CN102184017A - Lead optimizing method for P300 brain-computer interface - Google Patents

Abstract

The invention discloses a lead optimizing method for a P300 brain-computer interface (BCI) and relates to the technical field of the BCI. The method comprises the following steps of: acquiring an event phase locking value according to L leads with the preset number, establishing distance factor matrixes among leads according to the event phase locking value, and defining the intensity of phase synchronism among the leads; acquiring a clustering tree by a hierarchical clustering method according to the distance factor matrixes among the leads; establishing a lead importance sorted table according to the clustering tree and the intensity of phase synchronism among the leads; computing a precision rate of the lead importance sorted table, and acquiring L precision rate values; and sorting the L precision rate values, taking the lead combination with the highest precision rate value as the optimal lead combination, and outputting the optimal lead combination. In the method, the event phase locking value and the hierarchical clustering method are integrated, the number of characteristics sources is calculated and determined, the redundancy leads of a BCI system can be effectively reduced, the instability risk of the BCI system is reduced, and operation program is simplified.

Description

A kind of P300 brain-computer interface optimization method that leads

Technical field

The present invention relates to BCI (Brain-Computer Interface, brain-computer interface) technical field, BCI based on the P300 characteristic signal is the important BCI normal form of a class, lead and optimize a important issue as the BCI technology, crucial meaning is arranged, particularly a kind of P300 brain-computer interface optimization method that leads.

Background technology

The definition of the BCI that brain-computer interface international conference for the first time provides is: " BCI is a kind of communication control system that does not rely on brain nervus peripheralis and the normal output channel of muscle." in the present achievement in research; it mainly is by gathering and analyze different conditions servant's EEG signals; use certain engineering means to set up direct the interchange and control channel then between human brain and computing machine or other electronic equipment; thus realize a kind of brand-new message exchange and control technology, can particularly those have lost basic extremity motor function but the patient that has a normal thinking provides a kind of approach that carries out information interchange and control with the external world for the disabled person.Promptly can not need language or limb action, directly express wish or handle external device by control brain electricity.For this reason, the BCI technology also more and more comes into one's own.

Brain-computer interface normal form based on the P300 characteristic signal is proposed in 1988 by Farwell and Donchin at first.Its principle is based on the Oddball experiment model, and the rare goal stimulus of utilization brings out the P300 brain electricity composition among the ERP (Event Related Potential, event related potential).The system architecture synoptic diagram of P300 brain-computer interface as shown in Figure 1.The Oddball experiment model is meant, for two kinds of existing visual stimulus (acoustic stimuli or body sense stimulation etc.), wherein a kind of is rare goal stimulus target, and another kind is more relatively non-goal stimulus nontarget, and they stimulate the experimenter with certain sequence order.When the experimenter receives goal stimulus, can bring out ERP, its principal character is to stimulate about the 300ms of back the posivtive spike that amplitude is relatively large to occur, this posivtive spike just is called P300.The P300 characteristic pattern as shown in Figure 2, wherein on behalf of target, solid line stimulate, dotted line represent the nontarget stimulation.Fig. 3 meets 64 of the international standard layout viewing that leads.

An important issue about the P300 brain-computer interface is a characteristic optimization, and the optimization of leading then is one of them aspect.Usually in monitoring P300 EEG signals, can arrange at experimenter's scalp and 64 lead even 128 lead, a large amount of leading then can bring googol according to amount, and this has caused very big burden for follow-up signal Processing, has a strong impact on the real-time of BCI system.In addition, laying of electrode for encephalograms had relatively high expectations, and its job stability is relatively poor relatively, therefore, and many possibilities of leading and makeing mistakes with regard to many portions.And electrode for encephalograms has certain influence to user's comfort level.So how under the situation that guarantees signal characteristic validity, reducing the number that leads as much as possible is a significant problem.On the other hand, because the existence of individual difference makes the general combination of leading of neither one can meet each experimenter's individual sexual demand, this makes to lead to optimize and has more challenge, and is also more valuable.At present, to EEG signals lead the universal method optimized have a variety of, as genetic algorithm and SVM-RFE etc.But do not have a kind of special effective method to be optimized at leading of P300 brain-computer interface specially, universal method then can not satisfy the demand of P300 brain-computer interface fully.

Summary of the invention

In order to be optimized to leading of P300 brain-computer interface, satisfy the demand of P300 brain-computer interface, the invention provides a kind of P300 brain-computer interface optimization method that leads, see for details hereinafter and describe:

A kind of P300 brain-computer interface optimization method that leads said method comprising the steps of:

(1) lead according to predetermined number L and obtain incident phase locking value between leading, the value of L is the positive integer more than or equal to 2; Set up distance coefficient matrix between respectively leading, the phase synchronism intensity that definition is respectively led according to described incident phase locking value;

(2) according to described distance coefficient matrix between respectively leading, obtain clustering tree by the hierarchical clustering method;

(3) set up the importance ranking table that leads according to described clustering tree and described phase synchronism intensity of respectively leading;

(4) the described importance ranking table that leads is carried out accuracy and calculate, obtain L accuracy value;

(5) described L accuracy value sorted, the combination of leading that the accuracy value is the highest is as the optimum combination of leading, and exports the combination of leading of described optimum.

Described leading according to predetermined number L in the step (1) obtained incident phase locking value between leading; Set up distance coefficient matrix between respectively leading according to described incident phase locking value, the phase synchronism intensity that definition is respectively led is specially:

If obtain the eeg data of n goal stimulus and the eeg data of m non-goal stimulus through overtesting, the incident phase locking value of then leading between x and the y is specially:

${\mathrm{TPLV}}_{x,y}\left(t\right)=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{PLV}}_{x,y,t\arg \mathrm{et}}\left(t\right)-\frac{1}{m}\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{PLV}}_{x,y,\mathrm{nont}\arg \mathrm{et}}\left(t\right)$

Wherein, the value of n and m is the positive integer more than or equal to 1; ＜ _τRepresentative is carried out time average to the formula in the bracket;

Define described distance coefficient matrix between respectively leading, for two lead x and y arbitrarily, its distance coefficient matrix is specially:

${\mathrm{Dist}}_{x,y}=\underset{t}{\max }\left({\mathrm{TPLV}}_{x,y}\left(t\right)\right)$

According to described distance coefficient matrix between respectively leading, define described phase synchronism intensity of respectively leading, for any one x that leads, its phase synchronism intensity is:

${\mathrm{Wg}}_x=\underset{i}{\mathrm{\Σ}}{\mathrm{Dist}}_{x,i}.$

Described in the step (3) set up the importance ranking table that leads according to described clustering tree and described phase synchronism intensity of respectively leading and is specially:

Suppose to have the individual eeg data that leads of L, obtain the clustering tree that a L leads, the activity that is provided with L-1 features sources be reflected in L lead on, by the intercepting clustering tree, individual leading of L is divided into the L-1 class, then exists one to comprise two classes of leading, be designated as the lead x and the y that leads, when the phase synchronism intensity of the x that leads during greater than the phase synchronism intensity of the y that leads, the x that then selects to lead gets rid of the y that leads; The importance of the y that leads that gets rid of comes the L position; Lead for remaining L-1, the activity that is provided with L-2 features sources be reflected in L-1 lead on, by the intercepting clustering tree, individual leading of L-1 is divided into the L-2 class, then exist one to comprise two classes of leading, be designated as the lead x and the y that leads, when the phase synchronism intensity of the x that leads during greater than the phase synchronism intensity of the y that leads, the x that then selects to lead gets rid of the y that leads; The importance of the y that leads that gets rid of then comes the L-1 position; By that analogy, up to only surplus one lead till, remaining at last leads, and comes L-(L-1) position, obtains the L importance ranking table that leads.

Described in the step (4) carries out accuracy to the described importance ranking table that leads to be calculated, and obtains L accuracy value and is specially:

The data of leading of L-(L-1) position are carried out accuracy calculate, obtain the first accuracy value A1; The data of leading of L-(L-1) position and L-(L-2) position are carried out accuracy calculate, obtain the second accuracy value A2; The data of leading of L-(L-1) position, L-(L-2) position and L-(L-3) position are carried out accuracy calculate, obtain the 3rd accuracy value A3; By that analogy, up to obtaining L accuracy value AL.

The beneficial effect of technical scheme provided by the invention is:

The invention provides a kind of P300 brain-computer interface optimization method that leads, fusion event PLV of the present invention (Phase Locking Value, the phase locking value) and the hierarchical clustering method, the features sources number is inferred decision-making, selecting the optimum combination of leading on this basis, is a kind of brand-new P300 brain-computer interface optimisation technique of leading; This invention can effectively reduce the redundancy of BCI system and lead, reduce the instability risk of BCI system, simplify procedures, online degree and its commercialization of promotion of improving the BCI system are offered help, can obtain considerable economic and social benefit in field of human-computer interaction.

Description of drawings

The system architecture synoptic diagram of the P300 brain-computer interface that Fig. 1 provides for prior art;

The P300 characteristic pattern that Fig. 2 provides for prior art;

Fig. 3 meets 64 of the international standard layout viewing that leads for what prior art provided;

Fig. 4 is a clustering tree structural representation provided by the invention;

Fig. 5 is the lead process flow diagram of optimization method of a kind of P300 brain-computer interface provided by the invention.

Embodiment

For making the purpose, technical solutions and advantages of the present invention clearer, embodiment of the present invention is described further in detail below in conjunction with accompanying drawing.

In order to be optimized to leading of P300 brain-computer interface, satisfy the demand of P300 brain-computer interface, the embodiment of the invention provides a kind of P300 brain-computer interface optimization method that leads, and sees for details hereinafter to describe:

101: lead according to predetermined number L and to obtain incident phase locking value between leading; Distance coefficient matrix between foundation is respectively led according to the incident phase locking value between leading, the phase synchronism intensity that definition is respectively led;

Wherein, the predetermined number L that leads sets according to the needs in the practical application, and value is the positive integer more than or equal to 2, and during specific implementation, the embodiment of the invention does not limit this.

If a certain signal s (t), its analytical function z (t) can obtain by through type (1-1)

$\hat{s}\left(t\right)=\frac{1}{\mathrm{\π}}{\∫}_{-\∞}^{\∞}\frac{s\left(\mathrm{\τ}\right)}{t-\mathrm{\τ}}\mathrm{d\τ}---(1-2)$

Signal The Hilbert that is s (t) changes, and can write out the instantaneous phase of signal s (t):

Suppose that predetermined number is 2, promptly exists two EEG signals s that lead _x(t) and s _y(t), its phase place is respectively

With

The phase locking value of x and y of then leading can be obtained by formula (1-4):

Wherein,＜ _τRepresentative is carried out time average to the formula in the bracket, and the window width of its time window is τ (τ=25ms in the embodiment of the invention is that example describes).If the complete synchronism of the phase place of two lead signals,

Then be stable, PLV _{X, y}(t)=1; If this two phase place of leading signal does not have synchronism, then

Be stochastic distribution, PL _{X, y}(t)=0.

If behind overtesting, obtain the eeg data of n goal stimulus target and the eeg data of m non-goal stimulus nontarget, then lead x and the incident phase locking value of leading between the y can be obtained by formula (1-6):

${\mathrm{TPLV}}_{x,y}\left(t\right)=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{PLV}}_{x,y,t\arg \mathrm{et}}\left(t\right)-\frac{1}{m}\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{PLV}}_{x,y,\mathrm{nont}\arg \mathrm{et}}\left(t\right)---(1-6)$

Wherein, the value of n and m is the positive integer more than or equal to 1.

The distance coefficient matrix D ist of definition between respectively leading, for two lead x and y arbitrarily, its distance coefficient matrix D ist:

${\mathrm{Dist}}_{x,y}=\underset{t}{\max }\left({\mathrm{TPLV}}_{x,y}\left(t\right)\right)---(1-7)$

According to the distance coefficient matrix D ist between respectively leading, the phase synchronism intensity Wg that respectively leads of definition, for any one x that leads, its phase synchronism intensity is:

${\mathrm{Wg}}_x=\underset{i}{\mathrm{\Σ}}{\mathrm{Dist}}_{x,i}---(1-8)$

102: the distance coefficient matrix according between respectively leading, obtain clustering tree by the hierarchical clustering method;

Wherein, the hierarchical clustering method, claim the grade clustering procedure again, be to use at most, study one of clustering method the most fully at present, its basic thought is the distance coefficient matrix that also progressively upgrades between respectively leading by setting up, find out and merge immediate two classes, till whole cluster objects are merged into a class.The embodiment of the invention utilizes the method (also having bee-line method, longest distance method, gravity model appoach and the class method of average in addition) based on ward to carry out hierarchical clustering to leading, and obtains clustering tree.Fig. 4 is the structural representation of clustering tree, and wherein on behalf of difference, numeral 1,2,3,4,5 lead respectively, and ordinate is represented distance.Lines a leads 5 and is divided into 4 classes, wherein leads 1 and to lead 2 be a class, and other lead and respectively become a class; Lines b then leads 5 and is divided into 3 classes, wherein leads 1 and to lead 2 be a class, and leading 3 is a class, and leading 4 and 5 is a class; Lines c leads 5 and is divided into 3 classes, and wherein leading 1,2 and 3 is a class, and leading 4 and 5 is a class.

103: set up the importance ranking table that leads according to the clustering tree and the phase synchronism intensity of respectively leading;

For example: certain two lead x and y, record be of the reflection of same features sources at scalp, will there be a lot of similar features in the signal of lead so x and y, thereby can produce the feature redundancy.In other words, if utilized the x that leads exactly, the y that leads so with very little, that is to say that the importance of the y that leads has descended to the influence of last classification accuracy rate.Therefore, determine to reflect leading and the number of features sources of features sources, effective minimizing number that leads is had great significance.

Promptly, setting up the importance ranking table that leads according to clustering tree and the phase synchronism intensity of respectively leading is specially: suppose to have the individual eeg data that leads of L, obtain the clustering tree that a L leads, the activity that is provided with L-1 features sources be reflected in L lead on, by the intercepting clustering tree, individual leading of L is divided into the L-1 class, then exist one to comprise two classes of leading, be designated as the lead x and the y that leads, when the phase synchronism intensity of the x that leads during greater than the phase synchronism intensity of the y that leads, the x that then selects to lead gets rid of the y that leads (maybe when the phase synchronism intensity of the x that leads during smaller or equal to the phase synchronism intensity of the y that leads, the y that then selects to lead gets rid of the x that leads); The importance of the y that leads that gets rid of then comes L position (or the importance of the x that leads that gets rid of then comes the L position); Lead for remaining L-1, the activity that continues to be provided with L-2 features sources be reflected in L-1 lead on, by the intercepting clustering tree, individual leading of L-1 is divided into the L-2 class, then exist one to comprise two classes of leading, be designated as the lead x and the y that leads, when the phase synchronism intensity of the x that leads phase synchronism intensity greater than the y that leads, the x that then selects to lead gets rid of the y that leads (maybe when the phase synchronism intensity of the x that leads during smaller or equal to the phase synchronism intensity of the y that leads, the y that then selects to lead gets rid of the x that leads); The importance of the y that leads that gets rid of then comes L-1 position (or the importance of the x that leads that gets rid of then comes the L position); By that analogy, up to only surplus one lead till, remaining at last leads, and comes L-(L-1) position, obtains the importance ranking table that a L leads.

Suppose the eeg data that has 64 to lead, to have obtained one 64 clustering tree of leading through two steps in front.Because do not know brain inside have actually the activity in several characteristic source be reflected in these 64 lead on, so carry out the decision-making of inferring of features sources number.The first step, the activity that is provided with 63 features sources be reflected in 64 lead on, so, exist a redundancy to lead.In order to find this redundancy to lead, by intercepting clustering tree, 64 are led is divided into 63 classes.So, have so class, wherein contain two and lead, be designated as x and y, other classes then have only one to lead.Think that lead x and y is reflection to same features sources, therefore need make screening to it, and the foundation of selecting is exactly the phase synchronism intensity Wg that leads.Suppose to lead the phase synchronism intensity Wg of x greater than the phase synchronism intensity Wg of the y that leads, then select x to get rid of y.The importance of the y that leads that gets rid of then comes the 64th.Second step, lead for remaining 63, the activity that continues to be provided with 62 features sources be reflected in 63 lead on, so, exist a redundancy to lead.In order to find this redundancy to lead, by intercepting clustering tree, 63 are led is divided into 62 classes.So, have so class, wherein contain two and lead, be designated as x and y, other classes then have only one to lead.Think that lead x and y is reflection to same features sources, therefore need make screening to it.And the foundation of selecting is exactly the phase synchronism intensity Wg that leads.Suppose to lead the phase synchronism intensity Wg of x greater than the phase synchronism intensity Wg of the y that leads, then select x to get rid of y.The importance of the y that leads that gets rid of then comes the 63rd.By that analogy, up to only surplus one lead till, then last remaining that leads, its importance maximum is last, obtains one 64 importance ranking table that leads.

104: the importance ranking table that leads is carried out accuracy calculate, obtain L accuracy value;

Wherein, this step is specially carries out accuracy calculating to the data of leading of L-(L-1) position, obtains the first accuracy value A1; The data of leading of L-(L-1) position and L-(L-2) position are carried out accuracy calculate, obtain the second accuracy value A2; The data of leading of L-(L-1) position, L-(L-2) position and L-(L-3) position are carried out accuracy calculate, obtain the 3rd accuracy value A3; By that analogy, up to obtaining L accuracy value AL.

Wherein, accuracy is calculated as: carry out 5 folding cross validations calculating accuracy according to the eeg data of n goal stimulus target and the eeg data of m non-goal stimulus nontarget, be about to all data and be divided into 5 parts of B1, B2, B3, B4 and B5 at random, get B1 earlier as test sample book, other 4 piece of data are as training sample, the sorter of setting up with training sample goes to calculate the accuracy of test sample book B1, obtains accuracy value R1.Get B2, B3, B4 and B5 then successively as test sample book, other are training sample, obtain accuracy value R2, R3, R4 and R5 respectively.The mean value of getting these 5 accuracy values at last is the accuracy of 5 folding cross validations.Wherein, during specific implementation, also can carry out 6 folding cross validations according to the needs in the practical application and calculate accuracy, be about to all data and be divided into 6 parts of B1, B2, B3, B4, B5 and B6 at random, get B1 earlier as test sample book, other 5 piece of data are described in detail referring to above as training sample, do not repeat them here.

105: L accuracy value sorted, and the combination of leading that the accuracy value is the highest is as the optimum combination of leading, and exports the optimum combination of leading.

Wherein, can carry out from high to low or from low to high ordering L accuracy value, or adopt other sort method, during specific implementation, the embodiment of the invention does not limit this.

The feasibility of leading optimization method with an a kind of P300 brain-computer interface of simply verifying that the embodiment of the invention provides below, see hereinafter description for details:

A kind of P300 brain-computer interface that the application of the invention embodiment provides optimization method that leads, 64 of 5 experimenters are led be optimized, the result shows, keeping under the constant situation of accuracy (obtaining) by 3 stack eigenwerts, on average can reduce 46 leads, verify the feasibility of the method that the embodiment of the invention provides, satisfied the needs in the practical application.

In sum, the embodiment of the invention provides a kind of P300 brain-computer interface optimization method that leads, embodiment of the invention fusion event PLV and hierarchical clustering method, the features sources number is inferred decision-making, selecting the optimum combination of leading on this basis, is a kind of brand-new P300 brain-computer interface optimisation technique of leading; The embodiment of the invention can effectively reduce the redundancy of BCI system and lead, reduce the instability risk of BCI system, simplify procedures, online degree and its commercialization of promotion of improving the BCI system are offered help, can obtain considerable economic and social benefit in field of human-computer interaction.

It will be appreciated by those skilled in the art that accompanying drawing is the synoptic diagram of a preferred embodiment, the invention described above embodiment sequence number is not represented the quality of embodiment just to description.

The above only is preferred embodiment of the present invention, and is in order to restriction the present invention, within the spirit and principles in the present invention not all, any modification of being done, is equal to replacement, improvement etc., all should be included within protection scope of the present invention.

Claims (4)

1. P300 brain-computer interface optimization method that leads is characterized in that, said method comprising the steps of:

(1) lead according to predetermined number L and obtain incident phase locking value between leading, the value of L is the positive integer more than or equal to 2; Set up distance coefficient matrix between respectively leading, the phase synchronism intensity that definition is respectively led according to described incident phase locking value;

(2) according to described distance coefficient matrix between respectively leading, obtain clustering tree by the hierarchical clustering method;

(3) set up the importance ranking table that leads according to described clustering tree and described phase synchronism intensity of respectively leading;

(4) the described importance ranking table that leads is carried out accuracy and calculate, obtain L accuracy value;

(5) described L accuracy value sorted, the combination of leading that the accuracy value is the highest is as the optimum combination of leading, and exports the combination of leading of described optimum.

2. a kind of P300 brain-computer interface according to claim 1 optimization method that leads is characterized in that, described the leading according to predetermined number L in the step (1) obtained incident phase locking value between leading; Set up distance coefficient matrix between respectively leading according to described incident phase locking value, the phase synchronism intensity that definition is respectively led is specially:

If obtain the eeg data of n goal stimulus and the eeg data of m non-goal stimulus through overtesting, the incident phase locking value of then leading between x and the y is specially:

${\mathrm{TPLV}}_{x,y}\left(t\right)=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{PLV}}_{x,y,t\arg \mathrm{et}}\left(t\right)-\frac{1}{m}\underset{i=1}{\overset{m}{\mathrm{\Σ}}}{\mathrm{PLV}}_{x,y,\mathrm{nont}\arg \mathrm{et}}\left(t\right)$

Wherein, the value of n and m is the positive integer more than or equal to 1;

＜ _τRepresentative is carried out time average to the formula in the bracket;

Define described distance coefficient matrix between respectively leading, for two lead x and y arbitrarily, its distance coefficient matrix is specially:

${\mathrm{Dist}}_{x,y}=\underset{t}{\max }\left({\mathrm{TPLV}}_{x,y}\left(t\right)\right)$

According to described distance coefficient matrix between respectively leading, define described phase synchronism intensity of respectively leading, for any one x that leads, its phase synchronism intensity is:

${\mathrm{Wg}}_x=\underset{i}{\mathrm{\Σ}}{\mathrm{Dist}}_{x,i}.$

3. a kind of P300 brain-computer interface according to claim 1 optimization method that leads is characterized in that, described in the step (3) set up the importance ranking table that leads according to described clustering tree and described phase synchronism intensity of respectively leading and be specially:

Suppose to have the individual eeg data that leads of L, obtain the clustering tree that a L leads, the activity that is provided with L-1 features sources be reflected in L lead on, by the intercepting clustering tree, individual leading of L is divided into the L-1 class, then exists one to comprise two classes of leading, be designated as the lead x and the y that leads, when the phase synchronism intensity of the x that leads during greater than the phase synchronism intensity of the y that leads, the x that then selects to lead gets rid of the y that leads; The importance of the y that leads that gets rid of comes the L position; Lead for remaining L-1, the activity that is provided with L-2 features sources be reflected in L-1 lead on, by the intercepting clustering tree, individual leading of L-1 is divided into the L-2 class, then exist one to comprise two classes of leading, be designated as the lead x and the y that leads, when the phase synchronism intensity of the x that leads during greater than the phase synchronism intensity of the y that leads, the x that then selects to lead gets rid of the y that leads; The importance of the y that leads that gets rid of then comes the L-1 position; By that analogy, up to only surplus one lead till, remaining at last leads, and comes L-(L-1) position, obtains the L importance ranking table that leads.

4. a kind of P300 brain-computer interface according to claim 1 optimization method that leads is characterized in that, described in the step (4) carries out accuracy to the described importance ranking table that leads to be calculated, and obtains L accuracy value and is specially:

The data of leading of L-(L-1) position are carried out accuracy calculate, obtain the first accuracy value A1; The data of leading of L-(L-1) position and L-(L-2) position are carried out accuracy calculate, obtain the second accuracy value A2; The data of leading of L-(L-1) position, L-(L-2) position and L-(L-3) position are carried out accuracy calculate, obtain the 3rd accuracy value A3; By that analogy, up to obtaining L accuracy value AL.

Images