Active upper limb rehabilitation training method and system based on brain-computer interface

Abstract

The invention provides an active upper limb rehabilitation training method and system based on a brain-computer interface, and the method comprises the steps: collecting motor imagery electroencephalogram data, and dividing the motor imagery electroencephalogram data into offline data and online data; performing model training through the offline data to obtain an offline electroencephalogram model; analyzing and processing the online data through the offline electroencephalogram model to obtain a motion intention, storing the motion intention, and converting the motion intention into a control instruction; selecting rehabilitation modes of the exoskeleton according to the degree of dyskinesia, wherein the rehabilitation modes comprise an active rehabilitation mode and a passive rehabilitation mode; the exoskeleton completes a rehabilitation training task according to the control instruction and the rehabilitation mode. According to the method, the brain neural signal identification efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of brain-computer interface, and in particular to an active upper limb rehabilitation training method and system based on brain-computer interface. Background Art

[0002] At present, the number of stroke patients in my country is increasing, and the most obvious feature of these patients is upper limb motor dysfunction, which brings great inconvenience to patients' daily life. However, most of the current rehabilitation equipment is passive mechanical equipment, which requires the cooperation of multiple medical staff when patients are undergoing rehabilitation. This greatly limits the effect of rehabilitation and makes patients feel tired.

[0003] The emergence of brain-computer interface (BCI) has brought good news to patients with limb dysfunction. BCI is a communication control system that does not rely on the normal output pathways composed of peripheral nerves and muscles in the brain. Motor imagery is when the brain has the intention to move but the limbs do not perform the action. Motor imagery is used to activate and repair the patient's damaged brain neural network, thereby improving the patient's autonomous movement ability.

[0004] However, existing brain-computer interface-based rehabilitation training adopts a relatively single method, which can only train based on the subject's active motor imagery, and thus cannot efficiently and correctly identify brain nerve signals. Summary of the invention

[0005] In view of this, the present invention provides an active upper limb rehabilitation training method and system based on brain-computer interface to solve the above problems.

[0006] The present invention provides an active upper limb rehabilitation training method based on a brain-computer interface, comprising: collecting motor imagery EEG data, dividing the motor imagery EEG data into offline data and online data; performing model training through the offline data to obtain an offline EEG model; analyzing and processing the online data through the offline EEG model to obtain movement intentions, saving the movement intentions, and converting them into control instructions; selecting an exoskeleton rehabilitation mode according to the degree of movement disorder, the rehabilitation mode including an active rehabilitation mode and a passive rehabilitation mode; and the exoskeleton completing the rehabilitation training task according to the control instructions and the rehabilitation mode.

[0007] In another implementation of the present invention, the active training mode is that the subject wears a rehabilitation exoskeleton and actively controls the rehabilitation exoskeleton through active motor imagery after offline model training; the passive training mode is that the subject is stimulated and trained by external assistants.

[0008] In another implementation of the present invention, the exoskeleton includes a shoulder control mechanism, an elbow control mechanism and a wrist control mechanism; the shoulder control mechanism is used to control the shoulder to complete the shoulder rotation movement task; the elbow control mechanism is used to control the elbow to complete the elbow flexion movement task; and the wrist control mechanism is used to control the wrist to complete the wrist rotation movement task.

[0009] In another implementation of the present invention, the shoulder control mechanism includes a support bracket and a control motor, and the support bracket supports the exoskeleton.

[0010] In another implementation of the present invention, the elbow control mechanism includes an upper arm cup, a forearm cup telescopic rod and a control motor; the upper arm cup and the forearm cup are worn on the upper arm and the forearm respectively, and are connected by the telescopic rod. At the same time, the telescopic rod can adjust the appropriate length according to users with different arm lengths.

[0011] In another implementation of the present invention, the wrist control mechanism includes gears at both ends, a hand grip and a control motor; the control motor drives the gear at one end to rotate, thereby driving the gear at the other end to engage, thereby achieving the effect of wrist joint rotation.

[0012] Another aspect of the present invention provides an active upper limb rehabilitation training system based on a brain-computer interface, comprising: an EEG signal acquisition module: collecting motor imagery EEG data, and dividing the motor imagery EEG data into offline data and online data; an EEG signal processing module: performing model training through the offline data to obtain an offline EEG model; analyzing and processing the online data through the offline EEG model to obtain movement intentions, saving the movement intentions, and converting them into control instructions; an exoskeleton execution module: selecting an exoskeleton rehabilitation mode according to the degree of movement disorder, the rehabilitation mode including an active rehabilitation mode and a passive rehabilitation mode; the exoskeleton completes the rehabilitation training task according to the control instructions and the rehabilitation mode.

[0013] The active upper limb rehabilitation training method based on brain-computer interface of the present invention adopts a combination of offline data and online data in the EEG signal processing part, firstly adopts an offline algorithm to perform model training on the offline data, and then uses the offline model to select and judge the action in the online data part, effectively improving the recognition accuracy and achieving a good action recognition effect; it has two rehabilitation modes, and the subjects can choose the corresponding rehabilitation mode according to their own impairment. In the active mode, the subjects use their own active motor imagination intention to stimulate rehabilitation throughout the process to restore the damaged area of ​​the brain. In the passive mode, rehabilitation is carried out through the intervention of outside personnel and the cooperation of their own motor imagination. Both modes can enhance the autonomous rehabilitation ability of people with motor dysfunction. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. By reading the detailed description of the following implementation, the advantages and benefits of the solutions become clear to those skilled in the art. The drawings are only used to illustrate the preferred implementation and are not to be considered as limiting the present invention.

[0015] In the attached picture:

[0016] Figure 1 This is a flow chart of an active upper limb rehabilitation training method based on brain-computer interface according to an embodiment of the present invention.

[0017] Figure 2 Schematic diagram of a rehabilitation exoskeleton model according to an embodiment of the present invention.

[0018] Figure 3 Schematic diagram of an active upper limb rehabilitation training system based on brain-computer interface according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be described clearly and in detail below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in the field based on the embodiments in the embodiments of the present invention should fall within the scope of protection of the embodiments of the present invention.

[0020] Figure 1 A flowchart of an active upper limb rehabilitation training method based on a brain-computer interface provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, this embodiment mainly includes:

[0021] Motor imagery EEG data are collected and divided into offline data and online data.

[0022] Exemplarily, an EEG signal cap is worn on the subject's head, the subject's EEG signal is collected through a multi-channel sensor, and the collected data is preprocessed, and the preprocessing includes amplification and filtering, etc. For example, a head-mounted 64-lead EEG cap can be used.

[0023] The offline data is used to perform model training to obtain an offline EEG model.

[0024] The online data is analyzed and processed by the offline EEG model to obtain the movement intention, which is then saved and converted into a control instruction.

[0025] Exemplarily, a trained offline EEG model is used to analyze and judge the online EEG signals collected in real time, decompose the subject's intention, and convert it into control instructions.

[0026] The rehabilitation mode of the exoskeleton is selected according to the degree of movement disorder, and the rehabilitation mode includes an active rehabilitation mode and a passive rehabilitation mode.

[0027] Exemplarily, the active training mode is that after the subject is trained through an offline model, he wears a rehabilitation exoskeleton and actively controls the rehabilitation exoskeleton through active motor imagery; the passive training mode is that the subject is stimulated and trained through intervention by external assistants.

[0028] The exoskeleton completes the rehabilitation training task according to the control instruction and the rehabilitation mode.

[0029] For example, the exoskeleton is worn on the upper limbs of the subject, and the exoskeleton receives control instructions, completes corresponding rehabilitation movements, and stimulates the damaged area of ​​the brain.

[0030] The active upper limb rehabilitation training method based on brain-computer interface of the present invention adopts a combination of offline data and online data in the EEG signal processing part, firstly adopts an offline algorithm to perform model training on the offline data, and then uses the offline model to select and judge the action in the online data part, effectively improving the recognition accuracy and achieving a good action recognition effect; it has two rehabilitation modes, and the subjects can choose the corresponding rehabilitation mode according to their own impairment. In the active mode, the subjects use their own active motor imagination intention to stimulate rehabilitation throughout the process to restore the damaged area of ​​the brain. In the passive mode, rehabilitation is carried out through the intervention of outside personnel and the cooperation of their own motor imagination. Both modes can enhance the autonomous rehabilitation ability of people with motor dysfunction.

[0031] In another implementation of the present invention, the active training mode is that the subject wears a rehabilitation exoskeleton and actively controls the rehabilitation exoskeleton through active motor imagery after offline model training; the passive training mode is that the subject is stimulated and trained by external assistants.

[0032] In another implementation of the present invention, the exoskeleton includes a shoulder control mechanism, an elbow control mechanism and a wrist control mechanism; the shoulder control mechanism is used to control the shoulder to complete the shoulder rotation movement task; the elbow control mechanism is used to control the elbow to complete the elbow flexion movement task; and the wrist control mechanism is used to control the wrist to complete the wrist rotation movement task.

[0033] For example, Figure 2As shown in the figure, the exoskeleton has three degrees of freedom, which can realize the flexion / extension of the shoulder joint, the flexion / extension of the elbow joint, and the left / right rotation of the wrist joint. When the subject imagines these three actions, the data processing module analyzes them, recognizes the imagined actions, and completes the control of the exoskeleton.

[0034] In another implementation of the present invention, the shoulder control mechanism includes a support bracket and a control motor, and the support bracket supports the exoskeleton.

[0035] In another implementation of the present invention, the elbow control mechanism includes an upper arm cup, a forearm cup telescopic rod and a control motor; the upper arm cup and the forearm cup are worn on the upper arm and the forearm respectively, and are connected by the telescopic rod. At the same time, the telescopic rod can adjust the appropriate length according to users with different arm lengths.

[0036] In another implementation of the present invention, the wrist control mechanism includes gears at both ends, a hand grip and a control motor; the control motor drives the gear at one end to rotate, thereby driving the gear at the other end to engage, thereby achieving the effect of wrist joint rotation.

[0037] Another aspect of the present invention, as Figure 3 As shown, an active upper limb rehabilitation training system based on a brain-computer interface is provided, comprising:

[0038] EEG signal acquisition module: collects motor imagery EEG data, and divides the motor imagery EEG data into offline data and online data.

[0039] Exemplarily, the EEG signal acquisition module includes an acquisition unit and a communication unit, which are connected to each other. The acquisition unit acquires EEG signals through a multi-channel sensor, and the communication unit communicates through the TCP / IP protocol and is also responsible for transmitting the generated instructions between the exoskeleton and the EEG signal processing module.

[0040] EEG signal processing module: performs model training through the offline data to obtain an offline EEG model; analyzes and processes the online data through the offline EEG model to obtain movement intention, saves the movement intention, and converts it into control instructions.

[0041] Exoskeleton execution module: selects the rehabilitation mode of the exoskeleton according to the degree of movement disorder, and the rehabilitation mode includes active rehabilitation mode and passive rehabilitation mode; the exoskeleton completes the rehabilitation training task according to the control instruction and the rehabilitation mode.

[0042] The active upper limb rehabilitation training system based on brain-computer interface of the present invention adopts a combination of offline data and online data in the EEG signal processing part, firstly adopts an offline algorithm to perform model training on the offline data, and then uses the offline model to select and judge the action in the online data part, effectively improving the recognition accuracy and achieving a good action recognition effect; it has two rehabilitation modes, and the subjects can choose the corresponding rehabilitation mode according to their own impairment. In the active mode, the subjects use their own active motor imagination intention to stimulate rehabilitation throughout the process to restore the damaged area of ​​the brain. In the passive mode, rehabilitation is carried out through the intervention of outside personnel and the cooperation of their own motor imagination. Both modes can enhance the autonomous rehabilitation ability of people with motor dysfunction.

[0043] In another aspect of the present invention, an electronic device includes: a processor, a memory, a communication bus, and a communication interface.

[0044] in:

[0045] The processor, memory and communication interface communicate with each other through a communication bus.

[0046] Communication interface, used to communicate with other electronic devices or servers.

[0047] The processor is used to execute the program, and specifically can execute the steps of any one of the active upper limb rehabilitation training methods based on brain-computer interface in the above embodiments.

[0048] Specifically, the program may include program codes including computer operation instructions.

[0049] The processor may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0050] The memory is used to store programs. The memory may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0051] The program can be specifically used to enable the processor to execute to implement the steps of any one of the active upper limb rehabilitation training methods based on brain-computer interface described in the embodiment. The specific implementation of each step in the program can refer to the corresponding description in the steps and units executed by any one of the active upper limb rehabilitation training methods based on brain-computer interface in the above steps, which will not be repeated here. Technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described equipment and modules can refer to the corresponding process description in the aforementioned method embodiment.

[0052] The above method according to the embodiment of the present invention can be implemented in a server equipped with a central processing unit CPU and an image processing unit COU.

[0053] Thus far, specific embodiments of the present invention have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results.

[0054] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, back, etc.) are only used to explain the relative position relationship between the components in a certain specific order (as shown in the accompanying drawings). If the specific order changes, the directional indication will also change accordingly.

[0055] In the description of the present invention, the terms "first" and "second" are only used to facilitate the description of different components or names, and cannot be understood as indicating or implying a sequential relationship, relative importance, or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0057] It should be noted that although the specific embodiments of the present invention are described in detail in conjunction with the accompanying drawings, it should not be understood as limiting the scope of protection of the present invention. Within the scope described in the claims, various modifications and variations that can be made by those skilled in the art without creative work still belong to the scope of protection of the present invention.

[0058] The examples of the embodiments of the present invention are intended to concisely illustrate the technical features of the embodiments of the present invention so that those skilled in the art can intuitively understand the technical features of the embodiments of the present invention, and are not intended to be improper limitations of the embodiments of the present invention.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An active upper limb rehabilitation training method based on brain-computer interface, characterized in that: include: Collecting motor imagery EEG data, and dividing the motor imagery EEG data into offline data and online data; Performing model training using the offline data to obtain an offline EEG model; Analyzing and processing the online data through the offline EEG model to obtain movement intention, saving the movement intention, and converting it into a control instruction; Selecting a rehabilitation mode of the exoskeleton according to the degree of movement disorder, wherein the rehabilitation mode includes an active rehabilitation mode and a passive rehabilitation mode; The exoskeleton completes the rehabilitation training task according to the control instruction and the rehabilitation mode.

2. The method according to claim 1, characterized in that The active training mode is that after the subject has completed offline model training, he wears the rehabilitation exoskeleton and actively controls the rehabilitation exoskeleton by actively performing motor imagery; The passive training mode is that the subject is intervened by external assistants to conduct stimulation training on the subject.

3. The method according to claim 1, characterized in that The exoskeleton includes a shoulder control mechanism, an elbow control mechanism, and a wrist control mechanism; The shoulder control mechanism is used to control the shoulder to complete the shoulder rotation movement task; The elbow control mechanism is used to control the elbow to complete the elbow bending movement task; The wrist control mechanism is used to control the wrist to complete the wrist rotation movement task.

4. The method according to claim 3, characterized in that The shoulder control mechanism includes a support bracket and a control motor, and the support bracket supports the exoskeleton.

5. The method according to claim 3, characterized in that: The elbow control mechanism includes an upper arm cup, a forearm cup telescopic rod and a control motor; The upper arm cup and the forearm cup are respectively worn on the upper arm and the forearm, and are connected by a telescopic rod. At the same time, the telescopic rod can adjust a suitable length according to users with different arm lengths.

6. The method according to claim 3, characterized in that The wrist control mechanism includes gears at both ends, a hand grip and a control motor; The control motor drives the gear at one end to rotate, thereby driving the gear at the other end to mesh, thereby achieving the effect of wrist joint rotation.

7. An active upper limb rehabilitation training system based on brain-computer interface, characterized in that: include: EEG signal acquisition module: collects motor imagery EEG data, and divides the motor imagery EEG data into offline data and online data; EEG signal processing module: performs model training through the offline data to obtain an offline EEG model; analyzes and processes the online data through the offline EEG model to obtain movement intention, saves the movement intention, and converts it into a control instruction; Exoskeleton execution module: selects the rehabilitation mode of the exoskeleton according to the degree of movement disorder, and the rehabilitation mode includes active rehabilitation mode and passive rehabilitation mode; the exoskeleton completes the rehabilitation training task according to the control instruction and the rehabilitation mode.

Images