CN112826507A - Brain function network evolution modeling method for sensorineural deafness - Google Patents
Brain function network evolution modeling method for sensorineural deafness Download PDFInfo
- Publication number
- CN112826507A CN112826507A CN202110020097.2A CN202110020097A CN112826507A CN 112826507 A CN112826507 A CN 112826507A CN 202110020097 A CN202110020097 A CN 202110020097A CN 112826507 A CN112826507 A CN 112826507A
- Authority
- CN
- China
- Prior art keywords
- state
- brain
- evolution
- brain network
- time
- 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
- A61B5/12—Audiometering
- A61B5/121—Audiometering evaluating hearing capacity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4842—Monitoring progression or stage of a disease
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7246—Details of waveform analysis using correlation, e.g. template matching or determination of similarity
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Otolaryngology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a brain function network evolution modeling method for sensorineural deafness, comprising the following steps of S01, extracting brain network state data, analyzing and extracting state expression of a brain network by using a BOLD signal of resting state fMRI as an object through a sliding window technology to obtain high-dimensional vector expression of the brain network state; s02, acquiring low-dimensional mapping and clustering results by using the state observation matrix; s03, analyzing the conversion mode of the brain network state, constructing a state set according to the clustering result of the state, and analyzing the relation between switching and time between the states to obtain a time sequence diagram of the brain network state evolution on a time axis; s04, establishing an evolution process model through a time automaton theory according to a brain network state evolution sequence diagram by the aid of a brain network evolution model based on a time automaton, providing a quantitative brain network dynamic description model, effectively describing state conversion rules and evolution processes of a human brain network, having universality on different tested data, and identifying abnormal evolution processes of the tested data.
Description
Technical Field
The embodiment of the invention relates to the field of medical equipment, in particular to a portable sharp instrument box.
Background
Deafness is one of the common diseases seriously affecting human health and life, the incidence rate of deafness in adults is about 10%, the incidence rate of deafness is in a remarkable rising trend along with the increase of age, and the perception of sound is completed on the basis of a series of complex structures, wherein the series of structures not only comprise the collection and conduction of sound by ears, but also need the conduction and analysis of corresponding auditory nerves and auditory nerve centers.
At present, although research on the sensorineural deafness brain function network has achieved certain results, there are several problems still to be solved, firstly, the progress of the sensorineural deafness patient with the disease still does not understand how the brain function evolves, and secondly, the scientific and quantitative evaluation of the sensorineural deafness patient's brain auditory network function and the prediction of the direction of the later disease progress cannot be achieved.
Disclosure of Invention
The invention aims to provide a brain function network evolution modeling method for sensorineural deafness, which aims to solve the technical problems that the brain auditory network function of a patient with sensorineural deafness cannot be quantitatively evaluated and the later-stage disease progression direction cannot be predicted in the evolution process of the brain function along with the progression of deafness in the prior art.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
a brain function network evolution modeling method for sensorineural deafness comprises the following steps:
s01, extracting brain network state data, analyzing and extracting state expression of the brain network by using a BOLD signal of the resting state fMRI as an object through a sliding window technology, and obtaining high-dimensional vector expression of the brain network state;
s02, acquiring low-dimensional mapping and clustering results by using the state observation matrix, taking all brain network state high-dimensional vectors on a data acquisition time interval as objects, and acquiring point mapping of the states on a two-dimensional space by t-distribution random neighbor embedding to obtain clustering results of the states;
s03, analyzing the conversion mode of the brain network state, constructing a state set according to the clustering result of the state, and analyzing the relation between switching and time between the states to obtain a time sequence diagram of the brain network state evolution on a time axis;
s04, establishing an evolution process model through a time automaton theory according to the brain network state evolution sequence diagram based on the brain network evolution model of the time automaton, and providing a quantitative brain network dynamic description model.
As a preferred scheme of the present invention, the brain network state data extraction distinguishes brain regions according to an automatic anatomical label AAL template, extracts average BOLD signal time sequences of different brain regions within a sampling period, and obtains brain network state data by measuring a connection relationship between the brain regions through correlation analysis.
As a preferred scheme of the invention, a state observation matrix is constructed according to the brain network state data to obtain low-dimensional mapping and clustering results, and the method specifically comprises the following steps:
firstly, obtaining a brain network sample containing N time points, and setting the iteration number of dimensionality reduction and the low-dimensional space target dimensionality;
secondly, dividing the whole BOLD signal into a plurality of short signals by using a sliding window, obtaining a plurality of different function connection matrixes by adjusting the size of the window, and calculating Euclidean distances among different matrixes;
thirdly, calculating the low-dimensional space joint probability by taking the brain network dynamic characteristic matrix data points as the center, and defining a target function;
and finally, optimizing the objective function and obtaining a dimension reduction result.
As a preferable embodiment of the present invention, the dimensionality reduction result of the objective function in the two-dimensional space is stained in time sequence, and the brain network state distribution in the two-dimensional space at different time points is obtained.
As a preferred embodiment of the present invention, the time transition table is set according to the brain network state distribution, and includes a whole brain state evolution finite alphabet, a whole brain state evolution finite state set, a start state set, a whole brain state evolution finite clock set, and a brain network state transition rule set.
As a preferred scheme of the invention, the six-tuple is described through the time conversion table, a collection clock variable set is defined, and a dynamic evolution time interval of the brain network state is given through time interval sequential logic.
As a preferred scheme of the invention, the state description of the whole brain area on a single sampling point is obtained by sampling the blood oxygen dependent horizontal signal in the time interval, and the state set of the whole brain area is obtained by unsupervised clustering.
As a preferred scheme of the invention, the starting time and the state ending time of the collected data are set in the state set, and a brain network state survival function is constructed by adopting a non-parametric method.
As a preferred scheme of the invention, a t-distribution random neighbor embedding method is adopted to perform dimensionality reduction on the brain network state survival function to obtain a corresponding state transition set, and the stable states of all samples under each breakpoint condition are judged.
Compared with the prior art, the invention has the following beneficial effects:
the brain function network evolution modeling method for sensorineural deafness is characterized in that a state observation matrix of a whole brain area on a single time sampling point is constructed on the basis of the dynamic characteristics of the whole brain area network, then a state set of the whole brain area is obtained through unsupervised clustering, and on the basis, a time model is established for the dynamic evolution process of the brain network by adopting an automaton theory, so that when a BOLD signal enters a stable state can be judged according to the model, a quantitative analysis method is provided for judging a stable state critical point of the BOLD signal, the state conversion rule and the evolution process of the human brain network can be effectively described, universality is realized on different tested data, and the abnormal evolution process of the tested data can be identified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
Fig. 1 is a flowchart of a brain function network evolution modeling method for sensorineural deafness according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in figure 1, the invention provides a brain function network evolution modeling method for sensorineural deafness, which is characterized in that a state observation matrix of a whole brain area on a single time sampling point is constructed on the basis of the dynamic characteristics of the whole brain area network, then a state set of the whole brain area is obtained through unsupervised clustering, and on the basis, a time model is established for the dynamic evolution process of the brain network by adopting an automaton theory, so that when a BOLD signal enters a stable state can be judged according to the model, a quantitative analysis method is provided for judging the stable state critical point of the BOLD signal, the state conversion rule and the evolution process of the human brain network can be effectively described, the method has universality on different tested data, and the abnormal evolution process of the tested data can be identified.
The method comprises the following steps:
s01, extracting brain network state data, analyzing and extracting state expression of the brain network by using a BOLD signal of the resting state fMRI as an object through a sliding window technology, and obtaining high-dimensional vector expression of the brain network state;
s02, acquiring low-dimensional mapping and clustering results by using the state observation matrix, taking all brain network state high-dimensional vectors on a data acquisition time interval as objects, and acquiring point mapping of the states on a two-dimensional space by t-distribution random neighbor embedding to obtain clustering results of the states;
s03, analyzing the conversion mode of the brain network state, constructing a state set according to the clustering result of the state, and analyzing the relation between switching and time between the states to obtain a time sequence diagram of the brain network state evolution on a time axis;
s04, establishing an evolution process model through a time automaton theory according to the brain network state evolution sequence diagram based on the brain network evolution model of the time automaton, and providing a quantitative brain network dynamic description model.
In this embodiment, the specific state of the brain network at each time point is described by processing the BOLD signal in the sampling time interval, the state transition rule of the high-dimensional brain state observation matrix is observed after low-dimensional mapping is performed on the obtained high-dimensional brain state observation matrix, and on this basis, the state evolution process of the brain network is modeled by combining a time automaton, so that the purpose of quantitatively describing the dynamic characteristics of the brain network is achieved.
The brain network state data extraction distinguishes brain areas according to an automatic anatomical label AAL template, average BOLD signal time sequences of different brain areas in a sampling period are respectively extracted, and the connection relation among all the brain areas is measured by utilizing correlation analysis to obtain the brain network state data.
In this embodiment, the brain network state data extraction is to perform basic preprocessing on the original resting state functional magnetic resonance imaging data by using a Python platform, and obtain a whole brain region BOLD signal time sequence through the preprocessing.
Constructing a state observation matrix according to the brain network state data to obtain low-dimensional mapping and clustering results, and specifically comprising the following steps:
firstly, obtaining a brain network sample containing N time points, and setting the iteration number of dimensionality reduction and the low-dimensional space target dimensionality;
secondly, dividing the whole BOLD signal into a plurality of short signals by using a sliding window, obtaining a plurality of different function connection matrixes by adjusting the size of the window, and calculating Euclidean distances among different matrixes;
thirdly, calculating the low-dimensional space joint probability by taking the brain network dynamic characteristic matrix data points as the center, and defining a target function;
and finally, optimizing the objective function and obtaining a dimension reduction result.
In this embodiment, each row of the brain network state observation matrix is sequentially connected end to obtain a state observation row vector, which is regarded as a point in the high-dimensional space, and any two points x in the high-dimensional space are calculatediAnd xjBetween Euclidean distance to obtain similarity probability p between two pointsiAnd pjAnd then the joint probability p of i and j in a high-dimensional data space can be obtainedijAnd constructing an objective function by utilizing the KL divergence to measure the difference of two probability distributions of a high-dimensional space and a low-dimensional space, and finally searching the optimal solution of the low-dimensional space expression by gradient descent.
In the embodiment, the size of the window is adjusted by sliding the window, and the state of the data stream is not changed along with the continuous update of the state of the window, so that a real-time brain network state observation matrix can be constructed, and the brain network state can be truly reflected.
In this embodiment, the average BOLD signal time sequences of 90 brain regions in the sampling period are extracted, after the BOLD time sequences are extracted, the functional connection strength between the brain regions is calculated to determine the correlation between the brain regions, the degree of the connection relationship between the brain regions is measured by using correlation analysis, the tight strength of the connection between the brain regions is measured by the magnitude of the correlation coefficient, and the larger the absolute value of the correlation coefficient is, the stronger the correlation degree between the two brain regions is.
In this embodiment, the correlation analysis method mainly analyzes the linear relationship between variables, and reflects the closeness of the linear relationship between variables.
In this embodiment, a whole brain area BOLD signal is used as a continuous time-varying variable, a whole brain network function is analyzed by a pearson correlation analysis method, and a pearson correlation coefficient is used to calculate a correlation between two brain areas, where the formula is as follows:
wherein xiAnd xjRespectively representing a time series of voxels denoted i, j, i, j respectively representing the corresponding voxels,
and
represents the mean of the time series.
And dyeing the dimensionality reduction result of the target function in the two-dimensional space according to the time sequence to obtain the brain network state distribution of different time points in the two-dimensional space.
In this embodiment, after the dimension reduction result is stained, the visualized color of the data point may be set to different color values along with the advance of the sampling time.
And setting a time conversion table according to the brain network state distribution, wherein the time conversion table comprises a whole brain state evolution finite alphabet, a whole brain state evolution finite state set, a starting state set, a whole brain state evolution finite clock set and a brain network state conversion rule set.
In this embodiment, a time conversion table of brain network state distribution is used as a time sequence, a brain function network state observation window is used as a basis, a single-state observation matrix is successfully constructed, and all single-state observation matrices are integrated into a multi-state observation matrix, so as to obtain a space-time state expression of a whole brain network.
Describing the six-tuple through the time conversion table, defining an acquisition clock variable set, and giving a dynamic evolution time interval of the brain network state through time interval sequential logic.
In this embodiment, a time automaton describing the evolution of the global brain state is set as a six-tuple, in which the time transition table of the brain network state transition and the termination state of the brain network.
And obtaining the state description of the whole brain area on a single sampling point by sampling the blood oxygen dependent horizontal signal in the time interval, and obtaining the state set of the whole brain area through unsupervised clustering.
Setting the starting time and the state ending time of the acquired data in the state set, and constructing a brain network state survival function by adopting a non-parameter method.
And performing dimensionality reduction on the brain network state survival function by adopting a t-distribution random neighbor embedding method to obtain a state transition set corresponding to the brain network state survival function, and judging the stable states of all samples under each breakpoint condition.
In this embodiment, the time automaton formed in the brain network evolution process can be represented as a six-tuple, which can represent the transition of the brain network state, the brain network presenting five relatively stable states, the initial state of the brain network, the transition rule set, and the like of a normal person in a resting state, and the state evolution of the brain network can occur only when all conditions are satisfied simultaneously.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (9)
1. A brain function network evolution modeling method for sensorineural deafness is characterized by comprising the following steps: the method comprises the following steps:
s01, extracting brain network state data, analyzing and extracting state expression of the brain network by using a BOLD signal of the resting state fMRI as an object through a sliding window technology, and obtaining high-dimensional vector expression of the brain network state;
s02, acquiring low-dimensional mapping and clustering results by using the state observation matrix, taking all brain network state high-dimensional vectors on a data acquisition time interval as objects, and acquiring point mapping of the states on a two-dimensional space by t-distribution random neighbor embedding to obtain clustering results of the states;
s03, analyzing the conversion mode of the brain network state, constructing a state set according to the clustering result of the state, and analyzing the relation between switching and time between the states to obtain a time sequence diagram of the brain network state evolution on a time axis;
s04, establishing an evolution process model through a time automaton theory according to the brain network state evolution sequence diagram based on the brain network evolution model of the time automaton, and providing a quantitative brain network dynamic description model.
2. The brain function network evolution modeling method for sensorineural deafness according to claim 1, characterized in that: the brain network state data extraction distinguishes brain areas according to an automatic anatomical label AAL template, average BOLD signal time sequences of different brain areas in a sampling period are respectively extracted, and the connection relation among all the brain areas is measured by utilizing correlation analysis to obtain the brain network state data.
3. The brain function network evolution modeling method for sensorineural deafness according to claim 2, characterized in that: constructing a state observation matrix according to the brain network state data to obtain low-dimensional mapping and clustering results, and specifically comprising the following steps:
firstly, obtaining a brain network sample containing N time points, and setting the iteration number of dimensionality reduction and the low-dimensional space target dimensionality;
secondly, dividing the whole BOLD signal into a plurality of short signals by using a sliding window, obtaining a plurality of different function connection matrixes by adjusting the size of the window, and calculating Euclidean distances among different matrixes;
thirdly, calculating the low-dimensional space joint probability by taking the brain network dynamic characteristic matrix data points as the center, and defining a target function;
and finally, optimizing the objective function and obtaining a dimension reduction result.
4. The brain function network evolution modeling method for sensorineural deafness according to claim 3, characterized in that: and dyeing the dimensionality reduction result of the target function in the two-dimensional space according to the time sequence to obtain the brain network state distribution of different time points in the two-dimensional space.
5. The brain function network evolution modeling method for sensorineural deafness according to claim 4, characterized in that: and setting a time conversion table according to the brain network state distribution, wherein the time conversion table comprises a whole brain state evolution finite alphabet, a whole brain state evolution finite state set, a starting state set, a whole brain state evolution finite clock set and a brain network state conversion rule set.
6. The brain function network evolution modeling method for sensorineural deafness according to claim 5, characterized in that: describing the six-tuple through the time conversion table, defining an acquisition clock variable set, and giving a dynamic evolution time interval of the brain network state through time interval sequential logic.
7. The brain function network evolution modeling method for sensorineural deafness according to claim 6, characterized in that: and obtaining the state description of the whole brain area on a single sampling point by sampling the blood oxygen dependent horizontal signal in the time interval, and obtaining the state set of the whole brain area through unsupervised clustering.
8. The brain function network evolution modeling method for sensorineural deafness according to claim 7, characterized in that: setting the starting time and the state ending time of the acquired data in the state set, and constructing a brain network state survival function by adopting a non-parameter method.
9. The brain function network evolution modeling method for sensorineural deafness according to claim 8, characterized in that: and performing dimensionality reduction on the brain network state survival function by adopting a t-distribution random neighbor embedding method to obtain a state transition set corresponding to the brain network state survival function, and judging the stable states of all samples under each breakpoint condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110020097.2A CN112826507A (en) | 2021-01-07 | 2021-01-07 | Brain function network evolution modeling method for sensorineural deafness |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110020097.2A CN112826507A (en) | 2021-01-07 | 2021-01-07 | Brain function network evolution modeling method for sensorineural deafness |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112826507A true CN112826507A (en) | 2021-05-25 |
Family
ID=75928326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110020097.2A Pending CN112826507A (en) | 2021-01-07 | 2021-01-07 | Brain function network evolution modeling method for sensorineural deafness |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112826507A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283357A (en) * | 2021-06-01 | 2021-08-20 | 华中科技大学同济医学院附属协和医院 | Individual brain function network extraction method for brain function data analysis |
| CN113558635A (en) * | 2021-06-07 | 2021-10-29 | 华中科技大学同济医学院附属协和医院 | Evaluation method for neural deaf patient brain function network evolution |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361203A (en) * | 2014-10-17 | 2015-02-18 | 东南大学 | Social emotion competency evaluation system based on brain network time-space dynamics analysis |
| CN111325288A (en) * | 2020-03-17 | 2020-06-23 | 山东工商学院 | Clustering idea-based multi-view dynamic brain network characteristic dimension reduction method |
-
2021
- 2021-01-07 CN CN202110020097.2A patent/CN112826507A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361203A (en) * | 2014-10-17 | 2015-02-18 | 东南大学 | Social emotion competency evaluation system based on brain network time-space dynamics analysis |
| CN111325288A (en) * | 2020-03-17 | 2020-06-23 | 山东工商学院 | Clustering idea-based multi-view dynamic brain network characteristic dimension reduction method |
Non-Patent Citations (1)
| Title |
|---|
| 裴常福: "基于时间自动机的脑网络时空演化建模方法", 《计算机工程与应用》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283357A (en) * | 2021-06-01 | 2021-08-20 | 华中科技大学同济医学院附属协和医院 | Individual brain function network extraction method for brain function data analysis |
| CN113283357B (en) * | 2021-06-01 | 2022-06-07 | 华中科技大学同济医学院附属协和医院 | Individual brain function network extraction method for brain function data analysis |
| CN113558635A (en) * | 2021-06-07 | 2021-10-29 | 华中科技大学同济医学院附属协和医院 | Evaluation method for neural deaf patient brain function network evolution |
| CN113558635B (en) * | 2021-06-07 | 2023-09-19 | 华中科技大学同济医学院附属协和医院 | Evaluation method for brain function network evolution of nerve deafness patient |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113693613B (en) | Electroencephalogram signal classification method, electroencephalogram signal classification device, computer equipment and storage medium | |
| CN109543526B (en) | True and false facial paralysis recognition system based on depth difference characteristics | |
| CN109645989B (en) | Anesthesia depth estimation system | |
| CN110353673B (en) | Electroencephalogram channel selection method based on standard mutual information | |
| CN109480833A (en) | The pretreatment and recognition methods of epileptic's EEG signals based on artificial intelligence | |
| CN111407243B (en) | Pulse signal pressure identification method based on deep learning | |
| CN111009321A (en) | Application method of machine learning classification model in juvenile autism auxiliary diagnosis | |
| CN112826507A (en) | Brain function network evolution modeling method for sensorineural deafness | |
| CN112450947B (en) | Dynamic brain network analysis method for emotional arousal degree | |
| CN109583331B (en) | Deep learning-based accurate positioning method for positions of wrist vein and mouth of person | |
| CN112446891A (en) | Medical image segmentation method based on U-Net network brain glioma | |
| CN111259735B (en) | Single-person attitude estimation method based on multi-stage prediction feature enhanced convolutional neural network | |
| CN111956208B (en) | ECG signal classification method based on ultra-lightweight convolutional neural network | |
| CN108717548B (en) | Behavior recognition model updating method and system for dynamic increase of sensors | |
| CN112641451A (en) | Multi-scale residual error network sleep staging method and system based on single-channel electroencephalogram signal | |
| CN110503636B (en) | Parameter adjustment method, focus prediction method, parameter adjustment device and electronic equipment | |
| CN110897634A (en) | Electrocardiosignal generation method based on generation countermeasure network | |
| CN111931578B (en) | Electroencephalogram identification method based on minimum spanning tree and regional double-layer network | |
| CN117224082A (en) | Dynamic brain function network learning method based on graph learning optimization algorithm | |
| CN113907770B (en) | Ratchet composite wave detection and identification method and system based on feature fusion | |
| CN113283465B (en) | Diffusion tensor imaging data analysis method and device | |
| CN112668362B (en) | Human evidence comparison model training method for dynamic optimization class proxy | |
| CN111612746B (en) | Dynamic detection method for functional brain network central node based on graph theory | |
| CN114626408A (en) | Electroencephalogram signal classification method and device, electronic equipment, medium and product | |
| CN114266738A (en) | Longitudinal analysis method and system for mild brain injury magnetic resonance image data |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210525 |