CN104000586B - Patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene - Google Patents

Patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene Download PDF

Info

Publication number
CN104000586B
CN104000586B CN201410197868.5A CN201410197868A CN104000586B CN 104000586 B CN104000586 B CN 104000586B CN 201410197868 A CN201410197868 A CN 201410197868A CN 104000586 B CN104000586 B CN 104000586B
Authority
CN
China
Prior art keywords
mrow
msub
rehabilitation training
index
electromyographic signal
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.)
Active
Application number
CN201410197868.5A
Other languages
Chinese (zh)
Other versions
CN104000586A (en
Inventor
谢平
魏秀利
杜义浩
陈晓玲
宋妍
吴晓光
陈迎亚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yanshan University
Original Assignee
Yanshan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yanshan University filed Critical Yanshan University
Priority to CN201410197868.5A priority Critical patent/CN104000586B/en
Publication of CN104000586A publication Critical patent/CN104000586A/en
Application granted granted Critical
Publication of CN104000586B publication Critical patent/CN104000586B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

A kind of patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene, the control of virtual rehabilitation scene is realized by electromyographic signal, and combine the adaptive adjustment rehabilitation training intensity of brain myoelectricity fatigue index.The design of virtual rehabilitation scene is completed in the needs of syncerebrum apoplexy patient rehabilitation training and the suggestion of physiatrician, and proposes brainfag index, realizes the quantitative assessment of brain area fatigue；The motion intention that arm different motion pattern lower surface electromyographic signal feature obtains patient is extracted, realizes the control of virtual rehabilitation scene；Muscular fatigue, the fatigue state of brainfag index comprehensive characteristics acquisition rehabilitation are extracted, adaptive regulation rehabilitation training scene is realized, slows down or strengthen rehabilitation training intensity, avoid the secondary damage caused by improper training.The present invention has the advantages that high safety, intelligent height, training science, is not easy injury.

Description

Patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene
Technical field
The present invention relates to rehabilitation medicine equipment technical field, especially a kind of rehabilitation training system for patients with cerebral apoplexy And method.
Background technology
Cerebral apoplexy is well known apoplexy, and it has incidence of disease height, death rate height, disability rate height, recurrence rate height etc. Feature, so medical field is listed as its same coronary heart disease, cancer to threaten one of three big diseases of human health.Clinical research table Bright, by timely, positive rehabilitation training, most of paralytic can recover simple limb motion ability, even fully recover.Pass The stroke at convalescence treatment method of system is for theoretical foundation, mainly by physiatrician's hand with reflection or graded movement control Dynamic auxiliary Rehabilitation is trained, but the time of rehabilitation training and the course for the treatment of can not be protected, so as to influence rehabilitation efficacy.
With the continuous development of robot technology, the training of robot assisted motor function is arisen at the historic moment, and applied to brain soldier Middle patient's late rehabilitation training.Robot can control and quantify training strength, be objectively measured and move in the training process Learn the change with strength, there is provided patients with cerebral apoplexy repeatability, task orientation and the treatment of interactive mode.Gerdienk et al. recognizes Conventional exercises method is better than to the improvement of motion control for robot assisted technology, can effectively improve convalescence brain soldier Middle limbs of patient motion control and functional level.However, during current patients with cerebral apoplexy application healing robot auxiliary rehabilitation exercise, Receive passive treatment mostly, the motion intention of patient is seldom embodied in rehabilitation course, patient is participated in rehabilitation training Enthusiasm has been short of with initiative.
In recent years, domestic and international scientific research institution's Combining with technology of virtual reality realizes new treatment method --- area of computer aided Motor function training, and applied to patients with cerebral apoplexy late rehabilitation train, such as：EBRSR (Evidence- in 2008 Based Review of Stroke Rehabilitation) guide recommends in cerebral apoplexy using virtual reality technology to improve Patient motion function, recommendation intensity are A.Computer assisted motor function training, is to make patient notice collection by game In motion result rather than motion itself, the interest of rehabilitation can be strengthened to a certain extent.But above-mentioned calculating Machine auxiliary training system can only aid in patient to complete relatively simple rehabilitation training, be still difficult to transfer patient and be actively engaged in realizing And self-confidence.Simultaneously because being short of the Evaluation Strategy to patient physiological condition, fatigue is produced during Rehabilitation, is easy to occur Surprisingly cause second hurt, and then limit the clinical application of virtual reality technology.
The content of the invention
For mentioning deficiency of the current patients with cerebral apoplexy in rehabilitation training in above-mentioned technology, present invention aims at offer One kind is trained using virtual scene, understands patient fatigue's degree in the training process and can increase training interest and safety The patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene of property.
To achieve the above object, following technical scheme is employed：System of the present invention includes signal acquisition part, data Preprocessing part, motion index extraction part, sports fatigue index extraction part, virtual scene design part and rehabilitation training Experimental section；Wherein,
The EEG signals and electromyographic signal of patient are extracted described signal acquisition part；
Described data prediction part is filtered processing to the EEG signals and electromyographic signal that collect；
Described motion index extraction part is the analysis extraction of discharge capacity when being acted to patient muscle；
Described sports fatigue index extraction part is to carry out analysis extraction respectively to patient's EEG signals and electromyographic signal, And then judge sports fatigue or brainfag；
Described virtual scene design part is to be counted under computer environment based on Visual C#2010 exploitation designs Virtual scene and display output are generated on calculation machine, establishes man-machine interaction feedback mechanism；
Described rehabilitation training experimental section be patient according to rehabilitation training requirement in virtual scene, bent, stretched by arm Virtual palm completion appointed task in control virtual scene is waved with left and right.
In the signal acquisition part, the collection of electromyographic signal uses the differential input of bikini, and two of which is myoelectricity Differential input end, another is reference ground, and Differential Input electrode is placed at belly of muscle along muscle fibre direction；EEG signals Collection is acquired using 8 passage brain myoelectricity synchronous acquisition instrument, and 10~20 electrodes of adopting international standards place standard, pass through electrode Electrode is connected by cap with scalp, and using single-stage lead method, reference electrode lead is connected respectively to after the ear of left and right at mastoid process, ground connection electricity Pole arrangement is hit exactly overhead.
The data prediction part, distinguished using adaptive high-pass filter and adaptive 50Hz notch filters wave filter Processing is filtered to EEG signals, electromyographic signal, removes the baseline drift in signal and Hz noise；Reuse Butterworth Three rank band logical FIR filters are handled EEG signals, electromyographic signal, according to effective frequency range feature of signal, choose myoelectricity The cut-off frequency of signal is 2Hz~200Hz, and the cut-off frequency for choosing EEG signals is 2Hz~50Hz.
The motion index extracts part, and electromyographic signal motion index is as follows,
In formula, iEMG is integration myoelectricity value, the quantity of moving cell and putting for each moving cell when reflecting muscle movement TV university is small；T is the time of collection electromyographic signal；T is the cycle for the electromyographic signal that analysis collects；EMG (t) gathers for t The electromyographic signal for the respective muscle motion arrived.
The sports fatigue index extraction part includes electromyographic signal fatigue index and brainfag index；
(1) electromyographic signal fatigue index such as following formula,
In formula, MPF is frequency of average power, is the frequency of power spectrum curve position of centre of gravity, to the frequency spectrum of underload motion Change has compared with hypersensitivity；F is the frequency of electromyographic signal；P (f) is power spectrum function；
(2) brainfag index
Based on wavelet packet decomposition algorithm, converted using Binary Scale, EEG signals f (t) is decomposed into 4 layers, obtains brain Electric signal low frequency sub-band, by wavelet package reconstruction, it is the frequency band rhythm and pace of moving things where 4~8Hz to obtain slow wave, obtain fast wave be 12~ The frequency band rhythm and pace of moving things where 32Hz, wherein slow wave are θ ripples, and fast wave is β ripples, further tries to achieve the energy ratio of θ ripples and β ripples；
Comprise the following steps that：
1. WAVELET PACKET DECOMPOSITION
In formula, i=0,1,2 ..., 2j- 1, fj,i(ti) it is reconstruct brain electricity of the WAVELET PACKET DECOMPOSITION on jth node layer (j, i) Signal；
2. by Parseval theorems and 1. middle wavelet packet decomposition computation formula, EEG signals f (t) wavelet packets point can be calculated The energy spectrum of solution is：
In formula, Ej,i(ti) for the frequency band energy in EEG signals f (t) WAVELET PACKET DECOMPOSITIONs to node (j, i)；xi,π(i=0, 2,…,2j-1；π=1,2 ..., n) it is reconstruct EEG signals fj,i(ti) discrete point amplitude；N counts for signal sampling；
3. ask for brainfag index：
Table 1
According to table 1, wavelet packet subband (4,1) is reconstructed, obtains 4~8Hz rhythm and pace of moving things, as θ ripples, it is E to define its energyθ, Then byUnderstand：
Similarly, wavelet packet subband (4,3), (4,4), (4,5), (4,6), (4,7) are reconstructed, obtain 12~32Hz rhythm and pace of moving things, As β ripples, it is E to define its energyβ, equally byUnderstand：
It is F to define brainfag indexθ/β,
By the brainfag index F for analyzing certain patients with cerebral apoplexy convalescence C3 passageθ/βWith the change feelings of rehabilitation training time Condition, it is known that with the increase of run duration, Fθ/βAscendant trend is presented, this changes with adult from normal condition to fatigue state During, the slow wave (θ ripples) of EEG signals gradually increases, and it is consistent that fast wave (β ripples), which gradually decreases,.Therefore, by Fθ/βFor The quantitative assessment of brainfag state, realize the difficulty or ease adjustment of rehabilitation training scene.
The virtual scene design part, under computer environment, virtual scene is designed based on Visual C#2010； Control button is provided with virtual scene display window in computer, the control button includes START button, " rehabilitation is instructed White silk " button, " physical signs " button, " preservation " button, the Close button；START button is brain myoelectricity synchronous acquisition button； " rehabilitation training " button is rehabilitation training start button；" physical signs " button is myoelectricity motion index iEMG, electromyographic signal is tired Labor index MPF and brainfag index Fθ/βReal-time display button；" preservation " button is myoelectricity motion index iEMG, electromyographic signal Fatigue index MPF and brainfag index Fθ/βSave button；The Close button is rehabilitation training conclusion button；Virtual scene Rehabilitation training scene is the task platform of rehabilitation training.
The rehabilitation training experimental section, patient pass through hand according to the requirement of rehabilitation training scene in virtual scene design Brachiocylloosis, stretching, extension and left and right wave to control virtual palm in rehabilitation training scene to complete appointed task.
Present invention also offers a kind of patients with cerebral apoplexy recovery training method based on brain myoelectricity and virtual scene, the side Method gathers the EEG signals of patient and electromyographic signal and carries out signal transacting first, using electromyographic signal motion index as feature Vector is used for the motion intention for identifying patient, and electromyographic signal motion index iEMG is sent into the SVMs trained before In SVM-1, bending, stretching, extension and the left and right action waved of rehabilitation arm are identified, rehabilitation training is driven according to recognition result Virtual palm inside scene, it is dragged corresponding article (all kinds of fruit under virtual environment) and reach specified location (virtually Fruits basket under environment), complete the rehabilitation training project specified.
In rehabilitation training, MPF and F is consideredθ/βPatient motion muscular fatigue degree and motion brain can be reflected respectively Area's degree of fatigue, rehabilitation is corresponded into MPF and Fθ/βMaximum respectively averagely divide D grade (take D=6, D can basis The different rehabilitation stages are adjusted), different brackets corresponds to different fatigue states, and higher grade, and degree of fatigue is bigger, otherwise tired Labor degree is smaller.Every a cycle of training, electromyographic signal fatigue index and brainfag index are obtained, same be sent into is trained before Good support vector machines -2, the fatigue state of the cycle of training is identified, according to the level of fatigue of identification, triggering rehabilitation instruction Practice scene difficulty level control, the complexity of automatic adjusument rehabilitation training, so as to realize optimal rehabilitation training effect.
The course of work approximately as：
First, the needs trained with reference to patients with cerebral apoplexy late rehabilitation and the suggestion of physiatrician, based on Visual C# The rehabilitation training scene of the suitable patients with cerebral apoplexy late rehabilitation training of 2010 Independent Development Designs；Secondly, brainfag is proposed Index Fθ/β, realize the quantitative assessment of patient motion brain area fatigue in rehabilitation training；Again, by extracting the different fortune of arm Dynamic model formula lower surface electromyographic signal feature obtains the motion intention of patient, realizes the control to virtual rehabilitation scene, completes to specify Training program；Finally, the current rehabilitation of comprehensive characteristics acquisition by extracting muscular fatigue, brainfag caused by rehabilitation training is suffered from The fatigue state of person, and adaptive regulation rehabilitation training scene, slow down or strengthen rehabilitation training intensity, avoid improper training institute Caused by secondary damage, make that rehabilitation training is more intelligent, hommization.
Compared with prior art, the invention has the advantages that：
1st, the action trend that visual and clear patient can be shown on computer display, there is good interest, it is real The man-machine interaction feedback mechanism of existing virtual scene, improve the initiative and self-confidence of Rehabilitation training；
2nd, the muscular fatigue and brainfag situation of patient can be monitored at any time, and rehabilitation instruction is automatically adjusted according to tired classification results Experienced complexity, slow down or strengthen the intensity of rehabilitation training, secondary damage caused by avoiding improper training, realize optimal instruction Practice effect；
3rd, make more intelligent rehabilitation training, hommization, safe, promote the clinical practice of virtual reality technology to enter Journey, alleviate physiatrician's shortage, the present situation of healing robot supplemental training deficiency, there is important economy and social value.
Brief description of the drawings
Fig. 1 is the structural representation letter of the patients with cerebral apoplexy rehabilitation training system of the invention based on brain myoelectricity and virtual scene Figure.
Fig. 2 is the brain wave acquisition electrode of the patients with cerebral apoplexy rehabilitation training system of the invention based on brain myoelectricity and virtual scene Cap channel position figure.
Fig. 3 is the virtual scene display of the patients with cerebral apoplexy rehabilitation training system of the invention based on brain myoelectricity and virtual scene Surface chart.
Fig. 4 is the different fatigue degree of the patients with cerebral apoplexy rehabilitation training system of the invention based on brain myoelectricity and virtual scene Rehabilitation training scene display interface figure.
Fig. 5 is the EEG signals small echo of the patients with cerebral apoplexy rehabilitation training system of the invention based on brain myoelectricity and virtual scene Wrap 4 layers of decomposition result figure.
Fig. 6 is the brainfag index of the patients with cerebral apoplexy rehabilitation training system of the invention based on brain myoelectricity and virtual scene Fθ/βThe curve map changed with the training time.
Drawing reference numeral：1- electrode for encephalograms cap passage F3,2- electrode for encephalograms cap passage F4,3- electrode for encephalograms caps channel C 3,4- Electrode for encephalograms cap channel C 4,5- brain electricity reference electrode A1,6- brain electricity reference electrode A2,7- START button, 8- " rehabilitation training " Button, 9- " physical signs " button, 10- " preservation " button, 11- the Close buttons, 12- eeg datas waveform, 13- rehabilitation trainings Scene, 14- fruits baskets, 15- fruit figure (such as：Banana, apple, pears), the virtual palms of 16-, 17- data channel.
Embodiment
With reference to embodiment and accompanying drawing, the present invention is described in further detail：
In structure schematic diagram of the invention as shown in Figure 1, system of the present invention includes signal acquisition part, data Preprocessing part, motion index extraction part, sports fatigue index extraction part, virtual scene design part and rehabilitation training Experimental section；Wherein,
The EEG signals and electromyographic signal of patient are extracted described signal acquisition part；
Described data prediction part is filtered processing to the EEG signals and electromyographic signal that collect；
Described motion index extraction part is the analysis extraction of discharge capacity when being acted to patient muscle；
Described sports fatigue index extraction part is to carry out analysis extraction respectively to patient's EEG signals and electromyographic signal, And then judge sports fatigue or brainfag；
Described virtual scene design part is to be counted under computer environment based on Visual C#2010 exploitation designs Virtual scene and display output are generated on calculation machine, establishes man-machine interaction feedback mechanism；
Described rehabilitation training experimental section be patient according to rehabilitation training requirement in virtual scene, bent, stretched by arm Virtual palm completion appointed task in control virtual scene is waved with left and right.
Comprise the following steps that：
Step 1：Signal acquisition part
The collection of electromyographic signal uses the differential input of bikini, and two of which is the differential input end of myoelectricity, another For reference ground, Differential Input electrode is placed at belly of muscle along muscle fibre direction；The present invention relates to muscle be the bicipital muscle of arm And the triceps muscle of arm, the skin at position is first tested using alcohol wipe, to remove skin surface grease and scurf, adhesive electrode.Will Conducting wire is suitably fixed to reduce the interference that conducting wire rocks in action process as far as possible.
With reference to the brain wave acquisition electrode cap channel position figure of figure 2.Eeg signal acquisition uses 8 passage brain myoelectricity synchronous acquisition instrument It is acquired, 10~20 electrodes of adopting international standards place standard, and electrode is connected with scalp by electrode cap.It is because of the invention It is the brainfag index for extracting rehabilitation, Representative Region is sensorimotor cortex, therefore selects C3, C4 in electrode cap and generation It is acquired at F3, F4 of the preceding motor area of table.Using single-stage lead method, electrode slice A1, electrode slice A2 leads are connected respectively to a left side Mastoid process is hit exactly overhead as reference electrode, ground electrode arrangement after auris dextra.
Step 2：Data prediction part
Using adaptive high-pass filter and adaptive 50Hz notch filters wave filter respectively to EEG signals, electromyographic signal Processing is filtered, removes the baseline drift in signal and Hz noise；Reuse the rank band logical FIR filter pair of Butterworth three EEG signals, electromyographic signal are handled, according to effective frequency range feature of signal, choose electromyographic signal cut-off frequency be 2Hz~ 200Hz, the cut-off frequency for choosing EEG signals are 2Hz~50Hz.
Step 3：Motion index extracts part
Electromyographic signal motion index is as follows,
In formula, iEMG is integration myoelectricity value, the quantity of moving cell and putting for each moving cell when reflecting muscle movement TV university is small；T is the time of collection electromyographic signal；T is the cycle for the electromyographic signal that analysis collects；EMG (t) gathers for t The electromyographic signal for the respective muscle motion arrived.
Step 4：Sports fatigue index extraction part
Including electromyographic signal fatigue index and brainfag index；
(1) electromyographic signal fatigue index such as following formula,
In formula, MPF is frequency of average power, is the frequency of power spectrum curve position of centre of gravity, to the frequency spectrum of underload motion Change has compared with hypersensitivity；F is the frequency of electromyographic signal；P (f) is power spectrum function；
(2) brainfag index, based on wavelet packet decomposition algorithm, converted using Binary Scale, by EEG signals f (t) points Solve as 4 layers (as shown in table 1), acquisition EEG signals low frequency sub-band, by wavelet package reconstruction, where acquisition slow wave is 4~8Hz The frequency band rhythm and pace of moving things, it is the frequency band rhythm and pace of moving things where 12~32Hz to obtain fast wave, and wherein slow wave is θ ripples, and fast wave is β ripples, further tries to achieve θ The energy ratio of ripple and β ripples, is comprised the following steps that：
1. WAVELET PACKET DECOMPOSITION
In formula, i=0,1,2 ..., 2j- 1, fj,i(ti) it is reconstruct brain electricity of the WAVELET PACKET DECOMPOSITION on jth node layer (j, i) Signal；
2. by Parseval theorems and 1. middle wavelet packet decomposition computation formula, EEG signals f (t) wavelet packets point can be calculated The energy spectrum of solution is：
In formula, Ej,i(ti) for the frequency band energy in EEG signals f (t) WAVELET PACKET DECOMPOSITIONs to node (j, i)；xi,π(i=0, 2,…,2j-1；π=1,2 ..., n) it is reconstruct EEG signals fj,i(ti) discrete point amplitude；N counts for signal sampling；
3. ask for brainfag index
According to table 1, wavelet packet subband (4,1) is reconstructed, obtains 4~8Hz rhythm and pace of moving things, as θ ripples, it is E to define its energyθ, Then byUnderstand：
Similarly, wavelet packet subband (4,3), (4,4), (4,5), (4,6), (4,7) are reconstructed, obtain 12~32Hz rhythm and pace of moving things, As β ripples, it is E to define its energyβ, equally byUnderstand：
It is F to define brainfag indexθ/β,
With reference to figure 6, Fig. 6 is the brainfag index F of certain patients with cerebral apoplexy convalescence C3 passageθ/βWith the rehabilitation training time Situation of change, it is known that with the increase of run duration, Fθ/βAscendant trend is presented, this is with adult from normal condition to tired shape During state changes, the slow wave (θ ripples) of EEG signals gradually increases, and it is consistent that fast wave (β ripples), which gradually decreases,.Therefore, originally Invention is by Fθ/βFor the quantitative assessment of brainfag state, the difficulty or ease adjustment of rehabilitation training scene is realized.
Step 5：Virtual scene design part
With reference to figure 3, Fig. 3 is the virtual scene display surface chart of the present invention, is to combine patients with cerebral apoplexy late rehabilitation to instruct Experienced needs and the suggestion of physiatrician, under computer environment, the virtual scene based on Visual C#2010 designs；Counting Control button in calculation machine in virtual scene display window includes START button 1, " rehabilitation training " button 2, " physical signs " Button 3, " preservation " button 4, the Close button 5；START button is brain myoelectricity synchronous acquisition button；" rehabilitation training " button is Rehabilitation training start button；" physical signs " button is myoelectricity motion index, electromyographic signal fatigue index and brainfag index Real-time display button；" preservation " button is the save button of myoelectricity motion index, electromyographic signal fatigue index and brainfag index； The Close button is rehabilitation training conclusion button；The rehabilitation training scene of virtual scene is the task platform of rehabilitation training, including： Fruits basket 14, fruit are (such as：Banana) 15, virtual palm 16.
With reference to figure 4 (a~f), Fig. 4 (a~f) is designs different rehabilitation training fields for rehabilitation different fatigue state Scape, its Scene are gradually reduced by Fig. 4 (a) to Fig. 4 (f) difficulty, are shown as patient fatigue's degree is changed from small to big, corresponding Rehabilitation training scene difficulty is become different by difficulty, is embodied in when the degree of fatigue of patients with cerebral apoplexy gradually increases, patient passes through The bending of arm, stretch and control the upper and lower and left and right movement of virtual palm with left and right wave, complete various fruit being all put into basket In this sub task process, the species and number of fruit are gradually decreased by Fig. 4 (a) to Fig. 4 (f), i.e., rehabilitation training intensity with The increase of degree of fatigue and gradually weaken.Step 6：Rehabilitation training experimental section
Patient by arm bending, stretching, extension and left and right is waved according to the requirement of rehabilitation training scene in virtual scene design To control the virtual palm in rehabilitation training scene to complete appointed task.
Specific method is：
The EEG signals of patient are gathered first and electromyographic signal and carry out signal transacting, due to electromyographic signal motion index The size and movement velocity trend of muscular strength when iEMG can reflect muscular movement to a certain extent, using iEMG as feature to The motion intention for identifying patient is measured, after iEMG is asked for, support vector machines -1 trained before is sent into, identifies health The bending of multiple patient's arm, stretch and the left and right action waved, and the void inside manipulation rehabilitation training scene is driven according to recognition result Intend palm, it is dragged corresponding article (all kinds of fruit i.e. in virtual scene display interface) and reach specified location (fruit basket Son), and then complete the specified rehabilitation training project of rehabilitation scene requirement.Simultaneously, it is contemplated that electromyographic signal fatigue index MPF and brain Fatigue exponent Fθ/βPatient motion muscular fatigue degree and motion brain area degree of fatigue can be reflected respectively, rehabilitation is corresponding MPF and Fθ/βMaximum averagely divide 6 grades respectively, different brackets corresponds to different fatigue states, the more high tired journey of grade Degree is bigger, otherwise degree of fatigue is smaller, and wherein corresponding diagram 4 (a~f) is distinguished in class 6~1, i.e. different fatigue grade is corresponding different The rehabilitation training scene of difficulty.Every a cycle of training, an electromyographic signal fatigue index MPF and brainfag index are obtained Fθ/βAnd the supporting vector SVM-2 trained before is sent into, the fatigue state of the cycle of training is identified, and according to the tired of identification Labor grade W (W ∈ 1~6), triggering rehabilitation training scene difficulty level control, rehabilitation training scene M corresponding to selection (M ∈ a~ F), so as to the complexity of adaptive regulation rehabilitation training, and then optimal rehabilitation training effect is realized.
Embodiment described above is only that the preferred embodiment of the present invention is described, not to the scope of the present invention It is defined, on the premise of design spirit of the present invention is not departed from, those of ordinary skill in the art are to technical scheme The various modifications made and improvement, it all should fall into the protection domain of claims of the present invention determination.

Claims (5)

  1. A kind of 1. patients with cerebral apoplexy rehabilitation training system based on brain myoelectricity and virtual scene, it is characterised in that：The system bag Include signal acquisition part, data prediction part, motion index extraction part, sports fatigue index extraction part, virtual scene Design part and rehabilitation training experimental section；Wherein,
    The EEG signals and electromyographic signal of patient are extracted described signal acquisition part；
    Described data prediction part is filtered processing to the EEG signals and electromyographic signal that collect；
    Described motion index extraction part is the analysis extraction of discharge capacity when being acted to patient muscle；
    Described sports fatigue index extraction part is to carry out analysis extraction respectively to patient's EEG signals and electromyographic signal, and then Judge brainfag or sports fatigue；
    Described virtual scene design part is based on Visual C#2010 exploitation designs under computer environment, in computer Upper generation virtual scene and display output, establish man-machine interaction feedback mechanism；
    Described rehabilitation training experimental section is patient according to rehabilitation training requirement in virtual scene, bent by arm, stretch and it is left, Wave virtual palm in control virtual scene and complete appointed task in the right side；
    The electromyographic signal is used for the motion intention for identifying patient；Motion intention generation of the virtual scene based on patient；Institute State EEG signals and electromyographic signal is additionally operable to identify the level of fatigue of patient；The difficulty of rehabilitation training scene in the virtual scene Spend rank and controlled adjustment by the level of fatigue；The virtual scene design part is provided with the virtual palm；The virtual hand The action of the palm is controlled by the electromyographic signal；
    The sports fatigue index includes electromyographic signal fatigue index and brainfag index；
    (1) electromyographic signal fatigue index such as following formula,
    <mrow> <mi>M</mi> <mi>P</mi> <mi>F</mi> <mo>=</mo> <munderover> <mo>&amp;Integral;</mo> <mn>0</mn> <mi>&amp;infin;</mi> </munderover> <mi>f</mi> <mo>&amp;CenterDot;</mo> <mi>P</mi> <mrow> <mo>(</mo> <mi>f</mi> <mo>)</mo> </mrow> <mi>d</mi> <mi>f</mi> <mo>/</mo> <munderover> <mo>&amp;Integral;</mo> <mn>0</mn> <mi>&amp;infin;</mi> </munderover> <mi>P</mi> <mrow> <mo>(</mo> <mi>f</mi> <mo>)</mo> </mrow> <mi>d</mi> <mi>f</mi> </mrow>
    In formula, MPF is frequency of average power, is the frequency of power spectrum curve position of centre of gravity, to the spectral change of underload motion Have compared with hypersensitivity；F is the frequency of electromyographic signal；P (f) is power spectrum function；
    (2) brainfag index, based on wavelet packet decomposition algorithm, is converted using Binary Scale, and EEG signals f (t) is decomposed into 4 Layer, EEG signals low frequency sub-band is obtained, by wavelet package reconstruction, it is the frequency band rhythm and pace of moving things where 4~8Hz to obtain slow wave, is obtained fast Ripple is the frequency band rhythm and pace of moving things where 12~32Hz, and wherein slow wave is θ ripples, and fast wave is β ripples, further tries to achieve the energy of θ ripples and β ripples Than comprising the following steps that：
    1. WAVELET PACKET DECOMPOSITION
    <mrow> <mi>f</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mrow> <msup> <mn>2</mn> <mi>j</mi> </msup> <mo>-</mo> <mn>1</mn> </mrow> </munderover> <msub> <mi>f</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>i</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>f</mi> <mrow> <mi>j</mi> <mo>,</mo> <mn>0</mn> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mn>0</mn> </msub> <mo>)</mo> </mrow> <mo>+</mo> <msub> <mi>f</mi> <mrow> <mi>j</mi> <mo>,</mo> <mn>1</mn> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>+</mo> <mo>...</mo> <mo>+</mo> <msub> <mi>f</mi> <mrow> <mi>j</mi> <mo>,</mo> <msup> <mn>2</mn> <mi>j</mi> </msup> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msup> <mn>2</mn> <mi>j</mi> </msup> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> </mrow>
    In formula, i=0,1,2 ..., 2j- 1, fj,i(ti) it is reconstruct EEG signals of the WAVELET PACKET DECOMPOSITION on jth node layer (j, i)；
    2. by Parseval theorems and 1. middle wavelet packet decomposition computation formula, can be calculated EEG signals f (t) WAVELET PACKET DECOMPOSITIONs Energy spectrum is：
    <mrow> <msub> <mi>E</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>i</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mo>&amp;Integral;</mo> <mo>|</mo> <msub> <mi>f</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>i</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <msup> <mo>|</mo> <mn>2</mn> </msup> <mi>d</mi> <mi>t</mi> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>&amp;pi;</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <mo>|</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>&amp;pi;</mi> </mrow> </msub> <msup> <mo>|</mo> <mn>2</mn> </msup> </mrow>
    In formula, Ej,i(ti) for the frequency band energy in EEG signals f (t) WAVELET PACKET DECOMPOSITIONs to node (j, i)；
    xi,π(i=0,2 ..., 2j-1；π=1,2 ..., n) it is reconstruct EEG signals fj,i(ti) discrete point amplitude；N adopts for signal Number of samples；
    3. ask for brainfag index
    Calculate brainfag index using WAVELET PACKET DECOMPOSITION, EEG signals f (t) be decomposed into 4 layers, respectively wavelet packet subband (4, 0), (4,1), (4,2), (4,3), (4,4), (4,5), (4,6), (4,7), its corresponding frequency be respectively 0~4Hz, 4~8Hz, 8~12Hz, 12~16Hz, 16~20Hz, 20~24Hz, 24~28Hz, 28~32Hz；
    Wavelet packet subband (4,1) is reconstructed, obtains 4~8Hz rhythm and pace of moving things, as θ ripples, it is E to define its energyθ, then byUnderstand：
    <mrow> <msub> <mi>E</mi> <mi>&amp;theta;</mi> </msub> <mo>=</mo> <msub> <mi>E</mi> <mrow> <mn>4</mn> <mo>,</mo> <mn>1</mn> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mo>&amp;Integral;</mo> <mo>|</mo> <msub> <mi>f</mi> <mrow> <mn>4</mn> <mo>,</mo> <mn>1</mn> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <msup> <mo>|</mo> <mn>2</mn> </msup> <mi>d</mi> <mi>t</mi> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>&amp;pi;</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <mo>|</mo> <msub> <mi>x</mi> <mrow> <mn>1</mn> <mo>,</mo> <mi>&amp;pi;</mi> </mrow> </msub> <msup> <mo>|</mo> <mn>2</mn> </msup> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>3</mn> <mo>)</mo> </mrow> </mrow>
    Similarly, wavelet packet subband (4,3), (4,4), (4,5), (4,6), (4,7) are reconstructed, obtains 12~32Hz rhythm and pace of moving things, as β Ripple, it is E to define its energyβ, equally byUnderstand：
    <mrow> <msub> <mi>E</mi> <mi>&amp;beta;</mi> </msub> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>3</mn> </mrow> <mn>7</mn> </munderover> <msub> <mi>E</mi> <mrow> <mn>4</mn> <mo>,</mo> <mi>i</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>3</mn> </mrow> <mn>7</mn> </munderover> <mo>&amp;Integral;</mo> <mo>|</mo> <msub> <mi>f</mi> <mrow> <mn>4</mn> <mo>,</mo> <mi>i</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <msup> <mo>|</mo> <mn>2</mn> </msup> <mi>d</mi> <mi>t</mi> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>3</mn> </mrow> <mn>7</mn> </munderover> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>&amp;pi;</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <mo>|</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>&amp;pi;</mi> </mrow> </msub> <msup> <mo>|</mo> <mn>2</mn> </msup> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>4</mn> <mo>)</mo> </mrow> </mrow>
    It is F to define brainfag indexθ/β,
  2. 2. the patients with cerebral apoplexy rehabilitation training system according to claim 1 based on brain myoelectricity and virtual scene, its feature It is：In the signal acquisition part, the collection of electromyographic signal uses the differential input of bikini, and two of which is the difference of myoelectricity Input, another is reference ground, and Differential Input electrode is placed at belly of muscle along muscle fibre direction；Eeg signal acquisition It is acquired using 8 passage brain myoelectricity synchronous acquisition instrument, 10~20 electrodes of adopting international standards place standard, will by electrode cap Electrode is connected with scalp, and using single-stage lead method, reference electrode lead is connected respectively to after the ear of left and right at mastoid process, grounding electrode cloth Put and hit exactly overhead.
  3. 3. the patients with cerebral apoplexy rehabilitation training system according to claim 1 based on brain myoelectricity and virtual scene, its feature It is：The data prediction part, it is right respectively using adaptive high-pass filter and adaptive 50Hz notch filters wave filter EEG signals, electromyographic signal are filtered processing, remove the baseline drift in signal and Hz noise；Reuse Butterworth three Rank band logical FIR filter is handled EEG signals, electromyographic signal, according to effective frequency range feature of signal, chooses myoelectricity letter Number cut-off frequency be 2Hz~200Hz, the cut-off frequency for choosing EEG signals is 2Hz~50Hz.
  4. 4. the patients with cerebral apoplexy rehabilitation training system according to claim 1 based on brain myoelectricity and virtual scene, its feature It is：The motion index includes electromyographic signal motion index, and the electromyographic signal motion index is as follows,
    <mrow> <mi>i</mi> <mi>E</mi> <mi>M</mi> <mi>G</mi> <mo>=</mo> <munderover> <mo>&amp;Integral;</mo> <msub> <mi>t</mi> <mn>0</mn> </msub> <mrow> <msub> <mi>t</mi> <mn>0</mn> </msub> <mo>+</mo> <mi>T</mi> </mrow> </munderover> <mo>|</mo> <mi>E</mi> <mi>M</mi> <mi>G</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>|</mo> <mi>d</mi> <mi>t</mi> </mrow>
    In formula, iEMG is integration myoelectricity value, and the quantity of moving cell and the electric discharge of each moving cell are big when reflecting muscle movement It is small；T is the time of collection electromyographic signal；T is the cycle for the electromyographic signal that analysis collects；EMG (t) is what t collected The electromyographic signal of respective muscle motion.
  5. 5. the patients with cerebral apoplexy rehabilitation training system according to claim 1 based on brain myoelectricity and virtual scene, its feature It is：The virtual scene design part, under computer environment, virtual scene is designed based on Visual C#2010；Calculating Control button is provided with virtual scene display window in machine, the control button includes START button, " rehabilitation training " is pressed Button, " physical signs " button, " preservation " button, the Close button；START button is brain myoelectricity synchronous acquisition button；" rehabilitation Training " button is rehabilitation training start button；" physical signs " button is electromyographic signal motion index, electromyographic signal fatigue index With the real-time display button of brainfag index；" preservation " button is electromyographic signal motion index, electromyographic signal fatigue index and brain The save button of fatigue index；The Close button is rehabilitation training conclusion button；The rehabilitation training scene of virtual scene is rehabilitation The task platform of training.
CN201410197868.5A 2014-05-12 2014-05-12 Patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene Active CN104000586B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410197868.5A CN104000586B (en) 2014-05-12 2014-05-12 Patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410197868.5A CN104000586B (en) 2014-05-12 2014-05-12 Patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene

Publications (2)

Publication Number Publication Date
CN104000586A CN104000586A (en) 2014-08-27
CN104000586B true CN104000586B (en) 2017-12-29

Family

ID=51361694

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410197868.5A Active CN104000586B (en) 2014-05-12 2014-05-12 Patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene

Country Status (1)

Country Link
CN (1) CN104000586B (en)

Families Citing this family (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104258539B (en) * 2014-09-04 2016-06-15 燕山大学 A kind of old man rehabilitation mutual based on virtual reality and limb action and monitor system
CN104382595B (en) * 2014-10-27 2017-02-15 燕山大学 Upper limb rehabilitation system and method based on myoelectric signal and virtual reality interaction technology
CN104784892B (en) * 2015-03-26 2017-10-20 浙江大学 A kind of three-dimensional, which is stretched, grabs motion training device and method
CN105653039B (en) * 2016-01-20 2018-12-18 同济大学 A kind of hand motion automatic straightening recognition methods based on EEG signals detection
CN105700689B (en) * 2016-03-17 2018-07-13 北京工业大学 Virtually and the personalized MI-EEG of Skinner intensified learnings is trained and acquisition method based on mirror image
CN106128201B (en) * 2016-06-14 2018-12-21 北京航空航天大学 A kind of attention training system of immersion vision and the combination of discrete force control task
CN106250700B (en) * 2016-08-09 2019-10-01 京东方科技集团股份有限公司 Interactive rehabilitation system, interactive convalescence device and interactive method of rehabilitation
JP2018064740A (en) * 2016-10-19 2018-04-26 セイコーエプソン株式会社 Rehabilitation system
CN106779045A (en) * 2016-11-30 2017-05-31 东南大学 Rehabilitation training robot system and its application method based on virtual scene interaction
CN106725509B (en) * 2016-12-15 2020-04-07 佛山科学技术学院 Feature extraction method of biomechanical information
CN108154913A (en) * 2017-12-29 2018-06-12 北京精密机电控制设备研究所 A kind of rehabilitation training parameter determination method, device, electronic equipment and system
CN108354784A (en) * 2018-04-27 2018-08-03 深圳市迈步机器人科技有限公司 A kind of electronic equipment and control method
CN108681396B (en) * 2018-04-28 2021-07-06 北京机械设备研究所 Human-computer interaction system and method based on brain-myoelectricity bimodal neural signals
CN108735279B (en) * 2018-06-21 2022-04-12 广西虚拟现实科技有限公司 Virtual reality upper limb rehabilitation training system for stroke in brain and control method
CN109711260B (en) * 2018-11-28 2021-03-05 易念科技（深圳）有限公司 Fatigue state detection method, terminal device and medium
CN109568891A (en) * 2018-11-28 2019-04-05 东南大学 The main passive exercise schema control system of healing robot and method based on brain electricity
CN109568083B (en) * 2018-12-15 2024-01-05 华南理工大学 Multi-mode interaction upper limb rehabilitation robot training system
CN109674467A (en) * 2019-01-08 2019-04-26 大连理工大学 A kind of list guide lug eeg signal acquisition devices and methods therefor
CN109528203A (en) * 2019-01-21 2019-03-29 郑州大学 A kind of interactive patients with cerebral apoplexy gait training and evaluating system based on Multi-source Information Fusion
CN109992113B (en) * 2019-04-09 2020-05-15 燕山大学 MI-BCI system based on multi-scene induction and control method thereof
CN110060780A (en) * 2019-04-17 2019-07-26 浙江理工大学 A kind of cerebral apoplexy hand rehabilitation training system and method
CN110353667A (en) * 2019-06-24 2019-10-22 同济大学 A kind of rehabilitation of stroke patients system and control method
CN110495893B (en) * 2019-07-30 2021-01-29 西安交通大学 System and method for multi-level dynamic fusion recognition of continuous brain and muscle electricity of motor intention
CN110739042A (en) * 2019-10-29 2020-01-31 浙江迈联医疗科技有限公司 Limb movement rehabilitation method and device based on brain-computer interface, storage medium and equipment
CN112353407B (en) * 2020-10-27 2022-02-11 燕山大学 Evaluation system and method based on active training of neurological rehabilitation
CN112932474B (en) * 2021-01-26 2022-04-01 国家康复辅具研究中心 Rehabilitation training method and system based on cerebral blood oxygen and electromyographic signals
CN112987918A (en) * 2021-02-06 2021-06-18 杭州职业技术学院 VR mobile platform data processing method and device
CN112842825B (en) * 2021-02-24 2023-06-09 郑州铁路职业技术学院 Training device for rehabilitation and recovery of lower limbs
CN113713333B (en) * 2021-08-25 2022-08-05 西安交通大学 Dynamic virtual induction method and system for lower limb rehabilitation full training process
WO2023102908A1 (en) * 2021-12-10 2023-06-15 深圳大学 Multi-modal strength training assistance method and system
CN114470635B (en) * 2022-02-23 2023-02-28 郑州大学第三附属医院(河南省妇幼保健院) Rehabilitation training system and method based on active feedback
CN114694448B (en) * 2022-06-01 2022-08-30 深圳市心流科技有限公司 Concentration training method and device, intelligent terminal and storage medium
CN114756137B (en) * 2022-06-15 2022-09-27 深圳市心流科技有限公司 Training mode adjusting method and device for electromyographic signals and electroencephalographic signals
CN114783611B (en) * 2022-06-22 2022-08-23 新泰市中医医院 Neural recovered action detecting system based on artificial intelligence
CN114797036B (en) * 2022-06-27 2022-09-27 深圳市心流科技有限公司 Concentration training scheme making method, device, equipment and storage medium
CN117133402A (en) * 2023-08-30 2023-11-28 广东省中医院（广州中医药大学第二附属医院、广州中医药大学第二临床医学院、广东省中医药科学院） Method, device, equipment and readable storage medium for dynamically supervising patient rehabilitation

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101181176A (en) * 2007-12-10 2008-05-21 华中科技大学 Apparel type robot for healing hand function and control system thereof
CN101234224A (en) * 2008-01-29 2008-08-06 河海大学 Method for using virtual reality technique to help user executing training rehabilitation
CN103106343A (en) * 2013-01-29 2013-05-15 中山大学 Difficulty adjusting method for limb rehabilitation training
CN103431976A (en) * 2013-07-19 2013-12-11 燕山大学 Lower limb rehabilitation robot system based on myoelectric signal feedback, and control method thereof
CN103584855A (en) * 2013-10-24 2014-02-19 燕山大学 Electroencephalogram and electromyogram synchronous acquisition and information transfer characteristic analysis method

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5300096A (en) * 1992-06-03 1994-04-05 Hall H Eugene Electromyographic treatment device
US6001065A (en) * 1995-08-02 1999-12-14 Ibva Technologies, Inc. Method and apparatus for measuring and analyzing physiological signals for active or passive control of physical and virtual spaces and the contents therein
JP5154558B2 (en) * 2007-08-31 2013-02-27 公益財団法人東京都医学総合研究所 Quantitative motor function evaluation system and motor function evaluation program
CN101667346B (en) * 2009-09-18 2011-04-27 国家康复辅具研究中心 Rehabilitation training system of amputation upper limb based on virtual reality
CN103764021B (en) * 2011-05-20 2015-11-25 南洋理工大学 A kind ofly to repair for collaborative neuro-physiological and/or system, instrument, the apparatus and method of functional promotion
CN102184342B (en) * 2011-06-15 2013-11-20 青岛科技大学 Virtual-real fused hand function rehabilitation training system and method
CN202776300U (en) * 2012-04-13 2013-03-13 上海诺诚电气有限公司 Portable multi-media feedback training equipment
CN103750975B (en) * 2013-12-27 2016-01-06 天津理工大学 Based on exoskeleton finger recovery robot system and the method for work of brain electric control

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101181176A (en) * 2007-12-10 2008-05-21 华中科技大学 Apparel type robot for healing hand function and control system thereof
CN101234224A (en) * 2008-01-29 2008-08-06 河海大学 Method for using virtual reality technique to help user executing training rehabilitation
CN103106343A (en) * 2013-01-29 2013-05-15 中山大学 Difficulty adjusting method for limb rehabilitation training
CN103431976A (en) * 2013-07-19 2013-12-11 燕山大学 Lower limb rehabilitation robot system based on myoelectric signal feedback, and control method thereof
CN103584855A (en) * 2013-10-24 2014-02-19 燕山大学 Electroencephalogram and electromyogram synchronous acquisition and information transfer characteristic analysis method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
利用EEG信号的小波包变换与非线性分析实现精神疲劳状态的判定;韩清鹏;《振动与冲击》;20130128;第32卷(第2期);摘要和正文第1页右栏第2段到第5页左栏第3段，图1 *
基于EMD多尺度熵和ELM的运动想象脑电特征提取和模式识别;谢平等;《中国生物医学工程学报》;20131231;第32卷(第6期);全文 *
基于小波包变换的精神疲劳多参数脑电分析;王鹏等;《计算机工程与应用》;20111021;第47卷(第30期);全文 *

Also Published As

Publication number Publication date
CN104000586A (en) 2014-08-27

Similar Documents

Publication Publication Date Title
CN104000586B (en) Patients with cerebral apoplexy rehabilitation training system and method based on brain myoelectricity and virtual scene
CN104382595B (en) Upper limb rehabilitation system and method based on myoelectric signal and virtual reality interaction technology
CN109568083B (en) Multi-mode interaction upper limb rehabilitation robot training system
CN104107134B (en) Upper limbs training method and system based on EMG feedback
CN103431976B (en) Based on lower limb rehabilitation robot system and the control method thereof of electromyographic signal feedback
Yang et al. Automatic ocular artifacts removal in EEG using deep learning
CN103886215B (en) Walking ability analyzing method and device based on muscle collaboration
CN107928980B (en) A kind of autonomous rehabilitation training system of the hand of hemiplegic patient and training method
CN105054927B (en) The biological quantitative estimation method for degree of being actively engaged in a kind of lower limb rehabilitation system
CN110179643A (en) A kind of neck rehabilitation training system and training method based on annulus sensor
CN103845137B (en) Based on the robot control method of stable state vision inducting brain-machine interface
CN104173124B (en) A kind of upper limb healing system based on bio signal
CN110238863A (en) Based on brain electricity-electromyography signal lower limb rehabilitation robot control method and system
CN105853140A (en) Visual motion evoked brain-controlled lower limb active and passive cooperative rehabilitation training system
CN109992113A (en) A kind of MI-BCI system and its control method induced based on more scenes
CN107626040A (en) It is a kind of based on the rehabilitation system and method that can interact virtual reality and nerve electric stimulation
CN114748080B (en) Method and system for detecting and quantifying sensory-motor function
CN108743223A (en) A kind of the intelligent exoskeleton manipulators in rehabilitation and method automatically controlled based on strong side biology
CN103892829B (en) A kind of eye based on common space pattern moves signal recognition system and recognition methods thereof
CN102306303B (en) Electroencephalography signal characteristic extraction method based on small training samples
CN111631908B (en) Active hand rehabilitation system for stroke based on brain-computer interaction and deep learning
CN106236503A (en) The wearable exoskeleton system of the electrically driven (operated) upper limb of flesh and control method
CN113398422A (en) Rehabilitation training system and method based on motor imagery-brain-computer interface and virtual reality
CN114021604A (en) Motion imagery training system based on real-time feedback of 3D virtual reality technology
CN113274032A (en) Cerebral apoplexy rehabilitation training system and method based on SSVEP + MI brain-computer interface

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant