CN114305450A - Method for recognizing lower limb multi-joint motor imagery - Google Patents
Method for recognizing lower limb multi-joint motor imagery Download PDFInfo
- Publication number
- CN114305450A CN114305450A CN202210018280.3A CN202210018280A CN114305450A CN 114305450 A CN114305450 A CN 114305450A CN 202210018280 A CN202210018280 A CN 202210018280A CN 114305450 A CN114305450 A CN 114305450A
- Authority
- CN
- China
- Prior art keywords
- motor imagery
- identifying
- joint
- patient
- limb
- 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.)
- Granted
Links
Images
Landscapes
- Rehabilitation Tools (AREA)
Abstract
The invention belongs to the technical field of motor imagery, and particularly relates to a method for identifying multi-joint motor imagery of lower limbs, which comprises the following steps of collecting electroencephalogram signals when a patient does motor imagery on a certain limb joint, and carrying out signal preprocessing, feature extraction and classification identification; step two, decoding the currently imagined action of the patient; and step three, controlling the affected limb to do passive motion by driving the stimulator to form a closed loop as feedback, and repeatedly training. The invention can identify the multi-joint motor imagery of the lower limbs, enables a patient to more finely control the imagination action of the lower limbs in the rehabilitation training process, and is beneficial to improving the rehabilitation treatment effect.
Description
Technical Field
The invention belongs to the technical field of motor imagery, and particularly relates to a method for identifying multi-joint motor imagery of lower limbs.
Background
Motor imagery is one of important paradigms of BCI, psychology exercise of motor behaviors is performed without obvious motion output, the motor intention of a user can be directly mapped, and the BCI has unique advantages on rehabilitation training of patients who cannot perform autonomous movement. Based on the MI-BCI, the control can be realized in a natural and intuitive command mode, an information channel which directly uses a brain control peripheral is provided for patients with intact brains but seriously impaired limb movement functions, the patient can be repaired to the damaged motor nerves to a certain extent while the limb movement functions of the patient are improved in rehabilitation training, and the research is widely carried out.
The existing research shows that motor imagery can enable a patient with cerebral apoplexy to enhance and activate certain specific motor function areas in the brain, so as to achieve the effect of recovering motor ability, and has important significance for the rehabilitation of the patient with apoplexy or other patients with neurological dysfunction. Motor imagery has similar cognitive processes as motor performance. During motor imagery, the brain activates or inhibits specific nerve cells, resulting in a phenomenon of reduced amplitude or reduced energy of signals in partial frequency bands of electroencephalogram signals, which is called event-related desynchronization (ERD). In contrast, the phenomenon of the brain that the amplitude of the signal increases or the energy of the signal rises in the resting state is the event-related synchronization phenomenon. The ERD induced by the neural activity of different imaginary movements differs in location and energy, and by detecting this ERD characteristic difference, a specific imaginary movement pattern can be identified.
At present, motor imagery brain-computer interfaces mainly rely on spatial distribution characteristics of ERD/ERS to distinguish different motor imagery tasks, such as motor imagery based on left and right hands, because upper limbs (such as arms, fingers and the like) needing fine control are mapped to the outer surface of cerebral cortex and occupy a larger area of motor cortex, cerebral motor sensory cortical areas corresponding to the left and right hands are respectively distributed on the right and left sides of the brain, and obvious contralateral phenomena can occur when the motor imagery of the hands is performed. The classification accuracy of such brain-computer interface systems is relatively high. For patients with lower limb movement disorder, especially lower limb paralysis, MI-BCI can be used for motor imagery assisted training to reshape nerve pathways, and the brain directly controls an external mechanism to pull corresponding parts of the lower limbs to move, so that great convenience is brought to the patients, and the rehabilitation training effect of guiding limb movement by active movement consciousness is considered to be better than that of completely passive traction training in rehabilitation medicine. Therefore, for the patient population, the lower limb MI-BCI has great application value and practicability. Research shows that the ERD phenomenon also occurs when the motor imagery of the lower limb part is performed, so theoretically, the MI-BCI system can decode the motor intention of the lower limb according to the difference of the ERD characteristics, drive the execution structure to pull the corresponding part to perform the imagined action, and finish the active control of the brain to the lower affected limb, so that the better nerve induction effect is achieved, and the better rehabilitation treatment effect is brought.
However, the ERD phenomenon in which energy decline occurs induced by lower limb motor imagery is mainly concentrated in the center of cerebral cortex, which is different from the contralateral ERD phenomenon in hand motor imagery, and the left and right lower limbs correspond to the same projection area in cerebral cortex, so that the lower limb is more difficult to classify than the upper limb, and furthermore, according to the experimental phenomenon studied in the prior art, the electroencephalogram topographic distribution of the unilateral left and right foot motor imagery on the scalp does not show a difference, which means that ERS/ERD does not distinguish the EEG characteristics of the movement of the left and right feet. In the left and right ankle motor imagery, ERD phenomena are observed in almost the same position near the apex, which indicates that ERD characteristics of two motor imagery tasks (left and right feet) do not provide discrimination information, and thus the lower limb MI-BCI system using energy and distribution differences of ERD for motor-conscious decoding has not been effective for a long time. Therefore, there is a need for further improvement and design in the experimental paradigm.
The main joints of the lower limbs comprise ankles, knees, crotch and the like, when a human body normally walks, the normal walking can be completed by the mutual matching of multiple joints instead of simply relying on the movement of one joint, and common actions such as turning the ankles to drive the whole supporting legs to lift up and put down and turning the knee joints to drive the crus and the following parts to extend forwards. Although the lower limb MI-BCI system only provided with the left instruction and the right instruction can be used for dragging the left lower limb and the right lower limb to walk according to the brain active movement consciousness, particularly on one limb, the joint movement controlled in the mode is not subjectively issued by the brain, but passively issued by a machine and fixed movement. The reason is that the MI-BCI system only recognizes the directional motion consciousness of the patient wanting to move leftwards or rightwards, but does not recognize the motion consciousness of a specific single joint, in the form of words, the system can only drag the lower limb motion in a fixed motion mode, such as the left leg to move forwards, but cannot rely on the motion of a specific joint, such as the sole lifting or the leg stretching forwards, which is recognized by the multi-joint motion consciousness of the lower limb, which is intensely dragged by the patient. The MI-BCI containing the multi-joint motor imagery obviously improves the use value, enables a patient to have greater subjective participation sense in the rehabilitation training process, and enables the patient to more actively mobilize the nerve thinking imagery to specifically realize the complex actions of the joints, so that the MI-BCI has great help for reconstructing the nerve path from the brain to the joints. However, in order to realize the fine control of the lower limb movement, the expansion needs to be carried out on the basis of the original left and right control commands, taking the right lower limb as an example, the invention increases the imagination tasks of the limb at the same side at two parts of an ankle joint and a knee joint, namely the imagination of lifting the sole through the rotation of the ankle joint and the imagination of extending the shank through the rotation of the knee joint, so that the invention has four imagination actions on the limbs at both sides, namely the traditional instruction set of the MI-BCI of the left and right lower limbs is expanded by one time, and the fineness of the imagination actions is greatly enriched.
Brain Computer Interface (BCI) technology is to directly acquire Brain signals, convert the abstracted Brain signals into signals capable of operating an execution mechanism or being recognized by other machines through corresponding signal processing, feature extraction and pattern recognition methods, and recognize and predict consciousness activities of the Brain through the recognizable information. Motor Imagery (MI) is a mental activity in which the brain only imagines the execution of a limb action without the limb producing a significant actual action. The motor intention of a user can be decoded by a brain-computer interface (MI-BCI) technology based on motor imagery, the same imagination action is repeated in the brain for many times, and the function recovery of the damaged brain area of a stroke patient is realized by utilizing the plasticity of a human nerve channel, so that the life style of the stroke patient is assisted or improved. In a gait rehabilitation research control system, the recognition and classification of lower limb actions play an important role. Although the time resolution of the brain electrical signals is high, the spatial resolution is low, and the adverse factor limits the performance of the MI-BCI system of the lower limbs.
Disclosure of Invention
The invention aims to: aiming at the defects of the prior art, the method for identifying the lower limb multi-joint motor imagery is provided, the lower limb multi-joint motor imagery can be identified, a patient can control the imagination action of the lower limb more finely in the rehabilitation training process, and the rehabilitation treatment effect is improved.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for identifying multi-joint motor imagery of lower limbs comprises the steps of firstly, collecting electroencephalogram signals when a patient does motor imagery on a certain limb joint, and carrying out signal preprocessing, feature extraction and classification identification; step two, decoding the currently imagined action of the patient; and step three, controlling the affected limb to do passive motion by driving the stimulator to form a closed loop as feedback, and repeatedly training.
Preferably, the motor imagery of the left and right lower limbs is identified laterally and different joints of the ipsilateral limb are identified.
Preferably, in the MI-SSSEP hybrid paradigm, the corresponding task is performed while receiving electrical stimulation of a predetermined frequency at bilateral medial ankle posterior tibial nerves to induce SSSEP.
Preferably, the motor imagery includes a right ankle, a left ankle, a right knee, and a left knee.
Preferably, in the first step, the intensity of the electrical stimulation and the position of the electrode paste are adjusted, and the electrical stimulation is applied by two self-adhesive circular physiotherapy electrodes by adopting a biphasic pulse current with the pulse width of 200 mus.
Preferably, in the first step, the feature extraction and classification and identification includes:
effective electroencephalogram signal characteristics are extracted by adopting a common space mode algorithm, and mode recognition is carried out through a support vector machine.
Preferably, the method comprises the following steps: and intercepting 4s data in the task execution period, performing band-pass filtering on 8-13Hz, 13-27Hz, 27-29Hz and 32-34Hz, calculating a CSP projection matrix for the EEG component of each frequency band, and respectively extracting the spatial features of each EEG component.
The invention has the advantages that the invention identifies the lower limb multi-joint motor imagery based on the BCI system of the MI-SSSEP mixed normal form, namely, the SSSEP characteristic of MI modulation is generated by introducing the MI-SSSEP normal form, the action instruction set of the traditional lower limb MI-BCI system is expanded, and the system simultaneously identifies different joints on both sides and on the same side, so as to further improve the fineness of the system in the aspect of motor consciousness decoding, more mobilize the activity of a patient, enable the patient to participate in the action training more actively and form a more accurate nerve feedback loop. Compared with the ERD characteristic, the SSSEP characteristic in the mixed mode has better task separability, and the characteristic enables the MI-SSSEP mixed mode to be adopted to effectively identify the imaginary action of multiple joints of the lower limb, and improves the performance and application value of the MI-BCI system.
Drawings
Features, advantages and technical effects of exemplary embodiments of the present invention will be described below with reference to the accompanying drawings.
FIG. 1 is a schematic structural diagram of the present invention.
Fig. 2 is a schematic view of the movement of the lower limb joint of the present invention.
Fig. 3 is a schematic diagram of the electrical stimulation operation of the present invention.
FIG. 4 is a flow chart of the algorithm of the present invention.
Detailed Description
As used in the specification and in the claims, certain terms are used to refer to particular components. As one skilled in the art will appreciate, manufacturers may refer to a component by different names. This specification and claims do not intend to distinguish between components that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. "substantially" means within an acceptable error range, and a person skilled in the art can solve the technical problem within a certain error range to substantially achieve the technical effect.
Furthermore, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The present invention will be described in further detail with reference to fig. 1 to 4, but the present invention is not limited thereto.
