CN110974219A - Human brain idea recognition system based on invasive BCI - Google Patents
Human brain idea recognition system based on invasive BCI Download PDFInfo
- Publication number
- CN110974219A CN110974219A CN201911323418.5A CN201911323418A CN110974219A CN 110974219 A CN110974219 A CN 110974219A CN 201911323418 A CN201911323418 A CN 201911323418A CN 110974219 A CN110974219 A CN 110974219A
- Authority
- CN
- China
- Prior art keywords
- signal
- electroencephalogram
- algorithm
- idea
- human brain
- 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
- 210000004556 brain Anatomy 0.000 title claims abstract description 67
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 56
- 238000010801 machine learning Methods 0.000 claims abstract description 22
- 238000013135 deep learning Methods 0.000 claims abstract description 19
- 230000005540 biological transmission Effects 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000008054 signal transmission Effects 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 36
- 238000007917 intracranial administration Methods 0.000 claims description 25
- 238000004458 analytical method Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 210000001061 forehead Anatomy 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000012880 independent component analysis Methods 0.000 claims description 6
- 238000003909 pattern recognition Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 210000001652 frontal lobe Anatomy 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 claims description 3
- 239000012620 biological material Substances 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000007635 classification algorithm Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000004070 electrodeposition Methods 0.000 claims description 3
- 230000004424 eye movement Effects 0.000 claims description 3
- 238000002513 implantation Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 239000013307 optical fiber Substances 0.000 claims description 3
- 238000010223 real-time analysis Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000002490 cerebral effect Effects 0.000 claims 1
- 238000007477 logistic regression Methods 0.000 claims 1
- 230000008451 emotion Effects 0.000 abstract description 4
- 230000003993 interaction Effects 0.000 abstract description 4
- 239000000284 extract Substances 0.000 abstract 1
- 208000019901 Anxiety disease Diseases 0.000 description 6
- 230000006996 mental state Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000036506 anxiety Effects 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 210000005013 brain tissue Anatomy 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000008909 emotion recognition Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002599 functional magnetic resonance imaging Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 210000004498 neuroglial cell Anatomy 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 210000002442 prefrontal cortex Anatomy 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003936 working memory Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/168—Evaluating attention deficit, hyperactivity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/377—Electroencephalography [EEG] using evoked responses
Abstract
The invention discloses a human brain idea recognition system based on an invasive BCI (brain computer interaction) device. The system comprises a specially-made invasive brain wave collecting device component, a specially-made infinite signal transmission device component (the two components are collectively called specially-made invasive BCI devices), a mobile terminal APP for signal transmission and an electroencephalogram signal processing algorithm. The working principle of the system is as follows: (1) a specially-made invasive electroencephalogram signal device collects three-dimensional time-space electroencephalogram signals in the brain; (2) the signal enters a special transmission device, is synchronously amplified and coded, and is wirelessly transmitted to a mobile terminal; (3) after the mobile terminal receives the signals, the mobile terminal APP and the cloud terminal carry out real-time communication and upload electroencephalogram signals; (4) the cloud receives the electroencephalogram signals, decodes the electroencephalogram signals, identifies the signal stability through a preprocessing algorithm, extracts effective signal characteristics, identifies the signals through algorithms based on electroencephalogram machine learning and deep learning, identifies different emotions, ideas, imagined pictures, sounds, characters and the like of the human brain, returns the identification results to the mobile terminal for display, and can be synchronously applied to other human brain intelligent control devices to serve as signal input.
Description
The technical field is as follows:
the invention belongs to the technical field of human brain intracranial electroencephalogram signal identification, and particularly designs a system method for counting invasive BCI equipment human idea identification.
Background art:
the idea of the human brain is classified into emotion, hobby, instantaneous idea, motion instruction, and the like, and the most common application is to recognize the idea of the human brain on characters, music, images, and the like and to efficiently output the idea to a computer. The idea or idea of the human brain is traceable and can be obtained by collecting widely distributed brain wave changes in the cerebral cortex. Related art includes, but is not limited to: invasive and non-invasive techniques for intracranial signal collection, such as functional magnetic resonance imaging techniques; a technique of constructing three-dimensional electric field data with an electrode array; different ideas of human brain and algorithm technology of instruction recognition, etc.
The existing brain invasive equipment is mainly applied to the aspects of physically controlling disabled persons and the like, and the idea identification is only limited to simple instructions of body movement, and the comprehensive identification of abundant brain ideas is not available. For equipment for collecting human brain electrical signals, three-dimensional signal collection is few, and the equipment is limited to brain electrical signal collection of specific signal points, so that much information is lost, and the rich human brain state cannot be judged. The non-invasive three-dimensional brain signal detection system represented by functional nuclear magnetic imaging has insufficient precision in time domain and frequency domain to reach the degree of idea identification, and the required equipment is too bulky and expensive, so that the detection in daily life is not convenient.
Therefore, the human brain idea recognition system based on the invasive BCI equipment is designed, and after the functional chip is implanted, the idea state of the human brain can be detected in real time.
The invention content is as follows:
the invention aims to provide a comprehensive system based on invasive brain-computer interaction equipment, which aims to solve the problem of comprehensive identification of rich ideas of human brain, which cannot be solved by other methods at present. Real-time transmission and calculation, and the embedded equipment and wireless transmission technology which are packaged enable the scheme to carry out detection and calculation of brain signals in a wide range of life scenes. The analysis of the three-dimensional brain waves is realized through a machine learning algorithm and a deep learning algorithm, and the reading of human brain ideas and the application of idea control machine equipment can be provided.
The technical scheme is as follows:
in order to achieve the above purpose, the invention provides the following technical scheme: a human brain idea recognition system based on invasive BCI (brain computer interaction) equipment. The system comprises a set of idea information discrimination steps based on an invasive brain wave signal, and the steps apply four parts of a specially-made invasive brain wave collecting device component, a specially-made infinite signal transmission device component (the two components are commonly called as specially-made invasive BCI (brain computer interface) device), a mobile terminal APP for signal transmission and an electroencephalogram signal processing algorithm. The system comprises the following steps of discriminating the mind information based on the invasive electroencephalogram signal:
the first step is as follows: original electroencephalogram signals are collected through a specially-made implantable device, and the signals collected by the array type electrode arrangement can be restored into intracranial three-dimensional electroencephalogram signals;
the second step is that: the signal is synchronously amplified and coded through intracranial signal wireless transmission equipment and is transmitted to a mobile terminal through a 5G or Bluetooth module;
the third step: after receiving the signal, the mobile terminal APP directly uploads an undecoded signal file packet to a cloud high-performance computing server cluster for signal analysis and computation;
the fourth step: at a cloud server, applying a preprocessing algorithm to perform signal decoding, stability analysis and feature extraction;
the fifth step: and (3) performing signal analysis and calculation by using a machine learning algorithm and a deep learning algorithm, judging whether the characteristic parameters of various conventional ideas reach threshold values, and combining to obtain a comprehensive real-time human brain idea result.
Preferably: the signal acquisition and transmission steps in the first step and the second step are as follows:
the first step is as follows: the electrode array implantation position of the intracranial electroencephalogram signal acquisition equipment implanted by a user is positioned at the longitudinal fissure of the forehead and is vertically arranged, each electrode is divided into a left group and a right group, and the frontal lobe cortex of the left hemisphere and the right hemisphere are respectively detected;
the second step is that: the electrode array of the implanted equipment is transmitted to a signal processing and external transmission part assembly of the implanted equipment through a high-performance biomaterial optical fiber, and the assembly is periodically charged wirelessly through an external power supply device attached to the forehead;
the third step: the multi-electrode electroencephalogram signals are amplified by signal transmission equipment, then are integrated into high-frequency digital signals with larger information content through cross coding, and are transmitted to a mobile terminal;
the fourth step: and the mobile terminal transmits the received signal to the cloud server.
Preferably: the fourth step is that the calculation flow of the signal analysis and pretreatment steps is as follows:
the first step is as follows: decoding the high-speed transmitted digital signals, and restoring the digital signals into electroencephalogram signals of a multi-channel electrode array;
the second step is that: noise removal and conversion change are carried out through a filtering algorithm and principal component analysis, and the eye movement interference, the electrocardio interference, the myoelectricity interference, the power frequency interference, the high-frequency noise interference and the like are removed mainly through a regression method, a self-adaptive filtering method and an independent component analysis method;
the third step: constructing three-dimensional electric potential field distribution of the left and right frontal lobes by using different electrode position relations;
the fourth step: and performing time domain and frequency domain parameter extraction and feature transformation engineering on the analyzed three-dimensional electric wave change, and performing feature classification to be analyzed in the next step.
Preferably: and in the fifth step, the process of the electroencephalogram signal idea recognition and result judgment is as follows:
the first step is as follows: the step comprises the steps of analyzing an electroencephalogram signal by adopting a time domain and a frequency domain, extracting characteristics, identifying a signal and noise initially acquired by the signal, setting a filtering algorithm, and obtaining the most effective signal-to-noise ratio signal acquired based on invasive BCI equipment through different parameter adaptations;
the second step is that: calculating the characteristic combination of a time domain and a frequency domain by using an algorithm of machine learning and deep learning to obtain a series of parameters related to human brain idea;
the third step: establishing and continuously perfecting a human idea parameter feature library, and comparing whether the parameters obtained by real-time analysis reach a certain idea threshold value;
the fourth step: and combining all the ideas reaching the threshold value, judging the comprehensive idea category of the human brain through a classification algorithm, and obtaining a comprehensive result obtained by calculating the ideas of the human brain.
Preferably: and in the fifth step, the pattern recognition and result judgment process of the electroencephalogram signal machine learning is as follows:
the first step is as follows: the method realizes the signal analysis algorithm to process the modeling feature extraction of intracranial three-dimensional electroencephalogram data, and simultaneously introduces algorithm models such as a machine learning model, a decision tree, naive Bayes classification, a least square method, a logic regression, an integration method, a support vector machine, a clustering algorithm principal component analysis, a singular value decomposition, an independent component analysis and the like;
the second step is that: through the machine learning model selected in the first step and the labeled training of the model, index classification and automatic judgment recognition under the correlation of different human ideas and states are respectively carried out on various signal characteristics of a time domain and a frequency domain.
Preferably: the fifth step is that the pattern recognition and result judgment process of the deep learning of the electroencephalogram signal is as follows:
the first step is as follows: for large-scale and long-time user monitoring and identification, along with the robustness requirement and the automatic updating requirement of an intracranial electroencephalogram identification algorithm, along with the increase of the user quantity and the increase of the data set scale, the traditional signal analysis and machine learning algorithm cannot meet the requirement of designing an intracranial electroencephalogram processing model for carrying out an artificial intelligence algorithm in the aspects of algorithm updating and automatic identification efficiency;
the second step is that: by introducing a deep learning neural network, performing end-to-end deep learning modeling and operation on a GPU high-performance server, and mainly training by using a cyclic neural network structure and a convolution upgrading network structure based on partial intracranial electroencephalogram data with labels to form a classifier and a discriminator;
the third step: and meanwhile, the data set is continuously expanded, the neural network model algorithm is continuously updated, and the precision and the accuracy of the human brain idea index identification are continuously improved.
Compared with the prior art, the invention has the beneficial effects that:
(1) according to the invention, through a real-time wireless transmission and cloud analysis algorithm and an electrode array reasonably distributed in the longitudinal fissure of the brain, the three-dimensional electroencephalogram signals with high resolution in time and space in most areas of the prefrontal cortex of the brain can be analyzed in real time. And enough information is acquired to analyze the mind of the brain, and the information of the left hemisphere and the right hemisphere can be considered. Due to the fact that the monitoring area is wide, real-time transmission and high efficiency of an algorithm are achieved, and quick and accurate idea judgment can be achieved.
(2) The system of the invention designs the invasive electroencephalogram signal equipment in the longitudinal fissure of the brain, avoids a series of pathological changes possibly caused by penetration of a hard brain membrane, and simultaneously avoids the problem that the invasive BCI equipment cannot keep the electrode sensitivity for a long time due to interference of brain tissues and glial cells. The invasive equipment scheme with long-term low maintenance cost is realized. The application of the external wireless charging equipment realizes the control of the volume of the invasive equipment and reduces the damage to the brain tissue.
(3) The invention designs an analysis algorithm for various human brain ideas, and with the increase of user data, a deep learning framework has more recognition functions and can recognize the following but not limited human ideas: mood (joy, sadness, fear, anger, etc.), concentration level, depression and anxiety state, external stimulated brain presentation (text, sound, images, space, etc.), brain active commands (sports, associative, logical reasoning, etc.), working memory, etc.
(4) The invention realizes the detection and the discrimination of index parameters of various ideas such as human brain emotion (joy, sadness, fear, anger and the like), attention concentration degree, depression and anxiety states, external stimulated brain presentation (characters, sound, images, spaces and the like), brain active instructions (movement, association, logic reasoning and the like), work memory and the like, and the numerical value space of the corresponding index is generated by modeling according to a signal recognition algorithm, a machine learning algorithm and a deep learning algorithm to represent and discriminate the interval.
Description of the drawings:
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a block diagram of an invasive electrode alignment configuration of the present invention;
FIG. 3 is a schematic diagram of a signal acquisition and transmission process according to the present invention;
FIG. 4 is a schematic diagram of the signal analysis and pre-processing steps of the present invention;
FIG. 5 is a schematic diagram of an electroencephalogram signal idea identification and result judgment step according to the present invention;
FIG. 6 is a flow chart of a machine learning algorithm of the present invention;
the specific implementation mode is as follows:
the technical solutions in the embodiments of the present invention will be described in detail and removed completely 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 obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative effort belong to the protection scope of the present invention.
Referring to fig. 1-6, the present invention provides a technical solution: a human brain idea recognition system based on invasive BCI (brain computer interaction) equipment. The system comprises a set of ideological information discrimination steps based on an invasive electroencephalogram signal, and specifically comprises the following steps:
the first step is as follows: original electroencephalogram signals are collected through a specially-made implantable device, and the signals collected by the array type electrode arrangement can be restored into intracranial three-dimensional electroencephalogram signals;
the second step is that: the signal is synchronously amplified and coded through intracranial signal wireless transmission equipment and is transmitted to a mobile terminal through a 5G or Bluetooth module;
the third step: after receiving the signal, the mobile terminal APP directly uploads an undecoded signal file packet to a cloud high-performance computing server cluster for signal analysis and computation;
the fourth step: at a cloud server, applying a preprocessing algorithm to perform signal decoding, stability analysis and feature extraction;
the fifth step: and (3) performing signal analysis and calculation by using a machine learning algorithm and a deep learning algorithm, judging whether the characteristic parameters of various conventional ideas reach threshold values, and combining to obtain a comprehensive real-time human brain idea result.
In this embodiment, preferably, the signal acquisition and transmission step in the first step and the second step includes:
the first step is as follows: the electrode array implantation position of the intracranial electroencephalogram signal acquisition equipment implanted by a user is positioned at the longitudinal fissure of the forehead and is vertically arranged, each electrode is divided into a left group and a right group, and the frontal lobe cortex of the left hemisphere and the right hemisphere are respectively detected;
the second step is that: the electrode array of the implanted equipment is transmitted to a signal processing and external transmission part assembly of the implanted equipment through a high-performance biomaterial optical fiber, and the assembly is periodically charged wirelessly through an external power supply device attached to the forehead;
the third step: the multi-electrode electroencephalogram signals are amplified by signal transmission equipment, then are integrated into high-frequency digital signals with larger information content through cross coding, and are transmitted to a mobile terminal;
the fourth step: and the mobile terminal transmits the received signal to the cloud server.
In this embodiment, preferably, the calculation flow of the signal analyzing and preprocessing step in the fourth step is as follows:
the first step is as follows: decoding the high-speed transmitted digital signals, and restoring the digital signals into electroencephalogram signals of a multi-channel electrode array;
the second step is that: noise removal and conversion change are carried out through a filtering algorithm and principal component analysis, and the eye movement interference, the electrocardio interference, the myoelectricity interference, the power frequency interference, the high-frequency noise interference and the like are removed mainly through a regression method, a self-adaptive filtering method and an independent component analysis method;
the third step: constructing three-dimensional electric potential field distribution of the left and right frontal lobes by using different electrode position relations;
the fourth step: and performing time domain and frequency domain parameter extraction and feature transformation engineering on the analyzed three-dimensional electric wave change, and performing feature classification to be analyzed in the next step.
In this embodiment, preferably, the process of the electroencephalogram signal idea recognition and result judgment in the fifth step is as follows:
the first step is as follows: the step comprises the steps of analyzing an electroencephalogram signal by adopting a time domain and a frequency domain, extracting characteristics, identifying a signal and noise initially acquired by the signal, setting a filtering algorithm, and obtaining the most effective signal-to-noise ratio signal acquired based on invasive BCI equipment through different parameter adaptations;
the second step is that: calculating the characteristic combination of a time domain and a frequency domain by using an algorithm of machine learning and deep learning to obtain a series of parameters related to human brain idea;
the third step: establishing and continuously perfecting a human idea parameter feature library, and comparing whether the parameters obtained by real-time analysis reach a certain idea threshold value;
the fourth step: and combining all the ideas reaching the threshold value, judging the comprehensive idea category of the human brain through a classification algorithm, and obtaining a comprehensive result obtained by calculating the ideas of the human brain.
In this embodiment, preferably, the pattern recognition and result judgment process of the electroencephalogram signal machine learning in the fifth step is as follows:
the first step is as follows: the method realizes the signal analysis algorithm to process the modeling feature extraction of intracranial three-dimensional electroencephalogram data, and simultaneously introduces algorithm models such as a machine learning model, a decision tree, naive Bayes classification, a least square method, a logic regression, an integration method, a support vector machine, a clustering algorithm principal component analysis, a singular value decomposition, an independent component analysis and the like;
the second step is that: through the machine learning model selected in the first step and the labeled training of the model, index classification and automatic judgment recognition under the correlation of different human ideas and states are respectively carried out on various signal characteristics of a time domain and a frequency domain.
In this embodiment, preferably, the pattern recognition and result judgment process of deep learning of the electroencephalogram signal in the fifth step is as follows:
the first step is as follows: for large-scale and long-time user monitoring and identification, along with the robustness requirement and the automatic updating requirement of an intracranial electroencephalogram identification algorithm, along with the increase of the user quantity and the increase of the data set scale, the traditional signal analysis and machine learning algorithm cannot meet the requirement of designing an intracranial electroencephalogram processing model for carrying out an artificial intelligence algorithm in the aspects of algorithm updating and automatic identification efficiency;
the second step is that: by introducing a deep learning neural network, performing end-to-end deep learning modeling and operation on a GPU high-performance server, and mainly training by using a cyclic neural network structure and a convolution upgrading network structure based on partial intracranial electroencephalogram data with labels to form a classifier and a discriminator;
the third step: and meanwhile, the data set is continuously expanded, the neural network model algorithm is continuously updated, and the precision and the accuracy of the human brain idea index identification are continuously improved.
The emotion-related identification reference parameter range in the idea perception of the invention is as follows:
emotion recognition: reference ranges:
happy: the weakness is less than 60; normal [60, 120 ]; intensity > 120
Sadness: weak is less than 10; normal [10, 20 ]; intensity > 30
Fear: the weakness is less than 40; normal [40, 80 ]; intensity > 80
Anger: the weakness is less than 90; intensity > 120
Attention concentration degree identification: reference ranges:
the strong range of the attention control force is < 60
The normal range of attention control is [60-90]
The weak range of attention control is > 90
Depression and anxiety state identification: reference ranges:
good mental status without signs of depression 80
There is slight abnormality in the normal mental state, there is mild depression with the range of [40-80] mental state, there is 40 of mild depression and above
The mental state was normal and good, and there was no anxiety sign 5
There are slight abnormalities in mental state, the reference range for mild anxiety is [5-40] there are abnormalities in mental state, and the reference range for mild anxiety is 40.
Claims (6)
1. Human brain will identification system based on invasive BCI equipment, its characterized in that: the method comprises the steps of acquiring, transmitting and judging brain intracranial electroencephalograms, wherein the steps of acquiring, transmitting and judging the brain intracranial electroencephalograms comprise:
the first step is as follows: the original electroencephalogram signal is collected through a specially-made implantable device, and the signals collected by the array electrode arrangement can be restored into intracranial three-dimensional electroencephalogram signals;
the second step is that: the signal is synchronously amplified and coded through intracranial signal wireless transmission equipment and is transmitted to a mobile terminal through a 5G or Bluetooth module;
the third step: after receiving the signal, the mobile terminal APP directly uploads an undecoded signal file packet to a cloud high-performance computing server cluster for signal analysis and computation;
the fourth step: at a cloud server, applying a preprocessing algorithm to perform signal decoding, stability analysis and feature extraction;
the fifth step: and (3) performing signal analysis and calculation by using a machine learning algorithm and a deep learning algorithm, judging whether the characteristic parameters of various conventional ideas reach a threshold value, and combining to obtain a comprehensive real-time human brain idea result.
2. The human brain idea identification system based on invasive BCI equipment according to claim 1, characterized in that: the specific flow of the signal acquisition and transmission step in the first step and the second step is as follows:
the first step is as follows: the electrode array implantation position of the intracranial electroencephalogram signal acquisition equipment implanted by a user is positioned at the forehead cerebral longitudinal fissure and is vertically arranged, each electrode is divided into a left group and a right group, and the forehead cortex of the left hemisphere and the forehead cortex of the right hemisphere are respectively detected;
the second step is that: the electrode array of the implanted equipment is transmitted to a signal processing and external transmission part assembly of the implanted equipment through a high-performance biomaterial optical fiber, and the assembly is periodically charged wirelessly through an external power supply device attached to the forehead;
the third step: the multi-electrode electroencephalogram signals are amplified by signal transmission equipment, then are integrated into high-frequency digital signals with larger information content through cross coding, and are transmitted to a mobile terminal;
the fourth step: and the mobile terminal transmits the received signal to the cloud server.
3. The human brain idea identification system based on invasive BCI equipment according to claim 1, characterized in that: the fourth step is that the calculation flow of the signal analysis and pretreatment steps is as follows:
the first step is as follows: decoding the high-speed transmitted digital signals, and restoring the digital signals into electroencephalogram signals of a multi-channel electrode array;
the second step is that: noise removal and conversion change are carried out through a filtering algorithm and principal component analysis, and the eye movement interference, the electrocardio interference, the myoelectricity interference, the power frequency interference, the high-frequency noise interference and the like are removed mainly through a regression method, a self-adaptive filtering method and an independent component analysis method;
the third step: constructing three-dimensional potential field distribution of the left and right frontal lobes by using different electrode position relations;
the fourth step: and performing time domain and frequency domain parameter extraction and feature transformation engineering on the analyzed three-dimensional electric wave change, and performing feature classification to be analyzed in the next step.
4. The human brain idea identification system based on invasive BCI equipment according to claim 1, characterized in that: and in the fifth step, the process of the electroencephalogram signal idea recognition and result judgment is as follows:
the first step is as follows: the step comprises the steps of analyzing an electroencephalogram signal by adopting a time domain and a frequency domain, extracting characteristics, identifying a signal and noise initially acquired by the signal, setting a filtering algorithm, and obtaining the most effective signal-to-noise ratio signal acquired based on invasive BCI equipment through different parameter adaptations;
the second step is that: calculating the characteristic combination of a time domain and a frequency domain by using an algorithm of machine learning and deep learning to obtain a series of parameters related to human brain idea;
the third step: establishing and continuously perfecting a human idea parameter feature library, and comparing whether the parameters obtained by real-time analysis reach a certain idea threshold value or not;
the fourth step: and combining all the ideas reaching the threshold value, judging the comprehensive idea category of the human brain through a classification algorithm, and obtaining a comprehensive result obtained by calculating the idea of the human brain.
5. The human brain idea identification system based on invasive BCI equipment according to claim 1, characterized in that: and in the fifth step, the pattern recognition and result judgment process of the electroencephalogram signal machine learning is as follows:
the first step is as follows: the method realizes the signal analysis algorithm to process the modeling feature extraction of intracranial three-dimensional electroencephalogram data, and simultaneously introduces algorithm models such as a machine learning model, a decision tree, naive Bayes classification, a least square method, logistic regression, an integration method, a support vector machine, clustering algorithm principal component analysis, singular value decomposition, independent component analysis and the like;
the second step is that: through the machine learning model selected in the first step and the labeled training of the model, index classification and automatic judgment recognition under the correlation of different human ideas and states are respectively carried out on various signal characteristics of a time domain and a frequency domain.
6. The human brain idea identification system based on invasive BCI equipment according to claim 1, characterized in that: the fifth step is that the pattern recognition and result judgment process of the deep learning of the electroencephalogram signal is as follows:
the first step is as follows: for large-scale and long-time user monitoring and identification, along with the robustness requirement and the automatic updating requirement of an intracranial electroencephalogram identification algorithm, along with the increase of the user quantity and the increase of the data set scale, the traditional signal analysis and machine learning algorithm cannot meet the requirement of designing an intracranial electroencephalogram processing model for carrying out an artificial intelligence algorithm in the aspects of algorithm updating and automatic identification efficiency;
the second step is that: end-to-end deep learning modeling and operation are carried out on a GPU high-performance server by introducing a deep learning neural network, and a cyclic neural network structure and a convolution upgrading network structure are mainly used for training based on partial intracranial electroencephalogram data with labels to form a classifier and a discriminator;
the third step: and meanwhile, the data set is continuously expanded, the neural network model algorithm is continuously updated, and the precision and the accuracy of the human brain idea index identification are continuously improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911323418.5A CN110974219A (en) | 2019-12-20 | 2019-12-20 | Human brain idea recognition system based on invasive BCI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911323418.5A CN110974219A (en) | 2019-12-20 | 2019-12-20 | Human brain idea recognition system based on invasive BCI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110974219A true CN110974219A (en) | 2020-04-10 |
Family
ID=70073348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911323418.5A Pending CN110974219A (en) | 2019-12-20 | 2019-12-20 | Human brain idea recognition system based on invasive BCI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110974219A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111685779A (en) * | 2020-05-27 | 2020-09-22 | 北京脑陆科技有限公司 | Schizophrenia disorder screening method based on portable EEG equipment |
| CN113180605A (en) * | 2021-04-28 | 2021-07-30 | 中国科学院空天信息创新研究院 | Brain disease judgment system based on machine learning and intracranial multi-modal information fusion |
| CN113209470A (en) * | 2021-04-07 | 2021-08-06 | 北京脑陆科技有限公司 | Spine injured motor nerve control method and system based on invasive BCI |
| CN113209471A (en) * | 2021-04-07 | 2021-08-06 | 北京脑陆科技有限公司 | Signal acquisition and analysis method and system for deep intracerebral stimulation DBS equipment |
| CN113467609A (en) * | 2021-05-28 | 2021-10-01 | 北京脑陆科技有限公司 | Architecture method, device, terminal and medium of brain-computer interface BCI (brain computer interface) equipment |
| CN114356074A (en) * | 2021-11-30 | 2022-04-15 | 上海交通大学 | Animal brain-computer interface implementation method and system based on in-vivo fluorescence signal |
| CN114356074B (en) * | 2021-11-30 | 2024-04-23 | 上海交通大学 | Animal brain-computer interface implementation method and system based on in-vivo fluorescence signals |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080161894A1 (en) * | 2001-08-31 | 2008-07-03 | Biocontrol Medical Ltd. | Method for surgically implanting an electrode device |
| US20090093964A1 (en) * | 2005-11-17 | 2009-04-09 | Universite De Rennes 1 | Multi-dimensional parameter identification method and device: application to the location and reconstruction of deep electrical activities by means of surface observations |
| CN102770066A (en) * | 2009-12-01 | 2012-11-07 | 纽诺维有限公司 | Multi-channel brain or cortical activity monitoring and method |
| CN102894971A (en) * | 2011-07-29 | 2013-01-30 | 中国科学院沈阳自动化研究所 | Helmet for acquiring brain signal by combining electroencephalography with near-infrared spectroscopy |
| AU2013200230A1 (en) * | 2005-03-01 | 2013-01-31 | Advanced Neuromodulation Systems, Inc. | Method of treating depression, mood disorders and anxiety disorders using neuromodulation |
| AU2013205434A1 (en) * | 2013-04-26 | 2014-11-13 | Opie, Nicholas Lachlan DR | An implantable medical device for minimally invasive cortical measurement and stimulation |
| CN104635934A (en) * | 2015-02-28 | 2015-05-20 | 东南大学 | Brain-machine interface method based on logic thinking and imaginal thinking |
| CN105307565A (en) * | 2013-05-07 | 2016-02-03 | 圣犹达医疗用品电生理部门有限公司 | Utilization of electrode spatial arrangements for characterizing cardiac conduction conditions |
| CN105657638A (en) * | 2014-11-28 | 2016-06-08 | 三星电子株式会社 | Method and device for function sharing between electronic devices |
| CN106512216A (en) * | 2016-12-20 | 2017-03-22 | 北京品驰医疗设备有限公司 | Sacral nerve stimulation device having wireless charging device |
| WO2017084416A1 (en) * | 2015-11-17 | 2017-05-26 | 天津大学 | Feedback system based on motor imagery brain-computer interface |
| CN108733201A (en) * | 2017-04-19 | 2018-11-02 | 辽宁科技大学 | Aircraft three-dimensional extraterrestrial target search system and method based on brain electricity Yu eye electricity |
| KR20190030612A (en) * | 2017-09-14 | 2019-03-22 | 고려대학교 산학협력단 | System for providing subject-independent brain-computer interface and method thereof |
| CN109743656A (en) * | 2019-03-15 | 2019-05-10 | 南京邮电大学 | Smart motion earphone and its implementation and system based on brain electricity idea |
-
2019
- 2019-12-20 CN CN201911323418.5A patent/CN110974219A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080161894A1 (en) * | 2001-08-31 | 2008-07-03 | Biocontrol Medical Ltd. | Method for surgically implanting an electrode device |
| AU2013200230A1 (en) * | 2005-03-01 | 2013-01-31 | Advanced Neuromodulation Systems, Inc. | Method of treating depression, mood disorders and anxiety disorders using neuromodulation |
| US20090093964A1 (en) * | 2005-11-17 | 2009-04-09 | Universite De Rennes 1 | Multi-dimensional parameter identification method and device: application to the location and reconstruction of deep electrical activities by means of surface observations |
| CN102770066A (en) * | 2009-12-01 | 2012-11-07 | 纽诺维有限公司 | Multi-channel brain or cortical activity monitoring and method |
| CN102894971A (en) * | 2011-07-29 | 2013-01-30 | 中国科学院沈阳自动化研究所 | Helmet for acquiring brain signal by combining electroencephalography with near-infrared spectroscopy |
| AU2013205434A1 (en) * | 2013-04-26 | 2014-11-13 | Opie, Nicholas Lachlan DR | An implantable medical device for minimally invasive cortical measurement and stimulation |
| CN105307565A (en) * | 2013-05-07 | 2016-02-03 | 圣犹达医疗用品电生理部门有限公司 | Utilization of electrode spatial arrangements for characterizing cardiac conduction conditions |
| CN105657638A (en) * | 2014-11-28 | 2016-06-08 | 三星电子株式会社 | Method and device for function sharing between electronic devices |
| CN104635934A (en) * | 2015-02-28 | 2015-05-20 | 东南大学 | Brain-machine interface method based on logic thinking and imaginal thinking |
| WO2017084416A1 (en) * | 2015-11-17 | 2017-05-26 | 天津大学 | Feedback system based on motor imagery brain-computer interface |
| CN106512216A (en) * | 2016-12-20 | 2017-03-22 | 北京品驰医疗设备有限公司 | Sacral nerve stimulation device having wireless charging device |
| CN108733201A (en) * | 2017-04-19 | 2018-11-02 | 辽宁科技大学 | Aircraft three-dimensional extraterrestrial target search system and method based on brain electricity Yu eye electricity |
| KR20190030612A (en) * | 2017-09-14 | 2019-03-22 | 고려대학교 산학협력단 | System for providing subject-independent brain-computer interface and method thereof |
| CN109743656A (en) * | 2019-03-15 | 2019-05-10 | 南京邮电大学 | Smart motion earphone and its implementation and system based on brain electricity idea |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111685779A (en) * | 2020-05-27 | 2020-09-22 | 北京脑陆科技有限公司 | Schizophrenia disorder screening method based on portable EEG equipment |
| CN113209470A (en) * | 2021-04-07 | 2021-08-06 | 北京脑陆科技有限公司 | Spine injured motor nerve control method and system based on invasive BCI |
| CN113209471A (en) * | 2021-04-07 | 2021-08-06 | 北京脑陆科技有限公司 | Signal acquisition and analysis method and system for deep intracerebral stimulation DBS equipment |
| CN113180605A (en) * | 2021-04-28 | 2021-07-30 | 中国科学院空天信息创新研究院 | Brain disease judgment system based on machine learning and intracranial multi-modal information fusion |
| CN113467609A (en) * | 2021-05-28 | 2021-10-01 | 北京脑陆科技有限公司 | Architecture method, device, terminal and medium of brain-computer interface BCI (brain computer interface) equipment |
| CN114356074A (en) * | 2021-11-30 | 2022-04-15 | 上海交通大学 | Animal brain-computer interface implementation method and system based on in-vivo fluorescence signal |
| CN114356074B (en) * | 2021-11-30 | 2024-04-23 | 上海交通大学 | Animal brain-computer interface implementation method and system based on in-vivo fluorescence signals |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110974219A (en) | Human brain idea recognition system based on invasive BCI | |
| CN108776788B (en) | Brain wave-based identification method | |
| CN105877766B (en) | A kind of state of mind detection system and method based on the fusion of more physiological signals | |
| CN110353702A (en) | A kind of emotion identification method and system based on shallow-layer convolutional neural networks | |
| CN110604565A (en) | Brain health screening method based on portable EEG equipment | |
| CN111616682B (en) | Epileptic seizure early warning system based on portable electroencephalogram acquisition equipment and application | |
| CN106725452A (en) | Based on the EEG signal identification method that emotion induces | |
| CN110037693A (en) | A kind of mood classification method based on facial expression and EEG | |
| CN108420429A (en) | A kind of brain electricity epilepsy automatic identifying method based on the fusion of various visual angles depth characteristic | |
| CN114533086B (en) | Motor imagery brain electrolysis code method based on airspace characteristic time-frequency transformation | |
| CN107292296A (en) | A kind of human emotion wake-up degree classifying identification method of use EEG signals | |
| CN109359610A (en) | Construct method and system, the data characteristics classification method of CNN-GB model | |
| CN113010013A (en) | Wasserstein distance-based motor imagery electroencephalogram migration learning method | |
| WO2022100187A1 (en) | Mobile terminal-based method for identifying and monitoring emotions of user | |
| CN112057090B (en) | Emotion judgment wearable device and method based on body surface extremely-low-frequency potential difference characteristics | |
| CN114081439A (en) | Brain-like algorithm for sleep staging by applying prefrontal single-channel electroencephalogram signals | |
| Li et al. | Multi-modal emotion recognition based on deep learning of EEG and audio signals | |
| CN115414050A (en) | EEG brain network maximum clique detection method and system for realizing emotion recognition | |
| CN116400800A (en) | ALS patient human-computer interaction system and method based on brain-computer interface and artificial intelligence algorithm | |
| Ahmadi-Dastgerdi et al. | A vector quantization-based spike compression approach dedicated to multichannel neural recording microsystems | |
| CN107085468A (en) | A kind of real-time smart pen and its detection method for detecting and showing human emotion's state | |
| CN113180663A (en) | Emotion recognition method and system based on convolutional neural network | |
| CN111493896A (en) | Automatic early warning of sieve and intervention intelligent system of large-scale depression based on EEG equipment | |
| CN112906539B (en) | Object identification method based on EEG data | |
| CN116616800B (en) | Scalp electroencephalogram high-frequency oscillation signal identification method and device based on meta-shift learning |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200410 |