CN113589935A - Brain wave interaction method based on artificial intelligence and brain-computer interface cloud server - Google Patents
Brain wave interaction method based on artificial intelligence and brain-computer interface cloud server Download PDFInfo
- Publication number
- CN113589935A CN113589935A CN202110887872.4A CN202110887872A CN113589935A CN 113589935 A CN113589935 A CN 113589935A CN 202110887872 A CN202110887872 A CN 202110887872A CN 113589935 A CN113589935 A CN 113589935A
- Authority
- CN
- China
- Prior art keywords
- signal
- brain
- brain wave
- computer
- instructions
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/01—Indexing scheme relating to G06F3/01
- G06F2203/011—Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a brain wave interaction method based on artificial intelligence and a brain-computer interface cloud server, belonging to the technical field of brain wave interaction and comprising the following steps: s1: acquiring brain wave data: s2: signal analysis and transmission: s3: artificial intelligence signal interaction: s4: and (3) signal content error correction: s5: and (5) feedback information trimming. The brain wave interaction method based on artificial intelligence and the brain-computer interface cloud server can be used for medical treatment, explore potential intentions of people, do not need manual control, are directly controlled through central nervous system sensing signals, realize brain-computer interface and brain wave interaction, reduce inconvenience brought by analysis, save time, transmit instructions more quickly, improve control efficiency, delete wrong information, ensure accuracy of the instructions, reduce external signal interference when collecting brain wave signals, improve collection efficiency and ensure stability of signal transmission.
Description
Technical Field
The invention relates to the technical field of brain wave interaction, in particular to a brain wave interaction method based on artificial intelligence and a brain-computer interface cloud server.
Background
With the rapid development of brain-computer interfaces and industrial internet, the number of edge terminal devices has rapidly increased, and the amount of data generated by the edge terminal devices has reached the level of Zeyte (ZB). The brain-computer interface, also called as "brain port" or "brain-computer fusion perception", is an interface mode for controlling external equipment by the brain established by analyzing electroencephalogram signals, the brain-computer interface establishes a direct information path between the brain of a human or animal and the external equipment, and the biggest trouble of the existing human-computer interaction is that a computer is difficult to understand the scene of conversation and to discover the deep meaning behind the language, so that manual interference removal operation is required, and the interaction process becomes complicated.
Disclosure of Invention
The invention aims to provide an artificial intelligence-based brain wave interaction method and a brain-computer interface cloud server, which have the advantages that brain waves are directly related to actions, consciousness and emotions of human beings, the whole measurement process has no side effect on the human bodies, the brain-computer interface can be used for medical treatment, the potential intention of people is explored, manual control is not needed, the brain-computer interface can be directly controlled through a central nervous system induction signal, interaction between the brain-computer interface and the brain waves is realized, the inconvenience caused by analysis is reduced, the time is saved, the instruction transmission is more quickly carried out, the control efficiency is improved, the wrong information is deleted, the accuracy of the instruction is ensured, the external signal interference is reduced when the brain wave signals are collected, the collection efficiency is improved, and the stability of the signal transmission is ensured, so that the problems in the background technology are solved.
In order to achieve the purpose, the invention provides the following technical scheme:
an artificial intelligence-based brain wave interaction method comprises the following steps:
s1: acquiring brain wave data: the electroencephalogram acquisition module is arranged on the surface of the scalp of a subject and is fixed through an electrode cap; the electroencephalogram acquisition module is connected with a computer and acquires electroencephalogram signals induced by visual stimulation to obtain data required by analysis;
s2: signal analysis and transmission: the brain wave compiling system in the computer receives the brain wave signals induced by the brain wave acquisition module, analyzes the brain wave signals, compiles the analyzed signals into corresponding instructions and transmits the instructions to the computer;
s3: artificial intelligence signal interaction: the computer internal system receives the compiled instruction, executes the instruction, records the instruction information of the instruction in the execution process, collects and integrates the received instruction and stores the integrated instruction;
s4: and (3) signal content error correction: checking the instructions stored in the computer, performing corrective deletion aiming at the same instructions, performing production feedback investigation on the transmitted instructions, and performing regular and accurate investigation aiming at the behaviors operated by the instruction data computer;
s5: feedback information trimming: the control effect of the computer is fed back to the user, the user can adjust the brain control strategy according to the feedback, and the human brain can directly command and control the external equipment in the process through the brain-computer interface.
Further, in S1, the method includes the following steps:
s101: the electrode is arranged on the surface of the scalp of a subject and is fixed by an electrode cap, a user receives the electroencephalogram amplifier and adopts the existing device, a video display is placed at the front end of the user, and the electroencephalogram amplifier is connected with a computer;
s102: opening an operation interface and opening a visual stimulation screen, and expressing the intention of a user by watching a corresponding flickering function key on the visual stimulation screen by utilizing the characteristics that the human brain can generate different electroencephalograms for different things, motion or cognitive activities so as to promote the electroencephalograms to be generated on the cerebral cortex;
s103: the electroencephalogram electrode cap is used for collecting the signal, the signal is filtered, amplified and subjected to analog-to-digital conversion by the electroencephalogram collector body, and then data are transmitted to a computer by adopting a parallel port technology;
s104: the electrode cap is also internally provided with a plurality of groups of brain wave sensors which can sense and record eight thoughts of people, including attention, focusing, participation, attention, excitement, closeness, relaxation, pressure and the like.
Further, in S2, the method includes the following steps:
s201: the brain-computer interface is established through brain wave data acquisition, and a control signal directly comes from a central nervous system and is converted into an external control signal;
s202: the system collects brain signals, extracts features thereof for classification through a signal processing algorithm, and translates the results into control commands of external equipment;
s203: storing control commands compiled by different brain wave signals while extracting the brain wave signals, and regularly updating and inquiring the stored signal translation instructions;
s204: when the stored control commands are stored in a contrasting manner, when one electroencephalogram signal is generated to generate two groups of control commands during examination, the same commands are deleted when the same commands are the same, and when different commands are the different commands, the wrong commands are deleted after verification.
Further, in S3, the method includes the following steps:
s301: dividing a data field N with the length of N into sections, wherein the length of each section is M, respectively calculating the power spectrum of each section, and then averaging, thereby improving the variance characteristic;
s302: allowing each segment to have partial overlap, the data window d (n) of each segment can be a rectangular window, a Hanning window or a Hamming window, and the power spectrum of the i-th segment is set as
In the formula (I), the compound is shown in the specification,
the average power is
S303: through classification detection, mainly reflecting cognitive load, encoding brain wave signals sent by stimulation to form instructions, executing and outputting the instructions by a computer, through a training set,
satisfies the condition yi(w·xi+ b) -1 is equal to or greater than 0, i 1,2, l, according to the dual principle,
further, in S3, the method includes the following steps:
s401: a repository is generated in the computer, the executed instructions are collected and stored, and the stored quality signals are arranged regularly;
s402: arranging a carding system in a computer, carding and inquiring the arranged signal instructions, marking nodes for repeated instructions, and outputting memory instructions;
s403: and eliminating internal error signal instructions, deleting signal instruction records of the internal error signal instructions, and performing key arrangement on the signal instructions of the marked nodes.
Further, in S3, the method includes the following steps:
s501: generating a comparison data questionnaire while executing each signal instruction in the computer, and surveying according to the data;
s502: after analyzing and researching the data, feeding back the data to the user, carrying out substantial investigation aiming at the correctness of brain wave interaction, and carrying out overall investigation according to the accuracy of brain wave interaction realized by the collected brain wave signal;
s503: and collecting incorrect signal flows and analyzing so as to complete the new scheme according to the failure scheme column.
Further, in S102, the method for generating the electroencephalogram signal on the cerebral cortex includes the steps of adopting various types of neural feedback technologies such as vision, hearing, touch and the like to stimulate the brain response signal of the user to the maximum extent, and simultaneously researching a multi-modal brain-computer interaction technology to obtain richer and more stable human-computer interaction instructions.
The invention provides another technical scheme that: a brain-computer interface cloud server based on artificial intelligence comprises a signal collection system, a signal analysis system and a signal transmission system, wherein the signal collection system is in butt joint with an electroencephalogram signal, and the signal collection system converts the electroencephalogram signal into a system instruction through the signal analysis system and transmits the system instruction to a computer through the signal transmission system.
Furthermore, a signal interference shielding module, a brain wave sensor, a signal amplifier and a collecting module are arranged in the signal collecting system, the brain wave sensor senses a brain response signal excited by a user, and the signal amplifier amplifies the signal for filtering and collects the signal through the collecting module.
Furthermore, the signal analysis system classifies the characteristic data of the brain consciousness task state, analyzes the classified signals, compiles the analyzed signals into corresponding instructions and transmits the instructions to the computer through the signal transmission system.
Compared with the prior art, the invention has the beneficial effects that:
the brain wave interaction method based on artificial intelligence and the brain-computer interface cloud server break the classification mode of brain waves according to frequency bands, can adopt wavelet computing technology as a brain wave analysis and computation tool to decompose the brain waves into different brain state values, collect brain wave signals through electrodes and a brain wave collector, can be used for medical treatment and potential intention of people because the brain waves are directly related to actions, consciousness and emotion of the people and the whole measurement process has no side effect on the human body, analyze the brain wave data, output different signal instructions aiming at different emotional characteristics after classifying the brain wave data, thereby transmitting the brain wave data to a computer without manual control, directly controlling through central nervous system induction signals to realize brain-computer interface and brain wave interaction, when different control commands are stored, the emotional characteristics of the same brain wave appearing next time are that the inconvenience caused by analysis is reduced, time is saved, command transmission is carried out more quickly, the control efficiency is improved, wrong information is deleted, the accuracy of the command is ensured, the command information is recorded in the execution process, the received command is collected and integrated and then stored, later-stage investigation and signal output are facilitated, the command is analyzed as a case list, nodes are marked through commonly used commands, the command demand can be generated according to the memory, the use experience can be increased, after the signal command output is completed, data investigation and user feedback are carried out, the accuracy of the command output is detected, the authenticity and the accuracy of output signals in brain wave interaction are ensured, the implementation rate of brain wave interaction is ensured, and a signal interference shielding module is arranged in the signal collection system, Brain wave inductor and signal amplifier and collection module, brain wave inductor senses the brain response signal that the user arouses, signal amplifier amplifies signal filtering, and collect through collection module, signal analysis system has carried out the classification to the characteristic data of brain consciousness task state, and carried out the analysis with categorised signal, compile into corresponding instruction with the signal after the analysis, be carried for in the computer by signal transmission system, through set up signal interference shielding module in signal collection system, can be when brain wave signal collects, reduce external signal interference, improve collection efficiency, guarantee signal transmission's stability.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a flowchart illustrating step S1 according to the present invention;
FIG. 3 is a flowchart illustrating step S2 according to the present invention;
FIG. 4 is a flowchart illustrating step S3 according to the present invention;
FIG. 5 is a flowchart illustrating step S4 according to the present invention;
FIG. 6 is a flowchart illustrating step S5 according to the present invention;
fig. 7 is a block diagram of the signal collection system connection of the present invention.
In the figure: 1. a signal collection system; 11. a signal interference shielding module; 12. a brain wave sensor; 13. a signal amplifier; 14. a collection module; 2. a signal analysis system; 3. a signal transmission system.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a brain wave interaction method based on artificial intelligence and a brain-computer interface cloud server include the following steps:
s1: acquiring brain wave data: the electroencephalogram acquisition module is arranged on the surface of the scalp of a subject and is fixed through an electrode cap; the electroencephalogram acquisition module is connected with a computer and acquires electroencephalogram signals induced by visual stimulation to obtain data required by analysis;
s2: signal analysis and transmission: the brain wave compiling system in the computer receives the brain wave signals induced by the brain wave acquisition module, analyzes the brain wave signals, compiles the analyzed signals into corresponding instructions and transmits the instructions to the computer;
s3: artificial intelligence signal interaction: the computer internal system receives the compiled instruction, executes the instruction, records the instruction information of the instruction in the execution process, collects and integrates the received instruction and stores the integrated instruction;
s4: and (3) signal content error correction: checking the instructions stored in the computer, performing corrective deletion aiming at the same instructions, performing production feedback investigation on the transmitted instructions, and performing regular and accurate investigation aiming at the behaviors operated by the instruction data computer;
s5: feedback information trimming: the control effect of the computer is fed back to the user, the user can adjust the brain control strategy according to the feedback, and the human brain can directly command and control the external equipment in the process through the brain-computer interface.
Referring to fig. 2, the method for S1 includes the following steps:
s101: the electrode is arranged on the surface of the scalp of a subject and is fixed by an electrode cap, a user receives the electroencephalogram amplifier and adopts the existing device, a video display is placed at the front end of the user, and the electroencephalogram amplifier is connected with a computer;
s102: opening an operation interface and opening a visual stimulation screen, and expressing the intention of a user by watching a corresponding flickering function key on the visual stimulation screen by utilizing the characteristics that the human brain can generate different electroencephalograms for different things, motion or cognitive activities so as to promote the electroencephalograms to be generated on the cerebral cortex;
s103: the electroencephalogram electrode cap is used for collecting the signal, the signal is filtered, amplified and subjected to analog-to-digital conversion by the electroencephalogram collector body, and then data are transmitted to a computer by adopting a parallel port technology;
s104: the electrode cap is also internally provided with a plurality of groups of brain wave sensors which can sense and record eight thoughts of people, including attention, focusing, participation, attention, excitement, closeness, relaxation, pressure and the like.
The classification mode of the brain waves according to the frequency bands is broken through, wavelet computing technology can be adopted as an analysis and calculation tool of the brain waves, the brain waves are decomposed into different brain state values, brain wave signals are collected through the electrodes and the brain wave collecting instrument, and the brain waves are directly related to the actions, consciousness and emotion of human beings, and the whole measuring process has no side effect on the human bodies, so that the method can be used for medical treatment and can be used for exploring the potential intentions of people.
Referring to fig. 3, step S2 includes the following steps:
s201: the brain-computer interface is established through brain wave data acquisition, and a control signal directly comes from a central nervous system and is converted into an external control signal;
s202: the system collects brain signals, extracts features thereof for classification through a signal processing algorithm, and translates the results into control commands of external equipment;
s203: storing control commands compiled by different brain wave signals while extracting the brain wave signals, and regularly updating and inquiring the stored signal translation instructions;
s204: when the stored control commands are stored in a contrasting manner, when one electroencephalogram signal is generated to generate two groups of control commands during examination, the same commands are deleted when the same commands are the same, and when different commands are the different commands, the wrong commands are deleted after verification.
Carry out the analysis to brain wave data, output into different signal instruction to different emotion characteristics after classifying brain wave data, thereby transmit for the computer, do not need to control manually, directly control through central nervous system response signal, realize brain computer interface and brain wave interaction, when the control command of true difference is stored, the emotion characteristic that the same brain wave appears next time is, reduce the inconvenience that the analysis brought, save time, the more quick instruction transmission that carries on, improve control efficiency, at the information of deletion mistake, guarantee the accuracy of instruction.
Referring to fig. 4, step S3 includes the following steps:
s301: dividing a data field N with the length of N into sections, wherein the length of each section is M, respectively calculating the power spectrum of each section, and then averaging, thereby improving the variance characteristic;
s302: allowing each segment to have partial overlap, the data window d (n) of each segment can be a rectangular window, a Hanning window or a Hamming window, and the power spectrum of the i-th segment is set as
In the formula (I), the compound is shown in the specification,
the average power is
S303: through classification detection, mainly reflecting cognitive load, encoding brain wave signals sent by stimulation to form instructions, executing and outputting the instructions by a computer, through a training set,
satisfies the condition yi(w·xi+ b) -1 is equal to or greater than 0, i 1,2, l, according to the dual principle,
in the execution process, the instruction information is recorded, and the received instructions are collected, integrated and stored, so that later-stage examination and signal output are facilitated and are analyzed as case lists.
Referring to fig. 5, the method for S3 includes the following steps:
s401: a repository is generated in the computer, the executed instructions are collected and stored, and the stored quality signals are arranged regularly;
s402: arranging a carding system in a computer, carding and inquiring the arranged signal instructions, marking nodes for repeated instructions, and outputting memory instructions;
s403: and eliminating internal error signal instructions, deleting signal instruction records of the internal error signal instructions, and performing key arrangement on the signal instructions of the marked nodes.
By marking nodes for common instructions, the instruction requirements can be generated according to memory, and the use experience can be increased.
Please refer to fig. 6, which is directed to S3, including the following steps:
s501: generating a comparison data questionnaire while executing each signal instruction in the computer, and surveying according to the data;
s502: after analyzing and researching the data, feeding back the data to the user, carrying out substantial investigation aiming at the correctness of brain wave interaction, and carrying out overall investigation according to the accuracy of brain wave interaction realized by the collected brain wave signal;
s503: and collecting incorrect signal flows and analyzing so as to complete the new scheme according to the failure scheme column.
After the signal instruction is output, according to data investigation and user feedback, the accuracy of instruction output is detected, the authenticity and the accuracy of output signals during brain wave interaction are ensured, and the implementation rate of brain wave interaction is ensured.
Aiming at the S102, the method for generating the brain electrical signal stimulation on the cerebral cortex comprises the steps of adopting various types of nerve feedback technologies such as vision, auditory sensation and touch sensation to stimulate the brain response signal of the user to the maximum extent, and simultaneously researching a multi-mode brain-computer interaction technology to obtain richer and more stable human-computer interaction instructions.
Referring to fig. 7, the brain-computer interface cloud server includes a signal collection system 1, a signal analysis system 2 and a signal transmission system 3, the signal collection system 1 is connected with an electroencephalogram signal in an abutting mode, the signal collection system 1 converts the electroencephalogram signal into a system command through the signal analysis system 2 and transmits the system command into a computer through the signal transmission system 3, a signal interference shielding module 11, a electroencephalogram sensor 12, a signal amplifier 13 and a collection module 14 are arranged in the signal collection system 1, the electroencephalogram sensor 12 senses a brain response signal excited by a user, the signal amplifier 13 amplifies the signal for filtering and collects the signal through the collection module 14, the signal analysis system 2 classifies feature data of brain consciousness task state, analyzes the classified signal, compiles the analyzed signal into a corresponding command and transmits the command into the computer through the signal transmission system 3, by arranging the signal interference shielding module 11 in the signal collection system 1, external signal interference can be reduced, collection efficiency can be improved, and stability of signal transmission can be ensured when brain wave signals are collected.
In summary, the brain wave interaction method and the brain-computer interface cloud server based on artificial intelligence provided by the invention break the classification mode of brain waves according to frequency bands, can use wavelet computing technology as a brain wave analysis and computation tool to decompose the brain waves into different brain state values, collect brain wave signals through electrodes and a brain wave collector, because the brain waves are directly related to the actions, consciousness and emotion of human beings, and the whole measurement process has no side effect on the human body, can be used for medical treatment and potential intention of people, analyze the brain wave data, classify the brain wave data and output different signal instructions according to different emotional characteristics, thereby transmitting the brain wave data to a computer without manual control, directly controlling through central nervous system induction signals, realizing the interaction of the brain-computer interface and the brain waves, when different control commands are stored, the emotional characteristics of the same brain wave appearing next time are that the inconvenience caused by analysis is reduced, time is saved, command transmission is carried out more quickly, control efficiency is improved, wrong information is deleted, accuracy of the command is guaranteed, command information is recorded in the execution process, the received command is collected and integrated and then stored, later-stage investigation and signal output are facilitated, analysis is carried out as case lists, nodes are marked on commonly used commands, command requirements can be generated according to memory, use experience can be increased, after signal command output is completed, data investigation and user feedback are carried out, accuracy of command output is detected, authenticity and accuracy of output signals during brain wave interaction are guaranteed, implementation rate of brain wave interaction is guaranteed, and a signal interference shielding module 11 is arranged in the signal collection system 1, Brain wave inductor 12 and signal amplifier 13 and collection module 14, brain wave inductor 12 senses the brain response signal that the user arouses, signal amplifier 13 amplifies signal filtering, and collect through collection module 14, signal analysis system 2 has classified the characteristic data of brain consciousness task state, and analyzed categorised signal, compile into corresponding instruction with the signal after the analysis, carry for the computer by signal transmission system 3, through set up signal interference shielding module 11 in signal collection system 1, can be when the brain wave signal is collected, reduce external signal interference, improve collection efficiency, guarantee signal transmission's stability.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (10)
1. An artificial intelligence-based brain wave interaction method is characterized by comprising the following steps: the method comprises the following steps:
s1: acquiring brain wave data: the electroencephalogram acquisition module is arranged on the surface of the scalp of a subject and is fixed through an electrode cap; the electroencephalogram acquisition module is connected with a computer and acquires electroencephalogram signals induced by visual stimulation to obtain data required by analysis;
s2: signal analysis and transmission: the brain wave compiling system in the computer receives the brain wave signals induced by the brain wave acquisition module, analyzes the brain wave signals, compiles the analyzed signals into corresponding instructions and transmits the instructions to the computer;
s3: artificial intelligence signal interaction: the computer internal system receives the compiled instruction, executes the instruction, records the instruction information of the instruction in the execution process, collects and integrates the received instruction and stores the integrated instruction;
s4: and (3) signal content error correction: checking the instructions stored in the computer, performing corrective deletion aiming at the same instructions, performing production feedback investigation on the transmitted instructions, and performing regular and accurate investigation aiming at the behaviors operated by the instruction data computer;
s5: feedback information trimming: the control effect of the computer is fed back to the user, the user can adjust the brain control strategy according to the feedback, and the human brain can directly command and control the external equipment in the process through the brain-computer interface.
2. The brain wave interaction method based on artificial intelligence of claim 1, wherein: in the step S1, the method includes the following steps:
s101: the electrode is arranged on the surface of the scalp of a subject and is fixed by an electrode cap, a user receives the electroencephalogram amplifier and adopts the existing device, a video display is placed at the front end of the user, and the electroencephalogram amplifier is connected with a computer;
s102: opening an operation interface and opening a visual stimulation screen, and expressing the intention of a user by watching a corresponding flickering function key on the visual stimulation screen by utilizing the characteristics that the human brain can generate different electroencephalograms for different things, motion or cognitive activities so as to promote the electroencephalograms to be generated on the cerebral cortex;
s103: the electroencephalogram electrode cap is used for collecting the signal, the signal is filtered, amplified and subjected to analog-to-digital conversion by the electroencephalogram collector body, and then data are transmitted to a computer by adopting a parallel port technology;
s104: the electrode cap is also internally provided with a plurality of groups of brain wave sensors which can sense and record eight thoughts of people, including attention, focusing, participation, attention, excitement, closeness, relaxation, pressure and the like.
3. The brain wave interaction method based on artificial intelligence of claim 1, wherein: in the step S2, the method includes the following steps:
s201: the brain-computer interface is established through brain wave data acquisition, and a control signal directly comes from a central nervous system and is converted into an external control signal;
s202: the system collects brain signals, extracts features thereof for classification through a signal processing algorithm, and translates the results into control commands of external equipment;
s203: storing control commands compiled by different brain wave signals while extracting the brain wave signals, and regularly updating and inquiring the stored signal translation instructions;
s204: when the stored control commands are stored in a contrasting manner, when one electroencephalogram signal is generated to generate two groups of control commands during examination, the same commands are deleted when the same commands are the same, and when different commands are the different commands, the wrong commands are deleted after verification.
4. The brain wave interaction method based on artificial intelligence of claim 1, wherein: in the step S3, the method includes the following steps:
s301: dividing a data field N with the length of N into sections, wherein the length of each section is M, respectively calculating the power spectrum of each section, and then averaging, thereby improving the variance characteristic;
s302: allowing each segment to have partial overlap, the data window d (n) of each segment can be a rectangular window, a Hanning window or a Hamming window, and the power spectrum of the i-th segment is set as
In the formula (I), the compound is shown in the specification,
the average power is
S303: through classification detection, mainly reflecting cognitive load, encoding brain wave signals sent by stimulation to form instructions, executing and outputting the instructions by a computer, through a training set,
satisfies the condition yi(w·xi+ b) -1 is equal to or greater than 0, i 1,2, l, according to the dual principle,
5. the brain wave interaction method based on artificial intelligence of claim 4, wherein: in the step S3, the method includes the following steps:
s401: a repository is generated in the computer, the executed instructions are collected and stored, and the stored quality signals are arranged regularly;
s402: arranging a carding system in a computer, carding and inquiring the arranged signal instructions, marking nodes for repeated instructions, and outputting memory instructions;
s403: and eliminating internal error signal instructions, deleting signal instruction records of the internal error signal instructions, and performing key arrangement on the signal instructions of the marked nodes.
6. The brain wave interaction method based on artificial intelligence of claim 5, wherein: in the step S3, the method includes the following steps:
s501: generating a comparison data questionnaire while executing each signal instruction in the computer, and surveying according to the data;
s502: after analyzing and researching the data, feeding back the data to the user, carrying out substantial investigation aiming at the correctness of brain wave interaction, and carrying out overall investigation according to the accuracy of brain wave interaction realized by the collected brain wave signal;
s503: and collecting incorrect signal flows and analyzing so as to complete the new scheme according to the failure scheme column.
7. The brain wave interaction method based on artificial intelligence of claim 6, wherein: aiming at the S102, the method for generating the brain electrical signal stimulation on the cerebral cortex comprises the steps of adopting various types of nerve feedback technologies such as vision, auditory sensation and touch sensation to stimulate the brain response signal of the user to the maximum extent, and simultaneously researching a multi-mode brain-computer interaction technology to obtain richer and more stable human-computer interaction instructions.
8. The artificial intelligence based brain-computer interface cloud server of claim 7, wherein: the brain-computer interface cloud server comprises a signal collection system (1), a signal analysis system (2) and a signal transmission system (3), wherein the signal collection system (1) is in butt joint with the electroencephalogram signals, the signal collection system (1) converts the electroencephalogram signals into system instructions through the signal analysis system (2), and the system instructions are transmitted into a computer through the signal transmission system (3).
9. The artificial intelligence based brain-computer interface cloud server of claim 8, wherein: the signal collection system (1) is internally provided with a signal interference shielding module (11), a brain wave sensor (12), a signal amplifier (13) and a collection module (14), the brain wave sensor (12) senses a brain response signal excited by a user, and the signal amplifier (13) amplifies the signal and filters the signal, and the signal is collected through the collection module (14).
10. The artificial intelligence based brain-computer interface cloud server of claim 9, wherein: the signal analysis system (2) classifies the characteristic data of the brain consciousness task state, analyzes the classified signals, compiles the analyzed signals into corresponding instructions, and transmits the corresponding instructions to the computer through the signal transmission system (3).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110887872.4A CN113589935A (en) | 2021-08-03 | 2021-08-03 | Brain wave interaction method based on artificial intelligence and brain-computer interface cloud server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110887872.4A CN113589935A (en) | 2021-08-03 | 2021-08-03 | Brain wave interaction method based on artificial intelligence and brain-computer interface cloud server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113589935A true CN113589935A (en) | 2021-11-02 |
Family
ID=78254615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110887872.4A Pending CN113589935A (en) | 2021-08-03 | 2021-08-03 | Brain wave interaction method based on artificial intelligence and brain-computer interface cloud server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113589935A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114201041A (en) * | 2021-11-09 | 2022-03-18 | 北京电子工程总体研究所 | Human-computer interaction command method and device based on brain-computer interface |
| CN115153531A (en) * | 2022-06-22 | 2022-10-11 | 南开大学 | Method for detecting brain state stability characteristics |
| CN117159385A (en) * | 2023-09-19 | 2023-12-05 | 广东实验中学 | Intelligent medicine feeding system for disabled people fusing brain-computer interface technology |
-
2021
- 2021-08-03 CN CN202110887872.4A patent/CN113589935A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114201041A (en) * | 2021-11-09 | 2022-03-18 | 北京电子工程总体研究所 | Human-computer interaction command method and device based on brain-computer interface |
| CN114201041B (en) * | 2021-11-09 | 2024-01-26 | 北京电子工程总体研究所 | Man-machine interaction command method and device based on brain-computer interface |
| CN115153531A (en) * | 2022-06-22 | 2022-10-11 | 南开大学 | Method for detecting brain state stability characteristics |
| CN117159385A (en) * | 2023-09-19 | 2023-12-05 | 广东实验中学 | Intelligent medicine feeding system for disabled people fusing brain-computer interface technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Depression recognition using machine learning methods with different feature generation strategies | |
| Wang et al. | Channel selection method for EEG emotion recognition using normalized mutual information | |
| Huang et al. | Differences first in asymmetric brain: A bi-hemisphere discrepancy convolutional neural network for EEG emotion recognition | |
| CN110969108B (en) | Limb action recognition method based on autonomic motor imagery electroencephalogram | |
| CN113589935A (en) | Brain wave interaction method based on artificial intelligence and brain-computer interface cloud server | |
| CN111544015B (en) | Cognitive power-based control work efficiency analysis method, device and system | |
| CN112932502A (en) | Electroencephalogram emotion recognition method combining mutual information channel selection and hybrid neural network | |
| CN111598453B (en) | Control work efficiency analysis method, device and system based on execution force in virtual scene | |
| CN114533086B (en) | Motor imagery brain electrolysis code method based on airspace characteristic time-frequency transformation | |
| Kalaivani et al. | Prediction of biomedical signals using deep learning techniques | |
| CN116400800B (en) | ALS patient human-computer interaction system and method based on brain-computer interface and artificial intelligence algorithm | |
| CN115376695A (en) | Method, system and device for neuropsychological assessment and intervention based on augmented reality | |
| CN110584657A (en) | Attention detection method and system | |
| Li et al. | Emotion recognition based on multiple physiological signals | |
| CN113935380A (en) | Self-adaptive motor imagery brain-computer interface method and system based on template matching | |
| CN117883082A (en) | Abnormal emotion recognition method, system, equipment and medium | |
| CN113558644A (en) | Emotion classification method, medium and equipment for 3D matrix and multidimensional convolution network | |
| CN117612710A (en) | Medical diagnosis auxiliary system based on electroencephalogram signals and artificial intelligence classification | |
| CN117918863A (en) | Method and system for processing brain electrical signal real-time artifacts and extracting features | |
| CN113180662A (en) | EEG signal-based anxiety state intervention method and system | |
| CN112957049A (en) | Attention state monitoring device and method based on brain-computer interface equipment technology | |
| CN109431499B (en) | Botanic person home care auxiliary system and auxiliary method | |
| CN116115240A (en) | Electroencephalogram emotion recognition method based on multi-branch chart convolution network | |
| Manoni et al. | Long-term polygraphic monitoring through mems and charge transfer for low-power wearable applications | |
| Lu et al. | Study on characteristic of epileptic multi-electroencephalograph base on Hilbert-Huang transform and brain network dynamics |
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 |