The method for identifying the multi-joint motor imagery of the lower limbs comprises the steps of firstly, collecting electroencephalogram signals when a patient does motor imagery on a certain limb joint, and carrying out signal preprocessing, feature extraction and classification identification; step two, decoding the currently imagined action of the patient; and step three, controlling the affected limb to do passive motion by driving the stimulator to form a closed loop as feedback, and repeatedly training.
It should be noted that: referring to fig. 1, when the MI-BCI system operates, a patient makes motor imagery on a certain limb joint, the system simultaneously acquires electroencephalogram signals, the system decodes the current imaginal motion of the patient through signal preprocessing, feature extraction and classification recognition, and drives external devices such as a stimulator and the like to control the affected limb to make passive motion to serve as feedback to form a closed loop, and the training is repeated in such a way, so that the rehabilitation effect is achieved.
In the method for recognizing a multi-joint motor imagery of lower limbs according to the present invention, motor imagery of left and right lower limbs is laterally recognized, and different joints of the ipsilateral limb are recognized.
In the method for identifying multi-joint motor imagery of lower limbs according to the present invention, in the MI-SSSEP hybrid paradigm, the corresponding task is performed while electrical stimulation of a preset frequency is applied to bilateral medial ankle posterior tibial nerves to induce SSSEP.
In the method of identifying a lower limb multi-joint motor imagery according to the invention, the motor imagery includes a right ankle, a left ankle, a right knee and a left knee.
In the method for identifying the multi-joint motor imagery of the lower limbs, the first step further comprises adjusting the intensity of the electrical stimulation and the position of the electrode patch, wherein the electrical stimulation applies stimulation through two self-adhesive circular physiotherapy electrodes by adopting a biphasic pulse current with the pulse width of 200 mu s. Specifically, the left ankle stimulation frequency was 28Hz and the right ankle stimulation frequency was 33Hz, and the stimulation intensity was adjusted until the thumb of the subject tremors or contracts slightly to produce a stable and clearly visible SSSEP. The stimulation intensity of each test subject was determined according to the condition of each test subject.
During the experiment, the person is tried to sit on a seat which is about 1m away from the screen, the comfortable state is kept, and the body is prevented from moving greatly as far as possible. The experimental protocol for a single round, which contained 4 stages in total, was 10s in duration. The first stage is a preparation period, a white circle appears in the center of a screen, and the beginning of the test round experiment is reminded for 2s continuously, and the self state needs to be adjusted; then the task turns red and lights up to remind the person to be tried that the task is about to start, and meanwhile, the electric stimulator is started at the moment and lasts for 2 seconds; then, a motor imagery task period lasts for 4s, and the person to be tested executes corresponding imagery actions according to the prompt, if the prompt is 'right ankle imagery', the person to be tested tries to rotate the right ankle upwards to lift the sole, and the action is shown in fig. 2; if the right knee imagination is prompted, the user tries to rotate the right knee joint to extend the lower leg forwards; if the suggestion is 'left ankle imagination', the user tries to rotate the left ankle upwards to lift the sole; if the prompt is 'left knee imagination', the user tries to rotate the left knee joint to extend the lower leg forwards; finally, the rest period lasts for 2s, and the test can be slightly adjusted to prepare the next experiment. In each round, the red circle lights up while the subject is being administered an electrical stimulus that reaches a maximum over 0.5s and ends at 8s, as shown in fig. 3. The whole experiment is completed in a quiet and non-interfering environment.
The whole experiment is divided into 6 groups, 4 groups are offline experiments, 2 groups are online experiments, each group comprises 10 samples of four types of tasks, the total number of the samples is 40, the offline experiments are firstly carried out, the online experiments are carried out after 4 groups are finished, and the electroencephalogram offline data of the first 4 groups are used for establishing an identification model to decode the category of each test in the online experiments.
In the experiment, a 64-lead electroencephalogram acquisition system developed by Neuroscan company is adopted, 60-lead 0.5-100Hz electroencephalogram signals are acquired through a silver/silver chloride alloy electrode cap, and CB1, CB2, HEO and VEO leads are removed. The sampling frequency is 1000Hz, and 50Hz power frequency interference is filtered. The lead distribution of the electrode cap is according to the international standard 10/20 electrode system. Wherein the reference electrode is attached to the tip of the nose and the ground electrode is attached to the forehead. In the pre-processing, the raw data is spatially filtered using a co-average reference and the signal is down-sampled to 200 Hz.
And analyzing time-frequency domain characteristics of the EEG signals by adopting an event-related spectrum disturbance method, and analyzing an ERD/SSSEP mode under different imagination tasks. The definition formula of ERSP is as follows:
wherein n represents the number of experimental runs, Fk(f, t) refers to the spectral estimation at frequency f at time t of the k-th experiment. And (3) adopting short-time Fourier transform when ERSP is calculated, setting the tuning window width to be 256 sampling points, and subtracting the frequency spectrum average value in 2s before a task from the original data so as to remove the baseline. For each imagination task, the ERSP characteristics of the CZ leads were mainly analyzed.
In the method for identifying the multi-joint motor imagery of the lower limbs, the step one includes the following steps: effective electroencephalogram signal characteristics are extracted by adopting a common space mode algorithm, and mode recognition is carried out through a support vector machine.
In the method of identifying a lower limb multi-joint motor imagery according to the invention, comprising: and intercepting 4s data in the task execution period, performing band-pass filtering on 8-13Hz, 13-27Hz, 27-29Hz and 32-34Hz, calculating a CSP projection matrix for the EEG component of each frequency band, and respectively extracting the spatial features of each EEG component.
Referring to fig. 3, first, the original signal is preprocessed to obtain X, task period data of each sample is selected, and bandpass filtering is performed on corresponding characteristic frequency bands to obtain XiWherein, i is 1,2, 3 and 4 respectively corresponding to the frequency bands of 8-13Hz, 13-27Hz, 27-29Hz and 32-34 Hz. For each band, the training set X is dividedtrain_iAnd test set Xtest_iConstructing a CSP filter based on the training set sample to obtain a projection matrix Wi. From WiAfter spatial filtering, obtaining
Wherein Zip(p ═ 1,2, …,2m) is the filtered signal ZiAnd if the vectors of the middle-front m rows and the rear m rows are obtained, the feature calculation formula of a single trial is as follows:
taking m as 2, obtaining a feature vector f with the dimension of 1 x 4train_iThen f istrain＝[ftrain1,ftrain2,ftrain3,ftrain_4]The combination of the four frequency band features is a feature vector of 1 × 16. Test set characteristics ftestAnd the extraction process is similar, and the prediction result is obtained by sending the prediction result into a classifier constructed by the characteristics of the training set.
When the classifier is constructed, the trial times of imagining the lower limbs on the same side are classified into one class, if the right ankle and the right knee are classified into one class of the right lower limb, and the left ankle and the left knee are classified into one class of the left lower limb, and the two classes are used as a training set to construct the left/right classifier. And then, constructing an ipsilateral limb classifier by taking the ankle and knee tasks of the ipsilateral limb as two training sets, for example, constructing a right ankle/right knee classifier by using right ankle and right knee training set samples, and constructing a left ankle/left knee classifier by using left ankle and left knee training set samples. When the test set is identified, the left/right classifier is used for judging which side of the limb is imagined in the test, and the ipsilateral limb classifier is used for further judging whether the ankle joint or the knee joint is imagined. And counting the number of correct identification tests, wherein the proportion of the number of correct identification tests to the number of the test lumped samples is called the identification accuracy of the tested system in the experiment.
Variations and modifications to the above-described embodiments may also occur to those skilled in the art, which fall within the scope of the invention as disclosed and taught herein. Therefore, the present invention is not limited to the above-mentioned embodiments, and any obvious improvement, replacement or modification made by those skilled in the art based on the present invention is within the protection scope of the present invention. Furthermore, although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.
Claims (7)
1. A method of identifying a multi-joint motor imagery of a lower extremity, comprising:
firstly, acquiring an electroencephalogram signal when a patient performs motor imagery on a certain limb joint, and performing signal preprocessing, feature extraction and classification identification;
step two, decoding the currently imagined action of the patient;
and step three, controlling the affected limb to do passive motion by driving the stimulator to form a closed loop as feedback, and repeatedly training.
2. The method of identifying a lower extremity multi-articular motor imagery according to claim 1, further comprising: and laterally identifying the motor imagery of the left and right lower limbs, and identifying different joints of the limbs on the same side.
3. The method of identifying a lower extremity multi-articular motor imagery according to claim 1, further comprising: in the MI-SSSEP hybrid paradigm, the bilateral medial ankle posterior tibial nerves receive electrical stimulation at a predetermined frequency while performing the corresponding task to induce SSSEP.
4. A method for identifying a lower extremity multi-joint motor imagery according to claim 1, wherein: the motor imagery includes a right ankle, a left ankle, a right knee, and a left knee.
5. A method for identifying a lower extremity multi-joint motor imagery according to claim 1, wherein: in the first step, the intensity of electrical stimulation and the position of an electrode paste are adjusted, and the electrical stimulation is applied by two self-adhesive circular physiotherapy electrodes by adopting a two-phase pulse current with the pulse width of 200 mu s.
6. The method for recognizing multi-joint motor imagery of lower limbs according to claim 1, wherein in the first step, the feature extraction and classification recognition comprises:
effective electroencephalogram signal characteristics are extracted by adopting a common space mode algorithm, and mode recognition is carried out through a support vector machine.
7. The method of identifying a lower extremity multi-articular motor imagery according to claim 6, comprising: and intercepting 4s data in the task execution period, performing band-pass filtering on 8-13Hz, 13-27Hz, 27-29Hz and 32-34Hz, calculating a CSP projection matrix for the EEG component of each frequency band, and respectively extracting the spatial features of each EEG component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210018280.3A CN114305450B (en) | 2022-01-07 | 2022-01-07 | Method for identifying lower limb multi-joint motor imagery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210018280.3A CN114305450B (en) | 2022-01-07 | 2022-01-07 | Method for identifying lower limb multi-joint motor imagery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114305450A true CN114305450A (en) | 2022-04-12 |
| CN114305450B CN114305450B (en) | 2023-09-19 |
Family
ID=81024733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210018280.3A Active CN114305450B (en) | 2022-01-07 | 2022-01-07 | Method for identifying lower limb multi-joint motor imagery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114305450B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101607893B1 (en) * | 2014-12-15 | 2016-04-11 | 고려대학교 산학협력단 | Apparatus for generating sssep and operating method thereof |
| CN106362287A (en) * | 2016-10-24 | 2017-02-01 | 天津大学 | Novel MI-SSSEP mixed brain-computer interface method and system thereof |
| CN106502404A (en) * | 2016-10-24 | 2017-03-15 | 天津大学 | A kind of new brain-machine interface method and system based on stable state somatosensory evoked potential |
| CN111544882A (en) * | 2020-04-30 | 2020-08-18 | 天津大学 | Novel cerebral stroke lower limb active rehabilitation system based on brain-computer interface and application |
| CN112137616A (en) * | 2020-09-22 | 2020-12-29 | 天津大学 | Consciousness detection device for multi-sense brain-body combined stimulation |
| CN112617863A (en) * | 2020-12-30 | 2021-04-09 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Hybrid online computer-computer interface method for identifying lateral direction of left and right foot movement intention |
| KR20210129437A (en) * | 2020-04-20 | 2021-10-28 | 한국과학기술연구원 | System and method for controlling exoskeleton robot using brain waves according to motion imagination |
| CN113807402A (en) * | 2021-08-23 | 2021-12-17 | 天津大学 | System for inhibiting MIs-triggering of MI-BCI system and training and testing method thereof |
-
2022
- 2022-01-07 CN CN202210018280.3A patent/CN114305450B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101607893B1 (en) * | 2014-12-15 | 2016-04-11 | 고려대학교 산학협력단 | Apparatus for generating sssep and operating method thereof |
| CN106362287A (en) * | 2016-10-24 | 2017-02-01 | 天津大学 | Novel MI-SSSEP mixed brain-computer interface method and system thereof |
| CN106502404A (en) * | 2016-10-24 | 2017-03-15 | 天津大学 | A kind of new brain-machine interface method and system based on stable state somatosensory evoked potential |
| KR20210129437A (en) * | 2020-04-20 | 2021-10-28 | 한국과학기술연구원 | System and method for controlling exoskeleton robot using brain waves according to motion imagination |
| CN111544882A (en) * | 2020-04-30 | 2020-08-18 | 天津大学 | Novel cerebral stroke lower limb active rehabilitation system based on brain-computer interface and application |
| CN112137616A (en) * | 2020-09-22 | 2020-12-29 | 天津大学 | Consciousness detection device for multi-sense brain-body combined stimulation |
| CN112617863A (en) * | 2020-12-30 | 2021-04-09 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Hybrid online computer-computer interface method for identifying lateral direction of left and right foot movement intention |
| CN113807402A (en) * | 2021-08-23 | 2021-12-17 | 天津大学 | System for inhibiting MIs-triggering of MI-BCI system and training and testing method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 张力新，常美榕，王仲朋，陈龙，明东: "SSSEP提升下肢MI-BCI系统性能及其多维脑电特征分析", 中国生物医学工程学报, vol. 40, no. 4, pages 429 - 437 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114305450B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gordleeva et al. | Real-time EEG–EMG human–machine interface-based control system for a lower-limb exoskeleton | |
| CN107315478B (en) | A kind of Mental imagery upper limb intelligent rehabilitation robot system and its training method | |
| Tortora et al. | Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network | |
| Rak et al. | Brain-computer interface as measurement and control system the review paper | |
| Gordleeva et al. | Exoskeleton control system based on motor-imaginary brain–computer interface | |
| CN104951082B (en) | A kind of brain-machine interface method for strengthening EEG signals using accidental resonance | |
| CN112617863B (en) | Hybrid online computer-computer interface method for identifying lateral direction of left and right foot movement intention | |
| CN110993056A (en) | Hybrid active rehabilitation method and device based on mirror image neurons and brain-computer interface | |
| 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 | |
| Tecchio et al. | Functional source separation and hand cortical representation for a brain–computer interface feature extraction | |
| US20220187913A1 (en) | Neurorehabilitation system and neurorehabilitation method | |
| Jochumsen et al. | Detection and classification of single-trial movement-related cortical potentials associated with functional lower limb movements | |
| Li et al. | Preliminary study of online real-time control system for lower extremity exoskeletons based on EEG and sEMG fusion | |
| Liu et al. | An EEG-based brain-computer interface for gait training | |
| CN114259651A (en) | Active real-time closed-loop electrical stimulation system for Parkinson's disease | |
| Liu et al. | Detection of lower-limb movement intention from EEG signals | |
| CN114305450B (en) | Method for identifying lower limb multi-joint motor imagery | |
| CN113807402A (en) | System for inhibiting MIs-triggering of MI-BCI system and training and testing method thereof | |
| CN100536958C (en) | Paralytic patient auxiliary nervous pathway restoring system | |
| CN114191260B (en) | Highly integrated brain-controlled nerve electric stimulation exoskeleton robot system and control method | |
| Lisi et al. | Noninvasive brain machine interfaces for assistive and rehabilitation robotics: a review | |
| CN115474948A (en) | Brain-computer interface method and system for enhancing lower limb motor imagery based on motion illusion | |
| Omedes et al. | Hierarchical decoding of grasping commands from EEG | |
| Ma et al. | A new EEG-based paradigm for classifying intention of compound-limbs movement |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |