CN106805968A - Electroencephalogram relaxation degree identification method and device - Google Patents
Electroencephalogram relaxation degree identification method and device Download PDFInfo
- Publication number
- CN106805968A CN106805968A CN201611184937.4A CN201611184937A CN106805968A CN 106805968 A CN106805968 A CN 106805968A CN 201611184937 A CN201611184937 A CN 201611184937A CN 106805968 A CN106805968 A CN 106805968A
- Authority
- CN
- China
- Prior art keywords
- brain
- signal
- electric array
- array signal
- eeg signals
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 210000004556 brain Anatomy 0.000 claims abstract description 237
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 230000005611 electricity Effects 0.000 claims description 62
- 238000000354 decomposition reaction Methods 0.000 claims description 17
- 238000009826 distribution Methods 0.000 claims description 12
- 238000005315 distribution function Methods 0.000 claims description 12
- 238000002592 echocardiography Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 7
- 238000005096 rolling process Methods 0.000 claims description 7
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 2
- 230000003321 amplification Effects 0.000 abstract 1
- 238000003199 nucleic acid amplification method Methods 0.000 abstract 1
- 239000010410 layer Substances 0.000 description 18
- 230000006870 function Effects 0.000 description 10
- 230000000694 effects Effects 0.000 description 7
- 239000000284 extract Substances 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 230000015654 memory Effects 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 210000003205 muscle Anatomy 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000000844 transformation Methods 0.000 description 3
- 230000001755 vocal effect Effects 0.000 description 3
- 208000020401 Depressive disease Diseases 0.000 description 2
- 208000013738 Sleep Initiation and Maintenance disease Diseases 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 206010022437 insomnia Diseases 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 206010003830 Automatism Diseases 0.000 description 1
- 206010019233 Headaches Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 238000003723 Smelting Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000013542 behavioral therapy Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 231100000869 headache Toxicity 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000000147 hypnotic effect Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000003534 oscillatory effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 230000003860 sleep quality Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 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
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- 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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Psychiatry (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Psychology (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Social Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses an electroencephalogram lofting degree identification method, which comprises the following steps: carrying out weighted moving average calculation on the electroencephalogram signals of the received first electroencephalogram sequence signals at all times to obtain second electroencephalogram sequence signals; taking the second brain electrical sequence signal as an original signal, taking an artifact sequence signal acquired synchronously with the second brain electrical sequence signal as a reference signal, and carrying out self-adaptive filtering on the second brain electrical sequence signal to obtain a third brain electrical sequence signal; extracting each brain wave from the third brain wave sequence signal; calculating the characteristics of each brain wave to obtain the characteristic quantity of the third brain wave sequence signal; and carrying out classification and identification according to the characteristic quantity to obtain the electroencephalogram amplification degree. The invention also provides an electroencephalogram release recognition device, which can realize rapid and accurate electroencephalogram release recognition.
Description
Technical field
The present invention relates to relaxation treatment field, more particularly to a kind of electricity allowance recognition methods of brain and device.
Background technology
Relaxation training is that one of most wide technology is used in behavior therapy, is set up and sends out on the basis of Experiment of Psychology
Consulting and treatment method that exhibition is got up, it mitigates climacteric in treatment Anxiety depression, nervous headache, insomnia, high blood pressure
The aspect such as syndrome and transformation bad behavior pattern achieves preferable curative effect.
Existing relaxation training mainly has recording to instruct, verbal assistance and biofeedback are instructed.Wherein, recording guidance method
Ossify, be not changed in, it is impossible to the state change content according to trainee；Verbal assistance then requires the object requirement to verbal assistance
It is very high, and limited by time, place；Biofeedback instructs that based on brain electricity feedback, the advantage of first two mode can be combined,
Thus receive significant attention.
Carry out biofeedback and instruct to need the allowance of identifying user, and recognize allowance firstly the need of from the original of user
The brain wave (including Delta, Theta, Alpha, Beta, Gamma ripple) of each frequency range is extracted in EEG signals, and calculates each
The feature of brain wave.But under actual conditions, original EEG signals are extremely faint, and it is highly susceptible to extraneous power frequency, magnetic field and disturbs
The interference of the factors such as dynamic, low-frequency d, tongue electricity artefact, perspiration artefact, eye electricity artefact, pulse artefact and Muscle artifacts, causes
The brain wave of extraction includes more noise, and then can not obtain and be calculated accurate feature.Wherein, Hz noise is relatively solid
It is fixed, removal is easier to, although low-frequency d can be filtered by wave filter, in view of the band attenuation that wave filter brings, directly
Low-frequency d information is accurately filtered by wave filter can produce influence to EEG signals；And in artefact signal, with eye electricity artefact and
Muscle artifacts are most difficult to remove, and this is higher mainly due to its signal amplitude, are several times even tens times of EEG signals, and
Its frequency has aliasing with original EEG signals in frequency domain.
The content of the invention
Regarding to the issue above, it is an object of the invention to provide a kind of electricity allowance recognition methods of brain and device, can remove
Low-frequency information and artefact signal in original EEG signals, obtain pure brain electric array signal, so as to realize accurate brain electricity
Allowance is recognized.
The invention provides a kind of electricity allowance recognition methods of brain, comprise the following steps：
EEG signals to each moment of the first brain electric array signal for receiving are weighted rolling average calculating, obtain
Second brain electric array signal；
With the second brain electric array signal as primary signal, obtained with the second brain electric array signal synchronous collection
Artefact sequence signal be reference signal, adaptive-filtering is carried out to the second brain electric array signal, obtain tritencepehalon electricity sequence
Column signal；
Each brain wave is extracted from the tritencepehalon electric array signal；
The feature of each brain wave is calculated, the characteristic quantity of the tritencepehalon electric array signal is obtained；
Classification and Identification is carried out according to the characteristic quantity, brain electricity allowance is obtained.
Preferably, the EEG signals at described pair of each moment of the first brain electric array signal of reception are weighted mobile flat
Calculate, obtain the second brain electric array signal and specifically include：
Based on the EEG signals at j-th current moment, obtain in the first brain electric array signal positioned at the (j- (N-1)/
2) the individual moment to the N number of EEG signals of (j+ (N-1)/2) between the individual moment energy；Wherein, N is default influence number, and N
It is odd number, j is more than the integer of (N+1)/2；
Weights are distributed according to the energy that default weights distribution function is the N number of EEG signals for obtaining；Wherein, N number of brain electricity
The weights sum of the energy of signal is 1；
Energy to N number of EEG signals is weighted summation according to the weights of distribution, obtains j-th new moment
The energy of EEG signals；
After being weighted summation to the energy of the EEG signals at each moment of the first brain electric array signal successively, root
According to the energy of the new EEG signals at all moment, the second brain electric array signal is generated.
Preferably, the EEG signals at described pair of each moment of the first brain electric array signal of reception are weighted mobile flat
Calculate, obtain the second brain electric array signal and specifically include：
Based on the EEG signals at j-th current moment, obtain in the first brain electric array signal positioned at (j-N) it is individual when
Carve to the energy of the N number of EEG signals between (j-1) individual moment；Wherein, N is default influence number, and j is the integer more than N；
Weights are distributed according to the energy that default weights distribution function is the N number of EEG signals for obtaining；Wherein, N number of brain electricity
The weights sum of the energy of signal is 1；
Energy to N number of EEG signals is weighted summation according to the weights of distribution, obtains j-th new moment
The energy of EEG signals；
After being weighted summation to the energy of the EEG signals at each moment of the first brain electric array signal successively, root
According to all moment new EEG signals energy, generate the second brain electric array signal.
Preferably, the weights distribution function is normal distyribution function.
Preferably, the sef-adapting filter optimizes through function chain neural network.
Preferably, it is described to extract each brain wave from the tritencepehalon electric array signal and specifically include：
Sample frequency according to Shannon-nyquist sampling principle and the tritencepehalon electric array signal carries out frequency range point
Layer, is calculated every layer of frequency range；
Every layer of frequency range and the frequency range of each brain wave in being layered according to the frequency range, it is determined that electric with each brain
The number of plies needed for the corresponding wavelet decomposition of ripple and reconstruct；
The number of plies according to needed for the wavelet decomposition corresponding with each brain wave and the morther wavelet being pre-selected carry out letter
Number decompose, obtain it is corresponding with each brain wave by frequency range divide multi-layer corrugated；
It is corresponding with each brain wave that the corresponding coefficient of the number of plies according to needed for the wavelet reconstruction and decomposition are obtained
The multi-layer corrugated, reconstruct obtains each brain wave.
Preferably, the morther wavelet be coif3 small echos, and the coif3 small echos centre frequency-bandwidth ratio through Wavelet Entropy
Adaptive optimization.
Preferably, the feature for calculating each brain wave, obtains the characteristic quantity of the tritencepehalon electric array signal, specifically
Including：
Calculate the energy of each brain wave；
According to the energy of each brain wave and the frequency range of each brain wave, the centre frequency of each brain wave is calculated,
Obtain the characteristic quantity of the tritencepehalon electric array signal.
Preferably, the feature of each brain wave is being calculated, after the characteristic quantity of the acquisition tritencepehalon electric array signal,
Classification and Identification is carried out according to the characteristic quantity, before obtaining brain electricity allowance, is also included：
Feature selecting is carried out to the characteristic quantity based on PCA.
The present invention also provides a kind of brain electricity allowance identifying device, including：
Weighted moving average unit, the EEG signals for each moment of the first brain electric array signal to receiving are carried out
Weighted moving average is calculated, and obtains the second brain electric array signal；
Adaptive-filtering unit, for the second brain electric array signal as primary signal, with electric with second brain
The artefact sequence signal that sequence signal synchronous acquisition is obtained is reference signal, and self adaptation is carried out to the second brain electric array signal
Filtering, obtains tritencepehalon electric array signal；
Brain wave extraction unit, for extracting each brain wave from the tritencepehalon electric array signal；
Feature amount calculation unit, the feature for calculating each brain wave obtains the spy of the tritencepehalon electric array signal
The amount of levying；
Brain electricity allowance recognition unit, for carrying out Classification and Identification according to the characteristic quantity, obtains brain electricity allowance.
Brain electricity allowance recognition methods and device that the present invention is provided, the brain is removed by using the method for weighted moving average
Low-frequency d information in electric array signal, it is ensured that will not be to head sequence signal sheet while low-frequency d information is removed
Body produces any interference and distorted signals occurs；The artefact signal in brain electric array signal is filtered using adaptive-filtering simultaneously,
Solve the problems, such as that the artefact signal in EEG signals is difficult to remove.The present invention can extract pure brain electricity from EEG signals
Sequence signal, and then ensure the accuracy of the brain wave and feature being calculated based on brain wave extracted, so as to ensure identification
The accuracy of the brain electricity allowance for obtaining, for biological feedback guidance provides data basis and foundation.
Brief description of the drawings
In order to illustrate more clearly of technical scheme, the accompanying drawing to be used needed for implementation method will be made below
Simply introduce, it should be apparent that, drawings in the following description are only some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of brain electricity allowance recognition methods provided in an embodiment of the present invention.
Fig. 2 be it is provided in an embodiment of the present invention original EEG signals cut into slices obtain the first brain electric array signal and show
It is intended to.
Fig. 3 is the principle that rolling average calculating is weighted to the first brain electric array signal provided in an embodiment of the present invention
Figure.
Fig. 4 is the fundamental diagram of sef-adapting filter provided in an embodiment of the present invention.
Fig. 5 is the schematic diagram cut into slices to tritencepehalon electric array signal provided in an embodiment of the present invention.
Fig. 6 is the graph of a relation of Shannon Wavelet Entropies provided in an embodiment of the present invention and centre frequency-bandwidth ratio.
Fig. 7 is the structural representation of brain electricity allowance identifying device provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Fig. 1 is referred to, a kind of brain electricity allowance recognition methods is the embodiment of the invention provides, it may include following steps：
S101, the EEG signals to each moment of the first brain electric array signal for receiving are weighted rolling average meter
Calculate, obtain the second brain electric array signal.
In embodiments of the present invention, original brain electric array signal can be gathered by electrode for encephalograms and obtained, wherein, usually,
The sample frequency of the original EEG signals is 500HZ, in order to reduce the amount of calculation of follow-up wavelet decomposition, need to carry out drop and adopt
Sample, it is such as down-sampled to 100HZ, as shown in Figure 2.
In embodiments of the present invention, (such as a few hours more long duration of the original EEG signals of electrode for encephalograms collection
It is even longer), it is therefore desirable to original EEG signals are cut into slices, to obtain the first brain electric array signal of suitable length, one
As, the time span of each section is 30 seconds (one section of each dotted line wire frame representation in Fig. 2), i.e., every section described first
The time span of brain electric array signal is 30 seconds.
