CN116994697A - Brain-computer interaction method based on complete spinal cord injury patient training evaluation - Google Patents
Brain-computer interaction method based on complete spinal cord injury patient training evaluation Download PDFInfo
- Publication number
- CN116994697A CN116994697A CN202310981320.9A CN202310981320A CN116994697A CN 116994697 A CN116994697 A CN 116994697A CN 202310981320 A CN202310981320 A CN 202310981320A CN 116994697 A CN116994697 A CN 116994697A
- Authority
- CN
- China
- Prior art keywords
- electroencephalogram
- signals
- multichannel
- channel
- erd
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000011156 evaluation Methods 0.000 title claims abstract description 23
- 208000020431 spinal cord injury Diseases 0.000 title claims abstract description 18
- 230000003993 interaction Effects 0.000 title claims abstract description 15
- 230000008569 process Effects 0.000 claims abstract description 9
- 230000008859 change Effects 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 28
- 238000012360 testing method Methods 0.000 claims description 24
- 210000004556 brain Anatomy 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 12
- 238000012706 support-vector machine Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000004424 eye movement Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000003183 myoelectrical effect Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 5
- 210000003141 lower extremity Anatomy 0.000 description 8
- 210000003128 head Anatomy 0.000 description 5
- 230000004064 dysfunction Effects 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 210000005036 nerve Anatomy 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 230000006378 damage Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 210000003414 extremity Anatomy 0.000 description 3
- 230000036544 posture Effects 0.000 description 3
- 206010033799 Paralysis Diseases 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000004761 scalp Anatomy 0.000 description 2
- 210000000278 spinal cord Anatomy 0.000 description 2
- 229910021607 Silver chloride Inorganic materials 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000003925 brain function Effects 0.000 description 1
- 238000009207 exercise therapy Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 230000007659 motor function Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000000554 physical therapy Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000007634 remodeling Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000037152 sensory function Effects 0.000 description 1
- HKZLPVFGJNLROG-UHFFFAOYSA-M silver monochloride Chemical compound [Cl-].[Ag+] HKZLPVFGJNLROG-UHFFFAOYSA-M 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
Classifications
-
- 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
- A61B5/24—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]
- A61B5/372—Analysis of electroencephalograms
- A61B5/374—Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
-
- 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]
- A61B5/377—Electroencephalography [EEG] using evoked responses
- A61B5/378—Visual stimuli
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Psychology (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Epidemiology (AREA)
- Human Computer Interaction (AREA)
- Neurosurgery (AREA)
- Neurology (AREA)
- Dermatology (AREA)
- Primary Health Care (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention provides a brain-computer interaction method based on complete spinal cord injury patient training evaluation. The brain-computer interaction method based on complete spinal cord injury patient training evaluation comprises the following steps: collecting multichannel electroencephalogram signals through multichannel electroencephalogram collecting equipment; carrying out data processing on the multichannel electroencephalogram signals to obtain electroencephalogram characteristics; constructing a rehabilitation training model based on the electroencephalogram characteristics; combining the rehabilitation training model with a preset virtual scene task to obtain a task execution result, wherein the virtual scene generates corresponding scene change in the process of executing the preset virtual scene task; and evaluating the task execution result to obtain a task evaluation result. The brain-computer interaction method based on complete spinal cord injury patient training evaluation improves the applicability of rehabilitation training and ensures the training effect of rehabilitation training.
Description
Technical Field
The invention relates to the field of biomedical engineering, in particular to a brain-computer interaction method based on training evaluation of patients suffering from complete spinal cord injury.
Background
Complete spinal cord injury is a damage to the structure and function of the spinal cord of T9-T12 caused by various reasons, and the sensory and motor functions below the injury level completely disappear. The most prominent treatment for full spinal cord transection injury is rehabilitation. The rehabilitation therapy can keep undamaged functions of the patient, and promote the recovery of the nerve functions of the patient through limb function exercise and physiotherapy.
In the prior art, there are methods for realizing rehabilitation training based on motor imagery, visual stimulation, electroencephalogram signal analysis and the like, but most of users are patients with upper limb movement dysfunction and certain movement capacity, and the patients with lower limb movement dysfunction and the nerve structures and functions of the patients are not considered.
Therefore, the rehabilitation training method in the prior art has poor applicability and training effect.
Disclosure of Invention
In view of the above, the present invention provides a brain-computer interaction method based on training evaluation of patients suffering from complete spinal cord injury, so as to solve the above-mentioned problems.
According to a first aspect of the present invention, there is provided a brain-computer interaction method based on training evaluation of patients with complete spinal cord injury, comprising: collecting multichannel electroencephalogram signals through multichannel electroencephalogram collecting equipment; carrying out data processing on the multichannel electroencephalogram signals to obtain electroencephalogram characteristics; constructing a rehabilitation training model based on the electroencephalogram characteristics; combining the rehabilitation training model with a preset virtual scene task to obtain a task execution result, wherein the virtual scene generates corresponding scene change in the process of executing the preset virtual scene task; and evaluating the task execution result to obtain a task evaluation result.
In another implementation of the present invention, a multi-channel electroencephalogram signal is acquired by a multi-channel electroencephalogram acquisition apparatus, including: the multichannel electroencephalogram acquisition equipment is an EEG acquisition head cap; and acquiring multichannel electroencephalogram signals through the EEG acquisition head cap.
In another implementation manner of the present invention, data processing is performed on a multi-channel electroencephalogram signal to obtain an electroencephalogram characteristic, including: preprocessing the multichannel electroencephalogram signals, wherein the preprocessing step at least comprises at least one of removing baseline drift, removing myoelectric interference, removing eye movement interference and removing 50Hz power frequency interference; performing multi-frequency band decomposition based on the preprocessed multi-channel brain electrical signals to obtain multi-channel brain electrical signals with multiple frequency bands; and extracting characteristics of the multi-channel electroencephalogram signals in a plurality of frequency bands to obtain the characteristics of the electroencephalogram ERD/ERS.
In another implementation manner of the present invention, multi-band decomposition is performed based on the preprocessed multi-channel electroencephalogram signals to obtain multi-channel electroencephalogram signals with multiple frequency bands, including: based on the preprocessed electroencephalogram signals, a multichannel electroencephalogram signal time sequence is constructed, wherein the multichannel electroencephalogram signal time sequence is as follows:
X＝{x 1 ,x 2 ,…,x i ,…,x N }；
and carrying out multi-frequency band decomposition on the multi-channel electroencephalogram signal time sequence by a frequency band decomposition method to obtain multi-channel electroencephalogram signals in a plurality of frequency bands.
In another implementation manner of the present invention, a multi-band decomposition method is used to perform multi-band decomposition on a multi-band electroencephalogram signal time sequence to obtain multi-band multi-channel electroencephalogram signals, including: performing multi-frequency band decomposition on the multi-channel electroencephalogram signal time sequence based on a Gabor wavelet decomposition analysis method to obtain multi-channel electroencephalogram signals with multiple frequency bands, wherein the multi-channel electroencephalogram signals comprise correlated synchronization and desynchronization of EEG events with strong correlation, and the frequency band change range is 3-35Hz; the calculation formula of the Gabor wavelet decomposition analysis method is as follows:
X f ＝h(f,t)*x(t)≡∫h(u)x(t+u)duX f(i,j)
wherein ,Xf The amplitude characteristic of the time series representing the frequency f at the time point t is set to nHz, the frequency resolution is set, and a plurality of frequency band signals of the center frequencies f=1n, 2n, … Hz are extracted respectively, and h (f, t) is a Gabor function, specifically:
wherein ,ω0 Is a dimensionless constant, k 1 For normalizing the coefficients, the center frequency ω=ω 0 A, a is a scale factor, t is the current time, t 0 For the initial time, j is an imaginary unit.
In another implementation manner of the present invention, feature extraction is performed on multi-channel electroencephalogram signals of a plurality of frequency bands to obtain electroencephalogram ERD/ERS features, including: the inter-trial variance IV is calculated for each band EEG for each channel:
wherein ,Xf(i,j) Representing the amplitude of the jth sample point of the EEG test run i at a particular frequency band f after Gabor filtering,the average value of the j sampling points of all the trials is the average value, and N is the experimental trial number; calculating based on the variance IV between the trials to obtain the ERD/ERS data characteristics of each brain; and combining the ERD/ERS data characteristics of each brain electricity to obtain an ERD/ERS data characteristic vector group.
In another implementation of the invention, the electroencephalogram ERD/ERS data features are expressed as:
wherein ,r represents the average energy in the reference period, n 0 Represents a reference time start point, and k represents a reference time length.
In another implementation of the invention, the set of electroencephalogram ERD/ERS data feature vectors is represented as:
F＝[s 1 ,s 2 ,…,s N ]。
in another implementation of the present invention, constructing a rehabilitation training model based on an electroencephalogram feature includes: dividing the EEG ERD/ERS characteristic vector group F into a training set F T And test set F P The method comprises the steps of carrying out a first treatment on the surface of the Training set F based on Support Vector Machine (SVM) T And test set F P Learning is carried out, and a rehabilitation training model is obtained.
In another implementation of the present invention, the brain-computer interaction method based on training evaluation of patients with complete spinal cord injury further comprises: based on training set F T Testing is carried out, and a test result is obtained; and analyzing the test result to determine the validity of the model.
In the brain-computer interaction method based on complete spinal cord injury patient training evaluation, a rehabilitation training model is constructed based on the brain-computer characteristics of a user, so that the training model has pertinence, a rehabilitation training model and a preset virtual scene task are combined, and VR equipment gives visual feedback information to the user, so that a patient with lower limb movement dysfunction, especially a patient with lower limb complete paralysis, can perform rehabilitation training, the user experience is increased, the brain nerve plasticity of the user is further improved, the applicability of the rehabilitation training is improved, the task execution result is evaluated, the task evaluation result is obtained, and the training effect of the rehabilitation training is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described, and advantages and benefits in the solutions will become apparent to those skilled in the art from reading the detailed description of the embodiments below. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. In the drawings:
FIG. 1 is a flow chart of the steps of a brain-computer interaction method based on training evaluation of patients with complete spinal cord injury according to one embodiment of the invention.
Fig. 2 is a block diagram of a brain-computer interaction system based on training evaluation of patients with complete spinal cord injury according to another embodiment of the invention.
FIG. 3 is a schematic illustration of an experimental paradigm interface according to another embodiment of the present invention.
Fig. 4 is a schematic diagram of a system application scenario according to another embodiment of the present invention.
Fig. 5 is a virtual scene task guidance diagram according to another embodiment of the invention.
Detailed Description
In order to make the technical solutions in the embodiments of the present invention better understood by those skilled in the art, the technical solutions in the embodiments of the present invention will be clearly and specifically described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the present invention, shall fall within the scope of protection of the embodiments of the present invention.
Fig. 1 is a flowchart of steps of a brain-computer interaction method based on training evaluation of a patient with complete spinal cord injury according to an embodiment of the present invention, as shown in fig. 1, the embodiment mainly includes the following steps:
s101, acquiring multichannel brain electrical signals through multichannel brain electrical acquisition equipment.
By way of example, the electroencephalogram signals of the user are acquired through the multichannel electroencephalogram acquisition device, the electroencephalogram signals are generated when the user uses the motor imagery rehabilitation training paradigm presentation system, arrows pointing to the left direction or the right direction appear on a display screen in the process of using the motor imagery rehabilitation training paradigm presentation system, as shown in fig. 3, the user imagines the movement of a left limb or a right limb according to the pointing of the arrows, the appearance sequence of the two types of arrows in an experiment is random, but the number of the occurrence sequences of the two types of arrows is the same, and at least 30 times of electroencephalogram signal acquisition is carried out on the user to form a data set.
S102, carrying out data processing on the multichannel brain electrical signals to obtain brain electrical characteristics.
Illustratively, motor imagery or motor performance can activate the cortex of the brain's contralateral sensorimotor region and promote this region metabolism and increased blood flow, resulting in a decrease or blockage in the amplitude of oscillations of the alpha (8-12 Hz) and beta (13-30 Hz) rhythms of the brain, an electrophysiological phenomenon known as event-related desynchronization (ERD/ERS). And performing multi-frequency band decomposition on the multi-channel electroencephalogram signals subjected to the interference removal pretreatment by adopting a frequency band decomposition method to obtain multi-channel electroencephalogram signals in a plurality of frequency bands, and performing feature extraction on the obtained multi-channel electroencephalogram signals in the plurality of frequency bands to obtain electroencephalogram ERD/ERS features.
S103, constructing a rehabilitation training model based on the electroencephalogram characteristics.
Illustratively, a rehabilitation training model is constructed based on the electroencephalogram characteristics, wherein the rehabilitation training model is a training model based on CSP (common space mode) and SVM (classification mode), and has individual adaptability.
S104, combining the rehabilitation training model with a preset virtual scene task to obtain a task execution result, wherein the virtual scene generates corresponding scene change in the process of executing the preset virtual scene task.
Illustratively, the rehabilitation training model is combined with the virtual scene task, so that when a patient with complete spinal cord injury imagines the movement of the lower limb, the virtual scene changes correspondingly, and visual feedback information is given to the patient through the VR device, as shown in FIG. 5.
It should be appreciated that for patients with unskilled use of the motor imagery rehabilitation training paradigm presentation system, the accuracy of the rehabilitation training model may be low, requiring model training to be re-performed before lower limb rehabilitation training and evaluation. The duration of a single experiment for rehabilitation training and evaluation of lower limbs needs to be up to 6 minutes, and a proper amount of rest time is needed to be added between experiments in consideration of fatigue generated by long-time experiments of patients.
S105, evaluating the task execution result to obtain a task evaluation result.
In the brain-computer interaction method based on complete spinal cord injury patient training evaluation, a rehabilitation training model is constructed based on the brain-computer characteristics of a user, so that the training model has pertinence, a rehabilitation training model and a preset virtual scene task are combined, and VR equipment gives visual feedback information to the user, so that a patient with lower limb movement dysfunction, especially a patient with lower limb complete paralysis, can perform rehabilitation training, the user experience is increased, the brain nerve plasticity of the user is further improved, the applicability of the rehabilitation training is improved, the task execution result is evaluated, the task evaluation result is obtained, and the training effect of the rehabilitation training is ensured.
In another implementation of the present invention, a multi-channel electroencephalogram signal is acquired by a multi-channel electroencephalogram acquisition apparatus, including: the multichannel electroencephalogram acquisition equipment is an EEG acquisition head cap; and acquiring multichannel electroencephalogram signals through the EEG acquisition head cap.
Illustratively, the multi-channel electroencephalogram acquisition device is an EEG acquisition headgear that a user wears on his head for motor imagery training tasks. The EEG collecting electrode adopts the scalp electroencephalogram collecting electrode made of standard Ag/AgCl materials according to the international standard 10-20 system, wherein the positions (F3, FZ, F4, FC3, FC4, C5, C3, CZ, C4, C6, CP3, CP4, P3, PZ and P4) of the leads of the electrodes are 15, and the scalp and the electrodes adopt special brain dielectric to ensure good conductivity, and the impedance is controlled below 20kΩ in the collecting process.
It should be understood that, as shown in fig. 2, the motor imagery rehabilitation training pattern presentation system includes an electroencephalogram acquisition cap, a display, VR equipment and the like, and as shown in fig. 4, in the system application scenario, during the process of using the motor imagery rehabilitation training pattern presentation system, a patient sits on a backrest wheelchair, is 75-90 cm away from the computer display, and both hands keep comfortable postures. Improves the enthusiasm of rehabilitation training of patients with complete spinal cord injury and achieves the effect of brain function remodeling.
In another implementation manner of the present invention, data processing is performed on a multi-channel electroencephalogram signal to obtain an electroencephalogram characteristic, including: preprocessing the multichannel electroencephalogram signals, wherein the preprocessing step at least comprises at least one of removing baseline drift, removing myoelectric interference, removing eye movement interference and removing 50Hz power frequency interference; performing multi-frequency band decomposition based on the preprocessed multi-channel brain electrical signals to obtain multi-channel brain electrical signals with multiple frequency bands; and extracting characteristics of the multi-channel electroencephalogram signals in a plurality of frequency bands to obtain the characteristics of the electroencephalogram ERD/ERS.
Illustratively, the disturbance removal pre-processing includes one or any combination of baseline wander removal, myoelectric disturbance removal, eye movement disturbance removal, and 50Hz mains frequency disturbance removal.
Preferably, the interference removal preprocessing can be performed by using matlab software.
In another implementation manner of the present invention, multi-band decomposition is performed based on the preprocessed multi-channel electroencephalogram signals to obtain multi-channel electroencephalogram signals with multiple frequency bands, including: based on the preprocessed electroencephalogram signals, a multichannel electroencephalogram signal time sequence is constructed, wherein the multichannel electroencephalogram signal time sequence is as follows:
X＝{x 1 ,x 2 ,…,x i ,…,x N }；
and carrying out multi-frequency band decomposition on the multi-channel electroencephalogram signal time sequence by a frequency band decomposition method to obtain multi-channel electroencephalogram signals in a plurality of frequency bands.
In another implementation manner of the present invention, a multi-band decomposition method is used to perform multi-band decomposition on a multi-band electroencephalogram signal time sequence to obtain multi-band multi-channel electroencephalogram signals, including: performing multi-frequency band decomposition on the multi-channel electroencephalogram signal time sequence based on a Gabor wavelet decomposition analysis method to obtain multi-channel electroencephalogram signals with multiple frequency bands, wherein the multi-channel electroencephalogram signals comprise correlated synchronization and desynchronization of EEG events with strong correlation, and the frequency band change range is 3-35Hz; the calculation formula of the Gabor wavelet decomposition analysis method is as follows:
X f ＝h(f,t)*x(t)≡∫h(u)x(t+u)duX f(i,j)
wherein ,Xf The amplitude characteristic of the time series representing the frequency f at the time point t is set to nHz, the frequency resolution is set, and a plurality of frequency band signals of the center frequencies f=1n, 2n, … Hz are extracted respectively, and h (f, t) is a Gabor function, specifically:
wherein ,ω0 Is a dimensionless constant, k 1 For normalizing the coefficients, the center frequency ω=ω 0 A, a is a scale factor, t is the current time, t 0 For the initial time, j is an imaginary unit.
Illustratively, gabor wavelet decomposition is carried out on the multichannel electroencephalogram signal time sequence to obtain a 1Hz sub-band, wherein the sub-band comprises relevant synchronization and desynchronization of EEG events with strong correlation, and the frequency range is 3-35Hz.
In another implementation manner of the present invention, feature extraction is performed on multi-channel electroencephalogram signals of a plurality of frequency bands to obtain electroencephalogram ERD/ERS features, including: the inter-trial variance IV is calculated for each band EEG for each channel:
wherein ,Xf(i,j) Representing the amplitude of the jth sample point of the EEG test run i at a particular frequency band f after Gabor filtering,the average value of the j sampling points of all the trials is the average value, and N is the experimental trial number; calculating based on the variance IV between the trials to obtain the ERD/ERS data characteristics of each brain; and combining the ERD/ERS data characteristics of each brain electricity to obtain an ERD/ERS data characteristic vector group.
Illustratively, as shown in fig. 2, ERD/ERS average quantization is performed on the obtained multi-channel electroencephalogram signals in multiple frequency bands, so as to obtain electroencephalogram ERD/ERS characteristics.
It should be appreciated that the ERD/ERS is quantified based on an algorithm of the inter-trial variances (intertrial variance, IV).
The inter-trial variance IV is calculated for each band EEG for each channel:
wherein ,Xf(i,j) Representing the amplitude of the jth sample point of the EEG test run i at a particular frequency band f after Gabor filtering,the average value of all the jth sampling points is obtained, and N is the experimental test times.
And calculating to obtain the EEG ERD/ERS data characteristics according to the obtained inter-test variance IV.
In another implementation of the invention, the electroencephalogram ERD/ERS data features are expressed as:
wherein ,r represents the average energy over a reference period of time，n 0 Represents a reference time start point, and k represents a reference time length.
Illustratively, the ERD/ERS quantized values are expressed by the percentage of variance change relative to each sampling point over a reference time, and are the characteristics of the electroencephalogram data:
wherein R represents the average energy in the reference period, n 0 Represents a reference time start point, and k represents a reference time length.
In another implementation of the invention, the set of electroencephalogram ERD/ERS data feature vectors is represented as:
F＝[s 1 ,s 2 ,…,s N ]。
illustratively, the calculation process of the electroencephalogram features is repeated, ERD/ERS data features of N test electroencephalogram sequences are obtained, and feature vector groups are formed:
F＝[s 1 ,s 2 ,…,s N ]。
in another implementation of the present invention, constructing a rehabilitation training model based on an electroencephalogram feature includes: dividing the EEG ERD/ERS characteristic vector group F into a training set F T And test set F P The method comprises the steps of carrying out a first treatment on the surface of the Training set F based on Support Vector Machine (SVM) T And test set F P Learning is carried out, and a rehabilitation training model is obtained.
Illustratively, the acquired electroencephalogram ERD/ERS feature vector group F is divided into a training set F T And test set F P And learning the acquired electroencephalogram ERD/ERS feature vector group based on a Support Vector Machine (SVM) to realize effective two classification of left and right of the action mode.
It is understood that the constructed rehabilitation training model based on the SVM is combined with the virtual scene task, so that the user can conduct two classifications of left and right tasks of motor imagery, guide the user to conduct rehabilitation training, evaluate the result of the rehabilitation training and accurately and effectively identify the two classification motor imagery tasks.
In another implementation of the present invention, the method further includes: testing based on the training set FT to obtain a test result; and analyzing the test result to determine the validity of the model.
Thus, specific embodiments of the present invention have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may be advantageous.
It should be noted that all directional indicators (such as up, down, left, right, and rear … …) in the embodiments of the present invention are merely used to explain the relative positional relationship, movement conditions, etc. between the components in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indicator is correspondingly changed.
In the description of the present invention, the terms "first," "second," and the like are used merely for convenience in describing the various components or names, and are not to be construed as indicating or implying a sequential relationship, relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
It should be noted that, although specific embodiments of the present invention have been described in detail with reference to the accompanying drawings, the present invention should not be construed as limiting the scope of the present invention. Various modifications and variations which may be made by those skilled in the art without the creative effort fall within the protection scope of the present invention within the scope described in the claims.
Examples of embodiments of the present invention are intended to briefly illustrate technical features of embodiments of the present invention so that those skilled in the art may intuitively understand the technical features of the embodiments of the present invention, and are not meant to be undue limitations of the embodiments of the present invention.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A brain-computer interaction method based on training evaluation of patients with complete spinal cord injury, comprising:
collecting multichannel electroencephalogram signals through multichannel electroencephalogram collecting equipment;
performing data processing on the multichannel electroencephalogram signals to obtain electroencephalogram characteristics;
constructing a rehabilitation training model based on the electroencephalogram characteristics;
combining the rehabilitation training model with a preset virtual scene task to obtain a task execution result, wherein a virtual scene generates a corresponding scene change in the process of executing the preset virtual scene task;
and evaluating the task execution result to obtain a task evaluation result.
2. The method of claim 1, wherein the acquiring the multichannel electroencephalogram signals by the multichannel electroencephalogram acquisition apparatus comprises:
the multichannel electroencephalogram acquisition equipment is an EEG acquisition headgear;
and acquiring multichannel EEG signals through the EEG acquisition head cap.
3. The method of claim 1, wherein the performing data processing on the multichannel electroencephalogram signal to obtain an electroencephalogram feature includes:
preprocessing the multichannel electroencephalogram signals, wherein the preprocessing step at least comprises at least one of removing baseline drift, removing myoelectric interference, removing eye movement interference and removing 50Hz power frequency interference;
performing multi-frequency band decomposition based on the preprocessed multi-channel brain electrical signals to obtain multi-channel brain electrical signals with multiple frequency bands;
and extracting characteristics of the multi-channel electroencephalogram signals in the multiple frequency bands to obtain electroencephalogram ERD/ERS characteristics.
4. The method according to claim 3, wherein the performing multi-band decomposition based on the preprocessed multi-channel electroencephalogram signals to obtain multi-channel electroencephalogram signals with multiple frequency bands includes:
based on the preprocessed electroencephalogram signals, a multichannel electroencephalogram signal time sequence is constructed, wherein the multichannel electroencephalogram signal time sequence is as follows:
X＝{x 1 ,x 2 ,…,x i ,…,x N }；
and carrying out multi-frequency band decomposition on the multi-channel electroencephalogram signal time sequence by a frequency band decomposition method to obtain multi-channel electroencephalogram signals with multiple frequency bands.
5. The method according to claim 4, wherein the multi-band decomposing the multi-band electroencephalogram signal time sequence by the band decomposing method to obtain multi-band electroencephalogram signals comprises:
performing multi-frequency band decomposition on the multi-channel electroencephalogram signal time sequence based on a Gabor wavelet decomposition analysis method to obtain multi-channel electroencephalogram signals with multiple frequency bands, wherein the multi-channel electroencephalogram signals comprise relevant synchronization and desynchronization of EEG events with strong correlation, and the frequency band change range is 3-35Hz;
the calculation formula of the Gabor wavelet decomposition analysis method is as follows:
X f ＝h(f,t)*x(t)≡∫h(u)x(t+u)duX f(i,j)
wherein ,Xf The amplitude characteristic of the time series representing the frequency f at the time point t is set to nHz, the frequency resolution is set, and a plurality of frequency band signals of the center frequencies f=1n, 2n, … Hz are extracted respectively, and h (f, t) is a Gabor function, specifically:
wherein ,ω0 Is a dimensionless constant, k 1 For normalizing the coefficients, the center frequency ω=ω 0 A, a is a scale factor, t is the current time, t 0 For the initial time, j is an imaginary unit.
6. The method according to claim 2, wherein the feature extraction of the multichannel electroencephalogram signals in the plurality of frequency bands to obtain electroencephalogram ERD/ERS features includes:
the inter-trial variance IV is calculated for each band EEG for each channel:
wherein ,Xf(i,j) Representing the amplitude of the jth sample point of the EEG test run i at a particular frequency band f after Gabor filtering,the average value of the j sampling points of all the trials is the average value, and N is the experimental trial number;
calculating based on the inter-test variance IV to obtain the ERD/ERS data characteristics of each brain;
and combining the electroencephalogram ERD/ERS data characteristics to obtain an electroencephalogram ERD/ERS data characteristic vector group.
7. The method of claim 6, wherein the electroencephalogram ERD/ERS data features are represented as:
wherein ,r represents the average energy in the reference period, n 0 Represents a reference time start point, and k represents a reference time length.
8. The method of claim 6, wherein the set of electroencephalogram ERD/ERS data feature vectors is represented as:
F＝[s 1 ,s 2 ,…,s N ]。
9. the method of claim 8, wherein the constructing a rehabilitation training model based on the electroencephalogram features comprises:
dividing the EEG ERD/ERS characteristic vector group F into a training set F T And test set F P ；
The training set F is based on a Support Vector Machine (SVM) T And test set F P Learning is carried out, and a rehabilitation training model is obtained.
10. The method as recited in claim 9, further comprising:
based on the training set F T Testing is carried out, and a test result is obtained;
and analyzing the test result to determine the validity of the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310981320.9A CN116994697A (en) | 2023-08-04 | 2023-08-04 | Brain-computer interaction method based on complete spinal cord injury patient training evaluation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310981320.9A CN116994697A (en) | 2023-08-04 | 2023-08-04 | Brain-computer interaction method based on complete spinal cord injury patient training evaluation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116994697A true CN116994697A (en) | 2023-11-03 |
Family
ID=88522983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310981320.9A Pending CN116994697A (en) | 2023-08-04 | 2023-08-04 | Brain-computer interaction method based on complete spinal cord injury patient training evaluation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116994697A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040010203A1 (en) * | 2002-07-12 | 2004-01-15 | Bionova Technologies Inc. | Method and apparatus for the estimation of anesthetic depth using wavelet analysis of the electroencephalogram |
| CN106419909A (en) * | 2016-09-12 | 2017-02-22 | 西安电子科技大学 | Multi-class motion imagination EEG signal classification method based on characteristic recombination and wavelet transformation |
| CN107562191A (en) * | 2017-08-03 | 2018-01-09 | 天津大学 | The online brain-machine interface method of fine Imaginary Movement based on composite character |
| CN111938991A (en) * | 2020-07-21 | 2020-11-17 | 燕山大学 | Hand rehabilitation training device and training method in double active control modes |
| CN115482907A (en) * | 2022-10-26 | 2022-12-16 | 上海中医药大学 | Active rehabilitation system combining electroencephalogram and myoelectricity and rehabilitation training method |
| CN116035597A (en) * | 2023-02-03 | 2023-05-02 | 首都医科大学宣武医院 | Electroencephalogram signal coupling analysis method, device and system |
-
2023
- 2023-08-04 CN CN202310981320.9A patent/CN116994697A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040010203A1 (en) * | 2002-07-12 | 2004-01-15 | Bionova Technologies Inc. | Method and apparatus for the estimation of anesthetic depth using wavelet analysis of the electroencephalogram |
| CN106419909A (en) * | 2016-09-12 | 2017-02-22 | 西安电子科技大学 | Multi-class motion imagination EEG signal classification method based on characteristic recombination and wavelet transformation |
| CN107562191A (en) * | 2017-08-03 | 2018-01-09 | 天津大学 | The online brain-machine interface method of fine Imaginary Movement based on composite character |
| CN111938991A (en) * | 2020-07-21 | 2020-11-17 | 燕山大学 | Hand rehabilitation training device and training method in double active control modes |
| CN115482907A (en) * | 2022-10-26 | 2022-12-16 | 上海中医药大学 | Active rehabilitation system combining electroencephalogram and myoelectricity and rehabilitation training method |
| CN116035597A (en) * | 2023-02-03 | 2023-05-02 | 首都医科大学宣武医院 | Electroencephalogram signal coupling analysis method, device and system |
Non-Patent Citations (1)
| Title |
|---|
| 王磊磊: "基于混合脑机接口的虚拟康复系统设计", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》, no. 3, 15 March 2020 (2020-03-15), pages 9 - 22 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | A novel EEMD-CCA approach to removing muscle artifacts for pervasive EEG | |
| CN110367974B (en) | Brain and muscle electric coupling research method based on variational modal decomposition-transfer entropy | |
| CN111227830B (en) | Electroencephalogram and electromyographic coupling analysis method based on complex improved multi-scale transfer entropy | |
| Dakin et al. | Rectification is required to extract oscillatory envelope modulation from surface electromyographic signals | |
| Aydemir et al. | Classifying various EMG and EOG artifacts in EEG signals | |
| CN112617863A (en) | Hybrid online computer-computer interface method for identifying lateral direction of left and right foot movement intention | |
| Feng et al. | Feature extraction algorithm based on csp and wavelet packet for motor imagery eeg signals | |
| Karakullukcu et al. | Detection of movement intention in eeg-based brain-computer interfaces using fourier-based synchrosqueezing transform | |
| Wang et al. | Incorporating EEG and EMG patterns to evaluate BCI-based long-term motor training | |
| Liu et al. | Detection of lower-limb movement intention from EEG signals | |
| CN116994697A (en) | Brain-computer interaction method based on complete spinal cord injury patient training evaluation | |
| CN114052750B (en) | Brain muscle information transfer rule extraction method based on standard template myoelectricity decomposition | |
| Cmiel et al. | EEG biofeedback | |
| Planelles et al. | First steps in the development of an EEG-based system to detect intention of gait initiation | |
| CN215017698U (en) | Rehabilitation training motion simulation visualization system | |
| CN111584033B (en) | Brain-controlled intelligent rehabilitation system movement intention recognition system based on multilayer ordered network | |
| Qi | Algorithms benchmarking for removing EOG artifacts in brain computer interface | |
| Li et al. | Single trial EEG classification of lower-limb movements using improved regularized common spatial pattern | |
| CN113807402A (en) | System for inhibiting MIs-triggering of MI-BCI system and training and testing method thereof | |
| Liu et al. | Performance evaluation of walking imagery training based on virtual environment in brain-computer interfaces | |
| Koctúrová et al. | Comparison of Dry Electrodes for Mobile EEG System. | |
| CN112006682A (en) | Left-right hand motor imagery electroencephalogram signal classification method based on multi-channel frequency characteristic customization | |
| Mulyanto et al. | EEG-based motion task for healthy subjects using time domain feature extraction: A preliminary study for finding parameter for stroke rehabilitation monitoring | |
| Qi | Evaluating algorithms of removing EOG artifacts with experimental data in brain computer interface | |
| Amri et al. | Feature Extraction on Brain Wave Activities in Rapid Serial Visual Presentation Stimulus |
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 |