CN102613972A - Extraction method of characteristics of electroencephalogram signals based on motor imagery - Google Patents
Extraction method of characteristics of electroencephalogram signals based on motor imagery Download PDFInfo
- Publication number
- CN102613972A CN102613972A CN2012100850134A CN201210085013A CN102613972A CN 102613972 A CN102613972 A CN 102613972A CN 2012100850134 A CN2012100850134 A CN 2012100850134A CN 201210085013 A CN201210085013 A CN 201210085013A CN 102613972 A CN102613972 A CN 102613972A
- Authority
- CN
- China
- Prior art keywords
- eeg signals
- eeg
- classification
- filtering
- vector
- 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
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses an extraction method of characteristics of electroencephalogram signals based on motor imagery. The method is characterized in that electroencephlography event-related desynchronized encephalic region, frequency and time information based on motor imagery are fully considered, so that high classification accuracy is obtained. The specific experimental procedures comprise data collection, pretreatment, frequency domain filtering, time domain segment, spatial filtering, and characteristic selection and classification. The extraction method overcomes the defect that in a conventional method, individual differences of event-related desynchronized encephalic region and frequency are only considered, fully considers the individual differences of event-related desynchronized time segments, has the advantages of accuracy and high resolution, and can be applied to off-line analysis of electroencephalogram signals without empirical data based on motor imagery.
Description
Technical field
The invention belongs to areas of information technology, more a step relates to and in life science, uses brain-computer interface (Brain-Computer Interface, BCI) system is to when imagination motion EEG signals Feature Extraction method.The present invention utilizes the method for distilling to the Imaginary EEG signal characteristic to extract characteristic, and grader is classified to characteristic, realizes the differentiation of the one-sided finger motion imagination, finally reaches the control to external devices such as switch, mouse, wheelchairs.
Background technology
When preparing and carrying out the one-sided finger motion imagination; The corticocerebral functional connection of people changes; Thereby cause the EEG signals energy of its offside brain motor sensory area mu and the beta rhythm and pace of moving things to weaken, and the EEG signals energy of its homonymy brain motor sensory area mu and the beta rhythm and pace of moving things strengthen.The energy variation of specific brain regions district CF EEG signals during the one-sided finger motion of this imagination is called as the relevant phenomenon that desynchronizes of incident.This phenomenon is the most basic characteristic of finger Imaginary EEG signal about differentiation.Therefore, the direction that the experimenter moves and imagines is differentiated in the analysis of EEG signals when moving the imagination through the experimenter, thereby realizes the control of device to external world.The method of the relevant phenomenon characteristic that desynchronizes of extraction incident at present, has common space mode method and filtering bandwidth common space mode method.
The common space mode method is that EEG signals are transformed to another space in certain space through a mapping matrix; In this conversion process, make the variance of EEG signals EEG signals under a kind of imagination state that moves maximize; The variance of EEG signals minimizes under the another kind of motion imagination state; Thereby the extraction individual features is distinguished this two kinds of motion imagination states.Beijing University of Technology is at its patent application document (application number 200810056839.1 of " imagining the method for distilling of the brain electrical feature of one-sided limb motion "; Applying date 2008.01.25; Grant number CN 101219048B authorizes a day 2010.06.23) a kind of method for distilling of imagining the brain electrical feature of one-sided limb motion of middle proposition.(Common Spatial Pattern, CSP) method and linear discriminant analysis (FDA) combine this patented technology, have reduced the dimension of input vector, have improved the generalization of grader, have improved classification accuracy rate to a certain extent with the common space pattern.But the common space mode method must be to specific frequency band and specific period.When carrying out motion imagination task, because the existence of individual variation, relevant frequency band and the period of desynchronizing of generation incident is inconsistent.The deficiency that this patented technology exists is; Only according in the past empirical data, to 1-2 second behind the one-sided limb motion of the imagination, the EEG signals of 8-31Hz are analyzed; Do not consider the generation incident individual difference of relevant desynchronize phenomenon time-frequency band and period; The brain electrical feature that causes utilizing this patented technology to extract can not demonstrate fully the difference of experimenter's EEG signals when imagining one-sided limb motion, utilizes this characteristic to classify, and classification accuracy rate is not high.
Filtering bandwidth common space mode method is considered the difference of the relevant frequency band that desynchronizes of generation incident when each experimenter imagines one-sided finger motion, to Imaginary EEG signal signals in different frequency bands; Utilize the common space mode method to extract signal characteristic, and, finally utilize grader that signal is classified through the automatic selected characteristic of mutual information method; Ang KK; Chin ZY, Haihong Z, et al. " Filter bank common spatial pattern (FBCSP) in brain-computer interface; " IEEE International Joint Conference on Neural Networks, 2390-2397 (2008).This method is passed through frequency domain filtering, space filtering, and four steps of feature selection and classification realize the differentiation of Imaginary EEG signals.The filtering of frequency domain is to utilize band filter EEG signals to be divided into the signal of a plurality of sub-bands; Space filtering is to extract corresponding CSP characteristic to each sub-band signal; Feature selection utilizes the mutual information method to choose automatically can to distinguish the CSP characteristic of two kinds of motion imagination states; According to pigeon-hole principle the CSP characteristic of selecting is classified.Because this method is considered the individual variation of frequency band, classifying quality increases.But; The deficiency that this method exists is; Move when imagination, the individual difference of the relevant period of desynchronizing of generation incident still is not considered, and the brain electrical feature that utilizes this method to extract still can not demonstrate fully the difference of experimenter's EEG signals when imagining one-sided limb motion; Utilize this characteristic to classify, classification accuracy rate is not high.
In sum; Method for distilling for the Imaginary EEG signal characteristic; The relevant brain district of desynchronizing of generation incident and the individual difference of frequency when existing method has only considered to imagine one-sided finger motion, the generation incident individual difference of period of desynchronizing of being correlated with when not considering the one-sided finger motion of the imagination, the brain electrical feature that extracts still can not demonstrate fully the difference of experimenter's EEG signals when imagining one-sided limb motion; Utilize this characteristic to classify, classification accuracy rate is not high.
Summary of the invention
The objective of the invention is to overcome the deficiency of above-mentioned existing EEG feature extraction method, EEG signals Feature Extraction method when proposing a kind of motion imagination.The information of EEG signals generation relevant brain district, frequency and time of desynchronizing of incident when this method takes into full account the motion imagination is so that obtain higher classification accuracy rate.
The main thought that realizes the inventive method is: the multichannel brain signal of telecommunication of gathering is done pretreatment, through frequency domain filtering, it is divided into p frequency band again; Signal to each frequency band carries out the time domain segmentation, is about to signal and is divided into an isometric q signal segment; All signal segments to each frequency band carry out the common space mode computation that parameter is m, obtain the characteristic vector of 2m element, and all elements in each characteristic vector is arranged in order, and constitute the total characteristic vector of p * q * 2m element; In the total characteristic vector, select and the right-hand man move mutual information between imagination task classification maximum to constitute optimal characteristics by p * q * m element vectorial; Utilize the Naive Bayes Classification device, take cross validation method,, obtain classification accuracy rate the classification of optimal characteristics vector.
According to above-mentioned main thought, the concrete realization of the inventive method comprises the steps:
(1) image data
The electrode cap that the eeg signal acquisition system wears through the experimenter is gathered the EEG signals of imagining one-sided finger motion;
(2) pretreatment
2a) space filtering: adopt the method for common average reference, the EEG signals of each electrode collection on experimenter's electrode cap are deducted the average of the EEG signals that all electrodes gather, obtain the EEG signals behind the common average reference space filtering;
2b) baseline correction: the EEG signals behind the common average reference space filtering are deducted baseline, obtain the EEG signals after the baseline correction;
2c) bandpass filtering: utilize finite impulse response filter, the EEG signals after the baseline correction are carried out bandpass filtering, obtain the EEG signals that frequency band is 4-40Hz;
2d) intercept signal section: utilize EEGLAB software, the intercepting experimenter imagines the EEG signals section in the one-sided finger motion process in the EEG signals behind bandpass filtering, obtains pretreated EEG signals;
(3) frequency domain filtering
Utilize band filter to pretreated EEG signals filtering, the sub-band EEG signals that obtain a plurality of equibands, zero lap frequency band, are arranged in order;
(4) time domain segmentation
Each sub-band EEG signals is blocked on a time period the subsignal that be divided into a plurality of equal time sections, non-overlapping copies, is arranged in order;
(5) space filtering
Adopt the common space mode method, each subsignal after the time domain segmentation is carried out space filtering, obtain imagining the EEG signals characteristic vector of one-sided finger motion; Each element in all characteristic vectors is arranged in order, constitutes the total characteristic vector;
(6) feature selection
In the total characteristic vector, select and the maximum element of mutual information that the right-hand man moves between imagination task classification constitutes the optimal characteristics vector;
(7) classification
Utilize the Naive Bayes Classification device, take cross validation method,, obtain classification accuracy rate the classification of optimal characteristics vector.
The present invention compared with prior art has following advantage:
First; The information of EEG signals generation relevant brain district, frequency and time of desynchronizing of incident when the present invention imagines owing to having considered simultaneously to move; Overcome the limitation of the individual difference of only considering relevant brain district of desynchronizing of generation incident and frequency in the prior art, can improve the classification accuracy rate of EEG signals effectively.
Second; The information of EEG signals generation relevant brain district, frequency and time of desynchronizing of incident when the present invention imagines owing to having considered simultaneously to move; Overcome and in the eeg signal classification process, depended on the limitation that empirical data is chosen the EEG signals of special time period, can realize analysis the EEG signals of rawness data.
Description of drawings
Fig. 1 is a flow chart of the present invention;
Fig. 2 is screen prompt symbol sketch map in the image data step of the present invention;
Fig. 3 is the sketch map of image data step of the present invention;
Fig. 4 is the sketch map of the embodiment of the invention.
The specific embodiment
1 couple of the present invention does further description below in conjunction with accompanying drawing.
Step 1, image data
The electrode cap that the eeg signal acquisition system wears through the experimenter is gathered the EEG signals of imagining one-sided finger motion.EEG signals are obtained by the electrode cap that is worn on experimenter's head, and pass through eeg amplifier amplification and A/D converter conversion, and the input computer is with the stored in form and the demonstration of signal voltage amplitude.
The experimenter wears electrode cap, is sitting in the display of looking squarely on the chair apart from about its 1m.The sample frequency of eeg signal acquisition system is 250Hz, and test electrode is respectively C3, Cz, and C4, the fluctuation codomain of EEG signals is ± 100 μ V.With reference to Fig. 2; In image data step of the present invention, the prompt of display has three kinds, and prompting is prepared in the representative that indicates spider in the display; The display acceptance of the bid has arrow representative imagination left hand motion prompting left, arrow representative imagination right hand motion prompting to the right.
With reference to figure 3, prompting appearred preparing in screen when image data embodiment of the present invention began 0 second to 3 seconds, and of short duration prompt tone occurred at the 2nd second (1kHz, 70ms).Subsequently, motion prompting of imagination left hand or the prompting of the imagination right hand appear in screen, and continue 1.25 seconds.At the 4th second, the experimenter began to imagine corresponding finger motion, and continued 3 seconds.Had a rest 1.5 seconds to 2.5 seconds behind each embodiment.Left and right sides finger motion thought experiment each 120 times, random alignment on the order.
Step 2, pretreatment
Utilize the preprocessing function of EEGLAB software that the EEG signals of gathering are carried out pretreatment.
2a) space filtering: adopt the method for common average reference, the EEG signals of each electrode collection on experimenter's electrode cap are deducted the average of the EEG signals that all electrodes gather, obtain the EEG signals behind the common average reference space filtering;
2b) baseline correction: imagine that with the experimenter 200ms EEG signals before the one-sided finger motion are baseline.EEG signals behind the common average reference space filtering are deducted baseline, obtain the EEG signals after the baseline correction;
2c) bandpass filtering: utilize finite impulse response filter, the EEG signals after the baseline correction are carried out bandpass filtering, obtain the EEG signals that frequency band is 4-40Hz;
2d) intercept signal section: utilize EEGLAB software, the intercepting experimenter imagines the EEG signals section in the one-sided finger motion process in the EEG signals behind bandpass filtering, obtains pretreated EEG signals;
Step 3, frequency domain filtering
Utilize finite impulse response filter to pretreated EEG signals filtering, obtain band bandwidth and be 4Hz, zero lap frequency band, the 9 sub-frequency bands EEG signals that are arranged in order;
Step 4, the time domain segmentation
Each sub-band EEG signals is blocked on a time period the subsignal that be divided into 32 equal time sections, non-overlapping copies, is arranged in order;
Step 5, space filtering
Adopt the common space mode method, each subsignal in the 9*32=288 sub-signals that draws after the time domain segmentation is carried out the space filtering of parameter m=1, obtain the EEG signals characteristic vector of the one-sided finger motion of the imagination of 2m=2 element.All elements in 288 characteristic vectors is arranged in order, constitutes the total characteristic vector of 288*2=576 element.
If the common space mode method makes the signal of a certain task that maximum variance arranged, meanwhile the signal in another task has minimum variance.Its ultimate principle is the covariance matrix simultaneous diagonalization to two kinds of task signals, extracts the main component that is used to distinguish two kinds of task signals.
The first step is estimated the covariance matrix of two type games imaginations EEG signals;
The mean approximation of the EEG signals behind the space filtering is zero, and covariance can be estimated as:
Wherein, ∑
ωBe the covariance matrix of class ω, n
ωBe the number of the EEG signals of type of belonging to ω,
Be i the EEG signals behind type of the belonging to ω space filtering, i=1,2 ..., n
ω, l is imagination left hand motion task class, r is the transposition symbol for imagination right hand motion class, T.
In second step,, obtain its common generalized eigenvector with two covariance matrix simultaneous diagonalizations; With the mapping matrix of this generalized eigenvector as the common space pattern;
Calculate generalized eigenvector W:
∑
lW=(∑
l+∑
r)WΛ
Wherein, ∑
lAnd ∑
rBe respectively the covariance matrix of imagination right-hand man motion EEG signals, because two covariance matrixes are simultaneous diagonalizations, ∑ then
lAnd ∑
rEigenvalue and be 1; W is the mapping matrix of common space pattern, and its column vector is the wave filter of common space mode map; Λ is by ∑
lThe diagonal matrix that constitutes of generalized eigenvalue.
The 3rd step; M column vector of preceding m column vector and back of the mapping matrix of common space pattern constituted wherein 1≤m<n/2 of alternate mapping matrix
, and n is the number of the mapping matrix column vector of common space pattern;
The 4th goes on foot, and extracts the characteristic vector of the EEG signals of distinguishing the two type games imagination according to following formula
Wherein, f is the characteristic vector expression of two type games imagination EEG signals;
Log () is a logarithmic function;
The diagonal matrix of diag () for taking advantage of the square matrix diagonal element to constitute;
T represents the transposition symbol;
S is the subsignal after the time domain segmentation;
Tr () for take advantage of the square matrix diagonal element with.
Step 6, feature selection
, the total characteristic vector of 576 elements selects in being arranged and 288 maximum elements of mutual information that the right-hand man moves between imagination task classification constitute the optimal characteristics vector.
Step 7, tagsort
Utilize the Naive Bayes Classification device, take cross validation method,, obtain classification accuracy rate the classification of optimal characteristics vector.
The optimal characteristics vector of the EEG signals that selection step 6 obtains is as test data, and the optimal characteristics vector of all the other EEG signals is as training data; Bayes classifier utilizes training data to set up disaggregated model, and test data substitution disaggregated model is obtained class categories, and match stop classification and actual task classification are correctly classified or the result of misclassification; Successively with the optimal characteristics vector of each EEG signals as a test data, add up the classification results of all test datas, obtain classification accuracy rate.
Below in conjunction with Fig. 4, concrete implementation of the present invention done further describing.
Image data: the electrode cap that the eeg signal acquisition system wears through the experimenter, gather the EEG signals of imagining one-sided finger motion.
Pretreatment: utilize the preprocessing function of EEGLAB software that the EEG signals of gathering are carried out pretreatment.
Frequency domain filtering: utilize finite impulse response filter to pretreated EEG signals filtering, obtain frequency band and be respectively 4-8Hz, 8-12Hz; 12-16Hz, 16-20Hz, 20-24Hz; 24-28Hz, 28-32Hz, 32-36Hz; The bandwidth of 36-40Hz is 4Hz, zero lap frequency band, the 9 sub-frequency bands EEG signals that are arranged in order
The time domain segmentation: each sub-band EEG signals is blocked on a time period, be divided into 0-0.125s, 0.125-0.250s, 0.250-0.325s, 0.325-0.500s ..., 32 equal time sections of 3.875-4s, non-overlapping copies, the subsignal that is arranged in order;
Space filtering: adopt the common space mode method, each subsignal in the 9*32=288 sub-signals that draws after the time domain segmentation is carried out the space filtering of parameter m=1, obtain the EEG signals characteristic vector of the one-sided finger motion of the imagination of 2m=2 element.All elements in 288 characteristic vectors is arranged in order, constitutes the total characteristic vector of 288*2=576 element.
Feature selection: in the total characteristic vector of 576 elements is arranged, select and 288 maximum elements of mutual information that the right-hand man moves between imagination task classification constitute the optimal characteristics vector.
Classification: utilize the Naive Bayes Classification device, take cross validation method,, obtain classification accuracy rate to the classification of optimal characteristics vector.
Claims (6)
1. the method for distilling of Imaginary EEG signal characteristic comprises:
(1) image data
The electrode cap that the eeg signal acquisition system wears through the experimenter is gathered the EEG signals of imagining one-sided finger motion;
(2) pretreatment
2a) space filtering: adopt the method for common average reference, the EEG signals of each electrode collection on experimenter's electrode cap are deducted the average of the EEG signals that all electrodes gather, obtain the EEG signals behind the common average reference space filtering;
2b) baseline correction: the EEG signals behind the common average reference space filtering are deducted baseline, obtain the EEG signals after the baseline correction;
2c) bandpass filtering: utilize finite impulse response filter, the EEG signals after the baseline correction are carried out bandpass filtering, obtain the EEG signals that frequency band is 4-40Hz;
2d) intercept signal section: utilize EEGLAB software, the intercepting experimenter imagines the EEG signals section in the one-sided finger motion process in the EEG signals behind bandpass filtering, obtains pretreated EEG signals;
(3) frequency domain filtering
Utilize band filter to pretreated EEG signals filtering, the sub-band EEG signals that obtain a plurality of equibands, zero lap frequency band, are arranged in order;
(4) time domain segmentation
Each sub-band EEG signals is blocked on a time period the subsignal that be divided into a plurality of equal time sections, non-overlapping copies, is arranged in order;
(5) space filtering
Adopt the common space mode method, each subsignal after the time domain segmentation is carried out space filtering, obtain imagining the EEG signals characteristic vector of one-sided finger motion; Each element in all characteristic vectors is arranged in order, constitutes the total characteristic vector;
(6) feature selection
In the total characteristic vector, select and the maximum element of mutual information that the right-hand man moves between imagination task classification constitutes the optimal characteristics vector;
(7) classification
Utilize the Naive Bayes Classification device, take cross validation method,, obtain classification accuracy rate the classification of optimal characteristics vector.
2. the method for distilling of Imaginary EEG signal characteristic according to claim 1 is characterized in that: step 2b) described baseline is imagined one-sided finger motion 200ms EEG signals before for the experimenter.
3. the method for distilling of Imaginary EEG signal characteristic according to claim 1 is characterized in that: the band filter described in the step (3) is a finite impulse response filter.
4. the method for distilling of Imaginary EEG signal characteristic according to claim 1 is characterized in that: the common space mode method described in the step (5) is:
The first step is estimated the covariance matrix of two type games imaginations EEG signals;
In second step,, obtain its common generalized eigenvector with two covariance matrix simultaneous diagonalizations; With the mapping matrix of this generalized eigenvector as the common space pattern;
The 3rd step; M column vector of preceding m column vector and back of the mapping matrix of common space pattern constituted wherein 1≤m<n/2 of alternate mapping matrix
, and n is the number of the mapping matrix column vector of common space pattern;
The 4th goes on foot, and extracts the characteristic vector of the EEG signals of distinguishing the two type games imagination according to following formula
Wherein, f is the characteristic vector expression of two type games imagination EEG signals;
Log () is a logarithmic function;
The diagonal matrix of diag () for taking advantage of the square matrix diagonal element to constitute;
T represents the transposition symbol;
S is the subsignal after the time domain segmentation;
Tr () for take advantage of the square matrix diagonal element with.
5. the method for distilling of Imaginary EEG signal characteristic according to claim 1 is characterized in that: the number of the optimal characteristics vector element described in the step (6) is the half the of total characteristic vector element number.
6. the method for distilling of Imaginary EEG signal characteristic according to claim 1; It is characterized in that: the cross validation method described in the step (7) is meant; The optimal characteristics vector of the EEG signals that selection step (6) obtains is as test data, and the optimal characteristics vector of all the other EEG signals is as training data; Grader utilizes training data to set up disaggregated model, and test data substitution disaggregated model is obtained class categories, and match stop classification and actual task classification are correctly classified or the result of misclassification; Successively with the optimal characteristics vector of each EEG signals as a test data, add up the classification results of all test datas, obtain classification accuracy rate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012100850134A CN102613972A (en) | 2012-03-28 | 2012-03-28 | Extraction method of characteristics of electroencephalogram signals based on motor imagery |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012100850134A CN102613972A (en) | 2012-03-28 | 2012-03-28 | Extraction method of characteristics of electroencephalogram signals based on motor imagery |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102613972A true CN102613972A (en) | 2012-08-01 |
Family
ID=46554440
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012100850134A Pending CN102613972A (en) | 2012-03-28 | 2012-03-28 | Extraction method of characteristics of electroencephalogram signals based on motor imagery |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102613972A (en) |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102824172A (en) * | 2012-08-28 | 2012-12-19 | 浙江大学 | EEG (electroencephalogram) feature extraction method |
CN103258215A (en) * | 2013-05-10 | 2013-08-21 | 杭州电子科技大学 | Multi-lead correlation analysis electroencephalo-graph (EEG) feature extraction 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 |
CN103735262B (en) * | 2013-09-22 | 2015-04-29 | 杭州电子科技大学 | Dual-tree complex wavelet and common spatial pattern combined electroencephalogram characteristic extraction method |
CN104586387A (en) * | 2015-01-19 | 2015-05-06 | 秦皇岛市惠斯安普医学系统有限公司 | Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters |
CN105447475A (en) * | 2015-12-21 | 2016-03-30 | 安徽大学 | Independent component analysis based glancing signal sample optimization method |
CN105653039A (en) * | 2016-01-20 | 2016-06-08 | 同济大学 | Hand motion automatic correction and recognition method based on electroencephalogram signal detection |
CN106446762A (en) * | 2016-07-07 | 2017-02-22 | 哈尔滨工程大学 | Motion imagination EEG classification processing method based on sparse representation classification algorithm |
CN106648087A (en) * | 2016-12-12 | 2017-05-10 | 西北工业大学 | Feature EEG (electroencephalogram) processing method based on consciousness task |
US20170172497A1 (en) * | 2014-09-04 | 2017-06-22 | University Health Network | Method and system for brain activity signal-based treatment and/or control of user devices |
CN106943140A (en) * | 2017-03-08 | 2017-07-14 | 重庆邮电大学 | A kind of Mental imagery EEG feature extraction method based on RandomSelect RCSP |
CN107516452A (en) * | 2017-08-17 | 2017-12-26 | 北京航空航天大学 | A kind of general flight simulation simulated environment evaluation system |
CN107644566A (en) * | 2017-08-17 | 2018-01-30 | 北京航空航天大学 | A kind of brain electricity evaluation system of the simulated flight device based on brain electricity |
CN108563324A (en) * | 2018-03-04 | 2018-09-21 | 天津大学 | A kind of Mental imagery brain-computer interface design method of procedure-oriented control |
CN109657642A (en) * | 2018-12-29 | 2019-04-19 | 山东建筑大学 | A kind of Mental imagery Method of EEG signals classification and system based on Riemann's distance |
CN109685071A (en) * | 2018-11-30 | 2019-04-26 | 杭州电子科技大学 | Brain electricity classification method based on the study of common space pattern feature width |
CN109998536A (en) * | 2019-03-28 | 2019-07-12 | 西安交通大学 | A kind of epilepsy detection integrated circuit and its training method based on support vector machines |
CN110175510A (en) * | 2019-04-10 | 2019-08-27 | 杭州电子科技大学 | Multi-mode Mental imagery recognition methods based on brain function network characterization |
CN111338483A (en) * | 2020-03-20 | 2020-06-26 | 海南大学 | Method and system for controlling equipment, control equipment and readable storage medium |
CN111931578A (en) * | 2020-07-07 | 2020-11-13 | 杭州电子科技大学 | Electroencephalogram identification method based on minimum spanning tree and regional double-layer network |
CN111990992A (en) * | 2020-09-03 | 2020-11-27 | 山东中科先进技术研究院有限公司 | Electroencephalogram-based autonomous movement intention identification method and system |
CN112006682A (en) * | 2020-06-02 | 2020-12-01 | 东南大学 | Left-right hand motor imagery electroencephalogram signal classification method based on multi-channel frequency characteristic customization |
CN112379782A (en) * | 2020-12-11 | 2021-02-19 | 吉林大学 | Mouse control method based on electroencephalogram signals |
CN113143291A (en) * | 2021-05-11 | 2021-07-23 | 燕山大学 | Electroencephalogram feature extraction method under rapid sequence visual presentation |
CN113662562A (en) * | 2021-08-19 | 2021-11-19 | 西交利物浦大学 | Electroencephalogram signal feature extraction method and device for motor imagery task and storage medium |
CN113662561A (en) * | 2021-08-19 | 2021-11-19 | 西交利物浦大学 | Electroencephalogram feature extraction method and device of sub-band cascade common space mode |
CN113729733A (en) * | 2021-09-10 | 2021-12-03 | 天津大学 | Behavior test-based motor imagery neural response capability detection device |
CN113951896A (en) * | 2021-09-10 | 2022-01-21 | 之江实验室 | Brain-computer interface decoding method based on intracranial brain electricity and scalp brain electricity fusion |
CN114533084A (en) * | 2022-02-09 | 2022-05-27 | 北京师范大学 | Electroencephalogram feature extraction method and device, electronic equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101219048A (en) * | 2008-01-25 | 2008-07-16 | 北京工业大学 | Method for extracting brain electrical character of imagine movement of single side podosoma |
CN102178524A (en) * | 2011-05-23 | 2011-09-14 | 天津大学 | Synchronization likehood-based electroencephalograph and electromyography synergistic analyzing method |
-
2012
- 2012-03-28 CN CN2012100850134A patent/CN102613972A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101219048A (en) * | 2008-01-25 | 2008-07-16 | 北京工业大学 | Method for extracting brain electrical character of imagine movement of single side podosoma |
CN102178524A (en) * | 2011-05-23 | 2011-09-14 | 天津大学 | Synchronization likehood-based electroencephalograph and electromyography synergistic analyzing method |
Non-Patent Citations (1)
Title |
---|
侯秉文,刘鹏,周广玉,何嘉全: "基于运动想象脑机接口的AuFBCSP 方法", 《电子科技》 * |
Cited By (44)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102824172B (en) * | 2012-08-28 | 2014-03-19 | 浙江大学 | EEG (electroencephalogram) feature extraction method |
CN102824172A (en) * | 2012-08-28 | 2012-12-19 | 浙江大学 | EEG (electroencephalogram) feature extraction method |
CN103258215A (en) * | 2013-05-10 | 2013-08-21 | 杭州电子科技大学 | Multi-lead correlation analysis electroencephalo-graph (EEG) feature extraction method |
CN103735262B (en) * | 2013-09-22 | 2015-04-29 | 杭州电子科技大学 | Dual-tree complex wavelet and common spatial pattern combined electroencephalogram characteristic extraction method |
CN103961091B (en) * | 2014-04-15 | 2017-01-11 | 杭州电子科技大学 | Motor imagery electroencephalogram signal characteristic extracting method based on dual-tree complex wavelet sample entropy |
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 |
US20170172497A1 (en) * | 2014-09-04 | 2017-06-22 | University Health Network | Method and system for brain activity signal-based treatment and/or control of user devices |
US11955217B2 (en) | 2014-09-04 | 2024-04-09 | University Health Network | Method and system for brain activity signal-based treatment and/or control of user devices |
US10194858B2 (en) * | 2014-09-04 | 2019-02-05 | University Health Network | Method and system for brain activity signal-based treatment and/or control of user devices |
CN104586387A (en) * | 2015-01-19 | 2015-05-06 | 秦皇岛市惠斯安普医学系统有限公司 | Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters |
CN105447475A (en) * | 2015-12-21 | 2016-03-30 | 安徽大学 | Independent component analysis based glancing signal sample optimization method |
CN105653039A (en) * | 2016-01-20 | 2016-06-08 | 同济大学 | Hand motion automatic correction and recognition method based on electroencephalogram signal detection |
CN105653039B (en) * | 2016-01-20 | 2018-12-18 | 同济大学 | A kind of hand motion automatic straightening recognition methods based on EEG signals detection |
CN106446762A (en) * | 2016-07-07 | 2017-02-22 | 哈尔滨工程大学 | Motion imagination EEG classification processing method based on sparse representation classification algorithm |
CN106648087A (en) * | 2016-12-12 | 2017-05-10 | 西北工业大学 | Feature EEG (electroencephalogram) processing method based on consciousness task |
CN106648087B (en) * | 2016-12-12 | 2020-08-25 | 西北工业大学 | Feature EEG processing method based on consciousness task |
CN106943140A (en) * | 2017-03-08 | 2017-07-14 | 重庆邮电大学 | A kind of Mental imagery EEG feature extraction method based on RandomSelect RCSP |
CN107644566A (en) * | 2017-08-17 | 2018-01-30 | 北京航空航天大学 | A kind of brain electricity evaluation system of the simulated flight device based on brain electricity |
CN107516452A (en) * | 2017-08-17 | 2017-12-26 | 北京航空航天大学 | A kind of general flight simulation simulated environment evaluation system |
CN108563324A (en) * | 2018-03-04 | 2018-09-21 | 天津大学 | A kind of Mental imagery brain-computer interface design method of procedure-oriented control |
CN109685071A (en) * | 2018-11-30 | 2019-04-26 | 杭州电子科技大学 | Brain electricity classification method based on the study of common space pattern feature width |
CN109657642A (en) * | 2018-12-29 | 2019-04-19 | 山东建筑大学 | A kind of Mental imagery Method of EEG signals classification and system based on Riemann's distance |
CN109998536A (en) * | 2019-03-28 | 2019-07-12 | 西安交通大学 | A kind of epilepsy detection integrated circuit and its training method based on support vector machines |
CN110175510A (en) * | 2019-04-10 | 2019-08-27 | 杭州电子科技大学 | Multi-mode Mental imagery recognition methods based on brain function network characterization |
CN110175510B (en) * | 2019-04-10 | 2021-05-25 | 杭州电子科技大学 | Multi-mode motor imagery identification method based on brain function network characteristics |
CN111338483A (en) * | 2020-03-20 | 2020-06-26 | 海南大学 | Method and system for controlling equipment, control equipment and readable storage medium |
CN111338483B (en) * | 2020-03-20 | 2021-06-08 | 海南大学 | Method and system for controlling equipment, control equipment and readable storage medium |
CN112006682B (en) * | 2020-06-02 | 2022-09-30 | 东南大学 | Left-right hand motor imagery electroencephalogram signal classification method based on multi-channel frequency characteristic customization |
CN112006682A (en) * | 2020-06-02 | 2020-12-01 | 东南大学 | Left-right hand motor imagery electroencephalogram signal classification method based on multi-channel frequency characteristic customization |
CN111931578B (en) * | 2020-07-07 | 2023-09-22 | 杭州电子科技大学 | Electroencephalogram identification method based on minimum spanning tree and regional double-layer network |
CN111931578A (en) * | 2020-07-07 | 2020-11-13 | 杭州电子科技大学 | Electroencephalogram identification method based on minimum spanning tree and regional double-layer network |
CN111990992A (en) * | 2020-09-03 | 2020-11-27 | 山东中科先进技术研究院有限公司 | Electroencephalogram-based autonomous movement intention identification method and system |
CN112379782A (en) * | 2020-12-11 | 2021-02-19 | 吉林大学 | Mouse control method based on electroencephalogram signals |
CN113143291A (en) * | 2021-05-11 | 2021-07-23 | 燕山大学 | Electroencephalogram feature extraction method under rapid sequence visual presentation |
CN113143291B (en) * | 2021-05-11 | 2023-02-03 | 燕山大学 | Electroencephalogram feature extraction method under rapid sequence visual presentation |
CN113662561A (en) * | 2021-08-19 | 2021-11-19 | 西交利物浦大学 | Electroencephalogram feature extraction method and device of sub-band cascade common space mode |
CN113662561B (en) * | 2021-08-19 | 2024-03-01 | 西交利物浦大学 | Electroencephalogram feature extraction method and device of subband cascade co-space mode |
CN113662562A (en) * | 2021-08-19 | 2021-11-19 | 西交利物浦大学 | Electroencephalogram signal feature extraction method and device for motor imagery task and storage medium |
CN113662562B (en) * | 2021-08-19 | 2024-02-09 | 西交利物浦大学 | Electroencephalogram signal feature extraction method and device for motor imagery task and storage medium |
CN113951896A (en) * | 2021-09-10 | 2022-01-21 | 之江实验室 | Brain-computer interface decoding method based on intracranial brain electricity and scalp brain electricity fusion |
CN113729733B (en) * | 2021-09-10 | 2023-11-07 | 天津大学 | Motor imagery nerve response ability detection device based on behavior test |
CN113729733A (en) * | 2021-09-10 | 2021-12-03 | 天津大学 | Behavior test-based motor imagery neural response capability detection device |
CN114533084B (en) * | 2022-02-09 | 2023-07-14 | 北京师范大学 | Electroencephalogram feature extraction method and device, electronic equipment and storage medium |
CN114533084A (en) * | 2022-02-09 | 2022-05-27 | 北京师范大学 | Electroencephalogram feature extraction method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102613972A (en) | Extraction method of characteristics of electroencephalogram signals based on motor imagery | |
CN108960299B (en) | Method for identifying multi-class motor imagery electroencephalogram signals | |
Yu et al. | Analysis the effect of PCA for feature reduction in non-stationary EEG based motor imagery of BCI system | |
Bigdely-Shamlo et al. | Brain activity-based image classification from rapid serial visual presentation | |
CN102940490B (en) | Method for extracting motor imagery electroencephalogram signal feature based on non-linear dynamics | |
CN104586387A (en) | Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters | |
CN108280414A (en) | A kind of recognition methods of the Mental imagery EEG signals based on energy feature | |
CN104809434A (en) | Sleep staging method based on single-channel electroencephalogram signal ocular artifact removal | |
CN106569604A (en) | Audiovisual dual-mode semantic matching and semantic mismatch co-stimulus brain-computer interface paradigm | |
CN106419909A (en) | Multi-class motion imagination EEG signal classification method based on characteristic recombination and wavelet transformation | |
Lu et al. | Classification of EEG signal by STFT-CNN framework: identification of right-/left-hand motor imagination in BCI systems | |
CN108520239A (en) | A kind of Method of EEG signals classification and system | |
CN108042132A (en) | Brain electrical feature extracting method based on DWT and EMD fusions CSP | |
CN110163128A (en) | The Method of EEG signals classification of improved EMD algorithm combination wavelet package transforms and CSP algorithm | |
CN112528834B (en) | Electroencephalogram signal cross-test classification method of subband target alignment co-space mode | |
CN109271887A (en) | A kind of composite space filtering and template matching method for the identification of brain power mode | |
CN109730818A (en) | A kind of prosthetic hand control method based on deep learning | |
CN107661099A (en) | A kind of brain electricity analytical method for detecting the horizontal lower motion state of different Mental Workloads | |
CN104799852A (en) | Method for extracting movement imagination electroencephalogram characteristics based on ultralimit learning machine self encoding | |
CN111931656B (en) | User independent motor imagery classification model training method based on transfer learning | |
CN109858537A (en) | EEG feature extraction method of the improved EEMD in conjunction with CSP | |
Tong et al. | Combining multiple features for error detection and its application in brain–computer interface | |
Zhou et al. | How many channels are suitable for independent component analysis in motor imagery brain-computer interface | |
CN106648087A (en) | Feature EEG (electroencephalogram) processing method based on consciousness task | |
Niu et al. | Knowledge-driven feature component interpretable network for motor imagery classification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120801 |