period, and the eigenvalue of each force generation period signal subsequence is calculated in the following manner: Among them, S i represents the eigenvalue of the force generation period in the i-th gait movement cycle in the electromyogram sequence X″′, x″′ i (p) is the p-th electromyogram signal value in the force generation period of the i-th gait movement cycle, p ∈ [1, m], i ∈ [1, q], and both m and q are positive integers; A control module for creating an eigenvalue sequence based on the eigenvalue of each force generation period signal subsequence; generating an accumulated feature enhancement sequence based on the eigenvalue sequence; selecting a preset number of elements in the reverse order from the accumulated feature enhancement sequence, and determining whether the selected elements are less than a preset contraction feature threshold; when less than the preset contraction feature threshold, controlling the integrated functional patch to continue generating therapeutic electrical pulses, otherwise, controlling the integrated functional patch to generate relaxation electrical pulses.

2. The integrated wearable device for myoelectric monitoring and electrical stimulation intervention according to claim 1, wherein The wearable integrated electromyography monitoring and electrical stimulation intervention device further includes: A muscle contraction abnormality reference value generation module for generating a muscle contraction abnormality reference value according to the linear quantization estimation adjustment factor and the elements in the accumulated feature enhancement sequence; A muscle contraction abnormality reference value output module for outputting the muscle contraction abnormality reference value generated by the muscle contraction abnormality reference value generation module for reference.

3. The integrated wearable device for myoelectric monitoring and electrical stimulation intervention according to claim 1, wherein The control module includes: A stimulation electrical pulse intensity calculation unit for calculating the stimulation electrical pulse intensity according to the last element in the accumulated feature enhancement sequence, the fat layer and the skin thickness; A relaxation electrical pulse intensity calculation unit for calculating the relaxation electrical pulse intensity according to the last element in the accumulated feature enhancement sequence, the fat layer and the skin thickness.

4. The integrated wearable device for myoelectric monitoring and electrical stimulation intervention according to claim 1, characterized in that, The muscle force generation period electromyography signal processing module includes: A muscle force generation period electromyography signal division unit for dividing the muscle force generation period according to the smooth change degree of the collected surface electromyography signals.

5. The integrated wearable electromyogram monitoring and electrical stimulation intervention device according to claim 1, wherein, The electromyography signal preprocessing module includes: A normalization processing unit for normalizing the collected surface electromyography signal sequence.

6. The integrated wearable electromyogram monitoring and electrical stimulation intervention device according to claim 5, wherein The electromyography signal preprocessing module further includes: A denoising unit for denoising the normalized surface electromyography signal.

7. The integrated wearable electromyogram monitoring and electrical stimulation intervention device according to claim 6, characterized in that, The denoising unit is used for: Selecting a wavelet basis type and the level N of wavelet decomposition, performing N-layer wavelet decomposition on the noisy signal to obtain the wavelet coefficients of each layer; Threshold quantization of the high-frequency coefficients of wavelet decomposition, adopting a soft threshold quantization method, setting the threshold λ, when the wavelet coefficients converge to 0, the coefficients greater than λ are set to parameters related to λ, and for the wavelet coefficients less than λ, they are directly set to 0 to obtain a smoother denoised signal; Reconstructing the processed signal to obtain a new denoised sequence.

Images