Central nervous recovery training control method and system based on electroencephalogram electromyogram coherence analysis, electronic device and storage medium

Abstract

The application discloses a central nervous recovery training control method and system based on electroencephalogram and electromyogram coherence analysis, an electronic device and a storage medium. The central nervous recovery training control system comprises a control processing device. The control processing device is connected with at least one exoskeleton robot, at least one electroencephalogram sensor and at least one electromyogram sensor. The control processing device comprises a relationship setting module, a motion training module, a comparison feature signal acquisition module, a signal acquisition module, a feature signal acquisition module and a matching analysis control module.

Description

Technical Field

[0001] This invention belongs to the field of electronic information technology and relates to a training system, particularly to a central nervous system recovery training control method, system, electronic device and storage medium based on electroencephalogram and electromyogram coherence analysis. Background Technology

[0002] Brain injury often leaves behind different types of functional impairments, with motor dysfunction being the most common and having the greatest impact on patients' daily living activities. If motor function is not rehabilitated in time, symptoms such as muscle atrophy and muscle spasms will gradually appear, severely reducing patients' social participation and quality of life. Daily living activities largely depend on upper limb motor function, and improving upper limb motor function is key to helping patients improve their daily living activities, quality of life, and reintegration into society.

[0003] In recent years, studies such as functional magnetic resonance imaging (fMRI) and PET have shown that the brain possesses strong plasticity. During rehabilitation training, brain-injured patients may achieve motor function recovery through functional or structural remodeling of motor-related connections. Current rehabilitation training mainly includes passive and active rehabilitation training. Active rehabilitation is more beneficial for the functional recovery and neural pathway reconstruction of brain-injured patients. Many external devices are now used in the motor function rehabilitation of brain injuries, such as exoskeleton robots, brain-computer interfaces, electrical stimulation, and magnetic stimulation. However, the application of electroencephalography (EEG) and electromyography (EMG) coherence in the motor function rehabilitation of brain injuries still faces therapeutic limitations.

[0004] In existing studies on EEG-EMG coherence, training some signal components is very difficult, lacking precision and individualization. Further research is needed to determine how to extract effective EEG-EMG coupling based on neural connectivity for use in modulating electrical stimulation models.

[0005] Therefore, there is an urgent need to design a new method for modulating connections associated with specific motor movements to improve motor function, in order to overcome the bottlenecks of existing solutions. Summary of the Invention

[0006] This invention provides a central nervous system recovery training control method, system, electronic device, and storage medium based on electroencephalogram (EEG) and electromyogram (EMG) coherence analysis, which can be used to precisely promote the recovery of motor function caused by nervous system diseases.

[0007] To solve the above-mentioned technical problems, according to one aspect of the present invention, the following technical solution is adopted:

[0008] A central nervous system recovery training control method based on electroencephalogram (EEG) and electromyogram (EMG) coherence analysis, the central nervous system recovery training control method comprising:

[0009] Step S1: Match the set movements of individual limbs with the target muscle movements caused by the corresponding movements;

[0010] Step S2: When an individual performs a set movement training, acquire the EEG signal of the individual's limbs performing the set movement and the EMG signal of the corresponding target muscle; using the EEG signal of the motor-related brain region of the cerebral cortex and the synchronous motor-related target muscle EMG signal, calculate the EEG signal of the neural circuit that has a statistically significant difference from the EMG signal of the target muscle through the Pearson correlation coefficient, and use it as the comparison feature signal of the corresponding neural circuit; before the movement training begins, record the EEG signal and the corresponding target muscle EMG signal in the resting state synchronously;

[0011] Step S3: When an individual limb performs a set action, acquire the EEG signal of the individual limb performing the set action and the EMG signal of the target muscle corresponding to the action; calculate the EEG signal of the neural circuit that has a statistical difference from the EMG signal of the target muscle using the Pearson correlation coefficient, and use it as the feature signal of the corresponding neural circuit; match the feature signal with the feature signal calculated in step S2 to determine whether the obtained feature signal meets the set requirements; if it does not meet the set requirements, control the exoskeleton robot to assist the individual limb in completing the corresponding action.

[0012] In one embodiment of the present invention, in step S1, the action is a single action, and the single action drives a target muscle to perform an action.

[0013] In step S2, when an individual limb is training a set single movement, the electroencephalogram (EEG) signal of the individual limb performing the set single movement and the electromyogram (EMG) signal of the target muscle corresponding to the single movement are acquired.

[0014] Step S3: When an individual limb performs a set single action, acquire the electroencephalogram (EEG) signal of the individual limb performing the set single action and the electromyographic (EMG) signal of the single target muscle corresponding to the action.

[0015] In one embodiment of the present invention, in step S1, the action is a compound action, and the action drives the action of multiple target muscles.

[0016] In step S2, when an individual limb is training a set compound movement, the electroencephalogram (EEG) signal of the individual limb performing the set movement and the electromyographic (EMG) signal of multiple target muscles corresponding to the movement are acquired.

[0017] Step S3: When an individual limb performs a set action, acquire the electroencephalogram (EEG) signal of the individual limb performing the set action and the electromyographic (EMG) signal of multiple target muscles corresponding to the action.

[0018] In one embodiment of the present invention, in step S3, if the obtained feature signal does not meet the set requirements, it indicates that the patient needs to undergo rehabilitation training.

[0019] Step S3 further includes: if the obtained feature signal meets the set requirements, it indicates that the patient can perform the set action with the help of the exoskeleton robot; when the patient sends the control to the exoskeleton robot to perform the set action, the exoskeleton robot helps the patient complete the corresponding action.

[0020] According to another aspect of the present invention, the following technical solution is adopted: a central nervous system recovery training and control system based on electroencephalogram and electromyogram coherence analysis, wherein the central nervous system recovery training and control system includes a control processing device;

[0021] The control processing device is connected to at least one exoskeleton robot, at least one electroencephalogram (EEG) sensor, and at least one electromyogram (EMG) sensor, respectively.

[0022] The exoskeleton robot is installed on a designated individual limb to assist the corresponding individual limb in performing a designated action; the electroencephalogram (EEG) sensor is installed in a designated brain region to sense the EEG signals of the corresponding brain region; the electromyogram (EMG) sensor is installed in a designated target muscle to sense the EMG signals of the target muscle.

[0023] The control processing device includes:

[0024] The relationship setting module is used to match the set actions of an individual limb with the target muscle movements caused by the corresponding actions;

[0025] The movement training module is used to acquire the electroencephalogram (EEG) signals of an individual's limbs performing a set movement and the electromyographic (EMG) signals of the corresponding target muscles when the individual's limbs are performing a set movement training. Before the movement training begins, the EEG signals and the EMG signals of the corresponding target muscles in the resting state are recorded synchronously.

[0026] The comparison feature signal acquisition module is used to utilize the electroencephalogram (EEG) signals of the motor-related brain regions of the cerebral cortex and the electromyogram (EMG) signals of the synchronous motor-related target muscles. Through the Pearson correlation coefficient, the EEG signals of the neural circuits that have statistical differences from the EMG signals of the target muscles are calculated as the comparison feature signals of the corresponding neural circuits.

[0027] The signal acquisition module is used to acquire the electroencephalogram (EEG) signal of an individual's limbs performing a set action and the electromyographic (EMG) signal of the target muscle corresponding to that action when the individual's limbs perform the set action.

[0028] The feature signal acquisition module is used to calculate the electroencephalogram (EEG) signals of neural circuits that show statistical differences from the EMG signals of the target muscle using the Pearson correlation coefficient, and these signals are used as the feature signals of the corresponding neural circuits; and

[0029] The matching analysis control module is used to match the feature signal acquired by the feature signal acquisition module with the supply comparison feature signal to determine whether the obtained feature signal meets the set requirements; if it is determined that the feature signal does not meet the set requirements, a set control signal is sent to the corresponding exoskeleton robot.

[0030] As one embodiment of the present invention, the central nervous system recovery training control system further includes at least one exoskeleton robot, at least one electroencephalogram (EEG) sensor, and at least one electromyogram (EMG) sensor.

[0031] As one embodiment of the present invention, the relationship setting module is used to correspond the set single action of an individual limb with the single target muscle movement caused by the corresponding single action.

[0032] The motion training module is used to acquire the electroencephalogram (EEG) signal of an individual limb performing a set single motion and the electromyographic (EMG) signal of the single target muscle corresponding to that motion when the individual limb is performing a set single motion training; before the motion training begins, the EEG signal in the static state and the EMG signal of the corresponding single target muscle are recorded synchronously.

[0033] The signal acquisition module is used to acquire the electroencephalogram (EEG) signal of an individual limb performing a set single action and the electromyographic (EMG) signal of the single target muscle corresponding to that action when the individual limb performs a set single action.

[0034] As one embodiment of the present invention, the relationship setting module is used to correspond the set compound movements of an individual limb with the multiple target muscle movements caused by the corresponding compound movements.

[0035] The motion training module is used to acquire the electroencephalogram (EEG) signal of an individual limb performing a set compound motion and the electromyographic (EMG) signal of multiple target muscles corresponding to the motion when the individual limb is performing the set compound motion training; before the motion training begins, the EEG signal in the static state and the EMG signal of the multiple target muscles are recorded synchronously.

[0036] The signal acquisition module is used to acquire the electroencephalogram (EEG) signal of an individual limb performing a set compound movement and the electromyographic (EMG) signal of multiple target muscles corresponding to that movement when the individual limb performs the set compound movement.

[0037] According to another aspect of the present invention, the following technical solution is adopted: an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above method.

[0038] According to another aspect of the present invention, the following technical solution is adopted: a storage medium storing computer program instructions thereon, which, when executed by a processor, implement the steps of the above-described method.

[0039] The beneficial effects of this invention are as follows: The central nervous system recovery training control method, system, electronic device and storage medium based on electroencephalogram and electromyogram coherence analysis proposed in this invention can be used to precisely promote the recovery of motor function caused by nervous system diseases. Attached Figure Description

[0040] Figure 1 This is a flowchart of a central nervous system recovery training control method in one embodiment of the present invention.

[0041] Figure 2 This is a schematic diagram of the composition of a central nervous system recovery training control system in one embodiment of the present invention.

[0042] Figure 3 This is a schematic diagram illustrating the working principle of the central nervous system recovery training control system in one embodiment of the present invention.

[0043] Figure 4 This is a schematic diagram of the composition of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0044] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0045] To further understand the present invention, preferred embodiments of the present invention are described below in conjunction with examples. However, it should be understood that these descriptions are only for further illustrating the features and advantages of the present invention, and not for limiting the scope of the claims of the present invention.

[0046] The description in this section pertains to only a few typical embodiments, and the present invention is not limited to the scope of the embodiments described. Substitution of identical or similar prior art methods with some technical features in the embodiments is also within the scope of the description and protection of this invention.

[0047] The steps described in the various embodiments in the specification are for illustrative purposes only, and the implementation of this application is not limited by the order of the steps.

[0048] The term "connection" in this instruction manual includes both direct and indirect connections. The term "multiple" in this instruction manual refers to two or more connections.

[0049] This invention discloses a central nervous system recovery training control method based on electroencephalogram (EEG) and electromyogram (EMG) coherence analysis. Figure 1 This is a flowchart of a central nervous system recovery training control method according to an embodiment of the present invention. Figure 3 This is a schematic diagram illustrating the working principle of the central nervous system recovery training control system in one embodiment of the present invention; please refer to [link / reference]. Figure 1 , Figure 3 The central nervous system recovery training control method includes:

[0050]

Step S1

[0051]

Step S2

[0052]

Step S3

[0053] In one embodiment of the present invention, in step S1, the action is a single action, and the single action drives a target muscle action; in step S2, when an individual limb performs the single action training, the electroencephalogram (EEG) signal of the individual limb performing the single action and the electromyographic (EMG) signal of the target muscle corresponding to the single action are acquired; in step S3, when an individual limb performs the single action, the EEG signal of the individual limb performing the single action and the EMG signal of the target muscle corresponding to the action are acquired.

[0054] In one embodiment of the present invention, in step S1, the action is a compound action (such as the action of gripping a bottle with one's hand), and the action drives multiple target muscle actions; in step S2, when an individual limb performs the compound action training, the electroencephalogram (EEG) signal of the individual limb performing the compound action and the electromyographic (EMG) signal of the multiple target muscles corresponding to the action are acquired; in step S3, when an individual limb performs the compound action, the EEG signal of the individual limb performing the compound action and the EMG signal of the multiple target muscles corresponding to the action are acquired.

[0055] In one embodiment of the present invention, in step S3, if the obtained feature signal does not meet the set requirements, it indicates that the patient needs to undergo rehabilitation training (unable to perform other more complex movements and is in the rehabilitation training stage). The set requirements may be a preset set threshold, or a value obtained by setting parameters of the patient's body through a set function.

[0056] Step S3 further includes: if the obtained feature signal meets the set requirements, it indicates that the patient can perform the set action with the help of the exoskeleton robot, and the patient is allowed to send a control command to the exoskeleton robot to execute the set action; when the patient sends the control to the exoskeleton robot to execute the set action, the exoskeleton robot can help the patient complete the corresponding action (such as holding a water cup, chopsticks, spoon, etc.).

[0057] This invention also discloses a central nervous system recovery training and control system based on electroencephalogram (EEG) and electromyogram (EMG) coherence analysis. Figure 2 This is a schematic diagram of the composition of a central nervous system recovery training control system according to an embodiment of the present invention; please refer to [link / reference]. Figure 2 The central nervous system recovery training control system includes a control processing device 1; the control processing device 1 is connected to at least one exoskeleton robot 2, at least one electroencephalogram (EEG) sensor 3, and at least one electromyogram (EMG) sensor 4.

[0058] The exoskeleton robot 2 is mounted on a designated individual limb to assist the corresponding individual limb in performing a designated action; the electroencephalogram (EEG) sensor 3 is mounted on a designated brain region to sense the EEG signals of the corresponding brain region; and the electromyography (EMG) sensor 4 is mounted on a designated target muscle to sense the EMG signals of the target muscle. In one embodiment of the present invention, the central nervous system recovery training control system may include at least one exoskeleton robot 2, at least one EEG sensor 3, and at least one EMG sensor 4.

[0059] The control processing device 1 includes: a relationship setting module 101, an action training module 102, a comparison feature signal acquisition module 103, a signal acquisition module 104, a feature signal acquisition module 105, and a matching analysis control module 106.

[0060] The relationship setting module 101 is used to correspond the set action of an individual limb with the target muscle movement caused by the corresponding action.

[0061] The motion training module 102 is used to acquire the electroencephalogram (EEG) signal of an individual limb performing a set motion and the electromyographic (EMG) signal of the target muscle corresponding to the motion when the individual limb is performing a set motion training; before the motion training begins, the EEG signal in the static state and the EMG signal of the corresponding target muscle are recorded synchronously.

[0062] The comparison feature signal acquisition module 103 is used to use the electroencephalogram (EEG) signals of the motor-related brain regions of the cerebral cortex and the electromyogram (EMG) signals of the synchronous motor-related target muscles, and calculate the EEG signals of the neural circuits that have statistical differences from the EMG signals of the target muscles through the Pearson correlation coefficient, and use them as the comparison feature signals of the corresponding neural circuits.

[0063] The signal acquisition module 104 is used to acquire the electroencephalogram (EEG) signal of the individual limb performing the set action and the electromyogram (EMG) signal of the target muscle corresponding to the action when the individual limb performs the set action.

[0064] The feature signal acquisition module 105 is used to calculate the electroencephalogram (EEG) signal of the neural circuit that has a statistically significant difference from the electromyographic signal of the target muscle through the Pearson correlation coefficient, and use it as the feature signal of the corresponding neural circuit.

[0065] The matching analysis control module 106 is used to match the feature signal acquired by the feature signal acquisition module with the comparison pair feature signal, and determine whether the obtained feature signal meets the set requirements; if it is determined that it does not meet the set requirements, a set control signal is sent to the corresponding exoskeleton robot.

[0066] In one embodiment of the present invention, the relationship setting module 101 is used to correspond a set single action of an individual limb with a single target muscle movement caused by the corresponding single action; the single action drives a set target muscle movement. The action training module 102 is used to acquire the electroencephalogram (EEG) signal of the individual limb performing the set single action and the electromyographic (EMG) signal of the corresponding single target muscle when the individual limb is training with the set single action; before the action training begins, the EEG signal in the resting state and the EMG signal of the corresponding single target muscle are recorded synchronously. The signal acquisition module 104 is used to acquire the EEG signal of the individual limb performing the set single action and the EMG signal of the corresponding single target muscle when the individual limb is performing the set single action.

[0067] In another embodiment of the present invention, the relationship setting module 101 is used to associate a set compound movement of an individual limb with the movement of multiple target muscles caused by the corresponding compound movement. The movement training module 102 is used to acquire the electroencephalogram (EEG) signal of the individual limb performing the set compound movement and the electromyographic (EMG) signal of the multiple target muscles corresponding to the movement when the individual limb is training the set compound movement; before the movement training begins, the EEG signal in the resting state and the EMG signal of the multiple target muscles are recorded synchronously. The signal acquisition module 104 is used to acquire the EEG signal of the individual limb performing the set compound movement and the EMG signal of the multiple target muscles corresponding to the movement when the individual limb is performing the set compound movement.

[0068] In one embodiment of the present invention, if the feature signal determined by the matching analysis control module 106 does not meet the set requirements, it indicates that the patient needs to undergo rehabilitation training (unable to perform other more complex movements and is in the rehabilitation training stage). The set requirements may be a preset set threshold, or a value obtained by setting parameters of the patient's body through a set function.

[0069] If the feature signal obtained by the matching analysis control module 106 meets the set requirements, it indicates that the patient can perform the set action with the help of the exoskeleton robot, and the patient is allowed to send a control command to the exoskeleton robot to execute the set action; when the patient sends the control to the exoskeleton robot to execute the set action, the exoskeleton robot can help the patient complete the corresponding action (such as holding a water cup, chopsticks, spoon, etc.).

[0070] This invention also discloses an electronic device, Figure 4 This is a schematic diagram of the composition of an electronic device according to an embodiment of the present invention; please refer to [link / reference]. Figure 4 At the hardware level, the electronic device includes a memory, a processor, and at least one network interface; the processor may be a microprocessor, and the memory may include main memory, such as random access memory (RAM) or non-volatile memory. Of course, the electronic device may also include other hardware as needed.

[0071] The processor, network interface, and memory are interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus may include an address bus, a data bus, a control bus, etc. The memory stores programs (including operating system programs and application programs); the programs may include program code, which may include computer operation instructions. The memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0072] In one embodiment, the processor can read the corresponding program from non-volatile memory into memory and then run it; the processor can execute the program stored in memory and specifically perform the following operations (e.g. Figure 1 As shown):

[0073]

Step S1

[0074]

Step S2

[0075]

Step S3

[0076] This invention further discloses a storage medium storing computer program instructions, which, when executed by a processor, implement the following steps of the method of this invention (e.g. Figure 1 As shown):

[0077]

Step S1

[0078]

Step S2

[0079]

Step S3

[0080] In summary, the central nervous system recovery training control method, system, electronic device, and storage medium proposed in this invention based on electroencephalogram (EEG) and electromyogram (EMG) coherence analysis can be used to precisely promote the recovery of motor function caused by nervous system diseases.

[0081] It should be noted that this application can be implemented in software and / or a combination of software and hardware; for example, it can be implemented using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In some embodiments, the software program of this application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium; for example, RAM memory, magnetic or optical drives, floppy disks, and similar devices. In addition, some steps or functions of this application can be implemented in hardware; for example, as circuitry that cooperates with a processor to perform the various steps or functions.

[0082] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0083] The description and application of the present invention herein are illustrative and not intended to limit the scope of the invention to the embodiments described above. Effects or advantages involved in the embodiments may not be apparent due to various factors, and the description of effects or advantages is not intended to limit the embodiments. Variations and modifications of the embodiments disclosed herein are possible, and various substitutions and equivalents of the components in the embodiments are well known to those skilled in the art. It should be apparent to those skilled in the art that the invention can be implemented in other forms, structures, arrangements, proportions, and with other components, materials, and parts without departing from the spirit or essential characteristics of the invention. Other variations and modifications can be made to the embodiments disclosed herein without departing from the scope and spirit of the invention.

Claims

1. A central nervous system recovery training control system based on electroencephalogram (EEG) and electromyogram (EMG) coherence analysis, characterized in that, The central nervous system recovery training control system includes a control processing device; The control processing device is connected to at least one exoskeleton robot, at least one electroencephalogram (EEG) sensor, and at least one electromyogram (EMG) sensor, respectively. The exoskeleton robot is set on a specific individual's limb to assist the corresponding individual's limb in completing a set action; the EEG sensor is set on a specific brain region to sense the EEG signals of the corresponding brain region. The electromyography sensor is installed on a target muscle to sense the electromyography signal of the target muscle. The control processing device includes: The relationship setting module is used to match the set actions of an individual limb with the target muscle movements caused by the corresponding actions; The movement training module is used to acquire the electroencephalogram (EEG) signals of an individual's limbs performing a set movement and the electromyographic (EMG) signals of the corresponding target muscles when the individual's limbs are performing a set movement training. Before the movement training begins, the EEG signals and the EMG signals of the corresponding target muscles in the resting state are recorded synchronously. The comparison feature signal acquisition module is used to utilize the electroencephalogram (EEG) signals of the motor-related brain regions of the cerebral cortex and the electromyogram (EMG) signals of the synchronous motor-related target muscles. Through the Pearson correlation coefficient, the EEG signals of the neural circuits that have statistical differences from the EMG signals of the target muscles are calculated as the comparison feature signals of the corresponding neural circuits. The signal acquisition module is used to acquire the electroencephalogram (EEG) signal of an individual's limbs performing a set action and the electromyographic (EMG) signal of the target muscle corresponding to that action when the individual's limbs perform the set action. The feature signal acquisition module is used to calculate the electroencephalogram (EEG) signals of neural circuits that show statistical differences from the EMG signals of the target muscle using the Pearson correlation coefficient, and these signals are used as the feature signals of the corresponding neural circuits; and The matching analysis control module is used to match the feature signal acquired by the feature signal acquisition module with the supply comparison feature signal, and determine whether the obtained feature signal meets the set requirements; if it is determined that it does not meet the set requirements, a set control signal is sent to the corresponding exoskeleton robot. The relationship setting module is used to map a single action of an individual limb to a single target muscle movement caused by that single action. The motion training module is used to acquire the electroencephalogram (EEG) signal of an individual limb performing a set single motion and the electromyographic (EMG) signal of the single target muscle corresponding to that motion when the individual limb is performing a set single motion training; before the motion training begins, the EEG signal in the static state and the EMG signal of the corresponding single target muscle are recorded synchronously. The signal acquisition module is used to acquire the electroencephalogram (EEG) signal of an individual limb performing a set single action and the electromyogram (EMG) signal of the single target muscle corresponding to that action when the individual limb performs a set single action. The relationship setting module is used to map the set compound movements of an individual limb to the single target muscle movements caused by the corresponding compound movements. The motion training module is used to acquire the electroencephalogram (EEG) signal of an individual limb performing a set compound motion and the electromyographic (EMG) signal of multiple target muscles corresponding to the motion when the individual limb is performing the set compound motion training; before the motion training begins, the EEG signal in the static state and the EMG signal of the multiple target muscles are recorded synchronously. The signal acquisition module is used to acquire the electroencephalogram (EEG) signal of an individual limb performing a set compound movement and the electromyographic (EMG) signal of multiple target muscles corresponding to that movement when the individual limb performs the set compound movement.

2. The central nervous system recovery training control system based on electroencephalogram and electromyogram coherence analysis according to claim 1, characterized in that: The central nervous system recovery training control system further includes at least one exoskeleton robot, at least one electroencephalogram (EEG) sensor, and at least one electromyogram (EMG) sensor.

Images