CN109901711B - Asynchronous real-time brain control method driven by weak myoelectricity artifact micro-expression electroencephalogram signals - Google Patents
Asynchronous real-time brain control method driven by weak myoelectricity artifact micro-expression electroencephalogram signals Download PDFInfo
- Publication number
- CN109901711B CN109901711B CN201910087028.6A CN201910087028A CN109901711B CN 109901711 B CN109901711 B CN 109901711B CN 201910087028 A CN201910087028 A CN 201910087028A CN 109901711 B CN109901711 B CN 109901711B
- Authority
- CN
- China
- Prior art keywords
- brain
- expression
- micro
- brain control
- controlled
- 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.)
- Active
Links
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses an asynchronous real-time brain control method driven by a weak myoelectric artifact micro-expression electroencephalogram signal. Taking 100ms electroencephalogram signals as a single signal source, and firstly, judging the brain control micro-expression attribute by utilizing the energy ratio of the myoelectric artifact. And secondly, executing brain control state start/stop brain control micro expression detection and effectiveness judgment, starting a brain control state after judging as a true brain control micro expression, entering the brain control state, performing brain control micro expression identification and effectiveness judgment after judging the attributes of the brain control micro expression, and generating a brain control instruction for controlling a controlled object or stopping the brain control state after judging as the true brain control micro expression. The invention realizes the start/stop of the brain control state and the action operation of 8 controlled objects based on the brain control micro expression, effectively improves the real-time property, the flexibility and the accuracy of the brain control method, increases the asynchronous brain control interface detection and the brain control micro expression validity judgment, improves the practical value of the brain control method, and can be widely applied to various brain control systems.
Description
Technical Field
The invention relates to the technical field of brain-computer interfaces, in particular to an asynchronous real-time brain control method driven by weak myoelectric artifact micro-expression electroencephalogram signals.
Background
Brain-Computer Interface (BCI) technology, i.e., taking user's electroencephalogram as a signal source, using advanced Computer information processing technology to decode the user's intention, avoiding the peripheral nerve/muscle system which may be damaged by the user, and establishing direct communication between the user's consciousness and peripheral devices. It has important application value in the fields of rehabilitation, high-risk operation, game entertainment, aerospace military and the like.
The traditional brain-computer interface is realized based on a Steady State Visual Evoked Potential (SSVEP) and Motor Imagery (MI) paradigm, wherein the SSVEP has the advantages of high accuracy and multiple identifiable categories, but due to the constraint of the paradigm principle, an additional Visual stimulator and Visual stimulation time are required, and the problems of equipment redundancy and limited response real-time performance exist in the problem of brain control; MI has the advantage of conforming to the spontaneous brain wave generation process of human brain, but because of the execution difficulty of imagination movement, extra subject adaptation time is needed, and the problems of low user friendliness and limited recognizable categories exist in the brain control problem. In addition, the existing research is based on the development of a synchronous brain-computer interface, namely, a user is only allowed to send instructions in a specific time period set by a system, the permission of the user for independently controlling the time for sending control instructions cannot be provided, and the application of the method is limited in the practical brain control problem.
In order to solve the problems of redundancy and low user friendliness of the conventional brain-computer interface device, chinese patent 201510423224, chinese patent 201510423398, and the like all disclose brain control methods based on expression-driven brain-computer interface paradigms. The related expression driving type brain control method does not consider the difference between the expression and the other daily facial expressions in the practical application process and the aesthetic degree of the user in the use process in the aspect of expression actions; only the prefrontal cortex and the edge system are included in the aspect of electroencephalogram signal channel selection, and the information expression of facial expression as facial muscle action in the cerebral motor cortex is omitted; in the aspect of the provided brain control expression and action, the method is only suitable for the operation of 4 control targets, and the number of the control targets is limited; in the working process of the brain control interface, an asynchronous brain control interface is not introduced, so that the autonomous start/stop of the brain control state of a user cannot be realized, and the practical application value is lacked.
In the brain control method derived based on the brain-computer interface technology, the problems of low real-time performance (low control instruction output frequency), redundant additional stimulators, function loss of asynchronous brain-computer interfaces (brain control interfaces), low user friendliness and the like exist at different degrees at the present stage.
Disclosure of Invention
The invention provides an asynchronous real-time brain control method driven by weak myoelectric artifact micro-expression electroencephalogram signals, aiming at the problems of the existing brain control method.
In order to achieve the above purpose, the invention adopts the following technical scheme:
an asynchronous real-time brain control method driven by weak myoelectric artifact micro-expression electroencephalogram signals comprises the following steps:
first stage-initiating brain control State
Judging the attribute of the facial expression of a user according to the myoelectric artifact of the electroencephalogram signal, if the facial expression belongs to the brain-controlled micro expression, carrying out brain-controlled micro expression recognition and effectiveness judgment on the facial expression, and if the recognized effective brain-controlled micro expression (called as true brain-controlled micro expression in the invention) is the brain-controlled state start/stop brain-controlled micro expression, entering the brain-controlled state;
second stage-asynchronous real-time control under brain control
And in the brain control state, judging the attribute of the facial expression of the user according to the myoelectric artifact of the electroencephalogram signal, if the facial expression belongs to the brain control micro expression, carrying out brain control micro expression recognition and effectiveness judgment on the facial expression, controlling the action of the controlled object according to the recognized effective brain control micro expression matched with the control instruction of the controlled object, or starting/stopping the brain control micro expression according to the recognized effective brain control state to stop the brain control state.
Preferably, the sampling period of the electroencephalogram signal is 100-150 ms.
Preferably, the acquisition channels of the brain electrical signals include prefrontal cortex, limbal brain system, and motor cortex channel locations (e.g., F7, F8, FC5, FC6, FCz, C3, C4, and Cz).
Preferably, the electroencephalogram signals obtained in a single sampling period are used as a signal source, the electromyographic artifact energy ratio of signals of prefrontal cortex channels (such as F7 and F8) in the signal source is calculated, and when the energy ratio is within a certain threshold interval (the threshold interval can be automatically adjusted by a user), the facial expression of the user is judged to be the brain-controlled micro expression. The prefrontal cortex area of the brain is close to the facial muscles of a human body, so that whether the prefrontal cortex area belongs to the brain-controlled micro-expression or not is determined according to the myoelectric artifact energy ratio of signals in the area.
Preferably, the brain-controlled micro expression is selected from the group consisting of eyebrow lifting, frown wrinkling, left-handed mouth, right-handed mouth, smile, mouth beeping, mouth opening, tooth biting and resting, and each brain-controlled micro expression is identified according to a classification model generated in advance by using an electroencephalogram signal.
Preferably, in the validity determination, if the recognition results of the brain-controlled micro-expressions in n consecutive electroencephalogram signal sampling periods are consistent (n is set by a user), the brain-controlled micro-expressions are determined to be valid, and corresponding brain-controlled instructions (control instructions for controlling the movement of the controlled object or start/stop instructions for the brain-controlled state of the controlled object) are generated.
The invention also provides an asynchronous real-time brain control system driven by the electroencephalogram signals of the weak electromyogram artifacts, which comprises an electroencephalogram signal acquisition module, an electroencephalogram signal data client and a controlled object, wherein the electroencephalogram signal data client comprises an electroencephalogram signal source module, a brain control micro-expression attribute determination module, a true brain control micro-expression determination module and a brain control instruction generation and transmission module, the electroencephalogram signal source module is used for receiving the electroencephalogram signals of a user periodically acquired by the electroencephalogram signal acquisition module, the brain control micro-expression attribute determination module is used for determining the brain control micro-expression in the facial expression made by the user according to the electroencephalogram signals, the true brain control micro-expression determination module is used for carrying out type identification on the brain control micro-expression made by the user and determining the effectiveness of the identified brain control micro-expression, and the brain control instruction generation and transmission module are used for comparing and matching the brain control micro-expression corresponding to the effective brain control micro-expression And controlling the command and sending the command to the controlled object.
The invention has the beneficial effects that:
based on the expression driving type brain-computer interface paradigm, the invention starts from the practical angle of the brain control method, takes the electroencephalogram signals under the facial micro-expression action of a user in the operation process as signal sources, and the user makes corresponding brain control micro-expressions according to the operation target of the controlled object, thereby not only realizing asynchronous real-time control on the controlled object in the brain control state, but also increasing the quantity of available brain control instructions of the controlled object, and further improving the real-time property, flexibility and accuracy of the brain control operation.
Furthermore, compared with the traditional brain control expression, the brain control micro expression weakens the action amplitude of the facial expression, is convenient for the user to operate daily, and provides more expression categories for operation.
Furthermore, the invention adds asynchronous brain control interface detection (asynchronous brain control interface brain control state start detection and brain control micro expression detection in a brain control state), brain control micro expression amplitude regulation (when the energy proportion of the myoelectric artifact is within a certain threshold value interval, the energy proportion of the myoelectric artifact is high, the micro expression action amplitude is large, and when the energy proportion of the myoelectric artifact is low, the micro expression action amplitude is small) and brain control micro expression validity judgment links, improves the practical value of the brain control method, effectively improves the stability of the brain control operation, and can be widely applied to various brain control systems.
Furthermore, the brain control instruction signal source is composed of micro-expression electroencephalogram signals with short sampling periods (100-150 ms), so that the time of the brain control signal source is shortened remarkably, and the real-time performance of brain control operation is improved effectively.
Drawings
Fig. 1 is a schematic diagram of an asynchronous real-time brain control system according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of the electrode arrangement position of the electroencephalogram signal acquisition module in the embodiment of the present invention.
FIG. 3 is a diagram illustrating brain-controlled micro-expressions according to an embodiment of the present invention; wherein, (a) is used for raising eyebrow, (b) is used for frowning, (c) is used for left-handed mouth, (d) is used for right-handed mouth, (e) is used for smiling, (f) is used for mouth-playing, (g) is used for mouth-opening, (h) is used for biting teeth, and (i) is in resting state; and in order to show the requirement, the micro-expression action amplitude is strengthened, and the teeth are bitten to perform mouth opening demonstration.
FIG. 4 is a flow chart of an asynchronous real-time brain control algorithm based on the driving of the weak myoelectric artifact micro-expression electroencephalogram signal in the embodiment of the invention.
Detailed Description
The invention is further illustrated by the following figures and examples. The embodiments are only used for explaining the technical idea and features of the present invention, and the scope of protection of the present invention is not limited by the embodiments.
Fig. 1 shows, by way of example, an asynchronous real-time brain control system driven by brain control micro-expression, which includes an electroencephalogram signal acquisition module, an electroencephalogram signal data client, and a controlled object. The electroencephalogram signal acquisition module comprises electroencephalogram signal acquisition equipment worn by a user, the position arrangement of an electroencephalogram cap channel of the electroencephalogram signal acquisition module accords with the international 10-20 standard, and an acquired multichannel electroencephalogram signal (100ms EEG) can be transmitted to an electroencephalogram signal data client through a local area network; the electroencephalogram signal data client receives electroencephalogram signal sampling data by using a computer, and completes electroencephalogram signal data processing work through a micro-expression brain control program, wherein the micro-expression brain control program is based on a Matlab platform and outputs brain control instructions to drive a controlled object to act according to the asynchronous real-time brain control algorithm based on the weak myoelectricity artifact micro-expression electroencephalogram signal driving provided by the invention; according to the matching of the brain control micro expression and different instructions, the system can control different controlled objects.
The brain-controlled micro expressions are facial expressions which are different from the existing brain-controlled expressions in the electromyographic artifact component energy ratio E of a series of electroencephalograms, can be used for recognizing and classifying the electroencephalograms by machine learning or deep learning, and weaken the action amplitude of the facial expressions compared with the existing brain-controlled expressions and show the characteristics of weak electromyographic artifacts. As the electromyographic artifact is more in a high-frequency part compared with other components in the electroencephalogram signal, the electromyographic artifact component can be obtained by selecting the filtering passband to be (75, fs/2] Hz, wherein fs is taken as the sampling frequency of the equipment.
In the invention, through analyzing EEG signal channel data (such as channels F7 and F8 and figure 2) which are easily interfered by facial muscle myoelectricity in an experiment, 9 kinds of brain-controlled micro expressions (figure 3) are obtained, wherein the brain-controlled micro expressions are respectively eyebrow lifting, frown wrinkling, left-handed mouth, right-handed mouth, smile, mouth beeping, mouth opening, tooth biting and rest. The electromyographic artifact component energy ratio E corresponding to the micro expressions has the following characteristics: e, value range: 5% -50%, wherein the high energy ratio indicates that the motion amplitude of the expression action muscle is large, and the low energy ratio indicates that the motion amplitude of the expression action muscle is small, so that the threshold range [ E ] of E can be specified1,E2]And the method is distinguished from the existing brain control expression, namely the judgment of the brain control micro expression attribute is realized. This threshold range [ E ] due to different usage habit differences1,E2]The micro expression can be automatically adjusted in the value range of E by a user, so that micro expressions belonging to a certain action amplitude can be conveniently appointed to execute brain control operation.
Experiments also show that the electroencephalogram signal after the electromyogram artifact components are removed through filtering can be used as a sample to train the electroencephalogram signal classifiers with the 9 brain-controlled micro-expressions, and effective automatic identification and classification capabilities are obtained. The electroencephalogram signal original data are subjected to band-pass filtering processing complementary with the filtering passband to obtain a pure electroencephalogram signal frequency band, time-space domain feature extraction can be achieved on the pure electroencephalogram signal by using a space filter based on a Common Spatial Pattern (CSP) algorithm, recognition of different brain control micro expressions can be achieved by combining Support Vector Machines (SVM) according to extracted signal features, and the space filter and the SVM classifier are generated by user training data in advance.
After the brain control micro expression corresponding to a certain electroencephalogram sampling time period of a user is identified, in order to avoid misoperation of a controlled object caused by facial expression misoperation of the user, on the other hand, in order to improve the control flexibility of the brain control instruction, validity judgment is carried out on the brain control micro expression of the user, namely real brain control micro expression identification is carried out, and different identification thresholds can be set according to different matched brain control instructions for different brain control micro expressions.
Referring to fig. 4, the asynchronous real-time brain control process driven by the brain control micro expression is described below by taking the above asynchronous real-time brain control system and 9 kinds of brain control micro expressions as examples:
(1) the controlled object is a 6-degree-of-freedom bionic artificial hand with a wrist joint and independently driven by five fingers, the computer communicates with the controlled object through a Bluetooth module, namely, a brain control command of the artificial hand generated after processing is sent to a driving controller embedded in a palm of the artificial hand by the computer through the Bluetooth module, and finally the artificial hand is driven by a motor to complete an action target.
(2) The user wears the electroencephalogram signal acquisition equipment to acquire the electroencephalogram signal of the user
An 8-channel Brilliant neurosenW 8 electroencephalogram acquisition device is selected, and an electroencephalogram cap is arranged on the positions of F7, F8, FC5, FC6, FCz, C3, C4 and Cz (shown in figure 2), namely, electroencephalogram signals of 8 channels are acquired. The reference electrode adopts an AFz and CPz channel double-reference-electrode arrangement scheme according to equipment, the sampling frequency is 1000Hz, and the acquired electroencephalogram signal data are transmitted to a computer through a local area network.
(3) The user adjusts the brain-controlled micro-expression attribute decision threshold. Namely the ratio of the electromyographic artifact component energy in the electroencephalogram signalAt the position of
And in time, judging whether the user executes the brain control micro expression.
(4) Setting each truth brain control micro expression decision threshold n epsilon { n by user1，……，n9And subscript numbers represent corresponding brain control microexpression. Namely, the 9 micro expressions respectively need n times of continuous and consistent brain control micro expression recognition results, so that the true brain control micro expression can be judged and effective brain control instructions can be generated. Wherein n is set1～n8≥3，n9Not less than 6, the corresponding settings (matching) of the artificial hand control command (① - ⑧) and the brain control micro-expression of the brain control state start/stop command are as follows:
① lifting eyebrows to control the closing action of palms;
② frown controlling the forefinger operation gesture (forefinger extended, remaining four fingers closed);
③ left-handed mouth controlling inward rotation of wrist;
④ the right-handed mouth controls the outward rotation of the wrist;
⑤ smiling to control the two fingers to pinch;
⑥ Du' ao controls the action of the index finger to return to hook (the other four fingers are closed);
⑦ mouth opening to control the artificial hand to reset (to all fingers to stretch and the wrist to return to normal);
⑧ resting control prosthetic hand motion maintenance;
⑨ the teeth bite to control the start/stop of brain control state.
(5) According to the brain control micro expression corresponding to the brain control state starting/stopping instruction, a user selects to start the brain control state at any time according to personal wishes to make 1 corresponding brain control micro expression.
(6) Starting micro-expression type brain control program
The electroencephalogram signal data forwarding protocol is used, an electroencephalogram signal data client receives electroencephalogram signal sampling data sent by an electroencephalogram signal acquisition device through a local area network, and the data processing work is completed by a micro-expression brain control program.
(7) The micro-expression brain control program receives 8-channel electroencephalogram signals according to a sampling period (100ms duration), and the sampling frequency of the device is 1000Hz, so that the acquired 100ms data actually correspond to 100 electroencephalogram signal sampling points of each 8 channels, and 8 multiplied by 100 original data corresponding to the current sampling period are obtained.
(8) Performing brain-controlled micro-expression attribute determination
The microexpression type brain control program extracts F7 channel data and F8 channel data which are easily interfered by facial muscle myoelectricity in 8 channels (8 multiplied by 100 original data), and the myoelectricity artifact frequency band is quickly extracted by using band-pass filtering, wherein the filtering pass band is (75,500)]Hz, comparing the frequency spectrum energy of the myoelectricity artifact signal with the frequency spectrum energy of the original signal, and calculating the energy ratio of the myoelectricity artifact component in the data, when the energy ratio is
Judging whether the expression belongs to brain-controlled micro expression, and entering the step (9); otherwise, sending a null value to the step (10) and returning to the step (7).
(9) Asynchronous brain control interface start detection (executing brain control state start/stop brain control micro expression recognition)
This step is essentially a 2-class problem of whether the brain-controlled state start/stop micro expression is true or not. The micro-expression brain control program selects a filter passband [0.5,75] Hz to perform band-pass filtering processing on the current 8 multiplied by 100 original data to a pure electroencephalogram signal frequency band, and a brain control state start/stop brain control micro-expression recognition result corresponding to the current sampling period is obtained by utilizing a pre-generated spatial filter and an SVM classifier.
(10) Validity judgment of brain control state start/stop brain control micro-expression recognition result
The micro-expression brain control program reserves the identification result of the micro-expression of starting/stopping the brain control in the current sampling period and a plurality of continuous sampling periods before the sampling period corresponding to the brain control state, takes the identification result of the current sampling period as the standard, and if the identification result is equal to the identification result of the past continuous n9If the secondary recognition results (the brain control state start/stop brain control micro expressions) are consistent, judging that the brain control micro expression recognition result recognized in the current sampling period is true, outputting a recognition result 1, and entering the step (11); otherwise, outputting a recognition result 0, and returning to the step (7).
(11) Brain control state start instruction generation
After a user makes a micro expression of tooth biting (brain control state start/stop brain control micro expression) according to personal wishes to start a brain control state, the micro expression type brain control program starts/stops the brain control micro expression according to the current true brain control state, enables a brain control state zone bit and generates a brain control state start instruction.
(12) Brain-controlled state initiation of controlled object
The micro-expression brain control program sends the generated brain control state starting instruction to the bionic artificial hand driving controller through the Bluetooth, and the bionic artificial hand brain control state prompt lamp turns green.
(13) The user makes corresponding 8 brain-controlled micro expressions (raising eyebrows, frowning, left-falling mouth, right-falling mouth, smiling, mouth-dug, mouth-opening or resting) according to the operation target of the artificial hand for operating the artificial hand; or selecting not to execute the brain control operation, not executing the brain control micro-expression action, and executing the free expression action; or selecting to stop the brain control state and the like, and making 1 corresponding brain control micro expression (tooth biting micro expression).
(14) The micro-expression type brain control program receives the current electroencephalogram signals with the duration of 100ms and 8 channels to judge the brain control micro-expression attributes, judges the brain control micro-expression actions, and enters the step (15); otherwise, sending a null value to the step (16), and continuing to receive the data of the next sampling period (100ms duration) and judging the brain control micro-expression attribute. The step (14) is implemented in the same way as the steps (7) and (8).
(15) Performing brain-controlled micro-expression recognition
This step is essentially a 9-class problem of 9 brain-controlled micro-expression. The classification algorithm used in this step is identical to that in step (9), and the spatial filter and the SVM classifier are generated in advance from user training data.
(16) Brain-controlled micro-expression recognition result validity judgment
The micro-expression brain control program keeps the current sampling period and the continuous n (n is equal to n { n) before the sampling period1，……，n9) } sampling periods correspond to the brain-controlled micro-expression recognition results, the recognition result of the current sampling period is taken as the standard, and if the recognition result of the current sampling period is consistent with the recognition results of n times of past continuous times, the brain-controlled micro-expression recognition result of the current sampling period is judgedIf true, outputting the result of identifying the true brain control micro expression, and entering the step (17); otherwise, returning to the step (14);
specifically, take the recognition result as ① type eyebrow raising micro expression, if n consecutive in the present and past1And (4) if the second recognition is the type ① eyebrow raising micro expression, judging that the identification result of the type ① eyebrow raising micro expression is true, outputting an identification result 1, entering the step (17), otherwise, outputting an identification result 0, and returning to the step (14).
(17) Matching current truth brain control micro-expression instructions
Comparing the real brain control micro expression of the current recognition result with a preset corresponding artificial hand control instruction of the brain control micro expression by the micro expression type brain control program, and entering the step (18) if 8 kinds of artificial hand operation brain control micro expressions (namely the brain control micro expressions are started/stopped in a non-brain control state) are output; otherwise (namely the brain control state starts/stops the brain control micro expression), the step (19) is entered.
(18) And (4) correspondingly generating a brain control instruction by the micro-expression type brain control program according to the current real brain control micro-expression, sending the brain control instruction to the artificial hand driving controller through Bluetooth communication, controlling the artificial hand to execute corresponding actions by the driving motor, and returning to the step (14) after the actions are executed.
(19) And (3) after the user makes the micro expression of the teeth biting again according to personal wishes, the micro expression type brain control program resets the brain control state zone bit according to the current real brain control state start/stop brain control micro expression to generate a brain control state stop instruction, the brain control state stop instruction is sent to the bionic artificial hand drive controller through Bluetooth, the bionic artificial hand brain control state prompt lamp turns to red, the brain control state of the controlled object stops, and the step (5) is returned.
The invention has the advantages that:
1. the asynchronous real-time brain control method driven by the weak myoelectricity artifact micro-expression brain electrical signal provided by the invention takes the short-time (for example, 100ms) brain electrical signal when a user does different brain control micro-expressions as a control signal source, realizes asynchronous and real-time control of a multi-target task of an external controlled object, and effectively improves the quantity of control commands and the output frequency of the control signal.
2. The invention weakens the action amplitude of facial expressions in the brain control process, adds the step of judging the brain control micro-expression attribute, provides the brain control micro-expression attribute judging threshold value which can be automatically adjusted by a user, effectively distinguishes the difference between the daily expressions (on one hand, the brain control expressions in the prior art, and on the other hand, other facial expressions which are not consistent with the brain control micro-expression amplitude of the user) and the brain control state micro-expressions, shortens the electroencephalogram signal duration required by single brain control instruction processing, realizes the real-time detection of an asynchronous brain control interface, and is more consistent with the daily application of the user.
3. The invention provides an effective brain control instruction generation threshold (namely a true brain control micro-expression judgment threshold n) which can be adjusted by a user, different judgment thresholds can be set aiming at different brain control instructions, and the stability, accuracy and flexibility of the brain control instructions under different application targets of the user are improved.
Claims (8)
1. An asynchronous real-time brain control method driven by weak myoelectric artifact micro-expression electroencephalogram signals is characterized in that: the method comprises the following steps:
1) initiating a brain controlled state
Judging the attribute of the facial expression of the user according to the myoelectric artifact of the electroencephalogram signal, if the facial expression belongs to the brain-controlled micro expression, carrying out brain-controlled micro expression recognition and effectiveness judgment on the facial expression, and if the recognized effective brain-controlled micro expression is the brain-controlled state start/stop brain-controlled micro expression, entering the brain-controlled state;
calculating the myoelectricity artifact energy ratio of a prefrontal cortex channel signal of a brain in a signal source by taking an electroencephalogram signal obtained in a single sampling period as the signal source, and judging that the facial expression of a user is brain-controlled micro-expression when the energy ratio is within a certain threshold interval; the threshold interval is specified by a user within the range of 5% -50%;
2) asynchronous real-time control under brain control state
And in the brain control state, judging the attribute of the facial expression of the user according to the myoelectric artifact of the electroencephalogram signal, if the facial expression belongs to the brain control micro expression, carrying out brain control micro expression recognition and effectiveness judgment on the facial expression, controlling the action of the controlled object according to the recognized effective brain control micro expression matched with the control instruction of the controlled object, or starting/stopping the brain control micro expression according to the recognized effective brain control state to stop the brain control state.
2. The asynchronous real-time brain control method driven by the weak myoelectric artifact micro-expression brain electric signal according to claim 1, characterized in that: the sampling period of the electroencephalogram signal is 100 ms.
3. The asynchronous real-time brain control method driven by the micro-emotional brain electrical signals of the weak myoelectric artifacts according to claim 1 or 2, characterized in that: the acquisition channel of the electroencephalogram signals comprises the positions of the prefrontal cortex of the brain, the cerebral marginal system and the cerebral motor cortex channel.
4. The asynchronous real-time brain control method driven by the weak myoelectric artifact micro-expression brain electric signal according to claim 1, characterized in that: the brain-controlled micro-expression is selected from raising eyebrows, frowning, left-handed, right-handed, smiling, mouth-opening, biting, or resting.
5. The asynchronous real-time brain control method driven by the micro-emotional brain electrical signals of the weak myoelectric artifacts according to claim 1 or 2, characterized in that: in the validity judgment, if the recognition results of the brain-controlled micro-expression in the continuous n electroencephalogram signal sampling periods are consistent, the brain-controlled micro-expression is judged to be valid.
6. An asynchronous real-time brain control system driven by weak myoelectric artifact micro-expression electroencephalogram signals is characterized in that: the brain wave signal data client comprises a brain wave signal source module, a brain control micro expression attribute judging module, a true brain control micro expression judging module and a brain control instruction generating and sending module, the electroencephalogram signal source module is used for receiving the electroencephalogram signals of the user periodically collected by the electroencephalogram signal collecting module, the brain control micro-expression attribute judging module is used for determining the brain control micro-expression in the facial expression of the user according to the myoelectric artifact of the electroencephalogram signal, the true brain-controlled micro expression judging module is used for identifying the brain-controlled micro expression made by the user and determining the effectiveness of the identified brain-controlled micro expression, the brain control instruction generating and sending module is used for comparing and matching the brain control instruction corresponding to the effective brain control micro expression and sending the brain control instruction to a controlled object;
the method comprises the steps of taking an electroencephalogram signal obtained in a single sampling period as a signal source, calculating the myoelectricity artifact energy ratio of a prefrontal cortex channel signal of the brain in the signal source, judging that the facial expression of a user is brain-controlled micro-expression when the energy ratio is within a certain threshold interval, and designating the threshold interval by the user within the range of 5% -50%.
7. The asynchronous real-time brain control system driven by the micro-emotional brain electrical signals of the weak myoelectric artifacts according to claim 6, characterized in that: the sampling period of the electroencephalogram signal is 100 ms.
8. The asynchronous real-time brain control system driven by the micro-emotional brain electrical signals of the weak myoelectric artifacts according to claim 7, characterized in that: the brain-controlled micro-expression is selected from raising eyebrows, frowning, left-handed, right-handed, smiling, mouth-opening, biting, or resting; in the validity determination, if the recognition results of the brain-controlled micro-expression in the continuous n electroencephalogram signal sampling periods are consistent, the brain-controlled micro-expression is judged to be valid.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910087028.6A CN109901711B (en) | 2019-01-29 | 2019-01-29 | Asynchronous real-time brain control method driven by weak myoelectricity artifact micro-expression electroencephalogram signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910087028.6A CN109901711B (en) | 2019-01-29 | 2019-01-29 | Asynchronous real-time brain control method driven by weak myoelectricity artifact micro-expression electroencephalogram signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109901711A CN109901711A (en) | 2019-06-18 |
| CN109901711B true CN109901711B (en) | 2020-06-19 |
Family
ID=66944481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910087028.6A Active CN109901711B (en) | 2019-01-29 | 2019-01-29 | Asynchronous real-time brain control method driven by weak myoelectricity artifact micro-expression electroencephalogram signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109901711B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611860B (en) * | 2020-04-22 | 2022-06-28 | 西南大学 | Micro-expression occurrence detection method and detection system |
| US11707233B1 (en) | 2022-12-16 | 2023-07-25 | Wisear | Simultaneous sub-Nyquist acquisition of a plurality of bioelectric signals |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102886102A (en) * | 2012-09-25 | 2013-01-23 | 深圳英智科技有限公司 | Mirror movement neuromodulation system |
| CN108836319A (en) * | 2018-03-08 | 2018-11-20 | 义乌市杰联电子科技有限公司 | A kind of nervous feedback system of fusion individuation encephalomere rule ratio and forehead myoelectricity energy |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923392A (en) * | 2010-09-02 | 2010-12-22 | 上海交通大学 | Asynchronous brain-computer interactive control method for EEG signal |
| CN103494609B (en) * | 2013-10-16 | 2015-05-06 | 南京麦澜德医疗科技有限公司 | Method for indicating electromyographic signal interference and method for removing interference |
| CN105853140B (en) * | 2016-03-24 | 2018-04-17 | 西安交通大学 | The brain control lower limb master of view-based access control model exercise induced passively cooperates with rehabilitation training system |
-
2019
- 2019-01-29 CN CN201910087028.6A patent/CN109901711B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102886102A (en) * | 2012-09-25 | 2013-01-23 | 深圳英智科技有限公司 | Mirror movement neuromodulation system |
| CN108836319A (en) * | 2018-03-08 | 2018-11-20 | 义乌市杰联电子科技有限公司 | A kind of nervous feedback system of fusion individuation encephalomere rule ratio and forehead myoelectricity energy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109901711A (en) | 2019-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106726030B (en) | Brain machine interface system and its application based on Clinical EEG Signals control robot movement | |
| CN101711709B (en) | Method for controlling electrically powered artificial hands by utilizing electro-coulogram and electroencephalogram information | |
| CN107957783A (en) | A kind of Multimode Intelligent control system and method based on brain electricity with myoelectric information | |
| Hargrove et al. | Multiple binary classifications via linear discriminant analysis for improved controllability of a powered prosthesis | |
| US20030176806A1 (en) | Method and system for an intelligent supervisory control system | |
| CN107273798A (en) | A kind of gesture identification method based on surface electromyogram signal | |
| CN104548347A (en) | Pure idea nerve muscle electrical stimulation control and nerve function evaluation system | |
| WO2008097201A1 (en) | A system and method for processing brain signals in a bci system | |
| CN103258215A (en) | Multi-lead correlation analysis electroencephalo-graph (EEG) feature extraction method | |
| CN112732090B (en) | Muscle cooperation-based user-independent real-time gesture recognition method | |
| CN109901711B (en) | Asynchronous real-time brain control method driven by weak myoelectricity artifact micro-expression electroencephalogram signals | |
| CN111584031B (en) | Brain-controlled intelligent limb rehabilitation system based on portable electroencephalogram acquisition equipment and application | |
| Birch et al. | Brain-computer interface research at the Neil Squire Foundation | |
| CN103955270A (en) | Character high-speed input method of brain-computer interface system based on P300 | |
| Fatima et al. | Towards a low cost Brain-computer Interface for real time control of a 2 DOF robotic arm | |
| CN113082448A (en) | Virtual immersion type autism children treatment system based on electroencephalogram signal and eye movement instrument | |
| CN115482907A (en) | Active rehabilitation system combining electroencephalogram and myoelectricity and rehabilitation training method | |
| WO2022099807A1 (en) | Robot natural control method based on electromyographic signal and error electroencephalographic potential | |
| Chen et al. | An adaptive feature extraction method for motor-imagery BCI systems | |
| CN108319367B (en) | Brain-computer interface method based on motion initiation evoked potential | |
| Andronache et al. | Automatic gesture recognition framework based on forearm emg activity | |
| Lisogurski et al. | Identification of finger flexions from continuous EEG as a brain computer interface | |
| CN109814720A (en) | A kind of brain control method and system of equipment | |
| Freer et al. | Adaptive Riemannian BCI for enhanced motor imagery training protocols | |
| Qu et al. | Pattern recognition of motor imagery EEG signal in noninvasive brain-computer interface |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |