CN108310633A - A kind of intelligent paralytic patient recovering aid system - Google Patents
A kind of intelligent paralytic patient recovering aid system Download PDFInfo
- Publication number
- CN108310633A CN108310633A CN201810101356.2A CN201810101356A CN108310633A CN 108310633 A CN108310633 A CN 108310633A CN 201810101356 A CN201810101356 A CN 201810101356A CN 108310633 A CN108310633 A CN 108310633A
- Authority
- CN
- China
- Prior art keywords
- module
- vector
- data
- matrix
- controller
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000001769 paralizing effect Effects 0.000 title abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 17
- 206010033799 Paralysis Diseases 0.000 claims abstract description 16
- 230000000694 effects Effects 0.000 claims abstract description 12
- 230000000638 stimulation Effects 0.000 claims abstract description 11
- 210000002569 neuron Anatomy 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims abstract description 5
- 239000013598 vector Substances 0.000 claims description 36
- 239000011159 matrix material Substances 0.000 claims description 27
- 238000012360 testing method Methods 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 10
- 230000003595 spectral effect Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 238000001035 drying Methods 0.000 claims description 4
- 210000004556 brain Anatomy 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000002203 pretreatment Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000002087 whitening effect Effects 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 2
- 210000002268 wool Anatomy 0.000 claims description 2
- 210000005036 nerve Anatomy 0.000 abstract description 6
- 208000012661 Dyskinesia Diseases 0.000 abstract description 2
- 230000001537 neural effect Effects 0.000 abstract 2
- 230000001771 impaired effect Effects 0.000 abstract 1
- 230000001225 therapeutic effect Effects 0.000 abstract 1
- 210000000653 nervous system Anatomy 0.000 description 3
- 210000003205 muscle Anatomy 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 206010003694 Atrophy Diseases 0.000 description 1
- 238000001467 acupuncture Methods 0.000 description 1
- 230000037444 atrophy Effects 0.000 description 1
- 230000008512 biological response Effects 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N1/00—Electrotherapy; Circuits therefor
- A61N1/18—Applying electric currents by contact electrodes
- A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
- A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
- A61N1/3605—Implantable neurostimulators for stimulating central or peripheral nerve system
- A61N1/3606—Implantable neurostimulators for stimulating central or peripheral nerve system adapted for a particular treatment
- A61N1/36067—Movement disorders, e.g. tremor or Parkinson disease
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N1/00—Electrotherapy; Circuits therefor
- A61N1/18—Applying electric currents by contact electrodes
- A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
- A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
- A61N1/3605—Implantable neurostimulators for stimulating central or peripheral nerve system
- A61N1/36128—Control systems
- A61N1/36135—Control systems using physiological parameters
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Neurosurgery (AREA)
- Neurology (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Psychiatry (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Physics & Mathematics (AREA)
- Radiology & Medical Imaging (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Hospice & Palliative Care (AREA)
- Signal Processing (AREA)
- Psychology (AREA)
- Electrotherapy Devices (AREA)
Abstract
The invention belongs to the field of medical instrument technology, disclose a kind of intelligent paralytic patient recovering aid system, including：Signal acquisition module, the EEG signals for acquiring paralytic；Preprocessing module is filtered for the EEG signals to acquisition, removes dry pretreatment；Controller, for being analyzed pretreated EEG signals, analog-to-digital conversion operation；Memory module, for realizing controller processing EEG signals storage；Electrical stimulation module, the neuron of the paralysis for EEG signals to be acted on to human body；Feedback module is used for the biological reflection of feedback neural member, convenient for making assessment to therapeutic effect.The present invention passes through autonomous restorative training, nerve impulse uploads to the impaired neural position of patient, so that patient obtains the effect that injured nerve system has also obtained corresponding exercise, the reconstruction for accelerating the rehabilitation and nerves within the body system of patient's injured nerve system, to which fundamentally treatment paralytic obtains dyskinesia.
Description
Technical Field
The invention belongs to the technical field of medical instruments, and particularly relates to an intelligent paralytic patient auxiliary rehabilitation system.
Background
The way for controlling limb movement of normal people is as follows; "brain-central nervous system-peripheral nervous system-skeletal muscle-limb movement". For paralyzed patients, in which the central nervous system is damaged, the movement commands of the brain cannot be transmitted to the muscles through normal body passages, thereby losing control over the limbs. At present, the rehabilitation therapy of paralytic patients mainly adopts the traditional methods of massage, acupuncture, electrical stimulation and the like. The methods play a certain positive role in delaying the atrophy of the residual limb muscles of the patient and assisting the rehabilitation, but the methods have longer treatment flow, higher cost and poor curative effect, and can not enable the residual limb of the patient to complete the original specific action.
In summary, the problems of the prior art are as follows: the existing rehabilitation therapy for the paralyzed patient has the defects of longer treatment process, higher cost, poor curative effect and incapability of enabling the stump of the patient to complete the original specific action.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intelligent paralytic patient auxiliary rehabilitation system.
The invention is realized in this way, an intelligent paralytic patient auxiliary rehabilitation system, which includes:
the signal acquisition module is used for acquiring the electroencephalogram signals of the paralyzed patient;
acquiring two types of EEG signals of n experimenters imagining no-movement, and respectively solving the covariance of training data of each experimenter;
step two, introducing regularization parameters α and β, combining the sum of covariance matrixes of the primary testers and the sum of covariance matrixes of the secondary testers under the action of the regularization parameters to construct two types of different motion imagery spatial filters, retaining the training data after filtering, extracting two types of vectors with maximized features, and constructing a learning dictionary, wherein the regularization parameters α and β specifically comprise the following steps:
separately summing the covariance matrices of class A and class B training samples RAAnd RBSum of covariance matrices of class A and class B training samples for all sub-testersAndtwo types of average regularized covariance matrices are constructed, and the formula is as follows:
wherein, N is the collection channel number, and I is N rank unit array, and tr is the trace of matrix, promptly: the sum of the elements on all the main diagonals of the matrix;
and (3) carrying out eigenvalue decomposition on the sum of the regularized covariance matrixes to obtain a whitening matrix P:
wherein,is a diagonal matrix of eigenvalues of Z,is a corresponding feature vector matrix;
the resulting Z is transformed as follows:
wherein Λ is a characteristic value diagonal matrix, U is a corresponding characteristic vector matrix, a characteristic vector corresponding to the maximum characteristic value in the diagonal matrix Λ is selected, and the spatial filter is constructed as follows:
W＝UT·P；
two classes of EEG signals X to be used in training samplesAAnd XBThrough a corresponding filter WA、WBThe method comprises the following steps:
FA＝WA T·XA
FB＝WB T·XB；
and then Fourier transform is carried out, the power spectral density value of the frequency at 8-15Hz is obtained, and the power spectral density value is used as a learning dictionary B ═ F of sparse representationAFB]；
Inputting test motor imagery data, performing spatial filtering according to the step two, and reserving the filtered test data;
identifying the test motor imagery data by using a signal sparse representation method, and determining the category of the test sample; the method comprises the following steps:
solving for the sparsely represented vector of test samples as follows:
wherein x is a sparse representation vector of a test motor imagery sample to be solved, y is the test motor imagery sample data to be solved, epsilon is an error threshold, and B is a learning dictionary formed by two types of feature vectors;
for each motion image i, according to the sparsity of the test sampleRepresenting a vectorCalculating residual error
WhereinIs to represent the vector by sparsenessIn the obtained new vector, element items corresponding to the ith type of motor imagery are the same as corresponding element items in the sparse representation vector, and other element items are all zero;
and using the category with the minimum residual error as a final motor imagery category identification result: is test sample data;
the preprocessing module is connected with the signal acquisition module through a USB and is used for carrying out filtering and drying preprocessing on the acquired electroencephalogram signals;
the controller is connected with the preprocessing module USB and is used for analyzing the preprocessed electroencephalogram signals, performing analog-to-digital conversion and the like;
the storage module is connected with the controller through a USB (universal serial bus) and used for realizing the storage of the electroencephalogram signals processed by the controller and facilitating the doctor to check and reply the treatment effect;
the electrical stimulation module is connected with the USB controller and is used for applying the electroencephalogram signals to paralyzed neurons of the human body;
and the feedback module is connected with the electrical stimulation module through a USB (universal serial bus) and is used for feeding back the biological reflection of the neuron, so that the treatment effect can be evaluated conveniently.
Further, the controller may be configured to apply a time-frequency domain matrix to the frequency hopping mixed signalThe pretreatment comprises the following steps:
first step, toWith a low-energy-removing pre-treatment, i.e. at each sampling instant p, willSetting the amplitude value smaller than the threshold epsilon to 0 to obtainThe setting of the threshold epsilon can be determined according to the average energy of the received signal;
secondly, find the nonzero time-frequency domain data of P time (P is 0, 1, 2, … P-1) and useIs shown in whichRepresenting time-frequency response at time pNormalizing and preprocessing the non-zero data by the corresponding frequency index when the non-zero data is not 0 to obtain a preprocessed vector b (p, q) ═ b1(p，q)，b2(p，q)，…，bM(p，q)]TWherein
The invention has the advantages and positive effects that: the movement intention of the paralyzed patient can be automatically analyzed, so that the patient can autonomously control the movement of the residual limb, the autonomous movement capability is recovered, and the control capability on the external environment is recovered; meanwhile, through the autonomous recovery motor training, the nerve impulse is uploaded to the damaged nerve part of the patient, so that the damaged nervous system of the patient also obtains the corresponding exercise effect, and the rehabilitation of the damaged nervous system of the patient and the reconstruction of the nervous system in vivo are accelerated, thereby fundamentally treating the dyskinesia of the paralyzed patient.
Drawings
FIG. 1 is a schematic structural diagram of an intelligent paralytic patient rehabilitation assistance system according to an embodiment of the present invention;
in the figure: 1. a signal acquisition module; 2. a preprocessing module; 3. a controller; 4. a storage module; 5. an electrical stimulation module; 6. and a feedback module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of the principles of the invention is provided in connection with the accompanying drawings.
As shown in fig. 1, the intelligent paralytic patient assisted rehabilitation system provided by the embodiment of the invention comprises: the device comprises a signal acquisition module 1, a preprocessing module 2, a controller 3, a storage module 4, an electrical stimulation module 5 and a feedback module 6.
The signal acquisition module 1 is used for acquiring electroencephalogram signals of paralyzed patients;
the preprocessing module 2 is connected with the signal acquisition module 1 through a USB and is used for carrying out filtering and drying preprocessing on the acquired electroencephalogram signals;
the controller 3 is connected with the preprocessing module 2 through a USB and is used for analyzing the preprocessed electroencephalogram signals, performing analog-to-digital conversion and the like;
the storage module 4 is connected with the controller 3 in a USB mode and used for storing the electroencephalogram signals processed by the controller 3 and facilitating the doctor to check and reply the treatment effect;
the electrical stimulation module 5 is connected with the controller 3 through a USB and is used for enabling the electroencephalogram signals to act on paralyzed neurons of the human body;
and the feedback module 6 is connected with the electrical stimulation module 5 in a USB (universal serial bus) manner and is used for feeding back the biological response of the neuron so as to conveniently evaluate the treatment effect.
The brain sack wool signal processing method of the signal acquisition module comprises the following steps:
acquiring two types of EEG signals of n experimenters imagining no-movement, and respectively solving the covariance of training data of each experimenter;
step two, introducing regularization parameters α and β, combining the sum of covariance matrixes of the primary testers and the sum of covariance matrixes of the secondary testers under the action of the regularization parameters to construct two types of different motion imagery spatial filters, retaining the training data after filtering, extracting two types of vectors with maximized features, and constructing a learning dictionary, wherein the regularization parameters α and β specifically comprise the following steps:
separately summing the covariance matrices of class A and class B training samples RAAnd RBSum of covariance matrices of class A and class B training samples for all sub-testersAndtwo types of average regularized covariance matrices are constructed, and the formula is as follows:
wherein, N is the collection channel number, and I is N rank unit array, and tr is the trace of matrix, promptly: the sum of the elements on all the main diagonals of the matrix;
and (3) carrying out eigenvalue decomposition on the sum of the regularized covariance matrixes to obtain a whitening matrix P:
wherein,is a diagonal matrix of eigenvalues of Z,is a corresponding feature vector matrix;
the resulting Z is transformed as follows:
wherein Λ is a characteristic value diagonal matrix, U is a corresponding characteristic vector matrix, a characteristic vector corresponding to the maximum characteristic value in the diagonal matrix Λ is selected, and the spatial filter is constructed as follows:
W＝UT·P；
two classes of EEG signals X to be used in training samplesAAnd XBThrough a corresponding filter WA、WBThe method comprises the following steps:
FA＝WA T·XA
FB＝WB T·XB；
and then Fourier transform is carried out, the power spectral density value of the frequency at 8-15Hz is obtained, and the power spectral density value is used as a learning dictionary B ═ F of sparse representationAFB]；
Inputting test motor imagery data, performing spatial filtering according to the step two, and reserving the filtered test data;
identifying the test motor imagery data by using a signal sparse representation method, and determining the category of the test sample; the method comprises the following steps:
solving for the sparsely represented vector of test samples as follows:
wherein x is a sparse representation vector of a test motor imagery sample to be solved, y is the test motor imagery sample data to be solved, epsilon is an error threshold, and B is a learning dictionary formed by two types of feature vectors;
for each motion image i, a vector is expressed according to the sparsity of the test sampleCalculating residual error
WhereinIs to represent the vector by sparsenessIn the obtained new vector, element items corresponding to the ith type of motor imagery are the same as corresponding element items in the sparse representation vector, and other element items are all zero;
and using the category with the minimum residual error as a final motor imagery category identification result: is test sample data;
the controller is used for carrying out time-frequency domain matrix on the frequency hopping mixed signalThe pretreatment comprises the following steps:
first step, toWith a low-energy-removing pre-treatment, i.e. at each sampling instant p, willSetting the amplitude value smaller than the threshold epsilon to 0 to obtainThe setting of the threshold epsilon can be determined according to the average energy of the received signal;
secondly, find the nonzero time-frequency domain data of P time (P is 0, 1, 2, … P-1) and useIs shown in whichRepresenting time-frequency response at time pNormalizing and preprocessing the non-zero data by the corresponding frequency index when the non-zero data is not 0 to obtain a preprocessed vector b (p, q) ═ b1(p，q)，b2(p，q)，…，bM(p，q)]TWherein
The working principle of the invention is as follows:
the signal acquisition module acquires an electroencephalogram signal of a paralyzed patient; the preprocessing module carries out filtering and drying preprocessing on the acquired electroencephalogram signals; the controller analyzes and performs analog-to-digital conversion and other operations on the preprocessed electroencephalogram signals; the storage module realizes the storage of the electroencephalogram signals processed by the controller, and is convenient for a doctor to check and reply the treatment effect; the electrical stimulation module acts the electroencephalogram signal on paralyzed neurons of the human body; the feedback module feeds back the biological reflection of the neuron, so that the treatment effect can be conveniently evaluated. The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (2)
1. An intelligent paralyzed patient assisted rehabilitation system, which is characterized in that the intelligent paralyzed patient assisted rehabilitation system comprises:
the signal acquisition module is used for acquiring the electroencephalogram signals of the paralyzed patient;
the brain sack wool signal processing method of the signal acquisition module comprises the following steps:
acquiring two types of EEG signals of n experimenters imagining no-movement, and respectively solving the covariance of training data of each experimenter;
step two, introducing regularization parameters α and β, combining the sum of covariance matrixes of the primary testers and the sum of covariance matrixes of the secondary testers under the action of the regularization parameters to construct two types of different motion imagery spatial filters, retaining the training data after filtering, extracting two types of vectors with maximized features, and constructing a learning dictionary, wherein the regularization parameters α and β specifically comprise the following steps:
separately summing the covariance matrices of class A and class B training samples RAAnd RBSum of covariance matrices of class A and class B training samples for all sub-testersAndtwo types of average regularized covariance matrices are constructed, and the formula is as follows:
wherein, N is the collection channel number, and I is N rank unit array, and tr is the trace of matrix, promptly: the sum of the elements on all the main diagonals of the matrix;
and (3) carrying out eigenvalue decomposition on the sum of the regularized covariance matrixes to obtain a whitening matrix P:
wherein,is a diagonal matrix of eigenvalues of Z,is a corresponding feature vector matrix;
the resulting Z is transformed as follows:
wherein Λ is a characteristic value diagonal matrix, U is a corresponding characteristic vector matrix, a characteristic vector corresponding to the maximum characteristic value in the diagonal matrix Λ is selected, and the spatial filter is constructed as follows:
W＝UT·P；
two classes of EEG signals X to be used in training samplesAAnd XBThrough a corresponding filter WA、WBThe method comprises the following steps:
FA＝WA T·XA
FB＝WB T·XB；
and then Fourier transform is carried out, the power spectral density value of the frequency at 8-15Hz is obtained, and the power spectral density value is used as a learning dictionary B ═ F of sparse representationAFB]；
Inputting test motor imagery data, performing spatial filtering according to the step two, and reserving the filtered test data;
identifying the test motor imagery data by using a signal sparse representation method, and determining the category of the test sample; the method comprises the following steps:
solving for the sparsely represented vector of test samples as follows:
wherein x is a sparse representation vector of a test motor imagery sample to be solved, y is the test motor imagery sample data to be solved, epsilon is an error threshold, and B is a learning dictionary formed by two types of feature vectors;
for each motion image i, a vector is expressed according to the sparsity of the test sampleCalculating residual error
WhereinIs to represent the vector by sparsenessIn the obtained new vector, element items corresponding to the ith type of motor imagery are the same as corresponding element items in the sparse representation vector, and other element items are all zero;
and using the category with the minimum residual error as a final motor imagery category identification result:is test sample data;
the preprocessing module is connected with the signal acquisition module through a USB and is used for carrying out filtering and drying preprocessing on the acquired electroencephalogram signals;
the controller is connected with the preprocessing module USB and is used for analyzing the preprocessed electroencephalogram signals, performing analog-to-digital conversion and the like;
the storage module is connected with the controller through a USB (universal serial bus) and used for realizing the storage of the electroencephalogram signals processed by the controller and facilitating the doctor to check and reply the treatment effect;
the electrical stimulation module is connected with the USB controller and is used for applying the electroencephalogram signals to paralyzed neurons of the human body;
and the feedback module is connected with the electrical stimulation module through a USB (universal serial bus) and is used for feeding back the biological reflection of the neuron, so that the treatment effect can be evaluated conveniently.
2. The intelligent paralyzed patient assisted rehabilitation system of claim 1 wherein said controller generates a time-frequency domain matrix for the frequency hopping mixed signalPerforming pretreatmentThe method specifically comprises the following two steps:
first step, toWith a low-energy-removing pre-treatment, i.e. at each sampling instant p, willSetting the amplitude value smaller than the threshold epsilon to 0 to obtainThe setting of the threshold epsilon can be determined according to the average energy of the received signal;
secondly, find the nonzero time-frequency domain data of P time (P is 0, 1, 2, … P-1) and useIs shown in whichRepresenting time-frequency response at time pNormalizing and preprocessing the non-zero data by the corresponding frequency index when the non-zero data is not 0 to obtain a preprocessed vector b (p, q) ═ b1(p，q)，b2(p，q)，…，bM(p，q)]TWherein
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810101356.2A CN108310633A (en) | 2018-02-01 | 2018-02-01 | A kind of intelligent paralytic patient recovering aid system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810101356.2A CN108310633A (en) | 2018-02-01 | 2018-02-01 | A kind of intelligent paralytic patient recovering aid system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108310633A true CN108310633A (en) | 2018-07-24 |
Family
ID=62890407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810101356.2A Pending CN108310633A (en) | 2018-02-01 | 2018-02-01 | A kind of intelligent paralytic patient recovering aid system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108310633A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117936103A (en) * | 2024-03-22 | 2024-04-26 | 莆田市军源特种装备科技有限公司 | Intelligent AI acupuncture model training system and method based on neural network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425249A (en) * | 2013-09-06 | 2013-12-04 | 西安电子科技大学 | Electroencephalogram signal classifying and recognizing method based on regularized CSP and regularized SRC and electroencephalogram signal remote control system |
| CN105727442A (en) * | 2015-12-16 | 2016-07-06 | 深圳先进技术研究院 | Closed-loop brain controlled functional electrical stimulation system |
| CN106901941A (en) * | 2017-02-21 | 2017-06-30 | 哈尔滨医科大学 | A kind of joint of vertebral column depressurized system |
-
2018
- 2018-02-01 CN CN201810101356.2A patent/CN108310633A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425249A (en) * | 2013-09-06 | 2013-12-04 | 西安电子科技大学 | Electroencephalogram signal classifying and recognizing method based on regularized CSP and regularized SRC and electroencephalogram signal remote control system |
| CN105727442A (en) * | 2015-12-16 | 2016-07-06 | 深圳先进技术研究院 | Closed-loop brain controlled functional electrical stimulation system |
| CN106901941A (en) * | 2017-02-21 | 2017-06-30 | 哈尔滨医科大学 | A kind of joint of vertebral column depressurized system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117936103A (en) * | 2024-03-22 | 2024-04-26 | 莆田市军源特种装备科技有限公司 | Intelligent AI acupuncture model training system and method based on neural network |
| CN117936103B (en) * | 2024-03-22 | 2024-05-28 | 莆田市军源特种装备科技有限公司 | Intelligent AI acupuncture model training system and method based on neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109620651B (en) | Intelligent auxiliary rehabilitation equipment based on synchronous brain and muscle electricity | |
| CN110238863B (en) | Lower limb rehabilitation robot control method and system based on electroencephalogram-electromyogram signals | |
| CN111584029A (en) | Electroencephalogram self-adaptive model based on discriminant confrontation network and application of electroencephalogram self-adaptive model in rehabilitation | |
| CN110974212A (en) | Electrocardio and myoelectric characteristic fused rehabilitation training motion state monitoring method and system | |
| Bai et al. | Upper Arm Motion High‐Density sEMG Recognition Optimization Based on Spatial and Time‐Frequency Domain Features | |
| CN105054928A (en) | Emotion display equipment based on BCI (brain-computer interface) device electroencephalogram acquisition and analysis | |
| CN114533086A (en) | Motor imagery electroencephalogram decoding method based on spatial domain characteristic time-frequency transformation | |
| Wang et al. | An approach of one-vs-rest filter bank common spatial pattern and spiking neural networks for multiple motor imagery decoding | |
| Li et al. | A method for suppressing electrical stimulation artifacts from electromyography | |
| CN115562488A (en) | Motor imagery brain-computer interface communication method, device, system, medium and equipment | |
| CN114082169B (en) | Disabled hand soft body rehabilitation robot motor imagery identification method based on electroencephalogram signals | |
| CN114186608B (en) | Hybrid brain-computer interface feature extraction method based on motor imagery | |
| Xie et al. | A brain controlled wheelchair based on common spatial pattern | |
| CN108310633A (en) | A kind of intelligent paralytic patient recovering aid system | |
| Wang et al. | Deep convolutional neural network for decoding EMG for human computer interaction | |
| Ji et al. | Stationary wavelet-based two-directional two-dimensional principal component analysis for EMG signal classification | |
| CN116831874A (en) | Lower limb rehabilitation device control method based on electromyographic signals | |
| Yu et al. | The research of sEMG movement pattern classification based on multiple fused wavelet function | |
| Asres et al. | A combination of AR and neural network technique for EMG pattern identification | |
| Ghane et al. | Robust understanding of EEG patterns in silent speech | |
| Jana et al. | A hybrid method for classification of physical action using discrete wavelet transform and artificial neural network | |
| Trifonov et al. | Biotechnical system for control to the exoskeleton limb based on surface myosignals for rehabilitation complexes | |
| Tian | Research on the relationship between brain signal analysis algorithm and invasive brain computer interface | |
| Ling et al. | A real-time leg motion recognition system by using Mahalanobis distance and LS_SVM | |
| Zhou et al. | Motor Imagery EEG-based Control of Intelligent Wheelchair Using Deep Belief Network Coupled with OVO-CSP Algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180724 |