Neuromuscular electrical stimulation rehabilitation control method and system based on electroencephalogram intention recognition

Abstract

The invention discloses a neuromuscular electrical stimulation rehabilitation control method and system based on electroencephalogram intention recognition, and relates to the technical field of intelligent rehabilitation control, and the method comprises the steps: collecting electroencephalogram signal data of a user in a rehabilitation training process, processing the electroencephalogram signal data, constructing an electroencephalogram intention discrimination model, and dynamically recognizing the current motion intention category of the user. Outputting a corresponding intention signal and a confidence coefficient; and outputting a neuromuscular electrical stimulation parameter set by adopting a neuromuscular electrical stimulation parameter optimization model according to the identified intention signal, the confidence coefficient and the current myoelectricity state, sending the neuromuscular electrical stimulation parameter set to neuromuscular electrical stimulation equipment, and controlling the target muscle group to perform electrical stimulation. According to the method disclosed by the invention, by constructing the electroencephalogram intention real-time identification and neuromuscular electrical stimulation closed-loop optimization control method, high-quality preprocessing of electroencephalogram signals, dynamic discrimination of intention and self-adaptive optimization of individualized electrical stimulation parameters are realized, and the motion intention and the myoelectricity state of the user can be accurately matched.

Description

Technical Field

[0001] The present invention relates to the field of intelligent rehabilitation control technology, and in particular to a neuromuscular electrical stimulation rehabilitation control method and system based on EEG intention recognition. Background Art

[0002] With the continuous development of neuroscience and rehabilitation medicine, the application of EEG-driven neuromodulation technology in the rehabilitation of motor dysfunction has attracted increasing attention. In recent years, brain-computer interface technology has rapidly advanced, enabling real-time acquisition and intelligent decoding of EEG signals, providing a data foundation for motor intention recognition and neuromuscular regulation. Furthermore, neuromuscular electrical stimulation, as an effective means of restoring muscle function, has been widely used in rehabilitation training for patients with hemiplegia, paraplegia, and muscular atrophy. Current research focuses on how to deeply integrate EEG intention recognition with personalized electrical stimulation control to form closed-loop, adaptive intelligent rehabilitation control strategies to enhance the accuracy and effectiveness of rehabilitation training.

[0003] At present, there are still many shortcomings in the existing EEG intention recognition and neuromuscular electrical stimulation control methods. First, the existing technologies mostly use simple feature extraction and classification algorithms, lack of sufficient exploration of the dynamic timing characteristics and nonlinear relationships in EEG signals, resulting in limited intention recognition accuracy and difficulty in meeting the real-time and stability requirements in complex rehabilitation scenarios. Secondly, most existing neuromuscular electrical stimulation strategies rely on preset parameters or fixed mapping relationships, lack of deep linkage mechanisms with the user's current intention confidence and myoelectric state, and cannot achieve dynamic optimization of stimulation parameters based on individual physiological states, which is prone to problems of insufficient or excessive stimulation. In addition, existing systems mostly use open-loop or semi-open-loop control architectures, lack of real-time myoelectric feedback closed-loop optimization, and difficulty in achieving individualized adaptive regulation of the electrical stimulation process. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: the existing EEG intention recognition and neuromuscular electrical stimulation control methods have insufficient intention recognition accuracy, lack of dynamic optimization mechanism for electrical stimulation parameters, lack of real-time closed-loop adaptive control capabilities, and how to achieve individualized optimization control of neuromuscular electrical stimulation based on real-time EEG intention driving.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition, comprising: using a multi-channel EEG acquisition device to collect the user's EEG signal data during rehabilitation training in real time, performing band-pass filtering, artifact removal and adaptive noise suppression on the EEG signal data, and outputting a purified EEG signal data stream; performing feature extraction on the purified EEG signal data stream, outputting a movement intention feature vector, constructing an EEG intention discrimination model to dynamically identify the user's current movement intention category, and outputting the corresponding intention signal and confidence; according to the identified intention signal and confidence as well as the current electromyography state, using a neuromuscular electrical stimulation parameter optimization model to output a neuromuscular electrical stimulation parameter set, and sending it to the neuromuscular electrical stimulation device to control the target muscle group for electrical stimulation.

[0007] As a preferred solution of the neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition described in the present invention, the bandpass filtering includes setting the passband range to 0.5 Hz to 45 Hz.

[0008] As a preferred solution of the neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition described in the present invention, the feature extraction includes extracting the movement intention feature vector from the purified EEG signal data stream by combining wavelet packet decomposition and power spectral density analysis.

[0009] As a preferred solution of the neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition described in the present invention, the EEG intention discrimination model includes performing kernel mapping processing on the motion intention feature vector, combining dynamic timing features and nonlinear activation functions to construct a multidimensional feature mapping space, and outputting corresponding intention signals and confidence levels.

[0010] As a preferred solution of the neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition described in the present invention, the output corresponding intention signal and confidence include intention category discrimination based on the confidence and the preset category threshold, and the final movement intention category is determined by comparing the discrimination score of each movement intention category with the corresponding threshold.

[0011] As a preferred solution of the neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition described in the present invention, the neuromuscular electrical stimulation parameter optimization model includes the fusion of movement intention category, intention confidence and real-time electromyographic state information, and adopts an optimization algorithm including nonlinear mapping, integral feedback and normalization regulation mechanism to output the electrical stimulation current amplitude, frequency and pulse width.

[0012] As a preferred solution of the neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition described in the present invention, the output neuromuscular electrical stimulation parameter set includes real-time collection of electromyographic response feedback data during the neuromuscular electrical stimulation process, and a dynamic adaptive adjustment mechanism is used based on the feedback data to update the feature weights, normalization regulation factors and feedback gain coefficients in the neuromuscular electrical stimulation parameter optimization model.

[0013] Another object of the present invention is to provide a neuromuscular electrical stimulation rehabilitation control system based on EEG intention recognition, which can extract features from the purified EEG signal data stream, output the movement intention feature vector, construct an EEG intention discrimination model to dynamically identify the user's current movement intention category, and output the corresponding intention signal and confidence level, thereby solving the problem of insufficient intention recognition accuracy in current EEG intention recognition and neuromuscular electrical stimulation control methods.

[0014] As a preferred solution of the neuromuscular electrical stimulation rehabilitation control system based on EEG intention recognition described in the present invention, it includes: an EEG signal real-time acquisition and preprocessing module, a movement intention feature extraction and dynamic discrimination module, and a neuromuscular electrical stimulation parameter optimization and execution control module; the EEG signal real-time acquisition and preprocessing module is used to use a multi-channel EEG acquisition device to collect the user's EEG signal data during rehabilitation training in real time, perform bandpass filtering, artifact removal, and adaptive noise suppression on the original EEG signal, and output a purified EEG signal data stream; the movement intention feature extraction and dynamic discrimination module is used to extract features from the purified EEG signal data stream, generate a movement intention feature vector, and dynamically identify the user's current movement intention category based on the EEG intention discrimination model, and output the intention signal and corresponding confidence in real time; the neuromuscular electrical stimulation parameter optimization and execution control module is used to dynamically generate a stimulation current amplitude, frequency, and pulse width parameter set based on the real-time identified movement intention signal, intention confidence, and current electromyography state, using a neuromuscular electrical stimulation parameter optimization model, to control the neuromuscular electrical stimulation device to drive the target muscle group to implement electrical stimulation.

[0015] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of a neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition.

[0016] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition.

[0017] Beneficial effects of the present invention: The neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition provided by the present invention can effectively eliminate low-frequency drift, high-frequency noise and non-brain source interference through real-time acquisition and high-quality preprocessing of multi-channel EEG signals, significantly improve the signal-to-noise ratio and stability of movement intention features, and provide reliable data support for subsequent intention discrimination. Based on dynamic feature extraction and kernel mapping discrimination model, high-precision real-time recognition of the user's current movement intention category and confidence level is achieved, and the electrical stimulation control strategy can be dynamically adjusted according to the user's intention, enhancing the active interactivity and individual adaptability of rehabilitation training. By integrating the neuromuscular electrical stimulation parameter optimization model of intention signal, confidence level and electromyographic state, it is possible to dynamically generate an individualized electrical stimulation parameter set to accurately match the user's physiological state and intention requirements, avoiding the problem of insufficient or excessive stimulation caused by traditional fixed parameter stimulation. Overall, the present invention realizes deep coupling and closed-loop optimization of EEG intention and electrical stimulation control, significantly improving the real-time, accuracy and safety of rehabilitation training, and has technical effects that are superior to existing open-loop control or static parameter mapping methods. It has important application prospects for improving the efficiency of neuromuscular function rehabilitation and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is an overall flow chart of a neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition provided in the first embodiment of the present invention.

[0020] Figure 2 A logical step diagram of a neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition provided in the first embodiment of the present invention.

[0021] Figure 3 This is an overall flow chart of a neuromuscular electrical stimulation rehabilitation control system based on EEG intention recognition provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0022] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0023] Example 1, with reference to Figure 1-Figure 2 , as one embodiment of the present invention, provides a neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition, comprising: S1: Through multi-channel EEG acquisition equipment, the user's EEG signal data during rehabilitation training is collected in real time, and the EEG signal data is subjected to bandpass filtering, artifact removal and adaptive noise suppression processing, and the purified EEG signal data stream is output.

[0024] Furthermore, by configuring multi-channel EEG acquisition equipment, real-time EEG activity signals from users during rehabilitation training scenarios can be collected. A high-sampling rate (no less than 512 Hz), multi-channel (no less than 16 channels) EEG acquisition system is preferred, covering key brain regions related to motor intention, such as the prefrontal cortex, central region, and parietal lobe.

[0025] The collected original EEG signal Motion artifacts, power frequency interference, and physiological noise are common, so multi-stage preprocessing is required. First, a bandpass filter (typical passband range 0.5 Hz to 45 Hz) is used to clean the signal in the frequency domain to remove low-frequency drift and high-frequency noise.

[0026] Subsequently, the independent component analysis (ICA) algorithm was applied to remove artifacts from the signal and separate and remove non-brain source components such as electrooculography and electromyography.

[0027] On this basis, an adaptive noise suppression algorithm (such as a transform domain adaptive filter) is used to suppress the remaining noise in real time, and finally the purified EEG signal is output. .

[0028] To further enhance feature availability, Normalization and segmented window processing are performed, and a sliding window mechanism (window width , sliding step length ) slices the continuous signal to provide a high-quality and stable data input source for subsequent feature extraction and intent discrimination models.

[0029] S2: Extract features from the purified EEG signal data stream, output the motion intention feature vector, build an EEG intention discrimination model to dynamically identify the user's current motion intention category, and output the corresponding intention signal and confidence level.

[0030] Furthermore, the purified EEG signal data is subjected to feature extraction processing using the time-frequency domain analysis method, wherein the wavelet packet decomposition and power spectrum density method are preferably used to extract the multidimensional EEG intention feature vector On this basis, based on the extracted EEG features, an EEG intention discrimination model is constructed. A discrimination mathematical model based on nested kernel mapping and temporal dynamic integral structure is preferably designed, and its discrimination score is Expressed as:

[0031] in, For the moment Target category The calculated motion intention discrimination score, is the EEG feature vector dimension, For the The coefficient of the feature, For the moment Extracted EEG characteristic value, the unit is energy density, For the The dynamic adjustment function corresponding to each feature, is the characteristic scaling factor, is the normalization adjustment parameter, For the The suppression factor of the feature, a positive real number, Indicates at time , No. The EEG feature value corresponding to each channel (or dimension).

[0032] like , indicating the category The intention judgment is very strong; if , in the critical judgment state; if , then it is not currently classified as a category .

[0033] It should be noted that the trained EEG intention classification model distinguishes the following four categories of movement intention tables, as shown in Table 1.

[0034] Table 1 Movement intention table

[0035] The threshold should be based on the discriminant score in a large number of EEG training samples. The usual practice is to use the mean of the positive discrimination scores of the training set and standard deviation , set to:

[0036] in is a regulating factor, usually , ensuring that the discrimination has a certain tolerance and avoiding overfitting.

[0037] Finally, the output After: If , then it is classified as category ; The system can be used at every moment , respectively calculated ; and compare their respective thresholds ,Finally, the category that meets the conditions and has the highest score is selected as the discrimination result.

[0038] During the rehabilitation training process, the system will The collected EEG feature vector Input the constructed EEG intention discrimination model and dynamically calculate each category The discrimination score of The judgment rule is set as follows: If , then the current classification is motion intention ; If there are multiple categories that meet the conditions, select The largest category is taken as the final judgment result.

[0039] The final output motion intention category signal The corresponding confidence information will serve as an important input for the generation and optimization of neuromuscular electrical stimulation parameters, driving the subsequent rehabilitation training control process.

[0040] S3: Based on the identified intention signal and confidence level as well as the current electromyographic state, the neuromuscular electrical stimulation parameter optimization model is used to output the neuromuscular electrical stimulation parameter set, which is sent to the neuromuscular electrical stimulation device to control the target muscle group for electrical stimulation.

[0041] Furthermore, based on the real-time recognized intention signal and confidence level, combined with the currently collected electromyographic state data, a neuromuscular electrical stimulation parameter optimization model is used;

[0042] in, For the moment The electrical stimulation current amplitude, is the electrical stimulation frequency, is the electrical stimulation pulse width, is the total dimension of input features, For the The weight of the dimensional feature on the amplitude adjustment, For the dimensional input eigenvalue, select ,in is the confidence of the current intent category, For the Real-time electromyographic signals of the channel, is the dynamic activation function, is the normalized adjustment factor, is the suppression coefficient, is the reference frequency scaling factor, Optimize the integration window width for frequency, represents the dynamic feedback weight, is the error between expected and actual myoelectricity, is the EMG change rate mapping angle, is the pulse width modulation gain coefficient, represents composite feature input, is the pulse width mapping coefficient, is the pulse width normalization adjustment factor, Indicates at time , No. The fusion signal value of the input features is usually the product of the intention confidence and the current electromyographic signal.

[0043] The value range is , typically , corresponding to low-intensity to high-intensity stimulation; The value range is , typically , low-frequency stimulation is used for relaxation, and high-frequency stimulation is used for contraction; The value range is , typically , the larger the pulse width, the stronger the stimulation depth.

[0044] This optimization model integrates intent category, intent confidence, and myoelectric state. Through a nonlinear mapping function, integral feedback, and normalized regulation, it dynamically adjusts electrical stimulation parameters, ensuring that the output parameters match the user's current movement intent and physiological state in real time. The optimization model supports adaptive parameter adjustment and dynamically optimizes the electrical stimulation control strategy based on individual user differences and real-time state changes. The resulting set of electrical stimulation parameters is transmitted in real time to the neuromuscular electrical stimulation device via an interface, driving the target muscle group to produce movement outputs that closely match the user's intent.

[0045] It should be noted that during the execution of neuromuscular electrical stimulation, electromyographic response feedback data is collected in real time, including the dynamic change trend of the electromyographic signal of the target muscle group after the stimulation response, and the difference information between the output and the expected movement intention.

[0046] The collected feedback data is input into the neuromuscular electrical stimulation parameter optimization model. Through the dynamic adaptive adjustment mechanism, the feature weights, normalization regulation factors and feedback gain coefficients in the model are updated in real time to achieve online optimization and adaptive learning of the model parameters.

[0047] Through closed-loop feedback optimization, the system can continuously optimize the output of electrical stimulation parameters according to changes in the user's current state, improve the accuracy, stability and individual adaptability of stimulation control, further enhance the effect of rehabilitation training, reduce the risk of stimulation side effects, and promote the intelligence and efficiency of the neuromuscular function recovery process.

[0048] Example 2, an embodiment of the present invention, provides a neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0049] First, experiments were conducted using a "Neuromuscular Electrical Stimulation Closed-Loop Rehabilitation System Driven by EEG Intention Recognition" to verify the effectiveness and optimization effects of the invented method in rehabilitation training. The experimental subjects were six patients with upper limb motor dysfunction, aged 35 to 55, all undergoing rehabilitation training and capable of expressing voluntary movement intentions. The experimental equipment included a 16-channel EEG acquisition system (sampling rate 512 Hz), a neuromuscular electrical stimulation device, a surface electromyography acquisition system, and a customized rehabilitation training platform.

[0050] During the experimental preparation phase, each subject was fitted with an EEG acquisition cap. A 16-channel layout covering the frontal, central, and parietal lobes was used, focusing on EEG signals related to upper limb movement intention. During EEG acquisition, real-time bandpass filtering (0.5-45 Hz) was performed, and independent component analysis (ICA) was used to remove oculoculographic and myoelectric artifacts. Transform domain adaptive filtering was then used to further suppress residual noise, resulting in a purified EEG signal stream.

[0051] The cleaned EEG signals were then sliced ​​using a sliding window mechanism (window width 1 second, step size 0.2 seconds) and fed into the feature extraction module. Wavelet packet decomposition and power spectral density analysis were used to extract EEG feature vectors, which were then fed into a trained EEG intention discrimination model based on nested kernel mapping and temporal dynamic integration. The model outputs real-time signals for four types of movement intentions (clenching fist, elbow flexion, arm raising, and resting) along with their corresponding confidence scores, which served as input to the neuromuscular electrical stimulation parameter optimization model.

[0052] During the electrical stimulation optimization phase, the model integrates the intent category, confidence level, and current electromyographic state to dynamically generate the electrical stimulation current amplitude A(t), frequency f(t), and pulse width d(t), which are then used to drive the neuromuscular electrical stimulation device in real time through an interface. The target muscles for electrical stimulation are the forearm flexors and biceps brachii on the affected side, with a stimulation frequency range of 10-100 Hz, a current amplitude of 5-100 Hz, a current amplitude of 580 mA, and a pulse width of 50-400 μs.

[0053] Simultaneously, EMG response data from the target muscle groups was collected in real time and fed into an optimization model for online adjustments, enabling closed-loop adaptive control. The experiment involved 30 minutes of continuous training, during which participants were repeatedly guided to actively attempt three types of movement intentions. The system responded in real time, adjusting stimulation parameters to dynamically drive muscle movement.

[0054] Table 2 Experimental data table

[0055] As shown in Table 2, the application of the "Neuromuscular Electrical Stimulation Rehabilitation Control Method Based on EEG Intention Recognition" described in this invention demonstrated significant advantages in the six experimental subjects. First, the accuracy of intent classification was generally above 88%, with a maximum of 93%. This demonstrates that the EEG intention discrimination model has excellent dynamic recognition capabilities. Compared with traditional methods based on linear discrimination or fixed thresholds, it significantly improves the accuracy and real-time performance of intent recognition, ensuring that the electrical stimulation control process can more accurately match user intent.

[0056] Secondly, the mean confidence level of intention remained stable above 0.80, demonstrating the model's adaptability to different subjects during actual rehabilitation training. The confidence output provided a stable basis for subsequent stimulation parameter optimization, supporting real-time dynamic parameter adjustment. Regarding electrical stimulation parameters, the optimization model dynamically adjusted current amplitude, frequency, and pulse width based on the individual state of the subject. During training, all subjects maintained electrical stimulation parameters within a safe and effective range, with no abnormalities of being too high or too low, ensuring the individualized adaptability and safety of electrical stimulation.

[0057] More significantly, the average improvement in electromyographic response (EMR) was approximately 34%, demonstrating the significant advantage of closed-loop optimization in dynamically matching users' physiological states compared to traditional fixed stimulation parameter methods (typically improving by 20% to 25%). Subjective comfort scores were generally above 4, further demonstrating the method's adaptability in terms of user experience and its potential to improve compliance and active participation in rehabilitation training.

[0058] In summary, the results of the examples fully demonstrate that the present invention is superior to the existing technology in terms of EEG intention discrimination accuracy, neuromuscular electrical stimulation parameter optimization capability, closed-loop feedback effect and user experience, reflecting the innovation and novelty of the technical solution in dynamic adaptive control and individualized rehabilitation training, and has good potential for clinical application and promotion.

[0059] Example 3, reference Figure 3 , which is an embodiment of the present invention, provides a neuromuscular electrical stimulation rehabilitation control system based on EEG intention recognition, including an EEG signal real-time acquisition and preprocessing module, a movement intention feature extraction and dynamic discrimination module, and a neuromuscular electrical stimulation parameter optimization and execution control module.

[0060] The real-time EEG signal acquisition and preprocessing module is used to collect the user's EEG signal data in real time during rehabilitation training through a multi-channel EEG acquisition device, perform band-pass filtering, artifact removal, and adaptive noise suppression on the original EEG signal, and output the purified EEG signal data stream. The movement intention feature extraction and dynamic discrimination module is used to extract features from the purified EEG signal data stream, generate a movement intention feature vector, and dynamically identify the user's current movement intention category based on the EEG intention discrimination model. The neuromuscular electrical stimulation parameter optimization and execution control module is used to dynamically generate the stimulation current amplitude, frequency and pulse width parameter set based on the real-time identified movement intention signal, intention confidence and current electromyography state, using the neuromuscular electrical stimulation parameter optimization model, and control the neuromuscular electrical stimulation device to drive the target muscle group to implement electrical stimulation.

[0061] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0062] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0063] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0064] It should be understood that various aspects of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gates for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gates, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc. It should be noted that the above embodiments are intended only to illustrate the technical solutions of the present invention and are not intended to be limiting. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art will understand that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and such modifications are intended to be encompassed by the claims of the present invention.

[0065] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition, characterized in that: include: Through multi-channel EEG acquisition equipment, the user's EEG signal data during rehabilitation training is collected in real time, and the EEG signal data is subjected to bandpass filtering, artifact removal and adaptive noise suppression processing, and the purified EEG signal data stream is output; Perform feature extraction on the purified EEG signal data stream, output the motion intention feature vector, build an EEG intention discrimination model to dynamically identify the user's current motion intention category, and output the corresponding intention signal and confidence level; According to the recognized intention signal and confidence as well as the current electromyographic state, the neuromuscular electrical stimulation parameter optimization model is used to output the neuromuscular electrical stimulation parameter set, which is sent to the neuromuscular electrical stimulation device to control the target muscle group for electrical stimulation.

2. The neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition according to claim 1, characterized in that: The bandpass filtering includes setting the passband range to be 0.5 Hz to 45 Hz.

3. The neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition according to claim 2, characterized in that: The feature extraction includes extracting the motion intention feature vector from the purified EEG signal data stream by combining wavelet packet decomposition and power spectrum density analysis.

4. The neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition according to claim 3, characterized in that: The EEG intention discrimination model includes performing kernel mapping processing on the motion intention feature vector, combining dynamic temporal features with nonlinear activation functions to construct a multidimensional feature mapping space, and outputting corresponding intention signals and confidence levels.

5. The neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition according to claim 4, characterized in that: The outputting of the corresponding intention signal and confidence level includes performing intention category discrimination based on the confidence level and a preset category threshold, and determining a final movement intention category by comparing each movement intention category discrimination score with the corresponding threshold.

6. The neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition according to claim 5, characterized in that: The neuromuscular electrical stimulation parameter optimization model includes the fusion of movement intention category, intention confidence and real-time myoelectric state information, and adopts an optimization algorithm including nonlinear mapping, integral feedback and normalization regulation mechanism to output electrical stimulation current amplitude, frequency and pulse width.

7. The neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition according to claim 6, characterized in that: The output neuromuscular electrical stimulation parameter set includes real-time collection of electromyographic response feedback data during the neuromuscular electrical stimulation process, and updating the feature weights, normalization regulation factors and feedback gain coefficients in the neuromuscular electrical stimulation parameter optimization model using a dynamic adaptive adjustment mechanism based on the feedback data.

8. A system using the neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition according to any one of claims 1 to 7, characterized in that: It includes EEG signal real-time acquisition and preprocessing module, movement intention feature extraction and dynamic discrimination module, neuromuscular electrical stimulation parameter optimization and execution control module; The EEG signal real-time acquisition and preprocessing module is used to collect the user's EEG signal data in real time during rehabilitation training through a multi-channel EEG acquisition device, perform bandpass filtering, artifact removal, and adaptive noise suppression on the original EEG signal, and output a purified EEG signal data stream; The movement intention feature extraction and dynamic discrimination module is used to extract features from the purified EEG signal data stream, generate a movement intention feature vector, and dynamically identify the user's current movement intention category based on the EEG intention discrimination model, and output the intention signal and corresponding confidence level in real time; The neuromuscular electrical stimulation parameter optimization and execution control module is used to dynamically generate stimulation current amplitude, frequency and pulse width parameter sets based on the real-time identified movement intention signal, intention confidence and current myoelectric state, using a neuromuscular electrical stimulation parameter optimization model, and control the neuromuscular electrical stimulation device to drive the target muscle group to implement electrical stimulation.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the neuromuscular electrical stimulation rehabilitation control method based on EEG intention recognition according to any one of claims 1 to 7 are implemented.

Images