In embodiments of the present invention, can also LPF high be carried out to the first brain electric array signal.Wherein, brain wave
Target frequency bands between 0.1-60Hz, therefore the first brain electric array signal can be filtered using FIR low pass filter
Brain electric information higher than 100Hz, suppresses high-frequency noise；The first brain electric array is filtered using FIR high-pass filters simultaneously to believe
Less than 0.05Hz brains electricity breath in number, to suppress the baseline drift of below 0.05Hz.
In embodiments of the present invention, the first brain electric array signal generally comprises low-frequency d information, and these low frequencies are straight
Stream information has that frequency range is Chong Die with each brain wave, therefore in order to ensure the degree of accuracy that brain wave is extracted, need to remove these low frequencies
DC information.
In embodiments of the present invention, the low-frequency d information can be removed using the method for weighted moving average.Wherein, use
The method of weighted moving average is predicted can smooth out influence of the fluctuation to predicting the outcome suddenly, therefore can play the removal low frequency
The effect of DC information.
Specifically, in one embodiment, step S101 includes：
S1011, based on the EEG signals at j-th current moment, being located in acquisition the first brain electric array signal
(j- (N-1)/2) the individual moment to the N number of EEG signals of (j+ (N-1)/2) between the individual moment energy；Wherein, N is default
Influence number, and N be odd number, j is more than the integer of (N+1)/2.
For example, it is assumed that the moment of EEG signals x (j) currently to be predicted is the 10th moment (i.e. j=10), influence number N
It is 5, then EEG signals influential on the EEG signals currently to be predicted are the 8th to the 12nd EEG signals at moment, i.e. x
(8)~x (12).Now, this 5 energy of the EEG signals at moment are first obtained.
S1012, weights are distributed according to the energy that default weights distribution function is the N number of EEG signals for obtaining；Wherein, N
The weights sum of the energy of individual EEG signals is 1.
In embodiments of the present invention, it is preferable that the weights distribution function is normal distyribution function, such as can be：Wherein, w (i) is i-th weights of the EEG signals at moment, and t (i) is i-th brain electricity at moment
The time of signal, τ represents the local message amount for needing to amplify.It is not that jth point is attached as shown in figure 3, being distributed using this weights
Nearly institute is a little all considered as the same proportion, but according to distance (time difference) imparting one proportion, realizes local message amount
Amplify, reduce the influence to current point away from information too far away.
It should be noted that after the weights of the energy of each EEG signals are calculated, in addition it is also necessary to be normalized, protect
The weights sum for demonstrate,proving the energy of N number of EEG signals is 1.
S1013, the energy to N number of EEG signals is weighted summation according to the weights of distribution, obtains new j-th
The energy of the EEG signals at moment.
I.e.：
S1014, is weighted to the energy of the EEG signals at each moment of the first brain electric array signal asks successively
With rear, the energy of the new EEG signals according to all moment, the second brain electric array signal is generated.
In the embodiment of the present invention, when carrying out low-frequency d to EEG signals, while consider before its moment with when
The influence of EEG signals after quarter to itself, therefore, while DC information is removed, moreover it is possible to play the electricity of the brain after avoiding the moment
Signal does not have the effect of influence on the signal at current time, it is impossible to embody the problem of the change of signal.
In another embodiment, step S101 is specifically included：
S1015, based on the EEG signals at j-th current moment, being located in acquisition the first brain electric array signal
(j-N) individual moment to the N number of EEG signals between (j-1) individual moment energy；Wherein, N is default influence number, and j is
Integer more than N.
For example, it is assumed that the moment of EEG signals x (j) currently to be corrected is the 10th moment (i.e. j=10), influence number N
It is 5, then EEG signals influential on the EEG signals currently to be corrected are the 5th to the 9th EEG signals at moment, i.e. x
(5)~x (9).Now, this 5 energy of the EEG signals at moment are first obtained.
S1016, weights are distributed according to the energy that default weights distribution function is the N number of EEG signals for obtaining；Wherein, N
The weights sum of the energy of individual EEG signals is 1.
S1017, the energy to N number of EEG signals is weighted summation according to the weights of distribution, obtains new j-th
The energy of the EEG signals at moment.
S1018, is weighted to the energy of the EEG signals at each moment of the first brain electric array signal asks successively
With rear, the energy of the new EEG signals according to all moment, the second brain electric array signal is generated.
In the embodiment of the present invention, when carrying out low-frequency d to EEG signals, the EEG signals before its moment are only accounted for
Influence to itself, thus it is guaranteed that signal is smooth.
S102, with the second brain electric array signal as primary signal, with the second brain electric array signal synchronously adopt
It is reference signal to integrate the artefact sequence signal for obtaining, and the second brain electric array signal is filtered using sef-adapting filter
Ripple, obtains tritencepehalon electric array signal.
In embodiments of the present invention, it is contemplated that also include various artefact sequence signals in the second brain electric array signal, such as
Tongue electricity artefact, perspiration artefact, eye electricity artefact, the interference such as pulse artefact and Muscle artifacts.The amplitude of these artefact signals is higher,
It is several times even tens times of EEG signals, and has aliasing in frequency domain with EEG signals, it is therefore desirable to is removed.
Specifically, the present invention can filter these artefact signals using adaptive-filtering.
First, sef-adapting filter is constructed, wherein the theory diagram of sef-adapting filter is as shown in figure 4, it is by original letter
Number (i.e. described second brain electric array signal) and the reference signal (artefact obtained with the second brain electric array signal synchronous collection
Sequence signal, such as tongue electricity artefact, perspiration artefact, eye electricity artefact, any one in pulse artefact and Muscle artifacts) two it is defeated
Enter composition.During filtering, after reference signal is through adaptive-filtering, it is compared with primary signal, obtains required brain electric array signal
Estimate signal (more pure brain electric array signal), wherein, wave filter constantly self readjusts its weights so that
Target error reaches minimum, and the brain electric array signal for finally giving is also purer.
It should be noted that in embodiments of the present invention, in order to strengthen the Nonlinear Processing ability of sef-adapting filter, carrying
Height filtering effect, the embodiment of the present invention also by function chain neural network (Function Link Neural Network,
FLNN) it is applied in above-mentioned sef-adapting filter, the principle of FLNN is that original input is tieed up using one group of orthogonal basis function
Number extension, linear dimensions is expanded to non-linear.Wherein, FLNN is made up of function expansion and single-layer perceptron two parts, function
The orthogonal basis of chain neural network uses Chebyshev's orthogonal polynomial, as shown in Equation 1.The basic function T of the FLNN such as institutes of formula 2
Show, network is exported as shown in Equation 3, and the nonlinear extensions to being input into are realized by FLNN, be more conducive to description the second brain electricity
The nonlinear characteristic of sequence signal, so that filter effect is more preferably.
It should be noted that in embodiments of the present invention, as shown in figure 5, after above-mentioned pretreatment is carried out, in addition it is also necessary to right
The tritencepehalon electric array signal of 30s carries out sectioning again, and the moving window of section is 6s, and this is section general in the world
Length, being capable of preferably signal Analysis.
S103, each brain wave is extracted from the tritencepehalon electric array signal.
Specifically, it may include following steps：
S1031, the sample frequency according to Shannon-nyquist sampling principle and the tritencepehalon electric array signal enters line frequency
Section layering, is calculated every layer of frequency range.
According to Shannon-nyquist sampling principle, if the sample frequency of the tritencepehalon electric array signal is fs, target is frequently
Section is f1-f2 (Hz), and the number of plies decomposed with wavelet transformation is N, from Nyquist law：
F1=(fs/2)/N1 (4)
F2=(fs/2)/N2 (5)
N>N1(N1>N2) (6)
The number of plies for needing the small echo of reconstruct is N2~N1 layers.
S1032, every layer of frequency range and the frequency range of each brain wave in being layered according to the frequency range, it is determined that with it is every
The number of plies needed for the corresponding wavelet decomposition of individual brain wave and reconstruct.
In embodiments of the present invention, the brain wave is including Delta ripples that frequency range is 0.5~3Hz, frequency range
The Theta ripples of 3~7Hz, frequency range are the Alpha ripples of 8~13Hz, Beta ripples, the frequency model that frequency range is 14~17Hz
Enclose the Gamma ripples for 34~50Hz.
Wherein, Delta ripples：Deep sleep E.E.G state：
It is deep sleep, automatism when the brain frequency of people is in Delta ripples.The sleep quality quality of people
There is very direct relation with Delta ripples.The sleep of Delta ripples is a kind of very deep sleep state, if when tossing about in bed
The wavy states of approximate Delta oneself are called out, insomnia just can be soon broken away from and be entered deep sleep.
Theta ripples：Depth is loosened, the subconsciousness state of no pressure
When the brain frequency of people is in Theta ripples, the consciousness of people is interrupted, and body is deep to be loosened, for extraneous letter
Breath present height by imply state, i.e., by hypnosis.Theta ripples are for triggering the sides such as deep memory, reinforcing long-term memory
Help greatly, so Theta ripples are referred to as " leading to the gate of memory and study ".
Alpha ripples：Study and the optimal E.E.G state thought deeply
When the brain frequency of people is in Alpha ripples, the Consciousness of people, but body loosens, and it provides meaning
Know and subconscious " bridge ".In this state, body and mind energy charge is minimum, and the energy that relative brain is obtained is higher, fortune
Work will quicker, smooth, acumen.Alpha ripples are considered as the optimal E.E.G state of people's study and thinking.
Beta ripples：E.E.G state when anxiety, pressure, brainfag
When people regain consciousness, most of the time brain frequency is in the wavy states of Beta.With the increase of Beta ripples, body is gradually
In tense situation, thus vivo immuning system ability is reduced, now the energy ezpenditure aggravation of people, easily tired, if insufficient
Rest, easily piles up pressure.Appropriate Beta ripples are lifted to notice and the development of cognitive behavior has positive role.
In embodiments of the present invention, it is assumed that the pending electrocardiosignal has been down-sampled to 100Hz, then fs is 100Hz,
Signal highest frequency is 50Hz, understands that the corresponding frequency range of each layer is as follows according to formula (4), (5), (6)：
| Frequency range | Frequency range/Hz | Frequency range | Frequency range/Hz |
| A1 | 0~25 | D1 | 25~50 |
| A2 | 1~12.5 | D2 | 12.5~25 |
| A3 | 0~6.25 | D3 | 6.25~12.5 |
| A4 | 0~3.125 | D4 | 3.125~6.25 |
| A5 | 0~1.625 | D5 | 1.625~3.125 |
| A6 | 0~0.8125 | D6 | 0.8125~1.625 |
| A7 | 0~0.40625 | D7 | 0.40625~0.8125 |
| A8 | 0~0.203125 | D8 | 0.203125~0.40625 |
| A9 | 0~0.10156 | D9 | 0.10156~0.203125 |
By taking Delta ripples as an example, its band limits is 0.5~3Hz.Therefore, the approximation coefficient (D5/ from the 5th, 6,7 layers
D6/D7 reconstruction signal) is carried out.
S1033, the number of plies according to needed for the wavelet decomposition corresponding with each brain wave and the morther wavelet being pre-selected
Signal decomposition is carried out, the multi-layer corrugated divided by frequency range corresponding with each brain wave is obtained.
In embodiments of the present invention, the extraction effect of empirical tests, coifN small echos and dmey small echos is preferable, and preferably, with
When coif3 wavelet basis is as morther wavelet, with optimal extraction effect.Thus the embodiment of the present invention is made using coif3 wavelet basis
For morther wavelet carries out wavelet decomposition.It is, of course, understood that in other embodiments of the invention, can also choose others
Morther wavelet, such as db small echos, the present invention are not specifically limited.
It should be noted that when using coif3 wavelet basis as morther wavelet, centre frequency and bandwidth are that influence coif3 is small
Ripple time frequency resolution key factor.Changing centre frequency-bandwidth ratio can just change the time frequency resolution of coif3 wavelet transformations.
When centre frequency-bandwidth ratio is optimal, the time frequency resolution highest of coif3 wavelet transformations.
Specifically, optimization process is as follows：
First, shown in the morther wavelet expression formula such as formula (7) of coif3 small echos.Wherein, fcRepresent the feature of female ripple ψ (t) frequently
Rate, is also centre frequency, σtIt is the standard deviation of Gaussian window, usual value is 1, σfIt is bandwidth, usual σf=1/2 π σt.Analysis
The morther wavelet of coif3 small echos understands that the speed of wavelet shapes oscillatory extinction is by bandwidth σfDetermine, the frequency of oscillation of waveform is by center
Frequency fcDetermine.The frequency resolution (formula 8) and temporal resolution (formula 9) of coif3 small echos can be calculated according to formula 1,
Wherein, fsIt is sample frequency, fcCentered on frequency, σfIt is bandwidth, fiIt is signal analysis frequency.
Then, it is exactly with general using the core concept of Shannon entropy optimization coif3 wavelet transformations centre frequency-bandwidth ratio
Rate distribution series piTo represent wavelet coefficient, p is then calculatediValue, expression formula is as shown in Equation 10.Wherein, piIt is a probability
Distribution series, is converted to by wavelet coefficient, with uncertainty.Its conversion formula as shown in Equation 11, X (fi, it is t) small
Wave system number.Centre frequency-bandwidth ratio fc/σfAnd the curved line relation between Shannon Wavelet Entropies, as shown in Figure 6.In this experiment,
As centre frequency-bandwidth ratio fc/σfWhen=4.43, based on Shannon Wavelet Entropy probability optimal theoreticals, it is known that when Shannon small echos
When entropy reaches minimum value, coif3 wavelet center frequencies-bandwidth ratio parameter is optimal, corresponding mother wavelet be exactly with feature into
Divide the small echo for most matching.
S1034, the corresponding coefficient of the number of plies according to needed for the wavelet reconstruction and decomposition obtain with each brain wave
The correspondence multi-layer corrugated, reconstruct obtains each brain wave.
From step S1032, the number of plies needed for wavelet reconstruction is the 5th, 6,7 layers, now, you can according to the small echo
The multi-layer corrugated that the corresponding coefficient of the number of plies and decomposition needed for reconstruct are obtained carries out signal reconstruction, obtains Delta ripples.
In embodiments of the present invention, it is only necessary to which it is available weight that the frequency range according to each brain wave selects the corresponding number of plies
Structure obtains each brain wave, and the present invention will not be described here.
Furthermore, it is necessary to explanation, in other embodiments of the invention, can also be returned using Kalman filter or certainly
Model is returned to extract each brain wave from the tritencepehalon electric array signal, the present invention will not be described here.
S104, calculates the feature of each brain wave, obtains the characteristic quantity of the tritencepehalon electric array signal.
In embodiments of the present invention, after each brain wave is obtained, it is possible to calculate the feature of each brain wave, so that
Obtain the characteristic quantity of the tritencepehalon electric array signal.Wherein, the feature of the brain wave include its time domain feature, its
The feature of frequency domain and its phase space feature.
As a example by calculating the brain wave in the feature of frequency domain, specifically, S104 may include：
S1041, calculates the energy of each brain wave.
S1042, according to the energy of each brain wave and the frequency range of each brain wave, calculates the center of each brain wave
Frequency, obtains the characteristic quantity of the tritencepehalon electric array signal.
As shown in Equation 12, centre frequency FC：
Wherein, fHIt is the upper limiting frequency of brain wave corresponding with signal wave, fLIt is the lower frequency limit of corresponding brain wave, example
Upper limiting frequency such as Delta ripples is 3Hz, and lower frequency limit is 0.5Hz.
In embodiments of the present invention, the centre frequency (and feature of each brain wave) of each brain wave is calculated successively, just
Obtain characteristic quantity of the tritencepehalon electric array signal in domain space.
S105, Classification and Identification is carried out according to the characteristic quantity, obtains brain electricity allowance.
In embodiments of the present invention, the characteristic quantity is input to the good grader of training in advance (such as neural network model
Or in SVMs), it is possible to identify that it is classified, and brain electricity allowance is obtained according to classification.Obtaining brain electricity allowance
Afterwards, it is possible to relaxation treatment is carried out according to brain electricity allowance, such as according to brain electricity allowance can loosen the choosing of guiding content
Select, mark and play, can accurately choose be best suitable for user loosen guiding content, earphone of arranging in pairs or groups plays to user；Simultaneously
Modulated along with the guiding content broadcast sound volume that loosens based on allowance, help user to loosen body and mind, alleviate anxiety-depression, pottery
Smelting sentiment, the individual character weakness that improves, elimination mental behavior disorder, holding psychology and Body health.
Brain electricity allowance recognition methods provided in an embodiment of the present invention, by described using the removal of weighted moving average algorithm
Low-frequency d information in brain electric array signal, it is ensured that head sequence signal will not be produced while low-frequency d information is gone
Any influence of life；The artefact signal in brain electric array signal is filtered using sef-adapting filter simultaneously, artefact signal is solved difficult
With the problem for removing.The present invention can extract out pure brain electric array signal, and then ensure the brain wave that extracts and based on brain electricity
The accuracy of the feature that ripple is calculated, for biological feedback guidance provides data basis and foundation.
Preferably, after step s 104, before step S105, also include：
Feature selecting is carried out to the characteristic quantity based on PCA.
In embodiments of the present invention, sometimes the dimension of the characteristic quantity of brain electric array signal is more, and containing linear
Continuous item, this speed that can influence classification and the degree of accuracy, therefore consideration carries out feature selecting and dimensionality reduction.
In the preferred embodiment, feature selecting and dimensionality reduction can be realized using Principal Component Analysis Algorithm.
Specifically：
First, data normalization treatment is carried out to the characteristic quantity.
Wherein：
Wherein, X'ijIt is the characteristic quantity after standardization；Mj、SjRespectively represent a certain row of initial data arithmetic mean of instantaneous value and
Standard (inclined) is poor.
Then, covariance matrix is obtained according to the characteristic quantity after data normalization treatment.
Wherein, covariance matrix D=XTX, i.e.,：
Wherein：
Secondly, the characteristic root and characteristic vector corresponding with each characteristic root of the covariance matrix are calculated；Wherein, it is described
The quantity of characteristic root is p, and described p characteristic root is in magnitude order.
Wherein, DP=P λ (18)
When j-th characteristic value is only considered, there is DPj=Pjλj, that is, solve | D- λjI |=0.Each λ is solved successively, and is made
Its order arrangement, i.e. λ by size1≥λ2≥…,≥λp≥0；Then each characteristic value corresponding characteristic vector P, Jin Erte can be obtained
Levy equation solution completion.
Then, obtain in p described characteristic root, contribution rate sum is more than the preceding m characteristic root of predetermined threshold；Wherein,
The contribution rate of each characteristic root is equal to the value sum of the value divided by p whole characteristic roots of the characteristic root.
First calculate the contribution rate of single principal component and added up, the number m of principal component is determined according to contribution rate of accumulative total, from
And the principal component chosen required for determining.The computing formula of contribution rate such as formula (19) is described.Contribution rate of accumulative total is preceding m contribution
The accumulation of rate and, such as shown in formula (20).The threshold value Dmax is typically taken between 85%~95%.According in previous step
Knowable to characteristic root sequence, λ1≥λ2≥…,≥λp>=0, from front to back (being also from big to small) characteristic root is added up successively,
Work as contribution rate of accumulative totalDuring more than Dmax, stop calculating, now the number of the characteristic root λ of cumulative calculation is m, then only
M principal component before needing to choose.
Finally, according to characteristic vector corresponding with described preceding m characteristic root and the input sample space, obtain it is main into
Get sub-matrix.
Wherein, the principal component scores matrix
In this preferred embodiment, contributed not substantially and with linear correlation in eliminating characteristic quantity using PCA
Characteristic quantity, on the premise of the degree of accuracy for not influenceing Classification and Identification, the dimension of input feature vector amount is reduced, it is achieved thereby that more
Quickly identification.
Fig. 7 is referred to, the embodiment of the present invention also provides a kind of brain electricity allowance identifying device 100, including：
Weighted moving average unit 10, the EEG signals for each moment of the first brain electric array signal to receiving enter
Row weighted moving average is calculated, and obtains the second brain electric array signal.
Adaptive-filtering unit 20, for the second brain electric array signal as primary signal, with second brain
The artefact sequence signal that electric array signal synchronous collection is obtained is reference signal, the second brain electric array signal is carried out adaptive
Should filter, obtain tritencepehalon electric array signal.
Brain wave extraction unit 30, for extracting each brain wave from the tritencepehalon electric array signal.
Feature amount calculation unit 40, the feature for calculating each brain wave obtains the tritencepehalon electric array signal
Characteristic quantity.
Brain electricity allowance recognition unit 50, for carrying out Classification and Identification according to the characteristic quantity, obtains brain electricity allowance.
Preferably, in one embodiment, the weighted moving average unit 10, specifically includes：
First EEG signals acquisition module, for the EEG signals based on j-th current moment, obtains first brain
In electric array signal positioned at (j- (N-1)/2) the individual moment to the N number of EEG signals of (j+ (N-1)/2) between the individual moment
Energy；Wherein, N is default influence number, and N is odd number, and j is more than the integer of (N+1)/2；
First weights distribute module, for according to the energy that default weights distribution function is the N number of EEG signals for obtaining
Distribution weights；Wherein, the weights sum of the energy of N number of EEG signals is 1；
First weighted sum module, is weighted according to the weights of distribution for the energy to N number of EEG signals and asks
With, the energy of the EEG signals at j-th new moment is obtained, wherein, when successively to each of the first brain electric array signal
After the energy of the EEG signals at quarter is weighted summation, the energy of the new EEG signals according to all moment generates the second brain
Electric array signal.
Preferably, in another embodiment, the weighted moving average unit 10, specifically includes：
Second EEG signals acquisition module, based on the EEG signals at j-th current moment, obtains the first brain electricity sequence
The energy positioned at (j-N) individual moment to the N number of EEG signals between (j-1) individual moment in column signal；Wherein, N is pre-
If influence number, j is the integer more than N；
Second weights distribute module, according to the energy distribution that default weights distribution function is the N number of EEG signals for obtaining
Weights；Wherein, the weights sum of the energy of N number of EEG signals is 1；
Second weighted sum module, the energy to N number of EEG signals is weighted summation according to the weights of distribution, obtains
To the energy of the EEG signals at j-th new moment；Wherein, successively to the brain at each moment of the first brain electric array signal
The energy of electric signal be weighted summation after, according to all moment new EEG signals energy, generation the second brain electricity sequence
Column signal.
Preferably, the weights distribution function is normal distyribution function.
Preferably, the brain wave extraction unit 30 is specially：
Frequency hierarchical block, for adopting according to Shannon-nyquist sampling principle and the tritencepehalon electric array signal
Sample frequency carries out frequency range layering, is calculated every layer of frequency range；
Number of plies determining module, for frequency range and the frequency model of each brain wave according to every layer in frequency range layering
Enclose, it is determined that the number of plies needed for wavelet decomposition corresponding with each brain wave and reconstruct；
Decomposing module, for the number of plies needed for the basis wavelet decomposition corresponding with each brain wave and is pre-selected
Morther wavelet carries out signal decomposition, obtains the multi-layer corrugated divided by frequency range corresponding with each brain wave；
Reconstructed module, for basis coefficient corresponding with the number of plies needed for the wavelet reconstruction and decomposition obtain and each
The corresponding multi-layer corrugated of brain wave, reconstruct obtains each brain wave.
Preferably, the feature amount calculation unit 40 is specifically included：
Energy computation module, the energy for calculating each brain wave.
Centre frequency computing module, for the frequency range according to the energy of each brain wave and each brain wave, calculates
The centre frequency of each brain wave, obtains the characteristic quantity of the tritencepehalon electric array signal.
Preferably, also include：
Feature Selection unit, for carrying out feature selecting to the characteristic quantity based on PCA.
Brain electricity allowance identifying device 100 provided in an embodiment of the present invention, institute is removed by using the method for weighted moving average
State the low-frequency d information in brain electric array signal, it is ensured that will not be to head sequence signal while low-frequency d information is gone
Produce any influence；The artefact signal in brain electric array signal is filtered using sef-adapting filter simultaneously, artefact signal is solved
It is difficult to the problem for removing.The present invention can extract out pure brain electric array signal, and then ensure the brain wave that extracts and based on brain
The accuracy of the feature that electric wave is calculated, for biological feedback guidance provides data basis and foundation.
Above disclosed is only a kind of preferred embodiment of the invention, can not limit the power of the present invention with this certainly
Sharp scope, one of ordinary skill in the art will appreciate that realizing all or part of flow of above-described embodiment, and weighs according to the present invention
Profit requires made equivalent variations, still falls within the covered scope of invention.
One of ordinary skill in the art will appreciate that all or part of flow in realizing above-described embodiment method, can be
The hardware of correlation is instructed to complete by computer program, described program can be stored in a computer read/write memory medium
In, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Claims (10)
1. a kind of brain electricity allowance recognition methods, it is characterised in that comprise the following steps：
EEG signals to each moment of the first brain electric array signal for receiving are weighted rolling average calculating, obtain second
Brain electric array signal；
With the second brain electric array signal as primary signal, with the puppet obtained with the second brain electric array signal synchronous collection
Mark sequence signal is reference signal, and adaptive-filtering is carried out to the second brain electric array signal, obtains tritencepehalon electric array letter
Number；
Each brain wave is extracted from the tritencepehalon electric array signal；
The feature of each brain wave is calculated, the characteristic quantity of the tritencepehalon electric array signal is obtained；
Classification and Identification is carried out according to the characteristic quantity, brain electricity allowance is obtained.
2. brain electricity allowance recognition methods according to claim 1, it is characterised in that described pair of the first brain electricity sequence of reception
The EEG signals at each moment of column signal are weighted rolling average calculating, obtain the second brain electric array signal and specifically include：
It is individual positioned at (j- (N-1)/2) in the first brain electric array signal of acquisition based on the EEG signals at j-th current moment
Moment to the N number of EEG signals of (j+ (N-1)/2) between the individual moment energy；Wherein, N is default influence number, and N is strange
Number, j is more than the integer of (N+1)/2；
Weights are distributed according to the energy that default weights distribution function is the N number of EEG signals for obtaining；Wherein, N number of EEG signals
Energy weights sum be 1；
Energy to N number of EEG signals is weighted summation according to the weights of distribution, obtains the brain electricity at j-th new moment
The energy of signal；
After being weighted summation to the energy of the EEG signals at each moment of the first brain electric array signal successively, according to institute
There is the energy of the new EEG signals at moment, generate the second brain electric array signal.
3. brain electricity allowance recognition methods according to claim 1, it is characterised in that described pair of the first brain electricity sequence of reception
The EEG signals at each moment of column signal are weighted rolling average calculating, obtain the second brain electric array signal and specifically include：
Based on the EEG signals at j-th current moment, obtain in the first brain electric array signal positioned at (j-N) individual moment extremely
The energy of the N number of EEG signals between (j-1) individual moment；Wherein, N is default influence number, and j is the integer more than N；
Weights are distributed according to the energy that default weights distribution function is the N number of EEG signals for obtaining；Wherein, N number of EEG signals
Energy weights sum be 1；
Energy to N number of EEG signals is weighted summation according to the weights of distribution, obtains the brain electricity at j-th new moment
The energy of signal；
After being weighted summation to the energy of the EEG signals at each moment of the first brain electric array signal successively, according to
The energy of the new EEG signals at all moment, generates the second brain electric array signal.
4. the brain electricity allowance recognition methods according to Claims 2 or 3, it is characterised in that the weights distribution function is
Normal distyribution function.
5. brain electricity allowance recognition methods according to claim 1, it is characterised in that the sef-adapting filter is through function
Chain neural network optimizes.
6. brain electricity allowance recognition methods according to claim 1, it is characterised in that described from the tritencepehalon electric array
Each brain wave is extracted in signal to specifically include：
Sample frequency according to Shannon-nyquist sampling principle and the tritencepehalon electric array signal carries out frequency range layering, meter
Calculation obtains every layer of frequency range；
Every layer of frequency range and the frequency range of each brain wave in being layered according to the frequency range, it is determined that with each brain wave pair
The number of plies needed for the wavelet decomposition answered and reconstruct；
The number of plies according to needed for the wavelet decomposition corresponding with each brain wave and the morther wavelet being pre-selected carry out signal point
Solution, obtains the multi-layer corrugated divided by frequency range corresponding with each brain wave；
The corresponding coefficient of the number of plies according to needed for the wavelet reconstruction and decomposition obtain it is corresponding with each brain wave described in
Multi-layer corrugated, reconstruct obtains each brain wave.
7. brain electricity allowance recognition methods according to claim 6, it is characterised in that the morther wavelet is coif3 small echos,
And centre frequency-the bandwidth ratio of the coif3 small echos is through Wavelet Entropy adaptive optimization.
8. brain electricity allowance recognition methods according to claim 1, it is characterised in that the spy of each brain wave of calculating
Levy, obtain the characteristic quantity of the tritencepehalon electric array signal, specifically include：
Calculate the energy of each brain wave；
According to the energy of each brain wave and the frequency range of each brain wave, the centre frequency of each brain wave is calculated, obtained
The characteristic quantity of the tritencepehalon electric array signal.
9. brain electricity allowance recognition methods according to claim 1, it is characterised in that calculating the spy of each brain wave
Levy, obtain after the characteristic quantity of the tritencepehalon electric array signal, Classification and Identification is being carried out according to the characteristic quantity, obtain brain electricity
Before allowance, also include：
Feature selecting is carried out to the characteristic quantity based on PCA.
10. a kind of brain electricity allowance identifying device, it is characterised in that including：
Weighted moving average unit, the EEG signals for each moment of the first brain electric array signal to receiving are weighted
Rolling average is calculated, and obtains the second brain electric array signal；
Adaptive-filtering unit, for the second brain electric array signal as primary signal, with the second brain electric array
The artefact sequence signal that signal synchronous collection is obtained is reference signal, and self adaptation filter is carried out to the second brain electric array signal
Ripple, obtains tritencepehalon electric array signal；
Brain wave extraction unit, for extracting each brain wave from the tritencepehalon electric array signal；
Feature amount calculation unit, the feature for calculating each brain wave obtains the characteristic quantity of the tritencepehalon electric array signal；
Brain electricity allowance recognition unit, for carrying out Classification and Identification according to the characteristic quantity, obtains brain electricity allowance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611184937.4A CN106805968A (en) | 2016-12-20 | 2016-12-20 | Electroencephalogram relaxation degree identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611184937.4A CN106805968A (en) | 2016-12-20 | 2016-12-20 | Electroencephalogram relaxation degree identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106805968A true CN106805968A (en) | 2017-06-09 |
Family
ID=59109489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611184937.4A Pending CN106805968A (en) | 2016-12-20 | 2016-12-20 | Electroencephalogram relaxation degree identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106805968A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108968915A (en) * | 2018-06-12 | 2018-12-11 | 山东大学 | Sleep state classification method and system based on entropy feature and support vector machines |
| CN109820503A (en) * | 2019-04-10 | 2019-05-31 | 合肥工业大学 | The synchronous minimizing technology of a variety of artefacts in single channel EEG signals |
| CN113143291A (en) * | 2021-05-11 | 2021-07-23 | 燕山大学 | Electroencephalogram feature extraction method under rapid sequence visual presentation |
| CN113509188A (en) * | 2021-04-20 | 2021-10-19 | 天津大学 | Method and device for amplifying electroencephalogram signal, electronic device and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101690659A (en) * | 2009-09-29 | 2010-04-07 | 华东理工大学 | Brain wave analysis method |
| CN103301002A (en) * | 2013-06-20 | 2013-09-18 | 北京师范大学 | Central-peripheral nerve recovery training method and system based on optical brain imaging |
| CN103735262A (en) * | 2013-09-22 | 2014-04-23 | 杭州电子科技大学 | Dual-tree complex wavelet and common spatial pattern combined electroencephalogram characteristic extraction method |
| CN103845052A (en) * | 2014-02-20 | 2014-06-11 | 清华大学 | Human body faint early warning method based on acquired electroencephalogram signals |
| CN103919565A (en) * | 2014-05-05 | 2014-07-16 | 重庆大学 | Fatigue driving electroencephalogram signal feature extraction and identification method |
| CN103961091A (en) * | 2014-04-15 | 2014-08-06 | 杭州电子科技大学 | Motor imagery electroencephalogram signal characteristic extracting method based on dual-tree complex wavelet sample entropy |
| CN104095632A (en) * | 2013-04-07 | 2014-10-15 | 常州博睿康科技有限公司 | Method for processing electroencephalogram noise under nuclear magnetism |
| CN105105774A (en) * | 2015-10-09 | 2015-12-02 | 吉林大学 | Driver alertness monitoring method and system based on electroencephalogram information |
| CN105326499A (en) * | 2015-08-19 | 2016-02-17 | 兰州大学 | Portable electroencephalogram collection system |
| CN105361880A (en) * | 2015-11-30 | 2016-03-02 | 上海乃欣电子科技有限公司 | Muscle movement event recognition system and method |
| CN106175699A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Intelligent sleep assisting equipment based on hypnosis |
| CN106178222A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Intelligent sleep assisting method and system based on hypnosis |
-
2016
- 2016-12-20 CN CN201611184937.4A patent/CN106805968A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101690659A (en) * | 2009-09-29 | 2010-04-07 | 华东理工大学 | Brain wave analysis method |
| CN104095632A (en) * | 2013-04-07 | 2014-10-15 | 常州博睿康科技有限公司 | Method for processing electroencephalogram noise under nuclear magnetism |
| CN103301002A (en) * | 2013-06-20 | 2013-09-18 | 北京师范大学 | Central-peripheral nerve recovery training method and system based on optical brain imaging |
| CN103735262A (en) * | 2013-09-22 | 2014-04-23 | 杭州电子科技大学 | Dual-tree complex wavelet and common spatial pattern combined electroencephalogram characteristic extraction method |
| CN103845052A (en) * | 2014-02-20 | 2014-06-11 | 清华大学 | Human body faint early warning method based on acquired electroencephalogram signals |
| CN103961091A (en) * | 2014-04-15 | 2014-08-06 | 杭州电子科技大学 | Motor imagery electroencephalogram signal characteristic extracting method based on dual-tree complex wavelet sample entropy |
| CN103919565A (en) * | 2014-05-05 | 2014-07-16 | 重庆大学 | Fatigue driving electroencephalogram signal feature extraction and identification method |
| CN105326499A (en) * | 2015-08-19 | 2016-02-17 | 兰州大学 | Portable electroencephalogram collection system |
| CN105105774A (en) * | 2015-10-09 | 2015-12-02 | 吉林大学 | Driver alertness monitoring method and system based on electroencephalogram information |
| CN105361880A (en) * | 2015-11-30 | 2016-03-02 | 上海乃欣电子科技有限公司 | Muscle movement event recognition system and method |
| CN106175699A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Intelligent sleep assisting equipment based on hypnosis |
| CN106178222A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Intelligent sleep assisting method and system based on hypnosis |
Non-Patent Citations (2)
| Title |
|---|
| XUE Q,等: "Neural-network-based adaptive matched filtering for QRS detection", 《IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING》 * |
| 何冬若 主编: "第二篇 神经外科麻醉临床 第七章 脑功能监测 五 脑电定量分析", 《医学理论研究最新方法实践 全科医学 （上册）》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108968915A (en) * | 2018-06-12 | 2018-12-11 | 山东大学 | Sleep state classification method and system based on entropy feature and support vector machines |
| CN109820503A (en) * | 2019-04-10 | 2019-05-31 | 合肥工业大学 | The synchronous minimizing technology of a variety of artefacts in single channel EEG signals |
| CN113509188A (en) * | 2021-04-20 | 2021-10-19 | 天津大学 | Method and device for amplifying electroencephalogram signal, electronic device and storage medium |
| CN113509188B (en) * | 2021-04-20 | 2022-08-26 | 天津大学 | Method and device for amplifying electroencephalogram signal, electronic device and storage medium |
| CN113143291A (en) * | 2021-05-11 | 2021-07-23 | 燕山大学 | Electroencephalogram feature extraction method under rapid sequence visual presentation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khosla et al. | A comparative analysis of signal processing and classification methods for different applications based on EEG signals | |
| CN107961007A (en) | A kind of electroencephalogramrecognition recognition method of combination convolutional neural networks and long memory network in short-term | |
| Maity et al. | Multifractal detrended fluctuation analysis of alpha and theta EEG rhythms with musical stimuli | |
| Güler et al. | Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients | |
| CN109498041B (en) | Driver road rage state identification method based on electroencephalogram and pulse information | |
| CN103610461B (en) | Based on the EEG Signal Denoising method of dual density small echo neighborhood dependent thresholds process | |
| CN106805968A (en) | Electroencephalogram relaxation degree identification method and device | |
| CN101515200B (en) | Target selecting method based on transient visual evoked electroencephalogram | |
| CN105147248A (en) | Physiological information-based depressive disorder evaluation system and evaluation method thereof | |
| CN103584872A (en) | Psychological stress assessment method based on multi-physiological-parameter integration | |
| CN204931634U (en) | Based on the depression evaluating system of physiologic information | |
| CN106963370A (en) | Electroencephalogram relaxation degree identification method and device based on support vector machine | |
| CN104809434A (en) | Sleep staging method based on single-channel electroencephalogram signal ocular artifact removal | |
| CN106388818A (en) | Method and system for extracting characteristic information of sleep state monitoring model | |
| CN106963369A (en) | Electroencephalogram relaxation degree identification method and device based on neural network model | |
| CN112861625B (en) | Determination method for stacked denoising self-encoder model | |
| CN104571533B (en) | A kind of apparatus and method based on brain-computer interface technology | |
| Karthikeyan et al. | ECG signals based mental stress assessment using wavelet transform | |
| CN106580319A (en) | Electroencephalogram relaxation degree identification method and device based on wavelet transformation | |
| Rachman et al. | Alcoholism classification based on eeg data using independent component analysis (ica), wavelet de-noising and probabilistic neural network (pnn) | |
| CN106388778A (en) | Electroencephalogram signal preprocessing method and system in sleep state analysis | |
| CN106805969B (en) | Electroencephalogram relaxation degree identification method and device based on Kalman filtering and wavelet transformation | |
| CN106333652A (en) | Sleep state analysis method | |
| CN106648087A (en) | Feature EEG (electroencephalogram) processing method based on consciousness task | |
| CN106923825B (en) | Electroencephalogram relaxation degree identification method and device based on frequency domain and phase space |
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: 20170609 |