CN116098633A - Minimally invasive intervention brain-computer interface ideation brain control system for consciousness disturbance - Google Patents
Minimally invasive intervention brain-computer interface ideation brain control system for consciousness disturbance Download PDFInfo
- Publication number
- CN116098633A CN116098633A CN202211592043.4A CN202211592043A CN116098633A CN 116098633 A CN116098633 A CN 116098633A CN 202211592043 A CN202211592043 A CN 202211592043A CN 116098633 A CN116098633 A CN 116098633A
- Authority
- CN
- China
- Prior art keywords
- brain
- signal
- electroencephalogram
- module
- data
- 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
-
- 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
- A61B5/24—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]
- A61B5/372—Analysis of electroencephalograms
- A61B5/374—Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
-
- 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]
- A61B5/384—Recording apparatus or displays specially adapted therefor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7221—Determining signal validity, reliability or quality
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Psychiatry (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Signal Processing (AREA)
- Psychology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention belongs to the technical field of consciousness brain control, and discloses a consciousness disturbance minimally invasive intervention brain-computer interface consciousness brain control system, which comprises the following components: the device comprises an electroencephalogram signal acquisition module, a main control module, a signal correction module, a signal extraction module, a signal identification module, a signal analysis module, a signal control module and a display module. The invention can be used for rapidly and accurately extracting the characteristic change of the brain signal data signals of the patients with consciousness disturbance through the signal extraction module, thereby detecting the state of the brain; meanwhile, the brain electrical identification model of the consciousness disturbance patient can be obtained through the signal identification module, and then the brain electrical identification model of the consciousness disturbance patient is adopted to analyze the collected brain electrical signals of the consciousness disturbance patient, so that the state type of the brain electrical signals of the consciousness disturbance patient is identified, the difference among individuals is avoided, and the accuracy of brain electrical state identification is improved.
Description
Technical Field
The invention belongs to the technical field of ideation brain control, and particularly relates to a minimally invasive intervention brain-computer interface ideation brain control system for consciousness disturbance.
Background
The heart of the idea control is to further convert the brain electrical information into corresponding actions through extraction, analysis and interpretation of the brain electrical information. "ideas" control, which is brain wave control by human, related scientific research has been over half a century; colloquially, humans are discharging when performing various physiological activities; when the heart beats, 1-2 millivolts is generated, the opening and closing of eyes generate 5-6 millivolts, and when the problem is considered, the brain generates 0.2-1 millivolts; if the potential activity of the brain is measured by a scientific instrument, a wave-like pattern is displayed on the screen, namely, brain waves; the brain wave activity has certain regularity characteristics and has a certain degree of corresponding relation with the consciousness of the brain; the brain wave frequency is obviously different under different states of excitation, tension, coma and the like, and is further divided into alpha, beta, delta and theta waves according to different frequencies between about 1 and 40 hertz; when people are highly concentrated under certain pressure, the frequency of brain waves is between 12 and 38 Hz, and the wave band is called beta wave and is brain waves in the 'consciousness' level; when the human attention is lowered and the brain wave is in a relaxed state, the frequency of the brain wave is lowered to 8-12 Hz, which is called alpha wave; after entering a sleep state, the brain wave frequency is further reduced and divided into theta waves (4-8 Hz) and delta waves (0.5-4 Hz), which respectively reflect the states of the person in the 'subconscious' and 'unconscious' stages; because the brain waves have the characteristic of being changed along with the emotion fluctuation, the development and the utilization of the brain waves by human beings become possible; however, the existing minimally invasive intervention brain-computer interface intention brain-control system for consciousness disturbance has low extraction speed and poor accuracy on the brain-electrical signals; meanwhile, the accuracy of electroencephalogram identification is low.
Through the above analysis, the problems and defects existing in the prior art are as follows:
(1) The existing minimally invasive intervention brain-computer interface ideation brain-control system for consciousness disturbance has low extraction speed and poor accuracy on brain-electrical signals.
(2) The accuracy of electroencephalogram identification is low.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a minimally invasive interventional brain-computer interface idea brain control system for consciousness disturbance.
The invention is realized in such a way that a minimally invasive intervention brain-computer interface idea brain-control system for consciousness disturbance comprises:
the device comprises an electroencephalogram signal acquisition module, a main control module, a signal correction module, a signal extraction module, a signal identification module, a signal analysis module, a signal control module and a display module;
the electroencephalogram signal acquisition module is connected with the main control module and used for acquiring electroencephalogram signals of patients with consciousness disturbance;
the main control module is connected with the electroencephalogram signal acquisition module, the signal correction module, the signal extraction module, the signal identification module, the signal analysis module, the signal control module and the display module and used for controlling the normal work of each module;
the signal correction module is connected with the main control module and used for correcting the acquired brain electrical signals;
the signal correction module correction method comprises the following steps:
configuring parameters of medical monitoring equipment, and sampling electroencephalogram signals at different moments through the medical monitoring equipment;
comparing the electroencephalogram signal value of each sampling point in an electroencephalogram signal period with a preset electroencephalogram signal value corresponding to the sampling point, wherein the electroencephalogram signal value of the sampling point is unchanged when the electroencephalogram signal value of the sampling point is equal to the corresponding preset electroencephalogram signal value; executing the following steps when the electroencephalogram signal value of the sampling point is unequal to the corresponding preset electroencephalogram signal value;
correcting the electroencephalogram signal value of the sampling point into a corresponding preset electroencephalogram signal value;
the electroencephalogram signal correction method further comprises the following steps:
storing preset electroencephalogram signal values corresponding to each sampling point;
starting from the second period of the electroencephalogram signal, wherein the preset electroencephalogram signal value is an electroencephalogram signal value corresponding to a sampling point of the first period of the electroencephalogram signal;
the signal extraction module is connected with the main control module and used for extracting the acquired brain electrical signals;
the signal identification module is connected with the main control module and used for identifying the acquired brain electrical signals;
the signal analysis module is connected with the main control module and used for analyzing the acquired brain electrical signals;
the signal control module is connected with the main control module and used for performing target control through the acquired electroencephalogram signals;
and the display module is connected with the main control module and used for displaying the acquired brain electrical signals.
Further, the signal extraction module identification method is as follows:
(1) Constructing an electroencephalogram database, and storing the acquired electroencephalogram data into the electroencephalogram database; acquiring and processing brain electrical signal data of a patient with background consciousness disturbance and brain electrical signal data of a patient with consciousness disturbance to be processed;
removing artifacts in the brain electrical signal data of the patient with the background consciousness disturbance and the brain electrical signal data of the patient with the consciousness disturbance to be processed, respectively obtaining an effective frequency band of the brain electrical signal data of the patient with the background consciousness disturbance and an effective frequency band of the brain electrical signal data of the patient with the consciousness disturbance to be processed, and dividing the effective frequency band of the brain electrical signal data of the patient with the background consciousness disturbance and the effective frequency band of the brain electrical signal data of the patient with the consciousness disturbance to be processed into a plurality of data segments;
removing artifacts by adopting band-pass filtering, wherein the frequency of an effective frequency band obtained after removing the artifacts is 1.6-70 Hz;
dividing an effective frequency band into a plurality of data segments by adopting a sliding time window method, wherein the length of the sliding time window is 1s, and the sliding step length is 0.2s;
(2) Respectively extracting time-frequency characteristics and morphological characteristics from each obtained data segment to obtain corresponding time-frequency characteristic values and morphological characteristic values of each data segment;
(3) Calculating a frequency distribution function of the time-frequency characteristic value and a frequency distribution function of the morphological characteristic value by using the time-frequency characteristic value and the morphological characteristic value of each data segment of the brain electrical signal data of the patient with the background consciousness disturbance;
obtaining a frequency distribution function of a time-frequency characteristic value and a frequency distribution function of a morphological characteristic value by adopting a frequency distribution histogram normalization method;
(4) Obtaining the probability of occurrence of the time-frequency characteristic value and the probability of occurrence of the morphological characteristic value of each data segment of the brain electrical signal data of the patient with the consciousness disturbance to be processed by utilizing the frequency distribution function of the time-frequency characteristic value and the frequency distribution function of the morphological characteristic value of the brain electrical signal data of the patient with the consciousness disturbance;
(5) The IMF-VoE characteristic value is obtained by the following calculation,
wherein t is the ordinal number of the data segment;
n is the number of eigenvalues;
pc is the probability of occurrence of time-frequency characteristic values or the probability of occurrence of morphological characteristic values of each data segment of brain wave signal data of the patient with the consciousness disturbance to be processed;
c is the ordinal number of the eigenvalue.
Further, extracting time-frequency characteristics of each obtained data segment by adopting an empirical mode decomposition method, taking the first three natural mode functions, and calculating to obtain a time-frequency characteristic value VoIMF of each data segment by using the following formula:
wherein xi is the intrinsic mode function value of each data point in each data segment;
i is the ordinal number of the data point for each data segment;
n is the number of data points for each data segment;
n is the ordinal number of the intrinsic mode function x;
t is the ordinal number of the data segment.
Further, the step of extracting morphological features from each of the obtained data segments is as follows:
a. performing mean filtering on each data segment to obtain smoothed data;
b. obtaining the maximum value of the smoothed data segment, and connecting the maximum value to obtain an upper envelope curve upper; obtaining the minimum value of the smoothed data segment to obtain a lower envelope curve Elower; the envelope range between the upper envelope and the lower envelope is found using:
Envwlope_Range(t)＝E upper (t)-E lower (t)
wherein t is the ordinal number of the data segment;
Envelpe_Range (t) is the envelope Range of the t-th data segment;
morphology feature values VoE for each data segment are calculated using the following,
wherein t is the ordinal number of the data segment;
n is the number of data points of each data segment;
i is the ordinal number of the data point in each data segment;
Envelope_Range (t) i is the Envelope value of the ith data point of the ith data segment;
Further, the signal identification module extraction method comprises the following steps:
1) Constructing an electroencephalogram identification model, and acquiring an electroencephalogram identification model corresponding to a patient with consciousness disturbance; collecting brain electrical signals of the patient with consciousness disturbance; denoising the electroencephalogram signals;
2) Extracting a characteristic value from the electroencephalogram signal; and analyzing the characteristic value by adopting the electroencephalogram identification model to identify the state type of the electroencephalogram.
Further, the extracting the characteristic value from the electroencephalogram signal specifically comprises,
converting the electroencephalogram signal from a time domain signal to a frequency domain signal to obtain an electroencephalogram frequency domain signal;
acquiring brain energy of each frequency in the brain electricity frequency domain signal;
respectively calculating the difference value of the brain energy of the current window of the brain electricity frequency domain signal and the brain energy of each window in the front N windows of the brain electricity frequency domain signal to obtain N brain energy difference values, wherein the N brain energy difference values form a first energy difference value;
calculating a difference value between the brain energy of the current window and the average brain energy obtained in advance when the consciousness disturbance patient is in a relaxed state, and obtaining a second energy difference value;
and taking the brain energy of each frequency, the first energy difference value and the second energy difference value as characteristic values of the brain electrical signals.
Further, the current window is a time period between the current time and the previous M times; wherein N is more than or equal to 1, and M is more than or equal to 1.
Further, the acquiring the electroencephalogram identification model corresponding to the patient with conscious disturbance specifically includes:
and acquiring an electroencephalogram identification model corresponding to the conscious disturbance patient from a pre-established model library.
Further, the acquiring the electroencephalogram identification model corresponding to the patient with conscious disturbance specifically includes:
collecting brain electrical signal samples of the brain of the patient with consciousness disturbance in different states;
extracting characteristic values from the electroencephalogram signal samples in each state respectively;
and training the characteristic values in each state, and constructing an electroencephalogram identification model corresponding to the conscious disturbance patient.
Further, before the extracting the characteristic value from the electroencephalogram signal, the method further includes:
and filtering the acquired electroencephalogram signals according to a preset frequency band.
In combination with the above technical solution and the technical problems to be solved, please analyze the following aspects to provide the following advantages and positive effects:
first, aiming at the technical problems in the prior art and the difficulty in solving the problems, the technical problems solved by the technical proposal of the invention are analyzed in detail and deeply by tightly combining the technical proposal to be protected, the results and data in the research and development process, and the like, and some technical effects brought after the problems are solved have creative technical effects. The specific description is as follows:
the invention combines the time-frequency characteristic and the morphological characteristic through the signal extraction module, has low calculation complexity and good real-time performance, and can be used for rapidly and accurately extracting the characteristic change of the brain electrical signal data signal of the patient with consciousness disturbance so as to detect the state of the brain; meanwhile, the brain electrical identification model of the consciousness disturbance patient can be obtained through the signal identification module, and then the brain electrical identification model of the consciousness disturbance patient is adopted to analyze the collected brain electrical signals of the consciousness disturbance patient, so that the state type of the brain electrical signals of the consciousness disturbance patient is identified, the difference among individuals is avoided, and the accuracy of brain electrical state identification is improved.
Secondly, the technical scheme is regarded as a whole or from the perspective of products, and the technical scheme to be protected has the following technical effects and advantages:
the invention combines the time-frequency characteristic and the morphological characteristic through the signal extraction module, has low calculation complexity and good real-time performance, and can be used for rapidly and accurately extracting the characteristic change of the brain electrical signal data signal of the patient with consciousness disturbance so as to detect the state of the brain; meanwhile, the brain electrical identification model of the consciousness disturbance patient can be obtained through the signal identification module, and then the brain electrical identification model of the consciousness disturbance patient is adopted to analyze the collected brain electrical signals of the consciousness disturbance patient, so that the state type of the brain electrical signals of the consciousness disturbance patient is identified, the difference among individuals is avoided, and the accuracy of brain electrical state identification is improved.
Drawings
Fig. 1 is a block diagram of a schematic brain-control system of a minimally invasive interventional brain-computer interface for consciousness disturbance provided by an embodiment of the invention.
Fig. 2 is a flowchart of a signal extraction module identification method according to an embodiment of the present invention.
Fig. 3 is a flowchart of a signal recognition module extraction method according to an embodiment of the present invention.
In fig. 1: 1. an electroencephalogram signal acquisition module; 2. a main control module; 3. a signal correction module; 4. a signal extraction module; 5. a signal identification module; 6. a signal analysis module; 7. a signal control module; 8. and a display module.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
1. The embodiments are explained. In order to fully understand how the invention may be embodied by those skilled in the art, this section is an illustrative embodiment in which the claims are presented for purposes of illustration.
As shown in fig. 1, a minimally invasive interventional brain-computer interface concept brain-control system for consciousness disturbance provided by an embodiment of the present invention includes: the brain electrical signal acquisition module 1, the main control module 2, the signal correction module 3, the signal extraction module 4, the signal identification module 5, the signal analysis module 6, the signal control module 7 and the display module 8.
The electroencephalogram signal acquisition module 1 is connected with the main control module 2 and is used for acquiring electroencephalogram signals of patients with consciousness disturbance;
the main control module 2 is connected with the electroencephalogram signal acquisition module 1, the signal correction module 3, the signal extraction module 4, the signal identification module 5, the signal analysis module 6, the signal control module 7 and the display module 8 and is used for controlling the normal work of each module;
the signal correction module 3 is connected with the main control module 2 and is used for correcting the acquired brain electrical signals;
the signal correction module correction method comprises the following steps:
configuring parameters of medical monitoring equipment, and sampling electroencephalogram signals at different moments through the medical monitoring equipment;
comparing the electroencephalogram signal value of each sampling point in an electroencephalogram signal period with a preset electroencephalogram signal value corresponding to the sampling point, wherein the electroencephalogram signal value of the sampling point is unchanged when the electroencephalogram signal value of the sampling point is equal to the corresponding preset electroencephalogram signal value; executing the following steps when the electroencephalogram signal value of the sampling point is unequal to the corresponding preset electroencephalogram signal value;
correcting the electroencephalogram signal value of the sampling point into a corresponding preset electroencephalogram signal value;
the electroencephalogram signal correction method further comprises the following steps:
storing preset electroencephalogram signal values corresponding to each sampling point;
starting from the second period of the electroencephalogram signal, wherein the preset electroencephalogram signal value is an electroencephalogram signal value corresponding to a sampling point of the first period of the electroencephalogram signal;
the signal extraction module 4 is connected with the main control module 2 and is used for extracting the acquired brain electrical signals;
the signal identification module 5 is connected with the main control module 2 and is used for identifying the acquired brain electrical signals;
the signal analysis module 6 is connected with the main control module 2 and is used for analyzing the acquired brain electrical signals;
the signal control module 7 is connected with the main control module 2 and is used for performing target control through the acquired brain electrical signals;
and the display module 8 is connected with the main control module 2 and is used for displaying the acquired brain electrical signals.
As shown in fig. 2, the signal extraction module 4 provided by the invention has the following identification method:
s101, constructing an electroencephalogram database, and storing acquired electroencephalogram data into the electroencephalogram database; acquiring and processing brain electrical signal data of a patient with background consciousness disturbance and brain electrical signal data of a patient with consciousness disturbance to be processed;
removing artifacts in the brain electrical signal data of the patient with the background consciousness disturbance and the brain electrical signal data of the patient with the consciousness disturbance to be processed, respectively obtaining an effective frequency band of the brain electrical signal data of the patient with the background consciousness disturbance and an effective frequency band of the brain electrical signal data of the patient with the consciousness disturbance to be processed, and dividing the effective frequency band of the brain electrical signal data of the patient with the background consciousness disturbance and the effective frequency band of the brain electrical signal data of the patient with the consciousness disturbance to be processed into a plurality of data segments;
removing artifacts by adopting band-pass filtering, wherein the frequency of an effective frequency band obtained after removing the artifacts is 1.6-70 Hz;
dividing an effective frequency band into a plurality of data segments by adopting a sliding time window method, wherein the length of the sliding time window is 1s, and the sliding step length is 0.2s;
s102, respectively extracting time-frequency characteristics and morphological characteristics of each obtained data segment to obtain corresponding time-frequency characteristic values and morphological characteristic values of each data segment;
s103, calculating a frequency distribution function of the time-frequency characteristic value and a frequency distribution function of the morphological characteristic value by using the time-frequency characteristic value and the morphological characteristic value of each data segment of the brain electrical signal data of the patient with the background consciousness disturbance;
obtaining a frequency distribution function of a time-frequency characteristic value and a frequency distribution function of a morphological characteristic value by adopting a frequency distribution histogram normalization method;
s104, obtaining the probability of occurrence of the time-frequency characteristic value and the probability of occurrence of the morphological characteristic value of each data segment of the brain electrical signal data of the patient with the consciousness disturbance to be processed by utilizing the frequency distribution function of the time-frequency characteristic value and the frequency distribution function of the morphological characteristic value of the brain electrical signal data of the patient with the consciousness disturbance;
s105, calculating to obtain IMF-VoE characteristic value by using the following formula,
wherein t is the ordinal number of the data segment;
n is the number of eigenvalues;
pc is the probability of occurrence of time-frequency characteristic values or the probability of occurrence of morphological characteristic values of each data segment of brain wave signal data of the patient with the consciousness disturbance to be processed;
c is the ordinal number of the eigenvalue.
According to the invention, the time-frequency characteristic is extracted from each obtained data segment by adopting an empirical mode decomposition method, the first three inherent mode functions are taken, and the time-frequency characteristic value VoIMF of each data segment is obtained by calculating the following formula:
wherein xi is the intrinsic mode function value of each data point in each data segment;
i is the ordinal number of the data point for each data segment;
n is the number of data points for each data segment;
n is the ordinal number of the intrinsic mode function x;
t is the ordinal number of the data segment.
The method for extracting morphological characteristics of each obtained data segment comprises the following steps:
a. performing mean filtering on each data segment to obtain smoothed data;
b. obtaining the maximum value of the smoothed data segment, and connecting the maximum value to obtain an upper envelope curve upper; obtaining the minimum value of the smoothed data segment to obtain a lower envelope curve Elower; the envelope range between the upper envelope and the lower envelope is found using:
Envelope_Range(t)＝E upper (t)-E lower (t)
wherein t is the ordinal number of the data segment;
Envelpe_Range (t) is the envelope Range of the t-th data segment;
morphology feature values VoE for each data segment are calculated using the following,
wherein t is the ordinal number of the data segment;
n is the number of data points of each data segment;
i is the ordinal number of the data point in each data segment;
Envelope_Range (t) i is the Envelope value of the ith data point of the ith data segment;
As shown in fig. 3, the signal identifying module 5 extraction method provided by the invention is as follows:
s201, constructing an electroencephalogram identification model, and acquiring the electroencephalogram identification model corresponding to the patient with conscious disturbance; collecting brain electrical signals of the patient with consciousness disturbance; denoising the electroencephalogram signals;
s202, extracting a characteristic value from the electroencephalogram signal; and analyzing the characteristic value by adopting the electroencephalogram identification model to identify the state type of the electroencephalogram.
The invention provides a method for extracting characteristic values from the electroencephalogram signals, which specifically comprises the following steps,
converting the electroencephalogram signal from a time domain signal to a frequency domain signal to obtain an electroencephalogram frequency domain signal;
acquiring brain energy of each frequency in the brain electricity frequency domain signal;
respectively calculating the difference value of the brain energy of the current window of the brain electricity frequency domain signal and the brain energy of each window in the front N windows of the brain electricity frequency domain signal to obtain N brain energy difference values, wherein the N brain energy difference values form a first energy difference value;
calculating a difference value between the brain energy of the current window and the average brain energy obtained in advance when the consciousness disturbance patient is in a relaxed state, and obtaining a second energy difference value;
and taking the brain energy of each frequency, the first energy difference value and the second energy difference value as characteristic values of the brain electrical signals.
The current window provided by the invention is a time period between the current time and the previous M times; wherein N is more than or equal to 1, and M is more than or equal to 1.
The invention provides an electroencephalogram identification model corresponding to a patient with conscious disturbance, which specifically comprises the following steps:
and acquiring an electroencephalogram identification model corresponding to the conscious disturbance patient from a pre-established model library.
The invention provides an electroencephalogram identification model corresponding to a patient with conscious disturbance, which specifically comprises the following steps:
collecting brain electrical signal samples of the brain of the patient with consciousness disturbance in different states;
extracting characteristic values from the electroencephalogram signal samples in each state respectively;
and training the characteristic values in each state, and constructing an electroencephalogram identification model corresponding to the conscious disturbance patient.
Before the characteristic value is extracted from the electroencephalogram signal, the method further comprises the following steps:
and filtering the acquired electroencephalogram signals according to a preset frequency band.
2. Application example. In order to prove the inventive and technical value of the technical solution of the present invention, this section is an application example on specific products or related technologies of the claim technical solution.
When the brain wave monitoring device works, firstly, brain electric signals of a patient with consciousness disturbance are collected through the brain electric signal collecting module 1; secondly, the main control module 2 corrects the acquired brain electrical signals through the signal correction module 3; extracting the acquired brain electrical signals through a signal extraction module 4; the collected brain electrical signals are identified through a signal identification module 5; then, analyzing the acquired electroencephalogram signals through a signal analysis module 6; the signal control module 7 is used for carrying out target control by utilizing the acquired electroencephalogram signals; finally, the collected brain electrical signals are displayed by a display module 8.
It should be noted that the embodiments of the present invention can be realized in hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those of ordinary skill in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device of the present invention and its modules may be implemented by hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., as well as software executed by various types of processors, or by a combination of the above hardware circuitry and software, such as firmware.
3. Evidence of the effect of the examples. The embodiment of the invention has a great advantage in the research and development or use process, and has the following description in combination with data, charts and the like of the test process.
The invention combines the time-frequency characteristic and the morphological characteristic through the signal extraction module, has low calculation complexity and good real-time performance, and can be used for rapidly and accurately extracting the characteristic change of the brain electrical signal data signal of the patient with consciousness disturbance so as to detect the state of the brain; meanwhile, the brain electrical identification model of the consciousness disturbance patient can be obtained through the signal identification module, and then the brain electrical identification model of the consciousness disturbance patient is adopted to analyze the collected brain electrical signals of the consciousness disturbance patient, so that the state type of the brain electrical signals of the consciousness disturbance patient is identified, the difference among individuals is avoided, and the accuracy of brain electrical state identification is improved.
The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the invention is not limited thereto, but any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention will be apparent to those skilled in the art within the scope of the present invention.
Claims (10)
1. A minimally invasive intervention brain-computer interface ideation brain-control system for consciousness disturbance, characterized in that the minimally invasive intervention brain-computer interface ideation brain-control system for consciousness disturbance comprises:
the device comprises an electroencephalogram signal acquisition module, a main control module, a signal correction module, a signal extraction module, a signal identification module, a signal analysis module, a signal control module and a display module;
the electroencephalogram signal acquisition module is connected with the main control module and used for acquiring electroencephalogram signals of patients with consciousness disturbance;
the main control module is connected with the electroencephalogram signal acquisition module, the signal correction module, the signal extraction module, the signal identification module, the signal analysis module, the signal control module and the display module and used for controlling the normal work of each module;
the signal correction module is connected with the main control module and used for correcting the acquired brain electrical signals;
the signal correction module correction method comprises the following steps:
configuring parameters of medical monitoring equipment, and sampling electroencephalogram signals at different moments through the medical monitoring equipment;
comparing the electroencephalogram signal value of each sampling point in an electroencephalogram signal period with a preset electroencephalogram signal value corresponding to the sampling point, wherein the electroencephalogram signal value of the sampling point is unchanged when the electroencephalogram signal value of the sampling point is equal to the corresponding preset electroencephalogram signal value; executing the following steps when the electroencephalogram signal value of the sampling point is unequal to the corresponding preset electroencephalogram signal value;
correcting the electroencephalogram signal value of the sampling point into a corresponding preset electroencephalogram signal value;
the electroencephalogram signal correction method further comprises the following steps:
storing preset electroencephalogram signal values corresponding to each sampling point;
starting from the second period of the electroencephalogram signal, wherein the preset electroencephalogram signal value is an electroencephalogram signal value corresponding to a sampling point of the first period of the electroencephalogram signal;
the signal extraction module is connected with the main control module and used for extracting the acquired brain electrical signals;
the signal identification module is connected with the main control module and used for identifying the acquired brain electrical signals;
the signal analysis module is connected with the main control module and used for analyzing the acquired brain electrical signals;
the signal control module is connected with the main control module and used for performing target control through the acquired electroencephalogram signals;
and the display module is connected with the main control module and used for displaying the acquired brain electrical signals.
2. The minimally invasive interventional brain-computer interface ideation brain-control system for consciousness disturbance according to claim 1, wherein the signal extraction module identification method is as follows:
(1) Constructing an electroencephalogram database, and storing the acquired electroencephalogram data into the electroencephalogram database; acquiring and processing brain electrical signal data of a patient with background consciousness disturbance and brain electrical signal data of a patient with consciousness disturbance to be processed;
removing artifacts in the brain electrical signal data of the patient with the background consciousness disturbance and the brain electrical signal data of the patient with the consciousness disturbance to be processed, respectively obtaining an effective frequency band of the brain electrical signal data of the patient with the background consciousness disturbance and an effective frequency band of the brain electrical signal data of the patient with the consciousness disturbance to be processed, and dividing the effective frequency band of the brain electrical signal data of the patient with the background consciousness disturbance and the effective frequency band of the brain electrical signal data of the patient with the consciousness disturbance to be processed into a plurality of data segments;
removing artifacts by adopting band-pass filtering, wherein the frequency of an effective frequency band obtained after removing the artifacts is 1.6-70 Hz;
dividing an effective frequency band into a plurality of data segments by adopting a sliding time window method, wherein the length of the sliding time window is 1s, and the sliding step length is 0.2s;
(2) Respectively extracting time-frequency characteristics and morphological characteristics from each obtained data segment to obtain corresponding time-frequency characteristic values and morphological characteristic values of each data segment;
(3) Calculating a frequency distribution function of the time-frequency characteristic value and a frequency distribution function of the morphological characteristic value by using the time-frequency characteristic value and the morphological characteristic value of each data segment of the brain electrical signal data of the patient with the background consciousness disturbance;
obtaining a frequency distribution function of a time-frequency characteristic value and a frequency distribution function of a morphological characteristic value by adopting a frequency distribution histogram normalization method;
(4) Obtaining the probability of occurrence of the time-frequency characteristic value and the probability of occurrence of the morphological characteristic value of each data segment of the brain electrical signal data of the patient with the consciousness disturbance to be processed by utilizing the frequency distribution function of the time-frequency characteristic value and the frequency distribution function of the morphological characteristic value of the brain electrical signal data of the patient with the consciousness disturbance;
(5) The IMF-VoE characteristic value is obtained by the following calculation,
wherein t is the ordinal number of the data segment;
n is the number of eigenvalues;
pc is the probability of occurrence of time-frequency characteristic values or the probability of occurrence of morphological characteristic values of each data segment of brain wave signal data of the patient with the consciousness disturbance to be processed;
c is the ordinal number of the eigenvalue.
3. The system for minimally invasive intervention brain-computer interface ideation brain-control of consciousness disturbance according to claim 2, wherein the time-frequency characteristics of each obtained data segment are extracted by adopting an empirical mode decomposition method, the first three natural mode functions are taken, and the time-frequency characteristic value VoIMF of each data segment is obtained by calculating by using the following formula:
wherein xi is the intrinsic mode function value of each data point in each data segment;
i is the ordinal number of the data point for each data segment;
n is the number of data points for each data segment;
n is the ordinal number of the intrinsic mode function x;
t is the ordinal number of the data segment.
4. The minimally invasive interventional brain-computer interface ideation brain-control system for conscious disturbance according to claim 2, wherein the step of extracting morphological features for each of the resulting data segments is as follows:
a. performing mean filtering on each data segment to obtain smoothed data;
b. obtaining the maximum value of the smoothed data segment, and connecting the maximum value to obtain an upper envelope curve upper; obtaining the minimum value of the smoothed data segment to obtain a lower envelope curve Elower; the envelope range between the upper envelope and the lower envelope is found using:
Rnvelope_Range(t)＝E upper (t)-E lowe r(t)
wherein t is the ordinal number of the data segment;
Envelpe_Range (t) is the envelope Range of the t-th data segment;
morphology feature values VoE for each data segment are calculated using the following,
wherein t is the ordinal number of the data segment;
n is the number of data points of each data segment;
i is the ordinal number of the data point in each data segment;
Envelope_Range (t) i is the Envelope value of the ith data point of the ith data segment;
5. The minimally invasive interventional brain-computer interface ideation brain-control system for consciousness disturbance according to claim 1, wherein the signal recognition module extraction method is as follows:
1) Constructing an electroencephalogram identification model, and acquiring an electroencephalogram identification model corresponding to a patient with consciousness disturbance; collecting brain electrical signals of the patient with consciousness disturbance; denoising the electroencephalogram signals;
2) Extracting a characteristic value from the electroencephalogram signal; and analyzing the characteristic value by adopting the electroencephalogram identification model to identify the state type of the electroencephalogram.
6. The minimally invasive interventional brain-computer interface ideation brain-control system for consciousness disturbance of claim 5, wherein the extracting of the characteristic value from the brain-electrical signal includes,
converting the electroencephalogram signal from a time domain signal to a frequency domain signal to obtain an electroencephalogram frequency domain signal;
acquiring brain energy of each frequency in the brain electricity frequency domain signal;
respectively calculating the difference value of the brain energy of the current window of the brain electricity frequency domain signal and the brain energy of each window in the front N windows of the brain electricity frequency domain signal to obtain N brain energy difference values, wherein the N brain energy difference values form a first energy difference value;
calculating a difference value between the brain energy of the current window and the average brain energy obtained in advance when the consciousness disturbance patient is in a relaxed state, and obtaining a second energy difference value;
and taking the brain energy of each frequency, the first energy difference value and the second energy difference value as characteristic values of the brain electrical signals.
7. The minimally invasive interventional brain-computer interface ideation brain-control system for consciousness disturbance of claim 6, wherein the current window is a time period between a current time and M times thereabout; wherein N is more than or equal to 1, and M is more than or equal to 1.
8. The system for minimally invasive intervention brain-computer interface ideation brain-control of consciousness disturbance according to claim 5, wherein the acquiring the brain-electrical identification model corresponding to the patient with consciousness disturbance specifically comprises:
and acquiring an electroencephalogram identification model corresponding to the conscious disturbance patient from a pre-established model library.
9. The system for minimally invasive intervention brain-computer interface ideation brain-control of consciousness disturbance according to claim 5, wherein the acquiring the brain-electrical identification model corresponding to the patient with consciousness disturbance specifically comprises:
collecting brain electrical signal samples of the brain of the patient with consciousness disturbance in different states;
extracting characteristic values from the electroencephalogram signal samples in each state respectively;
and training the characteristic values in each state, and constructing an electroencephalogram identification model corresponding to the conscious disturbance patient.
10. The minimally invasive interventional brain-computer interface ideation brain-control system for consciousness disturbance of claim 5, further comprising, prior to said extracting feature values from the electroencephalogram signals:
and filtering the acquired electroencephalogram signals according to a preset frequency band.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211592043.4A CN116098633A (en) | 2022-12-12 | 2022-12-12 | Minimally invasive intervention brain-computer interface ideation brain control system for consciousness disturbance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211592043.4A CN116098633A (en) | 2022-12-12 | 2022-12-12 | Minimally invasive intervention brain-computer interface ideation brain control system for consciousness disturbance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116098633A true CN116098633A (en) | 2023-05-12 |
Family
ID=86266601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211592043.4A Pending CN116098633A (en) | 2022-12-12 | 2022-12-12 | Minimally invasive intervention brain-computer interface ideation brain control system for consciousness disturbance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116098633A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117075741A (en) * | 2023-10-17 | 2023-11-17 | 首都医科大学附属北京天坛医院 | Consciousness interaction communication method and system |
-
2022
- 2022-12-12 CN CN202211592043.4A patent/CN116098633A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117075741A (en) * | 2023-10-17 | 2023-11-17 | 首都医科大学附属北京天坛医院 | Consciousness interaction communication method and system |
| CN117075741B (en) * | 2023-10-17 | 2023-12-12 | 首都医科大学附属北京天坛医院 | Consciousness interaction communication method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rahman et al. | Sleep stage classification using single-channel EOG | |
| CN110338786B (en) | Epileptic discharge identification and classification method, system, device and medium | |
| CN108742697B (en) | Heart sound signal classification method and terminal equipment | |
| US9380956B2 (en) | Method and apparatus for classifying cardiac arrhythmia | |
| Nakamura et al. | Complexity science for sleep stage classification from EEG | |
| Al-Ani | ECG waveform classification based on P-QRS-T wave recognition | |
| Li et al. | A deep learning approach to cardiovascular disease classification using empirical mode decomposition for ECG feature extraction | |
| CN115153463A (en) | Training method of sleep state recognition model, and sleep state recognition method and device | |
| CN116098633A (en) | Minimally invasive intervention brain-computer interface ideation brain control system for consciousness disturbance | |
| Qiao et al. | A dual self-calibrating framework for noninvasive fetal ECG R-peak detection | |
| Fatimah et al. | A multi-modal assessment of sleep stages using adaptive Fourier decomposition and machine learning | |
| US20200330040A1 (en) | Method and system for detecting noise in vital sign signal | |
| Chiu et al. | Get rid of the beat in mobile EEG applications: A framework towards automated cardiogenic artifact detection and removal in single-channel EEG | |
| TWI487503B (en) | Automatic sleep-stage scoring apparatus | |
| Zhong et al. | Maternal ECG removal using short time Fourier transform and convolutional auto-encoder | |
| Sá et al. | Heart disease detection architecture for lead I off-the-person ECG monitoring devices | |
| Asgari et al. | A robust approach toward recognizing valid arterial-blood-pressure pulses | |
| Jokić et al. | An efficient ECG modeling for heartbeat classification | |
| Omar et al. | Enhancing EEG signals classification using LSTM‐CNN architecture | |
| Yu et al. | Design and implementation of automatic sleep staging based on ECG signals | |
| CN114190940B (en) | Fatigue detection method and device, electronic equipment and storage medium | |
| Sharma et al. | An Efficient Approach for Recognition of Motor Imagery EEG Signals Using the Fourier Decomposition Method | |
| Mansourian et al. | Fetal QRS extraction from single-channel abdominal ECG using adaptive improved permutation entropy | |
| CN114521902B (en) | AR model feature and SVM classification-based working memory improvement experiment method and device | |
| CN117243584B (en) | Heart rate monitoring method and device based on bracelet type electrocardiograph equipment and storage medium |
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 |