CN112244774A - Brain-computer interface rehabilitation training system and method - Google Patents
Brain-computer interface rehabilitation training system and method Download PDFInfo
- Publication number
- CN112244774A CN112244774A CN202011117939.8A CN202011117939A CN112244774A CN 112244774 A CN112244774 A CN 112244774A CN 202011117939 A CN202011117939 A CN 202011117939A CN 112244774 A CN112244774 A CN 112244774A
- Authority
- CN
- China
- Prior art keywords
- brain
- training
- rehabilitation training
- computer interface
- idea
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 496
- 238000000034 method Methods 0.000 title claims abstract description 89
- 230000033001 locomotion Effects 0.000 claims abstract description 145
- 230000009471 action Effects 0.000 claims abstract description 80
- 238000012545 processing Methods 0.000 claims abstract description 71
- 238000011156 evaluation Methods 0.000 claims abstract description 56
- 210000004556 brain Anatomy 0.000 claims description 186
- 238000004364 calculation method Methods 0.000 claims description 54
- 230000000007 visual effect Effects 0.000 claims description 52
- 230000000763 evoking effect Effects 0.000 claims description 42
- 210000001652 frontal lobe Anatomy 0.000 claims description 37
- 210000000869 occipital lobe Anatomy 0.000 claims description 35
- 230000000638 stimulation Effects 0.000 claims description 34
- 230000001939 inductive effect Effects 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 17
- 239000000284 extract Substances 0.000 claims description 16
- 230000002747 voluntary effect Effects 0.000 claims description 3
- 230000001936 parietal effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 22
- 230000006698 induction Effects 0.000 abstract description 15
- 230000035945 sensitivity Effects 0.000 abstract description 5
- 238000000605 extraction Methods 0.000 abstract description 4
- 230000007830 nerve conduction Effects 0.000 abstract description 3
- 210000003414 extremity Anatomy 0.000 description 66
- 230000000875 corresponding effect Effects 0.000 description 55
- 210000003478 temporal lobe Anatomy 0.000 description 22
- 230000033764 rhythmic process Effects 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 12
- 210000001152 parietal lobe Anatomy 0.000 description 11
- 230000008859 change Effects 0.000 description 10
- 230000001276 controlling effect Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 230000000737 periodic effect Effects 0.000 description 7
- 238000010219 correlation analysis Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000012880 independent component analysis Methods 0.000 description 6
- 238000011084 recovery Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 230000003183 myoelectrical effect Effects 0.000 description 5
- 230000008447 perception Effects 0.000 description 5
- 238000000611 regression analysis Methods 0.000 description 5
- 210000001364 upper extremity Anatomy 0.000 description 5
- 230000001364 causal effect Effects 0.000 description 4
- 210000003141 lower extremity Anatomy 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000004886 head movement Effects 0.000 description 3
- 230000007659 motor function Effects 0.000 description 3
- 230000007383 nerve stimulation Effects 0.000 description 3
- 210000004027 cell Anatomy 0.000 description 2
- 230000001771 impaired effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000000386 athletic effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000001351 cycling effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000002040 relaxant effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
Abstract
The application provides a brain-computer interface rehabilitation training system and method, which are used for performing exercise training on limbs of a rehabilitation training recipient according to the active exercise idea of the rehabilitation training recipient to realize rehabilitation. The brain-computer interface rehabilitation training system comprises a motor idea induction device, a signal acquisition device, a processing device, a control device, a training device and an evaluation device. Through the brain-computer interface rehabilitation training system and the brain-computer interface rehabilitation training method, the initiative movement idea induced by a rehabilitation training receiver can be enhanced, the sensitivity and the accuracy of characteristic extraction from electroencephalogram signals are improved, the rehabilitation training action accurately follows the initiative movement idea, nerve conduction is further activated, the rehabilitation effect is obviously improved, the rehabilitation training effect can be fully and timely evaluated, doctors are allowed to intervene in rehabilitation training, and the rehabilitation training effect is effectively improved.
Description
Technical Field
The application relates to the field of brain-computer interfaces, in particular to a brain-computer interface rehabilitation training system and a brain-computer interface rehabilitation training method based on brain-computer interface technology.
Background
Brain-computer interface rehabilitation training based on brain-computer interface technology plays a very important role in recovery of motor function of brain-computer interface rehabilitation training receivers after illness. The brain-computer interface rehabilitation training technology based on the brain-computer interface technology can analyze electroencephalogram information related to active movement consciousness of a rehabilitation training receiver by collecting the electroencephalogram information, control rehabilitation training equipment based on the analysis result (related to the active movement consciousness), and perform limb movement training of the rehabilitation training receiver, so that rehabilitation is realized. Compared with the traditional rehabilitation method and the robot-assisted rehabilitation method, the brain-computer interface rehabilitation training technology based on the brain-computer interface technology can form a motor nerve stimulation closed loop path by enabling a rehabilitation training receiver to actively participate in rehabilitation training control, and can effectively improve the rehabilitation training effect.
However, the existing brain-computer interface rehabilitation training technology based on the brain-computer interface technology has several defects. For example, generally, a rehabilitation training recipient is difficult to perform motor imagery and induce electroencephalogram signal intensity to be low due to the damaged motor central nerve function, and the existing brain-computer interface rehabilitation technology is difficult to accurately and effectively extract active motor consciousness, so that a motor nerve stimulation closed-loop path is difficult to form, and the rehabilitation effect cannot be ensured; the existing brain-computer interface rehabilitation training technology cannot perform real-time rehabilitation evaluation on the rehabilitation training effect, and a rehabilitation training receiver or a doctor cannot master the rehabilitation training condition in real time; based on the existing brain-computer interface rehabilitation training technology, doctors cannot know the brain state change of a rehabilitation training receiver when the rehabilitation training receiver trains, so that the rehabilitation training receiver is difficult to conduct necessary guidance, and the rehabilitation training cannot be adjusted due to the lack of intervention technical means, and the rehabilitation training effect cannot be effectively improved.
Disclosure of Invention
According to an aspect of the present application, there is provided a brain-computer interface rehabilitation training system for performing exercise training on a limb of a rehabilitation training recipient according to an active exercise mind thereof to achieve rehabilitation, the brain-computer interface rehabilitation training system including:
the motor idea induction device presents a biological motion paradigm to induce an active motor idea so as to generate a plurality of corresponding electroencephalogram signals in a plurality of brain areas;
the signal acquisition device is used for acquiring a plurality of corresponding electroencephalogram signals in a plurality of brain areas;
the processing device is used for extracting a plurality of corresponding idea features from a plurality of electroencephalogram signals by processing the plurality of acquired electroencephalogram signals;
the control device generates training control parameters based on a plurality of mind characteristics and/or input instructions; and
the training device executes mechanical movement action and feedback stimulation action according to the training control parameters to complete limb training, so that rehabilitation is realized.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the training device also determines the motion state index according to limb training; and
the brain-computer interface rehabilitation training system further comprises:
and the evaluation device determines a training evaluation parameter according to the plurality of mind characteristics or the motion state index or the plurality of mind characteristics and the motion state index so as to evaluate the training state.
In a brain-computer interface rehabilitation training system according to an embodiment of the present application, a motor mind inducing device visually presents a biological motor paradigm to induce an active motor mind, and a plurality of brain regions including a parietal lobe region, a frontal lobe region, and an occipital lobe region;
the signal acquisition device respectively acquires corresponding apical lobe area electroencephalogram signals, frontal lobe area electroencephalogram signals and occipital lobe area electroencephalogram signals in the apical lobe area, the frontal lobe area and the occipital lobe area; and
the processing device respectively processes the top-lobe-area electroencephalogram signal, the frontal-lobe-area electroencephalogram signal and the occipital-lobe-area electroencephalogram signal, and extracts motor imagery idea characteristics, attention intensity idea characteristics and visual evoked idea characteristics from the top-lobe-area electroencephalogram signal, the frontal-lobe-area electroencephalogram signal and the occipital-lobe-area electroencephalogram signal.
In the brain-computer interface rehabilitation training system according to the embodiment of the present application, the signal acquisition device further acquires an electromyographic signal from a limb performing a limb movement; and
the processing device is also used for extracting the electromyographic strength idea characteristics from the electromyographic signals by processing the acquired electromyographic signals.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the processing device further performs weighted average calculation on the motor imagery mind characteristics, the attention intensity mind characteristics and the visual evoked mind characteristics, and takes the calculation result as the brain engagement index; and
the control device generates training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the processing device further performs weighted average calculation on the motor imagery mind characteristics and the attention intensity mind characteristics, and takes the calculation result as a brain engagement index; and
the control device generates training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the processing device further performs weighted average calculation on the motor imagery mind characteristics and the vision evoked mind characteristics, and takes the calculation result as a brain engagement index; and
the control device generates training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the processing device further performs weighted average calculation on the attention intensity idea features and the visual evoked idea features, and takes the calculation result as the brain engagement index; and
the control device generates training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the processing device further performs weighted average calculation on the motor imagery mind characteristics, the attention intensity mind characteristics, the visual evoked mind characteristics and the myoelectric intensity mind characteristics, and takes the calculation result as a brain engagement index; and
the control device generates training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the evaluation device determines a training evaluation parameter according to the brain engagement index, the exercise state index, or the brain engagement index and the exercise state index to evaluate the training state.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the evaluation device further determines a training evaluation parameter according to the brain engagement index, the motion state index, the plurality of electroencephalogram signals, and the electromyogram signal to evaluate the training state.
In the brain-computer interface rehabilitation training system according to the embodiment of the present application, the motor mind inducing means further audibly presents a biological motor paradigm to induce the active motor mind, and the plurality of brain regions further include a temporal lobe region;
the signal acquisition device is also used for acquiring a temporal lobe area electroencephalogram signal in the temporal lobe area; and
the processing device also processes the temporal lobe area electroencephalogram signals and extracts auditory idea features from the temporal lobe area electroencephalogram signals.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the processing device extracts power of a mu frequency band from each channel of a top-lobe-region electroencephalogram signal and performs regression analysis on the power distribution of the extracted power to determine motor imagery idea features, thereby extracting the motor imagery idea features from the top-lobe-region electroencephalogram signal;
the processing device calculates the ratio of beta-node energy to alpha-node energy of the brain electrical signals of the frontal lobe area, and multiplies the ratio by the weighted value of the head movement orientation to obtain the attention characteristic intensity, so that the attention intensity idea characteristics are extracted from the brain electrical signals of the frontal lobe area; and
the processing device performs sliding window typical correlation analysis on the occipital lobe area electroencephalogram signal and the harmonic thereof and the template signal to obtain a correlation coefficient, and the correlation coefficient is used as a visual evoked characteristic, so that the visual evoked characteristic is extracted from the occipital lobe area electroencephalogram signal.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the processing device further filters the top-lobe-region electroencephalogram signal and the frontal-lobe-region electroencephalogram signal through an ICA filter and a frequency band filter.
In the brain-computer interface rehabilitation training system according to the embodiment of the present application, the motor idea inducing means visually presents a biological motor paradigm to induce the active motor idea.
In a brain-computer interface rehabilitation training system according to an embodiment of the present application, a motor idea induction device visually presents an auxiliary steady-state periodic motor paradigm to enhance the induced active motor idea.
In the brain-computer interface rehabilitation training system according to the embodiment of the present application, the control device generates the training control parameter according to the comparison result by comparing the brain engagement index with a predetermined brain engagement threshold value.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the control device comprises an interface unit, and the interface unit is used for presenting the brain engagement index and receiving an input instruction to generate the training control parameter.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the training control parameters generated by the control device include an action mode parameter, an action control parameter and a stimulation control parameter, the action mode parameter is used for controlling the track of the mechanical movement action of the training device, the action control parameter is used for controlling the acting force and the speed of the mechanical movement action of the training device, and the stimulation control parameter is used for controlling the feedback stimulation action of the training device.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the motion state index determined by the training device comprises the acting force and the speed of the mechanical motion action of the training device.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the evaluation device determines the exercise intensity evaluation value based on the brain engagement index so as to evaluate the intensity of completing limb training.
In the brain-computer interface rehabilitation training system according to the embodiment of the present application, the evaluation means determines the motor dexterity evaluation value based on the time during which the brain engagement index exceeds the predetermined brain engagement threshold value to evaluate the dexterity degree of completing the limb training.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the evaluation device extracts rhythm signals of a mu frequency band and a beta frequency band from electroencephalogram signals, constructs a matrix and a brain network through a causal relationship model based on the extracted rhythm signals, and determines a motion intensity and a symmetry evaluation value according to the spatial distribution of the intensity of the brain network so as to evaluate the symmetry of the completed limb training.
In the brain-computer interface rehabilitation training system according to the embodiment of the application, the evaluation device determines the electromyographic signal strength characteristic evaluation value based on the strength change of the electromyographic signal so as to evaluate the recovery state of the limb strength after the limb training is completed.
Through the brain-computer interface rehabilitation training system according to the application, the initiative motor mind induced by a rehabilitation training receiver can be enhanced, the sensitivity and the accuracy of characteristic extraction from electroencephalogram signals are improved, the rehabilitation training action is enabled to accurately follow the initiative motor mind, nerve conduction is further activated, the rehabilitation effect is obviously improved, the rehabilitation training effect can be fully and timely evaluated, doctors are allowed to intervene in rehabilitation training, and the rehabilitation training effect is effectively improved.
According to another aspect of the application, a brain-computer interface rehabilitation training system method is also provided, which is used for carrying out motion training on limbs of a rehabilitation training recipient according to the active motion idea of the rehabilitation training recipient to realize rehabilitation. The brain-computer interface rehabilitation training method comprises the following steps:
presenting a biological motion paradigm to induce an active motor mind, thereby generating a corresponding plurality of electroencephalogram signals in a plurality of brain regions;
collecting a plurality of corresponding electroencephalogram signals in a plurality of brain areas;
extracting a plurality of corresponding idea features from a plurality of electroencephalogram signals by processing the plurality of acquired electroencephalogram signals;
generating training control parameters based on the plurality of mind features and/or the input instructions; and
and executing mechanical movement action and feedback stimulation action according to the training control parameters to finish limb training, thereby realizing rehabilitation.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, a motion state index is further determined according to limb training; and
and determining a training evaluation parameter according to the plurality of mind characteristics, or the motion state index, or the plurality of mind characteristics and the motion state index so as to evaluate the training state.
In a brain-computer interface rehabilitation training method according to an embodiment of the present application, a biological motion paradigm is visually presented to induce an active motor mind, and a plurality of brain regions include a parietal lobe region, a frontal lobe region, and an occipital lobe region;
collecting corresponding top leaf area electroencephalogram signals, frontal leaf area electroencephalogram signals and occipital leaf area electroencephalogram signals in the top leaf area, the frontal leaf area and the occipital leaf area respectively; and
and respectively processing the top-leaf-area electroencephalogram signal, the frontal-leaf-area electroencephalogram signal and the occipital-leaf-area electroencephalogram signal, and respectively extracting motor imagery idea characteristics, attention intensity idea characteristics and visual evoked idea characteristics from the top-leaf-area electroencephalogram signal, the frontal-leaf-area electroencephalogram signal and the occipital-leaf-area electroencephalogram signal.
In the brain-computer interface rehabilitation training method according to the embodiment of the present application, an electromyographic signal is also acquired from a limb performing limb movement, and
and extracting electromyographic strength idea characteristics from the electromyographic signals by processing the acquired electromyographic signals.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, weighted average calculation is further performed on motor imagery idea features, attention intensity idea features and visual evoked idea features, and the calculation result is used as a brain engagement index; and
training control parameters are generated based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, weighted average calculation is further performed on the motor imagery mind characteristics and the attention intensity mind characteristics, and the calculation result is used as a brain participation degree index; and
training control parameters are generated based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, weighted average calculation is further performed on motor imagery idea features and visual evoked idea features, and the calculation result is used as a brain engagement index; and
training control parameters are generated based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, weighted average calculation is further performed on the attention intensity idea features and the visual evoked idea features, and the calculation result is used as a brain engagement index; and
training control parameters are generated based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, weighted average calculation is further performed on motor imagery idea features, attention intensity idea features, visual evoked idea features and myoelectric intensity idea features, and the calculation result is used as a brain engagement index; and
training control parameters are generated based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, a training evaluation parameter is determined according to the brain engagement index, the exercise state index or the brain engagement index and the exercise state index so as to evaluate the training state.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, a training evaluation parameter is further determined according to the brain participation index, the motion state index, the plurality of electroencephalogram signals and the electromyogram signals so as to evaluate the training state.
In a brain-computer interface rehabilitation training method according to an embodiment of the present application, the biological motor paradigm is also presented audibly to induce an active motor mind, and the plurality of brain regions further include a temporal lobe region;
collecting temporalis electroencephalogram signals in the temporalis area; and
and processing the temporal lobe area electroencephalogram signals, and extracting auditory idea features from the temporal lobe area electroencephalogram signals.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, power of a mu frequency band is extracted from each channel of a top-lobe-region electroencephalogram signal, regression analysis is carried out on the power distribution of the extracted power to determine motor imagery idea features, and therefore the motor imagery idea features are extracted from the top-lobe-region electroencephalogram signal;
calculating the ratio of beta-node energy to alpha-node energy of the frontal lobe electroencephalogram signals, and multiplying the ratio by a head motion orientation weighted value to obtain attention characteristic intensity, so that attention intensity idea characteristics are extracted from the frontal lobe electroencephalogram signals; and
and performing sliding window typical correlation analysis on the occipital lobe electroencephalogram signal and the harmonic thereof and the template signal to obtain a correlation coefficient, and taking the correlation coefficient as a visual evoked characteristic so as to extract the visual evoked characteristic from the occipital lobe electroencephalogram signal.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, the top-lobe-region electroencephalogram signal and the frontal-lobe-region electroencephalogram signal are further filtered through an ICA filter and a frequency band filter.
In a brain-computer interface rehabilitation training method according to an embodiment of the present application, a biological motor paradigm is visually presented to induce an active motor concept.
In a brain-computer interface rehabilitation training method according to an embodiment of the present application, an assisted steady-state periodic motor paradigm is visually presented to augment an induced voluntary motor mind.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, the brain engagement index is compared with a predetermined brain engagement threshold value, and a training control parameter is generated according to the comparison result.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, the brain engagement index is presented and an input instruction is received to generate the training control parameter.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, the generated training control parameters include an action mode parameter, an action control parameter and a stimulation control parameter, the action mode parameter is used for controlling the track of the mechanical movement action of the limb training, the action control parameter is used for controlling the acting force and the speed of the mechanical movement action of the limb training, and the stimulation control parameter is used for controlling the feedback stimulation action of the limb training.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, the determined motion state index comprises the acting force and the speed of the mechanical motion action of limb training.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, the exercise intensity evaluation value is determined based on the brain engagement index so as to evaluate the intensity of finishing limb training.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, a motor dexterity evaluation value is determined based on the time for which the brain engagement index exceeds a predetermined brain engagement threshold value so as to evaluate the dexterity degree of completing limb training.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, rhythm signals of a mu frequency band and a beta frequency band are extracted from electroencephalogram signals, a matrix is constructed and a brain network is constructed through a causal relationship model based on the extracted rhythm signals, and the exercise intensity and the symmetry evaluation value are determined according to the spatial distribution of the intensity of the brain network, so that the intensity and the symmetry of limb training are evaluated.
In the brain-computer interface rehabilitation training method according to the embodiment of the application, an electromyographic signal strength characteristic evaluation value is determined based on the strength change of the electromyographic signal so as to evaluate the recovery state of the limb strength after the limb training is completed.
Through the brain-computer interface rehabilitation training method, active movement ideas induced by a rehabilitation training receiver can be enhanced, the sensitivity and the accuracy of characteristic extraction from electroencephalogram signals are improved, rehabilitation training actions accurately follow the active movement ideas, nerve conduction is further activated, the rehabilitation effect is obviously improved, the rehabilitation training effect can be fully and timely evaluated, doctors are allowed to intervene in rehabilitation training, and the rehabilitation training effect is effectively improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the application and together with the description serve to explain the principles of the application.
FIG. 1 illustrates a block diagram of a brain-computer interface rehabilitation training system according to one embodiment of the present application;
FIG. 2 illustrates a block diagram of a brain-computer interface rehabilitation training system according to one embodiment of the present application;
FIG. 3 illustrates a block diagram of a brain-computer interface rehabilitation training method according to one embodiment of the present application; and
fig. 4 shows a block diagram of a brain-computer interface rehabilitation training method according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are for purposes of illustration only and are not to be construed as limitations of the present application. For the sake of brevity, the same or similar reference numerals are used for the same or similar apparatus/method steps in the description of the various embodiments of the present application.
In addition, the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
According to one aspect of the application, a brain-computer interface rehabilitation training system is provided for performing motion training on limbs of a rehabilitation training recipient according to an active motion idea of the rehabilitation training recipient to achieve rehabilitation. The brain-computer interface rehabilitation training system according to the embodiment of the application is described below with reference to fig. 1 and 2 of the drawings.
Fig. 1 illustrates a block diagram of a brain-computer interface rehabilitation training system 10 that may exercise a limb of a rehabilitation training recipient according to the active motor mind of the rehabilitation training recipient to achieve rehabilitation, according to one embodiment of the present application. As shown in fig. 1, the brain-computer interface rehabilitation training system 10 may include a motor idea induction device 100, a signal acquisition device 200, a processing device 300, a control device 400, and a training device 500. In this embodiment, the motor mind inducing device 100 may present a biological motor paradigm to induce an active motor mind to produce a corresponding plurality of brain electrical signals in a plurality of brain regions; the signal acquisition device 200 can acquire a plurality of corresponding electroencephalogram signals in a plurality of brain areas; the processing device 300 may extract a plurality of corresponding ideogram features from the plurality of electroencephalogram signals by processing the plurality of acquired electroencephalogram signals; the control device 400 may generate training control parameters based on a plurality of mind features and/or input commands; and the training device 500 can perform mechanical movement actions and feedback stimulation actions according to the training control parameters to complete limb training, thereby realizing rehabilitation. Through the brain-computer interface rehabilitation training system according to the embodiment, the active movement consciousness can be accurately and effectively extracted, a motor nerve stimulation closed loop passage is formed, and the rehabilitation effect is improved.
In the brain-computer interface rehabilitation training system 10 according to this embodiment, the motor mind inducing apparatus 100 presents a biological motor paradigm to the rehabilitation training recipient to induce the recipient to generate an active motor mind, thereby generating a plurality of corresponding electroencephalograms in a plurality of brain areas of the brain thereof, so that a higher-intensity electroencephalogram can be induced, the active motor mind of the rehabilitation training recipient can be effectively extracted, and the rehabilitation training effect is further improved.
In the brain-computer interface rehabilitation training system according to other embodiments of the present application, the motor idea inducing device visually presents a biological motor paradigm to induce the active motor idea, so as to generate corresponding electroencephalogram signals in a parietal lobe region, a frontal lobe region, and an occipital lobe region of a brain of a rehabilitation training recipient, specifically, generate a parietal-lobe region electroencephalogram signal in the parietal lobe region, a frontal-lobe region electroencephalogram signal in the frontal lobe region, and generate an occipital-lobe region electroencephalogram signal in the occipital lobe region, respectively. Therefore, the electroencephalogram signals of the brain areas can be fused with one another by adopting a specific algorithm, and the situation that the signal strength induced by one or more brain areas is low due to the fact that motor imagery tasks are difficult to effectively execute because the motor central nervous functions of rehabilitation training receivers are damaged can be effectively avoided.
In one embodiment according to the present application, the motor will inducing device may display a target task in a specific scene to the rehabilitation training recipient through a display provided therein, for example, a desktop or a road surface as a background environment, a vibrating cell phone or a slow-moving bicycle as a task target, and also display a corresponding virtual limb model (for example, an upper limb or a lower limb) and a training action (for example, an action of stretching a hand to grip the cell phone or an action of riding a bicycle), thereby presenting a biological movement paradigm. In a preferred embodiment according to the present application, the display is a high refresh rate liquid crystal display.
In another embodiment according to the present application, the motor will induce device may display the target task in a specific scene to the rehabilitation training recipient through the VR device or VR glasses provided therein. Of course, the motor will also be able to visually display the target task in a particular scenario to the rehabilitation training recipient via any other suitable display device provided therein. In this case, the rehabilitation training recipient performs motor imagery of the corresponding action according to the corresponding visual presentation, thereby inducing active motor concepts.
In the brain-computer interface rehabilitation training system according to other embodiments of the present application, the motor idea inducing device may present the biological motion paradigm in an auditory manner in addition to the visual manner to induce the active motor idea, so that the corresponding temporal lobe area electroencephalogram signal may be generated in the temporal lobe area in the brain area. In the embodiment, the temporal lobe area electroencephalogram signal and corresponding electroencephalogram signals of other multiple brain areas are fused with each other, so that the training rehabilitation effect is improved.
In one embodiment according to the present application, the motion idea inducing device may play a prompt language (e.g., "the mobile phone sounds please hear" or "the front road is bumpy and accelerates riding") and an ambient sound effect to the rehabilitation training recipient through any suitable stereo hearing device provided therein and according to the corresponding target task, in addition to displaying the target task in a specific scene to the rehabilitation training recipient through the vision device provided therein. In this case, the rehabilitation training recipient performs motor imagery of the corresponding action according to the corresponding visual and auditory presentations, thereby inducing active motor concepts.
According to the embodiment of the application, the rehabilitation training receiver can carry out effective motor imagery, a specific task target and corresponding actions are presented in a biological motion paradigm through the motor idea induction device, the concentration degree of the rehabilitation training receiver in the motor imagery process can be effectively improved, stronger motion characteristics are activated, and high-intensity brain electrical signals are induced.
In one embodiment according to the application, the motor idea induction device further comprises a task-oriented environment setting module, a visual task target presenting module and a virtual/real action mode presenting module.
Specifically, the task-oriented environment setting module may set task-oriented training actions and parameters thereof, and construct a virtual environment. For example, for rehabilitation training of the upper limbs of a rehabilitation training recipient, a scene of holding a vibrating mobile phone to answer a call or a scene of holding a pen to write can be set, and the rehabilitation training recipient is required to complete a specific target holding task; to rehabilitation training recipient low limbs rehabilitation training, can set up the different road surface scenes of riding, require the rehabilitation training recipient to accomplish the action of riding. After the target task is selected, a corresponding virtual visual scene can be constructed according to the selected target task and through the task-oriented environment setting module.
The visual task target module can draw a virtual limb and a task object for inducing a rehabilitation training receiver, wherein various models can be selected for the virtual limb so as to achieve the best similarity with an affected limb of the rehabilitation training receiver; for the task object, various models can be selected, and diversity can be increased under the condition of providing similar movement task operation, so that the situation that the participation enthusiasm of a rehabilitation training receiver is reduced is prevented.
The virtual/real action mode presenting module can be used for drawing the motion tracks of various virtual training modes of a training limb (namely an affected limb) of a rehabilitation training receiver, so that a limb target in a visual task target makes periodic motion according to the tracks; the repetitive training actions of the healthy side limbs of the rehabilitation training receiver can be directly shot and recorded and presented through the mirror image technology, so that the rehabilitation training receiver considers that the corresponding actions are the actions finished by the affected side limbs of the rehabilitation training receiver.
In another embodiment according to the present application, the motor idea induction device further has a language induction module and an ambient interaction sound module. Specifically, in the process of observing and executing the motor imagery induction task by the rehabilitation training receiver, the language induction module plays prompt voices related to the task to inform the rehabilitation training receiver of how to imagine the task to be completed so as to assist the rehabilitation training receiver in learning the motor imagery process; and the environment interactive sound module can play the emotion of a relaxing music regulation rehabilitation training receiver and the environment sound effect of presenting a task process, for example, the paper pen contact sound when a hand holds a pen to write characters or the bicycle and road surface contact sound when a lower limb trains to ride can be played, so that a more vivid motor imagery execution action is presented to the rehabilitation training receiver.
In yet another embodiment according to the present application, the motor idea inducing means may also visually present an auxiliary steady-state periodic motor paradigm to enhance the induced active motor idea. In one embodiment according to the application, the motor idea inducing device further presents the flickering of traffic lights or the flickering of lights of other vehicles as an auxiliary steady-state periodic motor paradigm when presenting the riding bicycle task to the rehabilitation training recipient through the display, so that the induced active motor idea can be enhanced, and the brain electrical signals related to the induced active motor idea are enhanced. In another embodiment according to the present application, the motor concept inducing device, when presenting the riding bicycle task to the rehabilitation training recipient through the display, also presents the bicycle riding on an uphill road as an auxiliary steady-state periodic motor paradigm, whereby the induced active motor concept can be enhanced. In another embodiment according to the present application, when the rehabilitation training recipient observes the visual sense inducing action, the motor idea inducing device may further record the real task action of the rehabilitation training recipient's side limb, and the real task action is mapped into the affected side limb action after mirror image processing, so that the rehabilitation training recipient observes the inducing video of the real action of the rehabilitation training recipient, thereby further ensuring the mirror image neurons to be activated and enhancing the active motor consciousness of the rehabilitation training recipient.
Through the functions, the motor idea induction device can present the biological motion paradigm to a rehabilitation training receiver in a visual mode and/or an auditory mode, so that the rehabilitation training receiver receives a complete induction task, can complete the motor idea of a specific action along with an induction scene, and induces the active motor idea of the rehabilitation training receiver, thereby generating a plurality of electroencephalogram signals in a plurality of brain areas of the rehabilitation training receiver.
In one embodiment according to the present application, in the athletic idea inducing device, the task guide environment may be selected according to the symptoms of the rehabilitation training recipient, for example, in case of impaired motion function of upper limb hand, the training action task of stretching the hand to answer the mobile phone may be selected, and in case of impaired motion function of lower limb leg and foot, the acceleration cycling action task may be selected. Then, task difficulty and task action times of different levels can be selected according to the degree of motor function damage of the rehabilitation training receiver, wherein the task difficulty affects various initial parameters of the operating system, such as initial threshold of brain movement participation, action delay time, running speed and amplitude of rehabilitation exercise equipment and the like; the number of the task actions determines how many times of rehabilitation training actions are carried out and then the training is finished.
Continuing now with reference to fig. 1, a brain-computer interface rehabilitation training system 10 according to the embodiment shown in fig. 1 is described, after a plurality of brain electrical signals are generated in a plurality of brain areas by the motor mind inducing device 100, the signal collecting device 200 can collect the corresponding plurality of brain electrical signals in the plurality of brain areas.
The signal acquisition device 200 may acquire a plurality of electroencephalogram signals through any suitable electroencephalogram signal acquisition equipment. In one embodiment according to the present application, the signal acquisition apparatus 200 acquires a plurality of brain electrical signals through a multi-lead bioelectric signal acquisition device. In another embodiment according to the present application, the signal acquisition device 200 acquires a plurality of brain electrical signals through a whole brain high density multi-lead acquisition system.
In one embodiment according to the present application, the motor idea inducing device visually presents a biological motion paradigm to induce an active motor idea, thereby generating a parietal lobe region brain electrical signal in a parietal lobe region of a brain of a rehabilitation training recipient, a frontal lobe region brain electrical signal in the frontal lobe region, and a occipital lobe region brain electrical signal in the occipital lobe region, and accordingly, corresponding signal collecting electrodes may be respectively provided in the parietal lobe region, the frontal lobe region, and the occipital lobe region through a multi-lead bioelectric signal collecting apparatus, so that the signal collecting device may collect the parietal lobe region brain electrical signal, the frontal lobe region brain electrical signal, and the occipital lobe region brain electrical signal.
In another embodiment according to the present application, the signal collecting device collects temporal lobe area brain electrical signals in addition to the apical lobe area brain electrical signals, the frontal lobe area brain electrical signals, and the occipital lobe area brain electrical signals at the apical lobe area, the frontal lobe area, and the occipital lobe area, respectively, by the multi-lead bioelectric signal collecting device.
In yet another embodiment according to the present application, the signal collecting device collects electromyographic signals at a training limb of a rehabilitation training recipient through an electromyographic signal sensor in addition to collecting a parietal lobe region electroencephalographic signal, a frontal lobe region electroencephalographic signal, and an occipital lobe region electroencephalographic signal at a parietal lobe region, a frontal lobe region, and an occipital lobe region, respectively, and/or collecting a temporal lobe region electroencephalographic signal at a temporal lobe region through a multi-lead bioelectrical signal collecting device.
With continued reference to fig. 1, the processing device 300 of the brain-computer interface rehabilitation training system 10 according to the embodiment shown in fig. 1 may extract a plurality of corresponding ideographic features from a plurality of brain electrical signals by processing the plurality of acquired brain electrical signals.
In the brain-computer interface rehabilitation training system according to an embodiment of the present application, after the signal acquisition device respectively acquires corresponding apical lobe area electroencephalogram signals, frontal lobe area electroencephalogram signals, and occipital lobe area electroencephalogram signals in the apical lobe area, frontal lobe area, and occipital lobe area of the brain of a rehabilitation training recipient, the processing device may respectively process the apical lobe area electroencephalogram signals, the frontal lobe area electroencephalogram signals, and the occipital lobe area electroencephalogram signals, and extract motor imagery idea features, attention intensity idea features, and visual evoked idea features from the apical lobe area electroencephalogram signals, the frontal lobe area electroencephalogram signals, and the occipital lobe area electroencephalogram signals, respectively.
In the brain-computer interface rehabilitation training system according to another embodiment of the present application, after the signal acquisition device acquires the temporal lobe area electroencephalogram signal in the temporal lobe area, the processing device extracts the motor imagery idea feature, the attention intensity idea feature, and the visual evoked idea feature from the top lobe area electroencephalogram signal, the frontal lobe area electroencephalogram signal, and the occipital lobe area electroencephalogram signal, respectively, and extracts the auditory idea feature from the temporal lobe area electroencephalogram signal by processing the temporal lobe area electroencephalogram signal.
In the brain-computer interface rehabilitation training system according to still another embodiment of the present application, after the signal acquisition device acquires the electromyogram signals, the processing device may extract the motor imagery idea feature, the attention intensity idea feature, the visual evoked idea feature, and/or the auditory idea feature from the top lobe area electroencephalogram signals, the frontal lobe area electroencephalogram signals, the occipital lobe area electroencephalogram signals, and/or the temporal lobe area electroencephalogram signals, respectively, and may extract the electromyogram intensity idea feature from the electromyogram signals by processing the acquired electromyogram signals.
Specifically, the processing means may perform the extraction of each of the above-described conceptual features in an appropriate manner. In one embodiment according to the application, the processing device extracts power of a μ band from each channel of the top-lobe brain electrical signal and performs regression analysis on the power distribution of the extracted power to determine motor imagery idea features, thereby extracting the motor imagery idea features from the top-lobe brain electrical signal; the processing device calculates the ratio of beta-node energy to alpha-node energy of the brain electrical signals of the frontal lobe area, and multiplies the ratio by the weighted value of the head movement orientation to obtain the attention characteristic intensity, so that the attention intensity idea characteristic is extracted from the brain electrical signals of the frontal lobe area; and the processing device performs sliding window typical correlation analysis on the occipital lobe electroencephalogram signal and the harmonic thereof and the template signal to obtain a correlation coefficient, and takes the correlation coefficient as a visual evoked characteristic, thereby extracting the visual evoked characteristic from the occipital lobe electroencephalogram signal.
In other embodiments according to the present application, the processing device may process the rhythm wave of the electroencephalogram signal within 1 second, specifically, perform noise cancellation analysis on the top-lobe electroencephalogram signal and the frontal-lobe electroencephalogram signal within 1 second of input time, remove the electromyographic eye electrical artifact signals mixed in the electroencephalogram signal through an ICA filter, and perform frequency band filtering through a frequency band filter, wherein the filtering range of the frequency band filter is two electroencephalogram rhythm wave bands, such as 8Hz-13Hz (for alpha rhythm waves) and 13Hz-20Hz (for beta rhythm waves); for frontal lobe electroencephalogram signals, extracting power of an alpha frequency band from each channel through a Morlet wavelet algorithm, and performing regression analysis on alpha power distribution of different channels according to a pre-trained task label so as to determine corresponding motor imagery characteristic strength; calculating the ratio of beta-nodal energy to alpha-nodal energy of the frontal lobe electroencephalogram signals, and multiplying the ratio by a weighted value of head movement orientation to obtain the attention characteristic intensity; for the electroencephalogram signals in the occipital lobe visual area, performing sliding window typical correlation analysis on the electroencephalogram signals and second and third harmonics thereof and template signals (standard sine and cosine signals can be selected as the template signals) by adopting a typical correlation analysis method to obtain a correlation coefficient time spectrum, wherein the visual evoked potential of corresponding frequency can be induced by the motion frequency of a motion paradigm in the motion paradigm, so that the intensity change of visual characteristics is consistent with the correlation coefficient corresponding to the motion frequency, and the correlation coefficient can be used as the visual evoked characteristics so as to extract the visual evoked characteristics from the electroencephalogram signals in the occipital lobe area; for the electromyographic signals, an integrated electromyographic value (ieg) and a root mean square value of the electromyographic signals are taken as the electromyographic signal intensity characteristics.
According to one embodiment of the application, the signal acquisition device is used for acquiring the strength change of the electromyographic signals of key muscles of limbs in the movement process of a rehabilitation training recipient, and the processing device is used for calculating the integral electromyographic values and the root mean square values of the electromyographic signals by using a sliding window of 0.5-2 seconds as the electromyographic signal strength characteristics.
In the brain-computer interface rehabilitation training system according to one embodiment of the application, the processing device further performs signal processing including filtering on the electroencephalogram signal and/or the electromyogram signal acquired at the signal acquisition device. In one embodiment, the processing device may perform noise cancellation analysis on the top-lobe and frontal-lobe electroencephalograms, remove electromyographic eye electrical artifact signals mixed into the electroencephalograms through an ICA (independent component analysis) filter, and perform band filtering through a band filter. In one embodiment, the filtering range of the band filter may be two brain rhythm bands of 8Hz-13Hz (for alpha rhythm waves) and 13Hz-20Hz (for beta rhythm waves).
After extracting the corresponding features from the electroencephalogram signal and/or the electromyogram signal, the processing device can further process the features for subsequent operations.
In the brain-computer interface rehabilitation training system according to one embodiment of the present application, the processing device further performs weighted average calculation on the motor imagery mind characteristics, the attention intensity mind characteristics, and the visual evoked mind characteristics, and uses the calculation result as the brain engagement index.
In the brain-computer interface rehabilitation training system according to another embodiment of the present application, the processing device performs weighted average calculation on the motor imagery mind characteristics and the attention intensity mind characteristics, and uses the calculation result as the brain engagement index.
In a brain-computer interface rehabilitation training system according to still another embodiment of the present application, the processing device performs weighted average calculation on the motor imagery mind characteristics and the vision evoked mind characteristics, and uses the calculation result as a brain engagement indicator.
In a brain-computer interface rehabilitation training system according to still another embodiment of the present application, the processing means performs weighted average calculation on the above attention intensity mind characteristics and visual evoked mind characteristics, and takes the calculation result as a brain engagement indicator.
In a brain-computer interface rehabilitation training system according to still another embodiment of the present application, the processing means performs weighted average calculation on the above motor imagery mind characteristics, attention intensity mind characteristics, visual evoked mind characteristics, and myoelectric intensity mind characteristics, and takes the calculation result as a brain engagement index.
In the technical scheme according to the application, by integrating a plurality of mind characteristics into a brain engagement index in a specific manner, the active motor mind of a rehabilitation training recipient can be quantified with higher sensitivity and accuracy, and the training device can be controlled to execute mechanical motion action and feedback stimulation on the basis of the quantified active motor mind (i.e., the brain engagement index), so that the training device can more sensitively and accurately follow the active motor mind of the rehabilitation training recipient, thereby obtaining more effective rehabilitation training effect.
In one embodiment according to the application, the processing means applies the same weight to each feature when performing the weighted average calculation.
In one embodiment according to the present application, the processing device may determine the weight corresponding to each feature in the weighted average calculation based on a predetermined model and an adaptive algorithm.
In the above brain-computer interface rehabilitation training system according to the above embodiment, in the visual biological motion-induced paradigm, there is a correlation between the motor imagery will characteristics, the attention intensity will characteristics, and the visual evoked will characteristics, and therefore the brain engagement index obtained by fusing these three features has higher sensitivity and accuracy. More specifically, in the brain-computer interface rehabilitation training system, in the process of performing motor imagery by a rehabilitation training receiver, the brain engagement index is obtained by integrating the attention change, the motor imagery ERD/ERS (time-related desynchronization/event-related synchronization), the visual evoked potential characteristics and other indexes, and as the attention of the rehabilitation training receiver changes when the rehabilitation training receiver looks at the visual motor paradigm and the motor imagery characteristic change and the visual evoked potential frequency characteristics have correlation, compared with the prior art which uses the motor area lead signal alone, the brain motion engagement obtained by fusing the brain electrical signals with the multi-modal characteristics has better classification performance, low false positive rate and high system stability.
In one embodiment according to the application, the processing device may further determine a brain motor engagement threshold to perform the corresponding operations.
For this reason, in an embodiment according to the present application, when a rehabilitation training recipient performs rehabilitation training through a brain-computer interface rehabilitation training system according to the present application for the first time, pre-learning is required, at this time, the rehabilitation training recipient should perform motor imagery for a period of time according to the guidance of the motor idea guidance device, and during this process, a stationary state is ensured and the blink frequency is reduced, and the processing device may use the electroencephalogram signals and/or the electromyogram signals acquired during this process as training data to determine regression parameters and a brain motor engagement threshold value when the motor imagery characteristics are determined.
With continued reference now to FIG. 1, a brain-computer interface rehabilitation training system 10 in accordance with the embodiment illustrated in FIG. 1 will be described. The control device 400 of the brain-computer interface rehabilitation training system 10 may generate training control parameters based on a plurality of mental features and/or input instructions. In the brain-computer interface rehabilitation training system 10, the training control parameters generated by the control device 400 are used for controlling the training device 500 to perform corresponding operations.
Specifically, in the brain-computer interface rehabilitation training system 10, the control device 400 may output the training control parameters to the training device 500 based on the plurality of mind characteristics obtained by the processing device 300 or generate the training control parameters. As described above, the control apparatus performs weighted average calculation on a suitable combination of motor imagery will characteristics, attention intensity will characteristics, visual evoked will characteristics, and myoelectric intensity will characteristics, and takes the calculation result as a brain engagement index, on the basis of which the control apparatus 400 generates training control parameters accordingly.
In the brain-computer interface rehabilitation training system according to the present application, the control device may determine the motion pattern parameter according to the target task determined by the motor will inducing device and combine with other parameters/indices to generate the training control parameter. The motion pattern parameters here control the trajectory of the motion of the mechanical movement performed by the training device.
In the brain-computer interface rehabilitation training system according to an embodiment of the present application, the control device may generate the training control parameter by comparing the brain engagement index with a predetermined brain engagement threshold value and according to the comparison result. Thus, in the technical scheme according to the application, the biological motion paradigm is presented through the motion idea induction device to induce stronger active motion idea, corresponding brain electrical signals are generated in a plurality of brain areas, corresponding idea features are provided from the brain electrical signals, the training device can be controlled based on the idea features accurately reflecting the active motion idea, so that the training device can sensitively and accurately follow the active motion idea to execute mechanical motion action and feedback stimulation, and the rehabilitation training effect is improved.
In one embodiment according to the application, the brain engagement index input to the control device changes with time, and the control device judges that the brain engagement index meets the motion parameter adaptive adjustment algorithm condition, generates a training control parameter including an action command and a stimulation command, and specifically, when the brain engagement index exceeds a brain engagement threshold, outputs the action control command, or when the brain engagement index continuously increases for 3 seconds without decreasing, outputs the action command and the stimulation control command, otherwise, waits all the time. The action and stimulation control command comprises a starting parameter and an intensity parameter, wherein the starting parameter is a binary parameter and controls whether the task action of the perception feedback exercise training module is started or not. The intensity parameters control the specific motion mode of the task motion of the perception feedback motion training module according to different tasks, such as motion speed, motion amplitude and the like. The higher the average value of the exercise participation index is, the higher the intensity parameter is. And if the motion participation index does not exceed the index after the delay time, performing the next action.
In the brain-computer interface rehabilitation training system according to one embodiment of the present application, the training control parameters generated by the control device may include a motion mode parameter for controlling a trajectory of a mechanical movement motion of the training device, a motion control parameter for controlling an acting force and a velocity of the mechanical movement motion of the training device, and a stimulation control parameter for controlling a feedback stimulation motion of the training device. For the training device, it will be described in detail later.
In a brain-computer interface rehabilitation training system according to another embodiment of the present application, the motion state indicators determined by the training device further include the effort and speed of the mechanical motor action of the training device.
In one embodiment according to the application, for upper limb rehabilitation training of a rehabilitation training recipient, for example, when a target task is to grasp and answer a vibrating mobile phone, when a brain engagement index parameter of the rehabilitation training recipient exceeds a brain engagement index threshold, the control device generates a corresponding action mode parameter to control a hand exoskeleton device serving as a training device to simulate a grasping action track; the control device generates corresponding motion control parameters to control the hand exoskeleton device to perform the gripping motion and the gripping speed; the control device generates corresponding stimulation control parameters, so that after the hand exoskeleton executes the gripping action, the vibration unit in the training device is controlled to perform feedback stimulation action to simulate the perception and perception process of the upper limbs of the human body.
In another embodiment according to the present application, in lower limb rehabilitation training of a rehabilitation training recipient, for example, when a target task is to quickly ride on a stone road, when a brain engagement index of the rehabilitation training recipient exceeds a brain engagement threshold, the control device generates corresponding motion pattern parameters to control a leg training vehicle device as a training device to simulate a quick riding track; the control device generates corresponding action control parameters to control the leg training vehicle equipment to execute riding actions and the riding speed; the control device generates corresponding stimulation control parameters, so that after the leg training vehicle device executes the riding action, the vibration unit in the training device is controlled to perform feedback stimulation action, and the perception feeling process of the lower limbs of the human body is simulated.
On the other hand, in the brain-computer interface rehabilitation training system 10 according to the embodiment shown in fig. 1, the control device 400 may also generate training control parameters based on the input instruction. In the technical solution according to the present application, the input command is from outside the brain-computer interface rehabilitation training system, for example, may be a control command of a physician, so that the physician may intervene in rehabilitation training of a rehabilitation training recipient at an appropriate time.
In a brain-computer interface rehabilitation training system according to an embodiment of the application, a control device includes an interface unit that can present a brain engagement indicator and receive an input instruction to generate a training control parameter. In this embodiment, the interface unit may display parameters/indicators including the brain engagement indicator via the display, such that the physician may observe the brain engagement indicator of the rehabilitation recipient during the rehabilitation training, and may intervene in the rehabilitation training directly, e.g. manually, by changing a brain engagement threshold, such that the control device generates corresponding training control parameters according to the intervention performed by the physician via the interface unit, to control the training device accordingly. When manual intervention is carried out, a doctor can orally instruct a rehabilitation training receiver to carry out a motor imagination task, and timely adjusts a brain engagement threshold value according to the change trend of the brain engagement index of the rehabilitation training receiver, so that the rehabilitation training receiver can carry out effective rehabilitation training.
In the brain-computer interface rehabilitation training system according to another embodiment of the present application, the control device generates a corresponding training control parameter to control the training device to perform a specific rehabilitation training action, and adaptively controls the brain engagement threshold value, in addition to when the brain engagement index exceeds the brain engagement threshold value under normal conditions, and the brain engagement threshold value can be automatically adjusted according to the change of the brain engagement index of the rehabilitation training recipient and the past data record, thereby improving the operation flexibility and reducing the burden of the doctor.
Next, a description will be given of the training apparatus 500 of the brain-computer interface rehabilitation training system 10 according to the embodiment shown in fig. 1. The training device 500 may perform mechanical movement actions and feedback stimulation actions according to the training control parameters to complete limb training, thereby achieving rehabilitation. The training apparatus 500 may be any suitable rehabilitation training device, including a hand exoskeleton device, a leg training vehicle device, etc., as described above, to perform mechanical locomotion actions according to training control parameters.
In the brain-computer interface rehabilitation training system according to one embodiment of the present application, the training apparatus may further include a vibration device to provide feedback stimulation to simulate a sensation feeling of the limbs.
In the brain-computer interface rehabilitation training system according to one embodiment of the present application, as described above in the context of the control device, the training device may perform the mechanical movement action and the feedback stimulation action to complete the limb training according to the movement pattern parameters, the movement control parameters, and the stimulation control parameters generated by the control device, specifically, the movement pattern parameters are used to control the trajectory of the mechanical movement action of the training device, the movement control parameters are used to control the effort and speed of the mechanical movement action of the training device, and the stimulation control parameters are used to control the feedback stimulation action of the training device.
Fig. 2 illustrates a block diagram of a brain-computer interface rehabilitation training system according to an embodiment of the present application. As shown in fig. 2, the brain-computer interface rehabilitation training system 10 includes an evaluation device 600 in addition to the motor idea induction device 100, the signal acquisition device 200, the processing device 300, the control device 400, and the training device 500 as in the above embodiment.
In this embodiment, the motor mind inducing device 100 may present a biological motor paradigm to induce an active motor mind to produce a corresponding plurality of brain electrical signals in a plurality of brain regions; the signal acquisition device 200 can acquire a plurality of corresponding electroencephalogram signals in a plurality of brain areas; the processing device 300 may extract a plurality of corresponding ideogram features from the plurality of electroencephalogram signals by processing the plurality of acquired electroencephalogram signals; the control device 400 may generate training control parameters based on a plurality of mind features and/or input commands; the training device 500 can perform mechanical movement and feedback stimulation according to the training control parameters to complete limb training, and also determine movement state indexes according to the limb training, thereby realizing rehabilitation; and the evaluation device 600 may determine a training evaluation parameter according to the plurality of mind characteristics, or the motion state index, or the plurality of mind characteristics and the motion state index to evaluate the training state. In this embodiment, the evaluation device 600 may determine the training evaluation parameter according to the plurality of mind characteristics determined by the processing device 400, or determine the training evaluation parameter according to the exercise state index determined by the training device 500, or determine the training evaluation parameter according to the plurality of mind characteristics and the exercise state index. Through the rehabilitation training system according to the embodiment, the rehabilitation training receiver and the doctor can timely know the brain state and the change of the limb movement function state of the rehabilitation training receiver in the rehabilitation training process, and know the effect of the rehabilitation training, so that the rehabilitation training can be timely adjusted, and a basis can be provided for making a follow-up rehabilitation training plan.
In the rehabilitation training system according to an embodiment of the present application, in a case where the processing means performs weighted average calculation on a combination of the motor imagery mind feature, the attention intensity mind feature, and the visual evoked mind feature as described above, and takes the calculation result as the brain engagement index, the evaluation means may determine a training evaluation parameter from the brain engagement index, or the exercise state index, or the brain engagement index and the exercise state index to evaluate the training state.
In the rehabilitation training system according to one embodiment of the present application, in a case where the exercise state index determined by the training device includes the effort and speed of the mechanical exercise action of the training device, the evaluation device determines the exercise intensity evaluation value based on the brain engagement index to evaluate the intensity of the completion of the limb training.
In the brain-computer interface rehabilitation training system according to another embodiment of the present application, the evaluation means may determine a motor dexterity evaluation value based on a time during which the brain engagement indicator exceeds a predetermined brain engagement threshold value to evaluate a dexterity degree of completing the limb training.
In the brain-computer interface rehabilitation training system according to still another embodiment of the present application, the evaluation device may extract rhythm signals of a μ frequency band and a β frequency band from the electroencephalogram signal, construct a matrix and construct a brain network through a causal relationship model based on the extracted rhythm signals, and determine the exercise intensity and the symmetry evaluation value according to the spatial distribution of the intensity of the brain network to evaluate the symmetry of completing the limb training. In this embodiment, the signal acquisition device may acquire the electroencephalogram signal through the multi-lead electroencephalogram cap.
In the brain-computer interface rehabilitation training system according to still another embodiment of the present application, the evaluation means may determine the electromyogram signal strength characteristic evaluation value based on the strength variation of the electromyogram signal to evaluate the recovery state of the limb strength for completing the limb training.
In the brain-computer interface rehabilitation training system according to still another embodiment of the present application, the evaluation device may calculate the limb movement power of the rehabilitation training recipient from the force and velocity of the mechanical movement action of the training device, and use the power average value in the execution of the rehabilitation training task as the power index.
In the brain-computer interface rehabilitation training system according to an embodiment of the present application, the evaluation device may present the evaluation parameters in a scoring manner, or further normalize the scores with a preset maximum value and then perform weighted summation to obtain a total score of the comprehensive motor function as a comprehensive evaluation result. Through the interface unit of the control device, a doctor can pertinently determine relevant training parameters in the next stage of training according to various evaluation parameters and/or comprehensive evaluation results, for example, the task difficulty in a scene can be increased according to the recovery effect of the motion function, and sufficient iterative intensity training is ensured.
In the brain-computer interface rehabilitation training system according to an embodiment of the present application, the evaluation device may further store all data as training data of the motion parameter adaptive adjustment algorithm.
According to another aspect of the application, a brain-computer interface rehabilitation training method is further provided, and the method is used for carrying out motion training on limbs of a rehabilitation training recipient according to the active motion idea of the rehabilitation training recipient to achieve rehabilitation. The brain-computer interface rehabilitation training method according to the embodiment of the application is described below with reference to fig. 3 and 4 of the drawings attached to the specification.
Fig. 3 illustrates a brain-computer interface rehabilitation training method according to an embodiment of the present application, and as shown, the brain-computer interface rehabilitation training method M90 includes: s100, presenting a biological motion paradigm to induce an active motion idea so as to generate a plurality of corresponding electroencephalogram signals in a plurality of brain areas; s200, collecting a plurality of corresponding electroencephalogram signals in a plurality of brain areas; s300, processing the acquired electroencephalogram signals, and extracting a plurality of corresponding idea features from the electroencephalogram signals; s400, generating training control parameters based on a plurality of idea features and/or input instructions; and S500, executing mechanical movement action and feedback stimulation action according to the training control parameters to complete limb training, thereby realizing rehabilitation.
Fig. 4 illustrates a brain-computer interface rehabilitation training method according to another embodiment of the present application. As shown in the figure, the brain-computer interface rehabilitation training method M90 includes: s100, presenting a biological motion paradigm to induce an active motion idea so as to generate a plurality of corresponding electroencephalogram signals in a plurality of brain areas; s200, collecting a plurality of corresponding electroencephalogram signals in a plurality of brain areas; s300, processing the acquired electroencephalogram signals, and extracting a plurality of corresponding idea features from the electroencephalogram signals; s400, generating training control parameters based on a plurality of idea features and/or input instructions; s500, executing mechanical movement action and feedback stimulation action according to the training control parameters to finish limb training, and determining movement state indexes according to the limb training so as to realize rehabilitation; and determining a training evaluation parameter according to the plurality of mind characteristics, the motion state index or the plurality of mind characteristics and the motion state index so as to evaluate the training state.
The brain-computer interface rehabilitation training method according to the embodiment of the present application and the brain-computer interface rehabilitation training system according to the embodiment of the present application have close association in technical solutions, and the above description about the brain-computer interface rehabilitation training system can be applied to the brain-computer interface rehabilitation training method, so that only the technical solution about the brain-computer interface rehabilitation training method claimed in the present application is described in the following, and other specific contents about the brain-computer interface rehabilitation training system are not described herein again.
In a brain-computer interface rehabilitation training method according to an embodiment of the present application, a biological movement pattern may be visually presented to induce an active movement idea, and a plurality of brain regions include a parietal region, a frontal lobe region, and an occipital lobe region; collecting corresponding top leaf area electroencephalogram signals, frontal leaf area electroencephalogram signals and occipital leaf area electroencephalogram signals in the top leaf area, the frontal leaf area and the occipital leaf area respectively; and processing the top-lobe-area electroencephalogram signal, the frontal-lobe-area electroencephalogram signal and the occipital-lobe-area electroencephalogram signal respectively, and extracting motor imagery idea characteristics, attention intensity idea characteristics and visual evoked idea characteristics from the top-lobe-area electroencephalogram signal, the frontal-lobe-area electroencephalogram signal and the occipital-lobe-area electroencephalogram signal respectively.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, an electromyographic signal can be collected from a limb performing limb movement, and electromyographic strength idea features can be extracted from the electromyographic signal by processing the collected electromyographic signal.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, weighted average calculation can be further performed on motor imagery idea features, attention intensity idea features and visual evoked idea features, and the calculation result is used as a brain engagement index; and generating training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, weighted average calculation can be further performed on the motor imagery mind characteristics and the attention intensity mind characteristics, and the calculation result is used as a brain engagement index; and generating training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, weighted average calculation can be further performed on the motor imagery mind characteristics and the visual evoked mind characteristics, and the calculation result is used as a brain engagement index; and generating training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, weighted average calculation can be further performed on the attention intensity idea features and the visual evoked idea features, and the calculation result is used as a brain engagement index; and generating training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, weighted average calculation can be further performed on motor imagery idea features, attention intensity idea features, visual evoked idea features and myoelectric intensity idea features, and the calculation result is used as a brain engagement index; and generating training control parameters based on the brain engagement indicator and/or the input instruction.
In the brain-computer interface rehabilitation training method according to an embodiment of the present application, a training evaluation parameter may be determined according to the brain engagement index, or the exercise state index, or both the brain engagement index and the exercise state index to evaluate the training state.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, a training evaluation parameter can be further determined according to the brain participation index, the motion state index, the plurality of electroencephalogram signals and the electromyogram signals so as to evaluate the training state.
In the brain-computer interface rehabilitation training method according to an embodiment of the present application, the biological motor paradigm may also be presented audibly to induce an active motor mind, and the plurality of brain regions further include a temporal lobe region; collecting temporalis electroencephalogram signals in the temporalis area; and processing the temporal lobe area electroencephalogram signals, and extracting auditory idea features from the temporal lobe area electroencephalogram signals.
In the brain-computer interface rehabilitation training method according to one embodiment of the present application, power of a μ band may be extracted from each channel of a top-lobe-region electroencephalogram signal, and regression analysis may be performed on power distribution of the extracted power to determine motor imagery idea features, thereby extracting the motor imagery idea features from the top-lobe-region electroencephalogram signal; calculating the ratio of beta-node energy to alpha-node energy of the frontal lobe electroencephalogram signals, and multiplying the ratio by a head motion orientation weighted value to obtain attention characteristic intensity, so as to extract attention intensity idea characteristics from the frontal lobe electroencephalogram signals; and performing sliding window typical correlation analysis on the occipital lobe electroencephalogram signal and the harmonic thereof and the template signal to obtain a correlation coefficient, and taking the correlation coefficient as a visual evoked characteristic, thereby extracting the visual evoked characteristic from the occipital lobe electroencephalogram signal.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, the top-lobe-region electroencephalogram signal and the frontal-lobe-region electroencephalogram signal can be filtered through an ICA filter and a frequency band filter.
In a brain-computer interface rehabilitation training method according to an embodiment of the present application, a biological motor paradigm may be visually presented to induce an active motor concept.
In a brain-computer interface rehabilitation training method according to an embodiment of the present application, an assisted steady-state periodic motion paradigm may be visually presented to augment the induced voluntary motor mind.
In the brain-computer interface rehabilitation training method according to an embodiment of the present application, the training control parameter may be generated by comparing the brain engagement index with a predetermined brain engagement threshold value and according to the comparison result.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, the brain engagement index can be presented and an input instruction is received to generate the training control parameter.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, the generated training control parameters may include a motion mode parameter, a motion control parameter, and a stimulation control parameter, the motion mode parameter may be used to control a trajectory of a mechanical movement motion of the limb training, the motion control parameter is used to control an acting force and a speed of the mechanical movement motion of the limb training, and the stimulation control parameter is used to control a feedback stimulation motion of the limb training.
In a brain-computer interface rehabilitation training method according to an embodiment of the present application, the determined motion state index may include the effort and speed of the mechanical motor action of the limb training.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, a motion intensity evaluation value can be determined based on the brain engagement index to evaluate the intensity of completing limb training.
In the brain-computer interface rehabilitation training method according to an embodiment of the present application, a motor dexterity assessment value may be determined based on a time during which the brain engagement indicator exceeds a predetermined brain engagement threshold value to assess a dexterity degree of completing limb training.
In the brain-computer interface rehabilitation training method according to one embodiment of the application, rhythm signals of a mu frequency band and a beta frequency band can be extracted from electroencephalogram signals, a matrix is constructed and a brain network is constructed through a causal relationship model based on the extracted rhythm signals, and the exercise intensity and the symmetry evaluation value are determined according to the spatial distribution of the intensity of the brain network, so that the intensity and the symmetry of limb training can be evaluated.
In the brain-computer interface rehabilitation training method according to an embodiment of the present application, an electromyographic signal strength characteristic evaluation value may be determined based on a strength variation of the electromyographic signal to evaluate a recovery state of a limb strength at which a limb training is completed.
Embodiments according to the present application may be implemented in hardware, software, or a combination thereof. Furthermore, according to yet another aspect of the present application, a computer program comprising executable instructions for implementing a brain-computer interface rehabilitation training system method according to an embodiment of the present application is also presented.
Such a computer program may be stored using any form of memory, such as an optically or magnetically readable medium, chip, ROM, PROM, or other volatile or non-volatile device. According to an embodiment of the application, a machine-readable memory storing such a computer program is also proposed.
In the description herein, reference to the description of the terms "one embodiment/mode," "some embodiments/modes," "example," "specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/mode or example is included in at least one embodiment/mode or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to be the same embodiment/mode or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/aspects or examples and features of the various embodiments/aspects or examples described in this specification can be combined and combined by one skilled in the art without conflicting therewith.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
It should be understood by those skilled in the art that the above embodiments are only for clarity of explanation and are not intended to limit the scope of the present application. Other variations or modifications will occur to those skilled in the art based on the foregoing disclosure and are still within the scope of the present application.
Claims (10)
1. The brain-computer interface rehabilitation training system is used for carrying out motion training on limbs of a rehabilitation training receiver according to the active motion idea of the rehabilitation training receiver so as to realize rehabilitation, and comprises:
a motor idea inducing device which presents a biological motion paradigm to induce the active motor idea, thereby generating a plurality of corresponding electroencephalogram signals in a plurality of brain areas;
the signal acquisition device acquires the corresponding electroencephalogram signals in the brain areas;
the processing device is used for extracting a plurality of corresponding idea characteristics from the plurality of electroencephalogram signals by processing the plurality of acquired electroencephalogram signals;
the control device generates training control parameters based on the plurality of mind characteristics and/or input instructions; and
and the training device executes mechanical movement action and feedback stimulation action according to the training control parameters to finish the limb training, so that rehabilitation is realized.
2. The brain-computer interface rehabilitation training system of claim 1,
the training device also determines a motion state index according to the limb training; and
the brain-computer interface rehabilitation training system further comprises:
and the evaluation device determines a training evaluation parameter according to the plurality of mind characteristics, the motion state index or the plurality of mind characteristics and the motion state index so as to evaluate the training state.
3. The brain-computer interface rehabilitation training system of claim 1 or 2, wherein the motor mind inducing device visually presents a biological motor pattern to induce the active motor mind, and the plurality of brain regions include a parietal region, a frontal lobe region, and an occipital lobe region;
the signal acquisition device respectively acquires corresponding apical lobe area electroencephalogram signals, frontal lobe area electroencephalogram signals and occipital lobe area electroencephalogram signals in the apical lobe area, the frontal lobe area and the occipital lobe area; and
the processing device respectively processes the top-lobe-area electroencephalogram signal, the frontal-lobe-area electroencephalogram signal and the occipital-lobe-area electroencephalogram signal, and extracts motor imagery idea characteristics, attention intensity idea characteristics and visual evoked idea characteristics from the top-lobe-area electroencephalogram signal, the frontal-lobe-area electroencephalogram signal and the occipital-lobe-area electroencephalogram signal.
4. The brain-computer interface rehabilitation training system of claim 3,
the signal acquisition device is also used for acquiring electromyographic signals from the limbs performing the limb movement; and
the processing device is also used for extracting the electromyographic strength idea characteristics from the electromyographic signals by processing the acquired electromyographic signals.
5. The brain-computer interface rehabilitation training system of claim 3,
the processing device is also used for carrying out weighted average calculation on the motor imagery mind characteristics, the attention intensity mind characteristics and the vision evoked mind characteristics, and taking the calculation result as a brain participation index; and
the control device generates training control parameters based on the brain engagement indicator and/or input instructions.
6. The brain-computer interface rehabilitation training system of claim 3,
the processing device is also used for carrying out weighted average calculation on the motor imagery mind characteristics and the attention intensity mind characteristics, and the calculation result is used as a brain participation index; and
the control device generates training control parameters based on the brain engagement indicator and/or input instructions.
7. The brain-computer interface rehabilitation training system of claim 3,
the processing device is also used for carrying out weighted average calculation on the motor imagery mind characteristics and the visual evoked mind characteristics, and taking a calculation result as a brain participation index; and
the control device generates training control parameters based on the brain engagement indicator and/or input instructions.
8. The brain-computer interface rehabilitation training system of claim 3,
the processing device is also used for carrying out weighted average calculation on the attention intensity mind characteristics and the visual evoked mind characteristics, and taking the calculation result as a brain participation index; and
the control device generates training control parameters based on the brain engagement indicator and/or input instructions.
9. The brain-computer interface rehabilitation training method is used for performing exercise training on limbs of a rehabilitation training recipient according to the active exercise idea of the rehabilitation training recipient to realize rehabilitation, and comprises the following steps:
presenting a biological motor paradigm to induce the voluntary motor mind to produce a corresponding plurality of brain electrical signals in a plurality of brain regions;
acquiring a plurality of corresponding brain electrical signals in the plurality of brain areas;
extracting a plurality of corresponding idea features from the plurality of electroencephalogram signals by processing the plurality of acquired electroencephalogram signals;
generating training control parameters based on the plurality of mind features and/or input instructions; and
and executing mechanical movement action and feedback stimulation action according to the training control parameters to finish the limb training, thereby realizing rehabilitation.
10. The brain-computer interface rehabilitation training method of claim 9,
determining a motion state index according to the limb training; and
and determining training evaluation parameters according to the plurality of mind characteristics, the motion state index or the plurality of mind characteristics and the motion state index so as to evaluate the training state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011117939.8A CN112244774A (en) | 2020-10-19 | 2020-10-19 | Brain-computer interface rehabilitation training system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011117939.8A CN112244774A (en) | 2020-10-19 | 2020-10-19 | Brain-computer interface rehabilitation training system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112244774A true CN112244774A (en) | 2021-01-22 |
Family
ID=74244712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011117939.8A Pending CN112244774A (en) | 2020-10-19 | 2020-10-19 | Brain-computer interface rehabilitation training system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112244774A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113398422A (en) * | 2021-07-19 | 2021-09-17 | 燕山大学 | Rehabilitation training system and method based on motor imagery-brain-computer interface and virtual reality |
| CN113426081A (en) * | 2021-05-28 | 2021-09-24 | 杭州国辰迈联机器人科技有限公司 | Sitting and standing training control method and sitting and standing training system based on brain-computer interface |
| CN114146309A (en) * | 2021-12-07 | 2022-03-08 | 广州穗海新峰医疗设备制造股份有限公司 | Mirror neuron rehabilitation training system and method based on dynamic adjustment |
| CN114237387A (en) * | 2021-12-01 | 2022-03-25 | 辽宁科技大学 | Brain-computer interface multi-mode rehabilitation training system |
| CN114367090A (en) * | 2021-12-15 | 2022-04-19 | 郑州大学 | Upper limb training system, method and readable storage medium |
| CN114527878A (en) * | 2022-02-24 | 2022-05-24 | 温州医科大学 | Analysis method for quantifying brain-computer interface control motivation |
| WO2022179548A1 (en) * | 2021-02-26 | 2022-09-01 | 腾讯科技（深圳）有限公司 | Electroencephalogram signal classification method and apparatus, and device, storage medium and program product |
| CN115399787A (en) * | 2022-07-29 | 2022-11-29 | 山东海天智能工程有限公司 | Brain-computer interface and AR/VR interactive technology combined rehabilitation training system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102866775A (en) * | 2012-09-04 | 2013-01-09 | 同济大学 | System and method for controlling brain computer interface (BCI) based on multimode fusion |
| CN103399639A (en) * | 2013-08-14 | 2013-11-20 | 天津医科大学 | Combined brain-computer interface method and device based on SSVEP (Steady-State Visually Evoked Potentials) and P300 |
| CN103699216A (en) * | 2013-11-18 | 2014-04-02 | 南昌大学 | Email communication system and method based on motor imagery and visual attention mixed brain-computer interface |
| CN103699217A (en) * | 2013-11-18 | 2014-04-02 | 南昌大学 | Two-dimensional cursor motion control system and method based on motor imagery and steady-state visual evoked potential |
| CN105183167A (en) * | 2015-09-16 | 2015-12-23 | 电子科技大学 | Mouse movement control method based on movement imagery and mVEP signal control |
| CN105411580A (en) * | 2015-10-27 | 2016-03-23 | 中国航天员科研训练中心 | Brain control wheelchair system based on touch and auditory evoked potential |
| CN106569604A (en) * | 2016-11-04 | 2017-04-19 | 天津大学 | Audiovisual dual-mode semantic matching and semantic mismatch co-stimulus brain-computer interface paradigm |
| CN107315478A (en) * | 2017-07-05 | 2017-11-03 | 中国人民解放军第三军医大学 | A kind of Mental imagery upper limbs intelligent rehabilitation robot system and its training method |
| CN108681391A (en) * | 2018-03-19 | 2018-10-19 | 南京邮电大学 | A kind of EEG signals dummy keyboard design method based on multi-mode |
| CN109521870A (en) * | 2018-10-15 | 2019-03-26 | 天津大学 | A kind of brain-computer interface method that the audio visual based on RSVP normal form combines |
| CN111258428A (en) * | 2020-01-20 | 2020-06-09 | 西安臻泰智能科技有限公司 | Electroencephalogram control system and method |
-
2020
- 2020-10-19 CN CN202011117939.8A patent/CN112244774A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102866775A (en) * | 2012-09-04 | 2013-01-09 | 同济大学 | System and method for controlling brain computer interface (BCI) based on multimode fusion |
| CN103399639A (en) * | 2013-08-14 | 2013-11-20 | 天津医科大学 | Combined brain-computer interface method and device based on SSVEP (Steady-State Visually Evoked Potentials) and P300 |
| CN103699216A (en) * | 2013-11-18 | 2014-04-02 | 南昌大学 | Email communication system and method based on motor imagery and visual attention mixed brain-computer interface |
| CN103699217A (en) * | 2013-11-18 | 2014-04-02 | 南昌大学 | Two-dimensional cursor motion control system and method based on motor imagery and steady-state visual evoked potential |
| CN105183167A (en) * | 2015-09-16 | 2015-12-23 | 电子科技大学 | Mouse movement control method based on movement imagery and mVEP signal control |
| CN105411580A (en) * | 2015-10-27 | 2016-03-23 | 中国航天员科研训练中心 | Brain control wheelchair system based on touch and auditory evoked potential |
| CN106569604A (en) * | 2016-11-04 | 2017-04-19 | 天津大学 | Audiovisual dual-mode semantic matching and semantic mismatch co-stimulus brain-computer interface paradigm |
| CN107315478A (en) * | 2017-07-05 | 2017-11-03 | 中国人民解放军第三军医大学 | A kind of Mental imagery upper limbs intelligent rehabilitation robot system and its training method |
| CN108681391A (en) * | 2018-03-19 | 2018-10-19 | 南京邮电大学 | A kind of EEG signals dummy keyboard design method based on multi-mode |
| CN109521870A (en) * | 2018-10-15 | 2019-03-26 | 天津大学 | A kind of brain-computer interface method that the audio visual based on RSVP normal form combines |
| CN111258428A (en) * | 2020-01-20 | 2020-06-09 | 西安臻泰智能科技有限公司 | Electroencephalogram control system and method |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022179548A1 (en) * | 2021-02-26 | 2022-09-01 | 腾讯科技（深圳）有限公司 | Electroencephalogram signal classification method and apparatus, and device, storage medium and program product |
| CN113426081A (en) * | 2021-05-28 | 2021-09-24 | 杭州国辰迈联机器人科技有限公司 | Sitting and standing training control method and sitting and standing training system based on brain-computer interface |
| CN113398422A (en) * | 2021-07-19 | 2021-09-17 | 燕山大学 | Rehabilitation training system and method based on motor imagery-brain-computer interface and virtual reality |
| CN114237387A (en) * | 2021-12-01 | 2022-03-25 | 辽宁科技大学 | Brain-computer interface multi-mode rehabilitation training system |
| CN114146309A (en) * | 2021-12-07 | 2022-03-08 | 广州穗海新峰医疗设备制造股份有限公司 | Mirror neuron rehabilitation training system and method based on dynamic adjustment |
| CN114146309B (en) * | 2021-12-07 | 2022-11-25 | 广州穗海新峰医疗设备制造股份有限公司 | Mirror neuron rehabilitation training system and method based on dynamic adjustment |
| CN114367090A (en) * | 2021-12-15 | 2022-04-19 | 郑州大学 | Upper limb training system, method and readable storage medium |
| CN114527878A (en) * | 2022-02-24 | 2022-05-24 | 温州医科大学 | Analysis method for quantifying brain-computer interface control motivation |
| CN115399787A (en) * | 2022-07-29 | 2022-11-29 | 山东海天智能工程有限公司 | Brain-computer interface and AR/VR interactive technology combined rehabilitation training system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112244774A (en) | Brain-computer interface rehabilitation training system and method | |
| Hong et al. | Hybrid brain–computer interface techniques for improved classification accuracy and increased number of commands: a review | |
| Kohli et al. | A review on Virtual Reality and Augmented Reality use-cases of Brain Computer Interface based applications for smart cities | |
| Scherer et al. | Toward self-paced brain–computer communication: navigation through virtual worlds | |
| Pfurtscheller et al. | 15 years of BCI research at Graz University of Technology: current projects | |
| Zapała et al. | The impact of different visual feedbacks in user training on motor imagery control in BCI | |
| CN109166612B (en) | Large-scale game scene rehabilitation system and method based on eye movement and electroencephalogram information | |
| CN111258428B (en) | Brain electricity control system and method | |
| Alhargan et al. | Affect recognition in an interactive gaming environment using eye tracking | |
| CN107562191A (en) | The online brain-machine interface method of fine Imaginary Movement based on composite character | |
| CN114021604A (en) | Motion imagery training system based on real-time feedback of 3D virtual reality technology | |
| Korik et al. | Decoding imagined 3D arm movement trajectories from EEG to control two virtual arms—a pilot study | |
| CN110737331B (en) | Individualized cognitive training and rehabilitation method, device and equipment based on multi-task brain-computer interface | |
| Robinson et al. | Bi-directional imagined hand movement classification using low cost EEG-based BCI | |
| US20220187913A1 (en) | Neurorehabilitation system and neurorehabilitation method | |
| CN115482907A (en) | Active rehabilitation system combining electroencephalogram and myoelectricity and rehabilitation training method | |
| CN112987917B (en) | Motion imagery enhancement method, device, electronic equipment and storage medium | |
| CN113713333B (en) | Dynamic virtual induction method and system for lower limb rehabilitation full training process | |
| Hasan et al. | Preliminary study on real-time prediction of gait acceleration intention from volition-associated EEG patterns | |
| KR20230093103A (en) | Apparatus for controlling customized driving based on brain wave and method thereof | |
| Mustafa et al. | A brain-computer interface augmented reality framework with auto-adaptive ssvep recognition | |
| RU2654767C1 (en) | Method for rehabilitation of patients using virtual environment | |
| Khan et al. | EEG-based BCI systems for neurorehabilitation applications | |
| Costa et al. | Studying cognitive attention mechanisms during walking from EEG signals | |
| Henshaw | Improved brain-computer interface methods with application to gaming |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |