CN112754452B - Method, device and storage medium for generating brain impedance data - Google Patents
Method, device and storage medium for generating brain impedance data Download PDFInfo
- Publication number
- CN112754452B CN112754452B CN202011629285.7A CN202011629285A CN112754452B CN 112754452 B CN112754452 B CN 112754452B CN 202011629285 A CN202011629285 A CN 202011629285A CN 112754452 B CN112754452 B CN 112754452B
- Authority
- CN
- China
- Prior art keywords
- brain
- impedance data
- equivalent circuit
- data
- brain impedance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 176
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 230000009467 reduction Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 25
- 201000010099 disease Diseases 0.000 claims description 20
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 20
- 238000010801 machine learning Methods 0.000 claims description 20
- 238000004519 manufacturing process Methods 0.000 claims description 8
- 230000008485 antagonism Effects 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 8
- 238000012360 testing method Methods 0.000 description 4
- 239000003990 capacitor Substances 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 208000014644 Brain disease Diseases 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 231100000915 pathological change Toxicity 0.000 description 2
- 230000036285 pathological change Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 206010051290 Central nervous system lesion Diseases 0.000 description 1
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/053—Measuring electrical impedance or conductance of a portion of the body
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4058—Detecting, measuring or recording for evaluating the nervous system for evaluating the central nervous system
- A61B5/4064—Evaluating the brain
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application provides a method, a device and a storage medium for generating brain impedance data. The method comprises the following steps: receiving real brain impedance data; building an equivalent circuit structure based on the real brain impedance data; performing dimension reduction processing on the real brain impedance data through the equivalent circuit to obtain element parameter samples of the equivalent circuit; acquiring the corresponding relation between the element parameters and the brain state; producing multiple groups of element parameters under different brain states, and substituting the multiple groups of element parameters into an equivalent circuit so as to obtain multiple specific circuits corresponding to the different brain states; corresponding brain impedance data is generated at different frequencies using specific circuitry. According to the application, the impedance data generated by the equivalent circuit follows the actual physical rule, more effective information is introduced, and compared with the impedance data directly generated by the original data, the quality of the generated data is improved.
Description
Technical Field
The present application relates to the field of data generation and the field of machine learning, and in particular, to a method, an apparatus, and a storage medium for generating brain impedance data.
Background
Brain impedance data is a commonly used medical analysis data, and is widely used for detecting and analyzing various lesions of the brain.
The artificial intelligence can effectively analyze brain impedance data, and can determine which physiological and pathological changes of the brain occur by classifying the brain impedance data, so as to respond (such as treatment, prevention and the like) to the physiological and pathological changes of the brain. In artificial intelligence model training for brain impedance data analysis, a large amount of low-dimensional brain impedance data, especially brain impedance data when brain lesions occur, is needed, but less brain impedance data can be obtained in the actual acquisition process.
Although some brain impedance data generating methods exist at present, such as an antagonism generating network, a Monte Carlo method and the like, the methods directly generate brain impedance data by using the originally acquired brain impedance data, so that the generated data hardly meets the real physical characteristics.
Therefore, how to obtain a large amount of brain impedance data with low dimensionality, which can satisfy the real physical characteristics, is a technical problem to be solved.
Disclosure of Invention
In view of this, the present application provides a method, apparatus and storage medium for generating brain impedance data. According to the application, the impedance data generated by the equivalent circuit accords with the physical rule, and more effective information is introduced, so that the quality of the generated data is improved compared with the method for directly generating the impedance data by using the original data.
The application adopts the following technical means:
the application provides a method for generating brain impedance data, which comprises the following steps:
receiving real brain impedance data, including normal brain impedance data and brain impedance data in a disease state;
building an equivalent circuit structure based on the real brain impedance data;
performing dimension reduction processing on the real brain impedance data through the equivalent circuit to obtain element parameter samples of the equivalent circuit;
acquiring the corresponding relation between the element parameters and the brain state;
producing multiple groups of element parameters under different brain states, and substituting the multiple groups of element parameters into an equivalent circuit so as to obtain multiple specific circuits corresponding to the different brain states;
corresponding brain impedance data is generated at different frequencies using specific circuitry.
Further, the performing dimension reduction processing on the real brain impedance data through the equivalent circuit to obtain an element parameter sample of the equivalent circuit includes:
giving an impedance equation of the equivalent circuit according to the equivalent circuit structure;
and (3) making the impedance at each frequency equal to the real impedance, and solving the optimal value of the equation set to obtain the element parameters.
Further, the obtaining the correspondence between the component parameters and the brain state includes:
converting the real impedance data into element parameters;
clustering each element parameter;
and extracting the corresponding relation between the element parameters and the brain states according to the parameter distribution conditions of different brain states.
Further, the obtaining the correspondence between the component parameters and the brain state includes:
converting the real data into element parameters as samples;
training is performed by generating an antagonism network and generating new element parameter samples.
The application also provides a classification method of brain impedance data, which comprises the following steps:
the method of generating brain impedance data as claimed in any one of the preceding claims is repeatedly performed, generating a simulated brain impedance dataset comprising: normal brain simulated impedance data and simulated brain impedance data under disease conditions;
training a machine learning model with the simulated brain impedance dataset as a training dataset;
based on the machine learning model, brain impedance data is classified.
Further, the method further comprises the following steps:
the real brain impedance data is added to the training data set to train the machine learning model.
Further, the machine learning model is a neural network model, an SVM model or a random forest model.
The application also provides a device for generating brain impedance data, comprising:
a receiving module for receiving real brain impedance data, including normal brain impedance data and brain impedance data in a disease state;
a circuit building module for building an equivalent circuit structure based on the real brain impedance data;
the dimension reduction module is used for carrying out dimension reduction processing on the real brain impedance data through the equivalent circuit to obtain an element parameter sample of the equivalent circuit;
the corresponding relation acquisition module is used for acquiring the corresponding relation between the element parameters and the brain state;
the specific circuit acquisition module is used for producing a plurality of groups of element parameters under different brain states, and substituting the plurality of groups of element parameters into an equivalent circuit so as to obtain a plurality of specific circuits corresponding to the different brain states;
and the brain impedance data production module is used for generating corresponding brain impedance data at different frequencies by using specific circuits.
The application also provides a device for classifying brain impedance data, which comprises:
a simulated brain impedance dataset production module for repeatedly performing the method of generating brain impedance data as claimed in any one of the preceding claims, generating a simulated brain impedance dataset comprising: normal brain simulated impedance data and simulated brain impedance data under disease conditions;
a training module for training a machine learning model with the simulated brain impedance dataset as a training dataset;
a classification module for classifying brain impedance data based on the machine learning model.
The present application also provides a computer-readable storage medium having a set of computer instructions stored therein; the set of computer instructions, when executed by a processor, implement the method of generating brain impedance data described above or the method of classifying brain impedance data described above.
Compared with the prior art, the application has the following advantages:
1. according to the application, the impedance data generated by the equivalent circuit follows the actual physical rule, more effective information is introduced, and compared with the impedance data directly generated by the original data, the quality of the generated data is improved;
2. according to the application, a large number of equivalent circuit element parameters are generated according to the rules of the electronic element parameters corresponding to different brain diseases, and finally the equivalent circuit element parameters are converted into brain impedance data of different diseases, so that the problem of difficult acquisition of the brain impedance data is solved;
3. according to the application, the classifier is utilized to test the effect of the generated sample, and whether the equivalent circuit is continuously optimized is judged according to the test result, so that a closed-loop strategy of optimization- > feedback- > optimization is formed, and the quality of generated data is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of a method of generating brain impedance data according to the present application.
FIG. 2 is a flowchart showing the overall method for generating and evaluating brain impedance data according to the present application.
Fig. 3 is an equivalent circuit diagram provided in the embodiment.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
The application provides a method for generating brain impedance data, which comprises the following steps: receiving real brain impedance data, including normal brain impedance data and brain impedance data in a disease state; building an equivalent circuit structure based on the real brain impedance data; performing dimension reduction processing on the real brain impedance data through the equivalent circuit to obtain element parameter samples of the equivalent circuit; acquiring the corresponding relation between the element parameters and the brain state; producing multiple groups of element parameters under different brain states, and substituting the multiple groups of element parameters into an equivalent circuit so as to obtain multiple specific circuits corresponding to the different brain states; corresponding brain impedance data is generated at different frequencies using specific circuitry. The method is obtained as simulation data, but is very close to the real situation, and provides a large quantity of training data sets close to the real situation for machine learning.
Embodiments of the present application are described in further detail below with reference to the accompanying drawings.
A method for generating brain impedance data mainly comprises an S1 data collection step and an S2 sample generation step. Specifically:
the S1 data collection step mainly comprises the following steps: real brain impedance data is received, including normal brain impedance data and brain impedance data in a disease state.
The data acquisition mode and content in the application are as follows: the impedance meter emits an electrical signal at a plurality of frequency points, which is passed through the electrodes to the human brain, and then records the measured impedance values. The impedance value includes a real part and an imaginary part (which may also be expressed as amplitude and phase).
The step of S2 sample generation mainly comprises the following steps:
s2.1, building an equivalent circuit structure based on the real brain impedance data. The equivalent circuit needs to satisfy the characteristics of less elements, less data information loss, and the like. The equivalent circuit may include resistance, capacitance, inductance and constant phase angle elements, and as shown in fig. 3, is a possible form of equivalent circuit, and may be further constructed by using existing brain impedance data, by establishing a formula for iterative optimization or by impedance fitting software such as ZView. The impedance of the resistor may be represented as R (R is a resistance value in ohms), the impedance of the capacitor may be represented as 1/jwC (j is an imaginary unit, w is an angular frequency, C is a capacitance value in farads), the impedance of the inductor may be represented as jwL (L is an inductance value in henry), and the impedance of the constant phase angle element may be represented as 1/Q (jw) a (Q and a are coefficients, Q >0,0< a < 1).
S2.2, performing dimension reduction processing on the real brain impedance data through the equivalent circuit to obtain an element parameter sample of the equivalent circuit.
The specific method is as follows: the impedance equation of the circuit is given by the equivalent circuit structure, and by taking fig. 3 as an example, the impedance equation of the circuit can be expressed as
Z＝(A+B)/A/B
A＝[1+(R 1 +R 2 )Q 1 jwα 1 ]/(R 1 +R 1 R 2 Q 1 jwα 1 )+1/jwC 1
B＝(1+R 3 Q 2 jwα 2 )/R 3 ，
Wherein R is 1 、R 2 、R 3 Is the resistance value of three resistors, C 1 Is the capacitance value of the capacitor, Q 1 、Q 2 、α 1 、α 2 Is the parameter of two constant phase angle elements, w is the angular frequency, j is the imaginary unit, R 1 、R 2 、R 3 、C 1 、Q 1 、Q 2 、α 1 、α 2 I.e. unknown component parameters in the circuit, i.e. component parameters. For each frequency point, an impedance equation with the component parameters as unknowns can be given. The impedance at each frequency is equal to the real impedance, a system of equations can be obtained, and the optimal value of the system of equations (i.e. the error of the system of equations is minimized) can be solved to obtain the elementAnd (5) piece parameters. The number of the element parameters is far smaller than the number of the impedance data, so that the effect of reducing the dimension of the data is achieved.
S2.3, obtaining the corresponding relation between the element parameters and the brain state. The rules between the component parameters and the brain diseases in this step can be extracted in two ways.
Mode 1: the real impedance data are converted into element parameters, each element parameter is clustered, the distribution situation of different diseases is observed, and if the diseases can be distinguished through simple rules of a plurality of element parameters, the element parameters are generated according to the observed rules. Specifically, there are three diseases A, B, C, for example, in which a resistance value of a certain resistor in a circuit is very high, and in other cases, the resistance value is very low, and in which a capacitance value in a circuit is very low, and in other cases, the capacitance value is high, so that disease classification can be performed by the resistor and the inductor.
Mode 2: the component parameters into which the real data are converted are used as samples, trained with a Generation Antagonism Network (GAN) and new component parameter samples are generated. Specifically, for example, one GAN is used for each disease, and for a generator, noise is input, all element parameters corresponding to the disease are output, and for a discriminator, an input is a true sample and a generated sample, and an output is a confidence that it is judged that the input sample is a true sample).
S2.4, producing multiple groups of element parameters aiming at different brain states, substituting the multiple groups of element parameters into an equivalent circuit, thereby obtaining multiple specific circuits corresponding to the different brain states, and preparing for generating data.
S2.5 generates corresponding brain impedance data at different frequencies using specific circuitry.
Specifically, an equivalent circuit impedance value of a series connection of a capacitor with a capacitance value of 1 and a resistor with a resistance value of 6 can be expressed as 6-j/w, and when a 100Hz signal is taken as an input of the circuit, the impedance values of two ends of the circuit are 6-0.01j. When 1000Hz signal is used as input of the circuit, the impedance value of the two ends of the circuit is 6-0.001j, and the like, a series of brain impedance data of a person at different frequencies can be obtained.
The application also provides a classification method of brain impedance data, which comprises the following steps:
s3.1 repeatedly performing the method of generating brain impedance data as claimed in any one of the preceding claims, generating a simulated brain impedance dataset comprising: normal brain simulated impedance data and simulated brain impedance data in a disease state.
And S3.2, training a machine learning model by taking the simulated brain impedance data set as a training data set. The machine learning model is not limited explicitly, and various classifiers for machine learning such as a neural network model, an SVM model, a random forest model and the like can be selected.
And S3.3, classifying brain impedance data based on the machine learning model.
Further, the method further comprises:
s3.4, testing the trained classifier by using real data which is not used in the training process, and if the classifier effect of using the new training set is better than that of using only the real sample for training, the current simulation sample can be used for improving the classifier effect, so that the purpose of improving the classifier effect is achieved. Otherwise, more real brain impedance sample data is acquired, and the equivalent circuit is optimized. The effect of the classifier can be compared by means of confusion matrix, F1 index, etc. Specifically, recall and precision in confusion matrix obtained by two classifiers on a test set are directly compared through confusion matrix comparison, and the classifier with higher recall and higher precision has better effect. By F1 index comparison, first define: f (F) 1 The larger the value is, the better the classifier effect is.
Corresponding to the method for generating brain impedance data in the application, the application also provides a device for generating brain impedance data, which comprises the following steps: the device comprises a receiving module, a circuit building module, a dimension reduction module, a corresponding relation acquisition module, a specific circuit acquisition module and a brain impedance data production module. Wherein,
a receiving module for receiving real brain impedance data, including normal brain impedance data and brain impedance data in a disease state;
a circuit building module for building an equivalent circuit structure based on the real brain impedance data;
the dimension reduction module is used for carrying out dimension reduction processing on the real brain impedance data through the equivalent circuit to obtain an element parameter sample of the equivalent circuit;
the corresponding relation acquisition module is used for acquiring the corresponding relation between the element parameters and the brain state;
the specific circuit acquisition module is used for producing a plurality of groups of element parameters under different brain states, and substituting the plurality of groups of element parameters into an equivalent circuit so as to obtain a plurality of specific circuits corresponding to the different brain states;
and the brain impedance data production module is used for generating corresponding brain impedance data at different frequencies by using specific circuits.
For the embodiments of the present application, since they correspond to those in the above embodiments, the description is relatively simple, and the relevant similarities will be found in the description of the above embodiments, and will not be described in detail herein.
The application also provides a classification device of brain impedance data, which comprises: the device comprises a simulated brain impedance data set production module, a training module and a classification module.
Wherein,
a simulated brain impedance dataset production module for repeatedly performing the method of generating brain impedance data as claimed in any one of the preceding claims, generating a simulated brain impedance dataset comprising: normal brain simulated impedance data and simulated brain impedance data under disease conditions;
a training module for training a machine learning model with the simulated brain impedance dataset as a training dataset;
a classification module for classifying brain impedance data based on the machine learning model.
For the embodiments of the present application, since they correspond to those in the above embodiments, the description is relatively simple, and the relevant similarities will be found in the description of the above embodiments, and will not be described in detail herein.
The present application also provides a computer-readable storage medium having a set of computer instructions stored therein; the set of computer instructions, when executed by a processor, implement the method of generating brain impedance data described above or the method of classifying brain impedance data described above.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, for example, may be a logic function division, and may be implemented in another manner, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application.
Claims (9)
1. A method of generating brain impedance data, comprising:
receiving real brain impedance data, including normal brain impedance data and brain impedance data in a disease state;
building an equivalent circuit structure based on the real brain impedance data;
performing dimension reduction processing on the real brain impedance data through the equivalent circuit to obtain element parameter samples of the equivalent circuit, wherein the element parameter samples comprise:
the impedance equation of the equivalent circuit is given according to the equivalent circuit structure,
the impedance at each frequency is equal to the real impedance, and the optimal value of the equation set is solved to obtain element parameters;
acquiring the corresponding relation between the element parameters and the brain state;
generating multiple groups of element parameters aiming at different brain states, and substituting the multiple groups of element parameters into an equivalent circuit so as to obtain multiple specific circuits corresponding to the different brain states;
corresponding brain impedance data is generated at different frequencies using specific circuitry.
2. The method of generating brain impedance data according to claim 1, wherein the acquiring of the correspondence of the element parameter to the brain state comprises:
converting the real impedance data into element parameters;
clustering each element parameter;
and extracting the corresponding relation between the element parameters and the brain states according to the parameter distribution conditions of different brain states.
3. The method of generating brain impedance data according to claim 1, wherein the acquiring of the correspondence of the element parameter to the brain state comprises:
converting the real data into element parameters as samples;
training is performed by generating an antagonism network and generating new element parameter samples.
4. A method of classifying brain impedance data, comprising:
the method for generating brain impedance data according to any one of claims 1-3, being repeatedly performed, generating a simulated brain impedance dataset comprising: normal brain simulated impedance data and simulated brain impedance data under disease conditions;
training a machine learning model with the simulated brain impedance dataset as a training dataset;
based on the machine learning model, brain impedance data is classified.
5. The method of classifying brain impedance data according to claim 4, further comprising:
the real brain impedance data is added to the training data set to train the machine learning model.
6. The method of classifying brain impedance data according to claim 4, wherein the machine learning model is a neural network model, an SVM model, or a random forest model.
7. An apparatus for generating brain impedance data, comprising:
a receiving module for receiving real brain impedance data, including normal brain impedance data and brain impedance data in a disease state;
a circuit building module for building an equivalent circuit structure based on the real brain impedance data;
the dimension reduction module is used for carrying out dimension reduction processing on the real brain impedance data through the equivalent circuit to obtain element parameter samples of the equivalent circuit, and comprises the following steps:
the impedance equation of the equivalent circuit is given according to the equivalent circuit structure,
the impedance at each frequency is equal to the real impedance, and the optimal value of the equation set is solved to obtain element parameters;
the corresponding relation acquisition module is used for acquiring the corresponding relation between the element parameters and the brain state;
the specific circuit acquisition module is used for generating a plurality of groups of element parameters aiming at different brain states, and substituting the plurality of groups of element parameters into an equivalent circuit so as to obtain a plurality of specific circuits corresponding to the different brain states;
and the brain impedance data production module is used for generating corresponding brain impedance data at different frequencies by using specific circuits.
8. A device for classifying brain impedance data, comprising:
a simulated brain impedance dataset production module for repeatedly performing the method of generating brain impedance data as claimed in any one of claims 1 to 3, generating a simulated brain impedance dataset comprising: normal brain simulated impedance data and simulated brain impedance data under disease conditions;
a training module for training a machine learning model with the simulated brain impedance dataset as a training dataset;
a classification module for classifying brain impedance data based on the machine learning model.
9. A computer-readable storage medium having a set of computer instructions stored therein; the set of computer instructions, when executed by a processor, implements the method of generating brain impedance data of any one of claims 1-3 or the method of classifying brain impedance data of claims 4-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011629285.7A CN112754452B (en) | 2020-12-31 | 2020-12-31 | Method, device and storage medium for generating brain impedance data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011629285.7A CN112754452B (en) | 2020-12-31 | 2020-12-31 | Method, device and storage medium for generating brain impedance data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112754452A CN112754452A (en) | 2021-05-07 |
| CN112754452B true CN112754452B (en) | 2023-11-28 |
Family
ID=75699508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011629285.7A Active CN112754452B (en) | 2020-12-31 | 2020-12-31 | Method, device and storage medium for generating brain impedance data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112754452B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09327445A (en) * | 1996-06-13 | 1997-12-22 | Suzuki Motor Corp | Sensor for organism measurement |
| CN110720915A (en) * | 2019-09-09 | 2020-01-24 | 浙江工业大学 | Brain electrical impedance tomography method based on GAN |
| CN111528826A (en) * | 2020-05-25 | 2020-08-14 | 陈聪 | Method for acquiring brain impedance blood flow graph data |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110208084A1 (en) * | 2008-09-09 | 2011-08-25 | Fernando Seoane Martinez | Method and apparatus for brain damage detection |
| US20100076326A1 (en) * | 2008-09-22 | 2010-03-25 | Richard Jonathan Cohen | Method for estimating changes of cardiovascular indices using peripheal arterial blood pressure waveform |
| TWI563972B (en) * | 2014-06-11 | 2017-01-01 | 國立成功大學 | Signal process system and method for the same and bioimpedance detection device and element |
| JP6458171B2 (en) * | 2015-01-14 | 2019-01-23 | アールエス メディカル モニタリング リミテッド | Method and system for monitoring internal electrical impedance of a living body |
| ES2765802T3 (en) * | 2015-07-17 | 2020-06-11 | Quantium Medical S L | Device and method to assess the level of consciousness, pain and nociception during the waking state, sedation and general anesthesia |
| US11172868B2 (en) * | 2017-07-21 | 2021-11-16 | Yi Zheng | Screening of malignant glioma, brain tumors, and brain injuries using disturbance coefficient, differential impedances, and artificial neural network |
-
2020
- 2020-12-31 CN CN202011629285.7A patent/CN112754452B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09327445A (en) * | 1996-06-13 | 1997-12-22 | Suzuki Motor Corp | Sensor for organism measurement |
| CN110720915A (en) * | 2019-09-09 | 2020-01-24 | 浙江工业大学 | Brain electrical impedance tomography method based on GAN |
| CN111528826A (en) * | 2020-05-25 | 2020-08-14 | 陈聪 | Method for acquiring brain impedance blood flow graph data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112754452A (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110811609B (en) | Epileptic spike intelligent detection device based on self-adaptive template matching and machine learning algorithm fusion | |
| CN110443798B (en) | Autism detection method, device and system based on magnetic resonance image | |
| CN107122790B (en) | Non-invasive load identification algorithm based on hybrid neural network and ensemble learning | |
| CN106909784A (en) | Epileptic electroencephalogram (eeg) recognition methods based on two-dimentional time-frequency image depth convolutional neural networks | |
| CN108143409A (en) | Sleep stage method and device by stages | |
| CN106709469A (en) | Automatic sleep staging method based on multiple electroencephalogram and electromyography characteristics | |
| CN105615834A (en) | Sleep stage classification method and device based on sleep EEG (electroencephalogram) signals | |
| CN110706786B (en) | Non-contact intelligent psychological parameter analysis and evaluation system | |
| CN113295702B (en) | Electrical equipment fault diagnosis model training method and electrical equipment fault diagnosis method | |
| CN111110224A (en) | Electrocardiogram classification method and device based on multi-angle feature extraction | |
| CN106419911A (en) | Emotional detection method based on brain electric wave analysis | |
| CN107590455A (en) | A kind of high frequency partial discharge adaptive-filtering clustering method and device based on wavelet decomposition | |
| CN110543832A (en) | Electroencephalogram data classification method based on random forest and convolutional neural network | |
| CN114732424B (en) | Method for extracting complex network attribute of muscle fatigue state based on surface electromyographic signal | |
| CN114237046B (en) | Partial discharge pattern recognition method based on SIFT data feature extraction algorithm and BP neural network model | |
| CN115281685A (en) | Sleep stage identification method and device based on anomaly detection and computer readable storage medium | |
| CN112754452B (en) | Method, device and storage medium for generating brain impedance data | |
| CN110244216B (en) | Analog circuit fault diagnosis method based on cloud model optimization PNN | |
| CN108078563A (en) | A kind of EEG signal analysis method of integrated classifier | |
| CN106618552B (en) | A kind of detection model acquisition methods and device | |
| CN109117787A (en) | A kind of emotion EEG signal identification method and system | |
| CN113397563A (en) | Training method, device, terminal and medium for depression classification model | |
| Kaur et al. | An Intelligent Diagnosis System for Electrocardiogram (ECG) Images Using Artificial Neural Network (ANN) | |
| Borodyn et al. | Automated Osborn wave detection system based on wavelet features and neural network | |
| CN113133742B (en) | Knee joint signal feature extraction and classification method and device based on time domain multidimensional feature fusion |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 116000 room 206, no.8-9, software garden road, Ganjingzi District, Dalian City, Liaoning Province Applicant after: Neusoft Education Technology Group Co.,Ltd. Address before: 116000 room 206, no.8-9, software garden road, Ganjingzi District, Dalian City, Liaoning Province Applicant before: Dalian Neusoft Education Technology Group Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |