CN114403901A - Electroencephalogram signal processing device, method and medium - Google Patents
Electroencephalogram signal processing device, method and medium Download PDFInfo
- Publication number
- CN114403901A CN114403901A CN202210141615.0A CN202210141615A CN114403901A CN 114403901 A CN114403901 A CN 114403901A CN 202210141615 A CN202210141615 A CN 202210141615A CN 114403901 A CN114403901 A CN 114403901A
- Authority
- CN
- China
- Prior art keywords
- hyperactivity disorder
- adhd
- attention deficit
- deficit hyperactivity
- classification
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012545 processing Methods 0.000 title claims abstract description 30
- 208000006096 Attention Deficit Disorder with Hyperactivity Diseases 0.000 claims abstract description 280
- 208000036864 Attention deficit/hyperactivity disease Diseases 0.000 claims abstract description 272
- 238000001228 spectrum Methods 0.000 claims abstract description 76
- 238000012216 screening Methods 0.000 claims abstract description 45
- 230000006870 function Effects 0.000 claims abstract description 38
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 29
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 29
- 230000007547 defect Effects 0.000 claims abstract description 26
- 208000013403 hyperactivity Diseases 0.000 claims abstract description 24
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 208000015802 attention deficit-hyperactivity disease Diseases 0.000 claims description 268
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000013145 classification model Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 9
- 238000007619 statistical method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 abstract 2
- 208000035475 disorder Diseases 0.000 description 24
- 238000004422 calculation algorithm Methods 0.000 description 18
- 238000004458 analytical method Methods 0.000 description 17
- 230000008859 change Effects 0.000 description 12
- 238000012706 support-vector machine Methods 0.000 description 12
- 210000004556 brain Anatomy 0.000 description 8
- 230000007177 brain activity Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 238000003672 processing method Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 210000001061 forehead Anatomy 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 108010076504 Protein Sorting Signals Proteins 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000037213 diet Effects 0.000 description 2
- 235000005911 diet Nutrition 0.000 description 2
- 238000001035 drying Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000004904 shortening Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000027691 Conduct disease Diseases 0.000 description 1
- 208000020358 Learning disease Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 201000003723 learning disability Diseases 0.000 description 1
- 208000020016 psychiatric disease Diseases 0.000 description 1
- 210000004761 scalp Anatomy 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/168—Evaluating attention deficit, hyperactivity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- 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
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
-
- 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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Psychiatry (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Psychology (AREA)
- Developmental Disabilities (AREA)
- Physiology (AREA)
- Educational Technology (AREA)
- Child & Adolescent Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Mathematical Physics (AREA)
- Social Psychology (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The application discloses a device, a method and a medium for processing electroencephalogram signals. Wherein the device includes: the device comprises a to-be-analyzed signal determining module, an eigenmode function determining module, a Hilbert conversion module, a barrier characteristic determining module and a characteristic classification determining module, wherein the eigenmode function determining module is used for obtaining a plurality of eigenmode functions, the Hilbert conversion module is used for converting the eigenmode functions into a first Hilbert spectrum and a second Hilbert spectrum, the barrier characteristic determining module is used for determining attention defect hyperactivity disorder ADHD characteristics based on the first Hilbert spectrum and the second Hilbert spectrum, and the characteristic classification determining module is used for screening the attention defect hyperactivity disorder ADHD characteristics. According to the method, the EEG signals are processed by combining empirical mode decomposition and Hilbert transform, the purpose of automatically classifying the ADHD characteristics of the attention defect hyperactivity disorder is achieved, and the classification precision and accuracy of the ADHD characteristics of the attention defect hyperactivity disorder are improved.
Description
Technical Field
The present application relates to the field of brain wave processing technologies, and in particular, to a device, a method, and a medium for processing an electroencephalogram signal.
Background
Attention Deficit Hyperactivity Disorder (ADHD) is a common mental disorder in childhood, which is manifested by inattention, short Attention time, excessive impulsion, learning disorder, conduct disorder, poor adaptation and other problems. The current screening method for attention deficit hyperactivity disorder is as follows: the method has the advantages that firstly, diagnosis is carried out by depending on manual modes of parents, medical staff and the like, and the method has the problems of low accuracy, easiness in being influenced by subjective factors and incapability of finding the problems early; secondly, screening is completed through the matching mode of the electric signals, and the mode requires mass data to be acquired in the early stage, so that the technical problem of high acquisition cost exists, and meanwhile, the problem of screening failure caused by incapability of matching exists.
Disclosure of Invention
The present application provides a device, a method, an electronic device, and a computer-readable storage medium for processing an electroencephalogram signal, which can solve at least one of the above problems. The technical scheme is as follows:
according to a first aspect of the present application, there is provided an apparatus for processing an electroencephalogram signal, the apparatus comprising:
the analysis-waiting signal determining module is used for determining the electroencephalogram signals to be analyzed for the detected user;
the eigenmode function determining module is used for carrying out empirical mode decomposition on the electroencephalogram signal to be analyzed to obtain a plurality of eigenmode functions;
the Hilbert conversion module is used for converting the plurality of eigenmode functions into a first Hilbert spectrum representing the corresponding relation between time and instantaneous amplitude and a second Hilbert spectrum representing the corresponding relation between time and instantaneous frequency;
the obstacle feature determination module is used for determining the attention deficit hyperactivity disorder ADHD feature based on the first Hilbert spectrum and the second Hilbert spectrum;
and the characteristic classification determining module is used for classifying the attention deficit hyperactivity disorder ADHD characteristics to obtain the characteristic classification of the detected user.
According to a first aspect of the application, an obstacle feature determination module comprises:
the statistical characteristic extraction submodule is used for respectively carrying out statistical analysis on the first Hilbert spectrum and the second Hilbert spectrum to obtain statistical characteristics;
a disorder feature determination submodule for using the statistical features as attention deficit hyperactivity disorder ADHD features;
wherein the statistical features include at least kurtosis, skewness, standard deviation, median, and mean.
According to the first aspect of the application, the obstacle feature determination module further comprises, before the step of characterizing the statistical features as attention deficit hyperactivity disorder ADHD:
the first trend determining submodule is used for determining an amplitude mean value of instantaneous amplitude in preset first unit time length based on the first Hilbert spectrum so as to obtain a first variation trend aiming at the amplitude mean value;
the first trend determining submodule is used for determining a frequency mean value of instantaneous frequency within preset second unit time length based on the second Hilbert spectrum so as to obtain a second variation trend aiming at the frequency mean value;
an obstacle feature determination submodule comprising:
and the obstacle feature determination unit is used for taking the statistical feature, the first variation trend and the second variation trend as the attention deficit hyperactivity disorder ADHD feature.
According to a first aspect of the application, the feature classification determination module comprises:
and the first screening submodule is used for determining a classification result for the tested user according to a pre-constructed classification model for the attention deficit hyperactivity disorder ADHD characteristics and the attention deficit hyperactivity disorder ADHD characteristics.
According to a first aspect of the application, the feature classification determination module comprises:
the encryption processing submodule is used for encrypting the attention defect hyperactivity disorder characteristics to obtain a corresponding encryption value;
and the second screening submodule is used for inquiring the encrypted values in a preset screening result table to obtain a classification result aiming at the attention defect hyperactivity disorder ADHD characteristics of the detected user, wherein the screening result table comprises a plurality of encrypted values and classification results respectively corresponding to the encrypted values and aiming at the attention defect hyperactivity disorder ADHD characteristics.
According to a first aspect of the application, the module for determining a signal to be analyzed comprises:
the preprocessing submodule is used for preprocessing the original electroencephalogram signals of the detected user;
and the wavelet processing sub-module is used for performing wavelet decomposition and reconstruction on the preprocessed original electroencephalogram signal to obtain an electroencephalogram signal to be analyzed in a preset frequency band.
According to a first aspect of the application, the apparatus further comprises:
the personal information acquisition module is used for acquiring the personal information of the detected user by the user;
and the treatment information determining module is used for inputting the personal information and the classification result of the attention deficit hyperactivity disorder ADHD characteristics aiming at the detected user into a preset database to obtain a treatment guidance scheme aiming at the detected user, wherein the database comprises the corresponding relations of different personal information, the classification results of different attention deficit hyperactivity disorder ADHD characteristics and different treatment guidance schemes.
In a second aspect, a method for processing an electroencephalogram signal is provided, the method comprising:
determining an electroencephalogram signal to be analyzed for a detected user;
carrying out empirical mode decomposition on an electroencephalogram signal to be analyzed to obtain a plurality of eigenmode functions;
converting the plurality of eigenmode functions into a first Hilbert spectrum representing the corresponding relation between time and instantaneous amplitude and a second Hilbert spectrum representing the corresponding relation between time and instantaneous frequency;
determining Attention Deficit Hyperactivity Disorder (ADHD) features based on the first Hilbert spectrum and the second Hilbert spectrum;
and classifying the ADHD characteristics of the attention deficit hyperactivity disorder to obtain the characteristic classification of the detected user.
According to a second aspect of the application, the step of determining a characteristic of the attention deficit hyperactivity disorder ADHD based on the first hilbert spectrum and the second hilbert spectrum comprises:
respectively carrying out statistical analysis on the first Hilbert spectrum and the second Hilbert spectrum to obtain statistical characteristics;
taking the statistical features as attention deficit hyperactivity disorder ADHD features;
wherein the statistical features include at least kurtosis, skewness, standard deviation, median, and mean.
According to a second aspect of the application, the method further comprises, before the step of characterizing the statistical features as attention deficit hyperactivity disorder, ADHD: determining an amplitude mean value of the instantaneous amplitude within a preset first unit time length based on the first Hilbert spectrum to obtain a first variation trend aiming at the amplitude mean value; determining a frequency mean value of the instantaneous frequency within a preset second unit time length based on the second Hilbert spectrum to obtain a second variation trend aiming at the frequency mean value; a step of characterizing the statistical features as attention deficit hyperactivity disorder ADHD, comprising: the statistical feature, the first trend of change, and the second trend of change are taken as the attention deficit hyperactivity disorder ADHD feature.
According to the second aspect of the present application, the step of classifying the ADHD features to obtain a classification result for the detected user includes:
and determining a classification result for the tested user according to a pre-constructed classification model aiming at the attention deficit hyperactivity disorder ADHD characteristics and the attention deficit hyperactivity disorder ADHD characteristics.
According to the second aspect of the present application, the step of classifying the ADHD features to obtain a classification result for the detected user includes:
encrypting the ADHD characteristics of the attention deficit hyperactivity disorder to obtain a corresponding encrypted value;
and inquiring the encrypted values in a preset screening result table to obtain a classification result aiming at the tested user, wherein the screening result table comprises a plurality of encrypted values and classification results which are respectively corresponding to the encrypted values and aim at the attention defect hyperactivity disorder ADHD characteristics.
According to a second aspect of the application, the step of determining the electroencephalogram signal to be analyzed for the user to be tested comprises:
preprocessing an original electroencephalogram signal aiming at a detected user;
and performing wavelet decomposition and reconstruction on the preprocessed original electroencephalogram signal to obtain an electroencephalogram signal to be analyzed in a preset frequency band.
According to a second aspect of the application, the method further comprises:
acquiring personal information of a tested user;
and inputting the personal information and the classification result of the attention deficit hyperactivity disorder ADHD characteristics aiming at the detected user into a preset database to obtain a treatment guidance scheme aiming at the detected user, wherein the database comprises the corresponding relations of different personal information, the classification results of different attention deficit hyperactivity disorder ADHD characteristics and different treatment guidance schemes.
In a third aspect, an electronic device is provided, which includes:
one or more processors;
a memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: the processing method of the electroencephalogram signals is executed.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the above-described method of processing an electroencephalogram signal.
In a fifth aspect, a chip is provided for executing the above processing method for electroencephalogram signals.
In a sixth aspect, a brain-computer interface is provided, which includes a wearable device applying a chip for executing the above-mentioned processing method for brain electrical signals.
According to the method, the EEG signal to be analyzed of the user to be detected is determined, empirical mode decomposition is carried out on the EEG signal to be analyzed to obtain a plurality of eigenmode functions, the eigenmode functions are converted into a first Hilbert spectrum representing the corresponding relation between time and instantaneous amplitude and a second Hilbert spectrum representing the corresponding relation between time and instantaneous frequency, attention deficit hyperactivity disorder ADHD characteristics are determined based on the first Hilbert spectrum and the second Hilbert spectrum, the attention deficit hyperactivity disorder ADHD characteristics are further classified, classification results for the user to be detected are obtained, the EEG signal is processed by combining the empirical mode decomposition and Hilbert transformation, analysis of the signal in the time frequency direction is facilitated, the ADHD characteristic of attention deficit hyperactivity disorder can be extracted, and the classification mode of the attention deficit hyperactivity disorder characteristics is transferred from rough matching of the EEG signal to the precision characteristic analysis orbit for the patient On the basis, the automatic classification and identification purposes of the ADHD characteristics of the attention defect hyperactivity disorder are achieved, the classification precision and accuracy of the ADHD characteristics of the attention defect hyperactivity disorder are improved, and the problems that the screening result is large in error and subsequent treatment to patients is influenced due to the fact that the classification accuracy of the ADHD characteristics of the attention defect hyperactivity disorder is low are avoided.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.
Fig. 1 is a schematic structural diagram of a device for processing an electroencephalogram signal according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for processing an electroencephalogram signal according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an application system of the electroencephalogram signal processing method provided in the embodiment of the present application; and
fig. 4 is a schematic workflow diagram of an application system of a method for processing an electroencephalogram signal according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Yet another embodiment of the present application provides a device for processing brain electrical signals, as shown in fig. 4, the device 40 includes: a to-be-analyzed signal determination module 401, an eigenmode function determination module 402, a hilbert conversion module 403, an obstacle feature determination module 404, and a feature classification determination module 405.
And the to-be-analyzed signal determining module 401 is configured to determine an electroencephalogram signal to be analyzed for the user to be tested.
Specifically, the electroencephalogram signal to be analyzed of the user to be tested may be an original signal for the user to be tested, or may be a signal of a certain frequency band. When the method is applied, if the electroencephalogram signal to be analyzed is an original signal for a detected user, the electroencephalogram signal to be analyzed can be acquired from the electroencephalogram EEG acquisition equipment in real time to obtain the electroencephalogram signal to be analyzed, and can also be read locally to obtain the electroencephalogram signal to be analyzed; if the electroencephalogram signal to be analyzed is a signal of a certain frequency band aiming at the detected user, the original signal of the detected user can be decomposed to obtain the electroencephalogram signal to be analyzed which accords with the target.
The eigenmode function determining module 402 is configured to perform empirical mode decomposition on the electroencephalogram signal to be analyzed to obtain a plurality of eigenmode functions.
According to the embodiment of the application, the empirical mode decomposition algorithm is a self-adaptive algorithm based on the local characteristics of the time scale of a signal sequence and does not need to preset any basis function like a Fourier transform and wavelet transform method, so that each decomposed intrinsic mode function IMF component comprises local characteristic signals of different time scales of an original signal.
A hilbert transform module 403 for transforming the plurality of eigenmode functions into a first hilbert spectrum representing a correspondence of time and instantaneous amplitude and a second hilbert spectrum representing a correspondence of time and instantaneous frequency.
Specifically, each eigenmode function obtained through empirical mode decomposition is converted through a configured hilbert conversion algorithm to obtain a hilbert spectrum, so that time-frequency analysis and time-domain analysis of signals are achieved.
An obstacle feature determination module 404 for determining a feature of attention deficit hyperactivity disorder ADHD based on the first hilbert spectrum and the second hilbert spectrum.
Specifically, one or more feature extraction algorithms, such as a linear analysis algorithm, a nonlinear analysis algorithm, a statistical analysis algorithm, etc., may be preconfigured to analyze the hilbert spectrum according to the preconfigured feature extraction algorithm, so that the extracted features are used as the features of the attention deficit hyperactivity disorder ADHD.
And a feature classification determining module 405, configured to classify the attention deficit hyperactivity disorder ADHD features to obtain a feature classification to which the detected user belongs.
Specifically, a plurality of categories corresponding to the attention deficit hyperactivity disorder ADHD features may be preset, such as an attention deficit hyperactivity disorder ADHD feature classification a and an attention deficit hyperactivity disorder ADHD feature classification B, that is, a classification result of the attention deficit hyperactivity disorder ADHD features with respect to the feature classification to which the detected user belongs.
Specifically, the classification result to which the detected user belongs may be directly identified by using the attention deficit hyperactivity disorder ADHD feature, or the classification result may be identified after the attention deficit hyperactivity disorder ADHD feature is processed. More specifically, the manner of directly utilizing the attention deficit hyperactivity disorder ADHD feature to identify the classification result for the attention deficit hyperactivity disorder ADHD feature to which the detected user belongs may include: the method comprises the steps of firstly, identifying attention deficit hyperactivity disorder characteristics by pre-constructing a classification model aiming at the attention deficit hyperactivity disorder ADHD characteristics; and secondly, matching the attention deficit hyperactivity disorder ADHD characteristics in a pre-stored statistical characteristic database to obtain a classification result of the attention deficit hyperactivity disorder ADHD characteristics. For example, a two-classification Support Vector Machine (SVM) can be adopted to identify the characteristics of the Attention Deficit Hyperactivity Disorder (ADHD), so that whether the detected user has the Attention Deficit Hyperactivity Disorder (ADHD) or not is determined according to the classification result; the four-classification support vector machine SVM can also be adopted to identify the characteristics of the attention deficit hyperactivity disorder ADHD, and determine whether the detected user has the attention deficit hyperactivity disorder ADHD and the severity of the attention deficit hyperactivity disorder ADHD according to the identified classification.
Specifically, the classification result of the ADHD feature may be information for determining whether the detected user has the ADHD, or information for determining how much the detected user has the ADHD. When applied, the classification result of the attention deficit hyperactivity disorder ADHD feature can be represented by a predetermined identifier. For example, the classification result corresponding to the identifier "00" is clear, the classification result corresponding to the identifier "01" is mild disorder, the classification result corresponding to the identifier "10" is moderate disorder, and the classification result corresponding to the identifier "11" is severe disorder. It should be noted that the above representation manners of the classification results of the features of attention deficit hyperactivity disorder ADHD are only examples of how to determine the classification results, and in a specific application, any representation manner of the classification results of the features of attention deficit hyperactivity disorder ADHD is within the scope of the present application, and is not listed here.
According to the method, the EEG signal to be analyzed of the user to be detected is determined, empirical mode decomposition is carried out on the EEG signal to be analyzed, a plurality of eigenmode functions are obtained, the eigenmode functions are converted into a first Hilbert spectrum representing the corresponding relation between time and instantaneous amplitude and a second Hilbert spectrum representing the corresponding relation between time and instantaneous frequency, attention deficit hyperactivity disorder ADHD characteristics are determined based on the first Hilbert spectrum and the second Hilbert spectrum, the attention deficit hyperactivity disorder ADHD characteristics are screened, classification results of the attention deficit hyperactivity disorder ADHD characteristics of the user to be detected are obtained, the EEG signal is processed by combining the empirical mode decomposition and Hilbert transformation, analysis of the signal in the time-frequency direction is facilitated, defect hyperactivity disorder ADHD characteristics can be represented and extracted, and classification modes of the attention deficit hyperactivity disorder ADHD characteristics are transferred from rough matching of the EEG signal to be used for rough matching of the EEG signal On the precision characteristic analysis track of the characterization patient, the purpose of automatic classification and identification of the ADHD characteristics of the attention defect hyperactivity disorder is achieved, the classification precision and accuracy of the ADHD characteristics of the attention defect hyperactivity disorder are improved, and the problems that the screening result is large in error and treatment of subsequent patients is affected due to the fact that the classification accuracy of the ADHD characteristics of the attention defect hyperactivity disorder is low are solved.
Further, the obstacle feature determination module includes:
the statistical characteristic extraction submodule is used for respectively carrying out statistical analysis on the first Hilbert spectrum and the second Hilbert spectrum to obtain statistical characteristics;
a disorder feature determination submodule for using the statistical features as attention deficit hyperactivity disorder ADHD features;
wherein the statistical features include at least kurtosis, skewness, standard deviation, median, and mean.
In the embodiment of the present application, the statistical characteristics are set as kurtosis, skewness, standard deviation, median, and mean, and when the statistical characteristics are actually applied, other statistical characteristics, such as a ratio of adjacent peaks, may also be used as the attention deficit hyperactivity disorder ADHD characteristics.
Further, before the step of using the statistical features as the attention deficit hyperactivity disorder ADHD features, the disorder feature determination module further comprises:
the first trend determining submodule is used for determining an amplitude mean value of instantaneous amplitude in preset first unit time length based on the first Hilbert spectrum so as to obtain a first variation trend aiming at the amplitude mean value;
the first trend determining submodule is used for determining a frequency mean value of instantaneous frequency within preset second unit time length based on the second Hilbert spectrum so as to obtain a second variation trend aiming at the frequency mean value;
an obstacle feature determination submodule comprising:
and the obstacle feature determination unit is used for taking the statistical feature, the first variation trend and the second variation trend as the attention deficit hyperactivity disorder ADHD feature.
In an embodiment of the application, the first trend of change is used for representing the frequency of brain activity of the user in a certain time. Specifically, if the variation trend fluctuates greatly, the difficulty of focusing attention of the user is high; otherwise, the difficulty of the user in concentrating attention is easier.
In an embodiment of the present application, the second trend of change is used to characterize the severity of brain activity of the user over a period of time. Specifically, if the variation trend fluctuates greatly, the difficulty of focusing attention of the user is high; otherwise, the difficulty of the user in concentrating attention is easier.
Specifically, the maximum value and the minimum value of the instantaneous amplitude of the first hilbert spectrum in the first duration may be subjected to mean value calculation, and the maximum value and the minimum value are sorted according to the time sequence for fitting, so as to obtain the first variation trend.
Specifically, the maximum value and the minimum value of the instantaneous frequency of the second Hilbert spectrum in the second time duration are subjected to mean value calculation, and are sorted according to the time sequence for fitting to obtain a second variation trend.
According to the method and the device, the effect of reducing abnormal brain activities of the user caused by the abnormality is achieved by calculating the amplitude mean value of the instantaneous amplitude and the frequency mean value of the instantaneous frequency, the brain activities are quantified, effective screening data are provided for the screening of the defect hyperactivity disorder, and the purpose of further improving the screening accuracy is achieved.
Further, the feature classification determination module includes:
and the first screening submodule is used for determining a classification result for the tested user according to a pre-constructed classification model for the attention deficit hyperactivity disorder ADHD characteristics and the attention deficit hyperactivity disorder ADHD characteristics.
In the embodiment of the application, a two-classification vector machine SVM is adopted as a classification model of the ADHD characteristics of the attention deficit hyperactivity disorder. Before application, electroencephalogram signals of a patient with attention deficit hyperactivity disorder and a patient without attention deficit hyperactivity disorder are respectively collected and labeled with corresponding labels, so that sample data for training a binary classification vector machine (SVM) are obtained. In the training process, the sample can be divided into a training sample and a testing sample until the training is completed, so as to obtain the attention deficit hyperactivity disorder ADHD screening model.
Specifically, the output result of the classification model for the characteristics of attention deficit hyperactivity disorder ADHD is generally labeled information representing whether the user is ill or not, and whether the user is ill or not is queried through the labeled information. For example, if the annotation information is X, it is determined that the user has attention deficit hyperactivity disorder ADHD, otherwise the user is normal.
Further, the feature classification determination module includes:
the encryption processing submodule is used for encrypting the ADHD characteristics of the attention deficit hyperactivity disorder to obtain a corresponding encryption value;
and the second screening submodule is used for inquiring the encrypted values in a preset screening result table to obtain a classification result aiming at the detected user, wherein the screening result table comprises a plurality of encrypted values and classification results of the encrypted values respectively corresponding to the attention defect hyperactivity disorder ADHD characteristics.
Specifically, a hash function may be used to perform encryption processing on the attention deficit hyperactivity disorder ADHD feature to obtain a hash value, and the hash value is used as a key value for querying in the screening result table, so as to obtain a final classification result.
According to the embodiment of the application, the problem that the attention deficit hyperactivity disorder ADHD features are maliciously stolen can be effectively solved through the encryption processing, the effect of shortening the classifying time of the attention deficit hyperactivity disorder ADHD features is achieved, the classifying efficiency of the attention deficit hyperactivity disorder ADHD is improved, and an auxiliary basis is provided for diagnosis of the attention deficit hyperactivity disorder ADHD.
Further, the module for determining the signal to be analyzed comprises:
the preprocessing submodule is used for preprocessing the original electroencephalogram signals of the detected user;
and the wavelet processing sub-module is used for performing wavelet decomposition and reconstruction on the preprocessed original electroencephalogram signal to obtain an electroencephalogram signal to be analyzed in a preset frequency band.
In particular, the pre-processing performed by the pre-processing sub-module may include filtering, dessication, artifact removal, and the like. The original electroencephalogram signal of the user to be detected can be filtered by adopting a preset high-pass filter and a preset low-pass filter, so that the electroencephalogram signal to be analyzed which meets the requirements can be obtained. For example, a preset high-pass filter and a preset low-pass filter obtain 0.5-35Hz electroencephalogram signals to be analyzed.
Since the children with attention deficit hyperactivity disorder ADHD have more theta wave activity and weaker beta wave activity, the predetermined frequency band may be set to a frequency band to which the theta wave belongs, or set to frequency bands to which two kinds of waves, theta wave and beta wave, respectively, belong; meanwhile, in order to comprehensively analyze the health state of the patient, frequency bands corresponding to a plurality of waves such as alpha waves, beta waves and theta waves can be preselectively set at the same time, so that the signals are filtered by performing wavelet decomposition and reconstruction on the mechanical energy of the original brain electrical signals, and the signals conforming to the preset frequency bands are obtained. For example, the theta wave is taken as the electroencephalogram signal to be analyzed through wavelet decomposition and reconstruction.
Further, the apparatus further comprises:
the personal information acquisition module is used for acquiring the personal information of the detected user by the user;
and the treatment information determining module is used for inputting the personal information and the classification result of the attention deficit hyperactivity disorder ADHD characteristics aiming at the detected user into a preset database to obtain a treatment guidance scheme aiming at the detected user, wherein the database comprises the corresponding relations of different personal information, the classification results of different attention deficit hyperactivity disorder ADHD characteristics and different treatment guidance schemes.
Specifically, the personal information acquired by the personal information acquisition module may include age, gender, home address, contact information, lifestyle habits, and the like.
In particular, the database may be stored in a server or locally. For example, if the database is stored in the server, the user terminal may send the personal information and the screening result to the server as a query request, so that the server matches the query request in the database, and send the queried treatment guidance plan for the user to be tested to the user terminal.
In the embodiment of the application, the treatment guidance scheme for the tested user generally comprises prompt information for learning, life, diet, treatment and the like.
The embodiment of the application provides a method for processing an electroencephalogram signal, as shown in fig. 2, the method comprises the following steps: step S101 to step S105.
Step S101: and determining the electroencephalogram signals to be analyzed for the tested user.
Specifically, the electroencephalogram signal to be analyzed of the user to be tested may be an original signal for the user to be tested, or may be a signal of a certain frequency band. When the method is applied, if the electroencephalogram signal to be analyzed is an original signal for a detected user, the electroencephalogram signal to be analyzed can be acquired from the electroencephalogram EEG acquisition equipment in real time to obtain the electroencephalogram signal to be analyzed, and can also be read locally to obtain the electroencephalogram signal to be analyzed; if the electroencephalogram signal to be analyzed is a signal of a certain frequency band aiming at the detected user, the original signal of the detected user can be decomposed to obtain the electroencephalogram signal to be analyzed which accords with the target.
Step S102: and carrying out empirical mode decomposition on the electroencephalogram signal to be analyzed to obtain a plurality of eigenmode functions.
According to the embodiment of the application, the empirical mode decomposition algorithm is a self-adaptive algorithm based on the local characteristics of the time scale of a signal sequence and does not need to preset any basis function like a Fourier transform and wavelet transform method, so that each decomposed intrinsic mode function IMF component comprises local characteristic signals of different time scales of an original signal.
Step S103: the pairs of eigenmode functions are converted into a first hilbert spectrum characterizing a time to instantaneous amplitude correspondence and a second hilbert spectrum characterizing a time to instantaneous frequency correspondence.
Specifically, each eigenmode function obtained through empirical mode decomposition is converted through a configured hilbert conversion algorithm to obtain a hilbert spectrum, so that time-frequency analysis and time-domain analysis of signals are achieved.
Step S104: determining an attention deficit hyperactivity disorder feature based on the first Hilbert spectrum and the second Hilbert spectrum.
Specifically, one or more feature extraction algorithms, such as a linear analysis algorithm, a nonlinear analysis algorithm, a statistical analysis algorithm, and the like, may be preconfigured to analyze the hilbert spectrum according to the preconfigured feature extraction algorithm, so that the extracted features are used as the attention deficit hyperactivity disorder features.
Step S105: and classifying the ADHD characteristics of the attention deficit hyperactivity disorder to obtain a classification result to which the detected user belongs.
Specifically, the classification result to which the detected user belongs may be directly identified by using the attention deficit hyperactivity disorder ADHD feature, or the classification result may be identified after the attention deficit hyperactivity disorder ADHD feature is processed. More specifically, the manner of directly utilizing the attention deficit hyperactivity disorder ADHD feature to identify the classification result for the attention deficit hyperactivity disorder ADHD feature to which the detected user belongs may include: the method comprises the steps of firstly, identifying attention deficit hyperactivity disorder characteristics by pre-constructing a classification model aiming at the attention deficit hyperactivity disorder ADHD characteristics; and secondly, matching the attention deficit hyperactivity disorder ADHD characteristics in a pre-stored statistical characteristic database to obtain a classification result of the attention deficit hyperactivity disorder ADHD characteristics. For example, a two-classification Support Vector Machine (SVM) can be adopted to identify the characteristics of the Attention Deficit Hyperactivity Disorder (ADHD), so that whether the detected user has the Attention Deficit Hyperactivity Disorder (ADHD) or not is determined according to the classification result; the four-classification support vector machine SVM can also be adopted to identify the characteristics of the attention deficit hyperactivity disorder ADHD, and determine whether the detected user has the attention deficit hyperactivity disorder ADHD and the severity of the attention deficit hyperactivity disorder ADHD according to the identified classification.
Specifically, the classification result of attention deficit hyperactivity disorder ADHD may be information for determining whether the detected user has attention deficit hyperactivity disorder, or information for determining the degree to which the detected user has attention deficit hyperactivity disorder. When applicable, the screening results for attention deficit hyperactivity disorder ADHD can be identified by a predetermined identification. For example, the screening result corresponding to the identifier "00" is clear, the screening result corresponding to the identifier "01" is mild obstacle, the screening result corresponding to the identifier "10" is moderate obstacle, and the screening result corresponding to the identifier "11" is severe obstacle. It should be noted that the above representation manners for representing the screening results of attention deficit hyperactivity disorder ADHD are only examples of how to determine the screening results, and in a specific application, any representation manner for representing the screening results of attention deficit hyperactivity disorder ADHD is within the scope of the present application, and is not listed here.
According to the method, the EEG signal to be analyzed of the user to be detected is determined, empirical mode decomposition is carried out on the EEG signal to be analyzed, a plurality of eigenmode functions are obtained, the eigenmode functions are converted into a first Hilbert spectrum representing the corresponding relation between time and instantaneous amplitude and a second Hilbert spectrum representing the corresponding relation between time and instantaneous frequency, attention deficit hyperactivity disorder ADHD characteristics are determined based on the first Hilbert spectrum and the second Hilbert spectrum, the attention deficit hyperactivity disorder ADHD characteristics are screened, classification results of the attention deficit hyperactivity disorder ADHD characteristics of the user to be detected are obtained, the EEG signal is processed by combining the empirical mode decomposition and Hilbert transformation, analysis of the signal in the time-frequency direction is facilitated, defect hyperactivity disorder ADHD characteristics can be represented and extracted, and classification modes of the attention deficit hyperactivity disorder ADHD characteristics are transferred from rough matching of the EEG signal to be used for rough matching of the EEG signal On the precision characteristic analysis track of the characterization patient, the purpose of automatic classification and identification of the ADHD characteristics of the attention defect hyperactivity disorder is achieved, the classification precision and accuracy of the ADHD characteristics of the attention defect hyperactivity disorder are improved, and the problems that the screening result is large in error and treatment of subsequent patients is affected due to the fact that the classification accuracy of the ADHD characteristics of the attention defect hyperactivity disorder is low are solved.
In some embodiments, step S104 further comprises:
respectively carrying out statistical analysis on the first Hilbert spectrum and the second Hilbert spectrum to obtain statistical characteristics;
taking the statistical features as attention deficit hyperactivity disorder ADHD features;
wherein the statistical features include at least kurtosis, skewness, standard deviation, median, and mean.
In the embodiment of the application, the statistical characteristics are set as kurtosis, skewness, standard deviation, median and mean, and when the statistical characteristics are actually applied, other statistical characteristics, such as the ratio of adjacent peaks, can be used as the attention deficit hyperactivity disorder characteristics.
In some embodiments, step S104 further comprises:
respectively carrying out statistical analysis on the first Hilbert spectrum and the second Hilbert spectrum to obtain statistical characteristics, wherein the statistical characteristics at least comprise kurtosis, skewness, standard deviation, median and mean;
determining an amplitude mean value of the instantaneous amplitude within a preset first unit time length based on the first Hilbert spectrum to obtain a first variation trend aiming at the amplitude mean value;
determining a frequency mean value of the instantaneous frequency within a preset second unit time length based on the second Hilbert spectrum to obtain a second variation trend aiming at the frequency mean value;
the statistical feature, the first trend of change, and the second trend of change are taken as the attention deficit hyperactivity disorder ADHD feature.
In an embodiment of the application, the first trend of change is used for representing the frequency of brain activity of the user in a certain time. Specifically, if the variation trend fluctuates greatly, the difficulty of focusing attention of the user is high; otherwise, the difficulty of the user in concentrating attention is easier.
In an embodiment of the present application, the second trend of change is used to characterize the severity of brain activity of the user over a period of time. Specifically, if the variation trend fluctuates greatly, the difficulty of focusing attention of the user is high; otherwise, the difficulty of the user in concentrating attention is easier.
Specifically, the maximum value and the minimum value of the instantaneous amplitude of the first hilbert spectrum in the first duration may be subjected to mean value calculation, and the maximum value and the minimum value are sorted according to the time sequence for fitting, so as to obtain the first variation trend.
Specifically, the maximum value and the minimum value of the instantaneous frequency of the second Hilbert spectrum in the second time duration are subjected to mean value calculation, and are sorted according to the time sequence for fitting to obtain a second variation trend.
According to the method and the device, the effect of reducing abnormal brain activities of the user caused by the abnormality is achieved by calculating the amplitude mean value of the instantaneous amplitude and the frequency mean value of the instantaneous frequency, the brain activities are quantified, effective data are provided for the classification of the defect hyperactivity ADHD characteristics, and the purpose of further improving the classification accuracy is achieved.
In some embodiments, step S105 further comprises:
and determining a classification result for the tested user according to a pre-constructed classification model aiming at the attention deficit hyperactivity disorder ADHD characteristics and the attention deficit hyperactivity disorder ADHD characteristics.
In the embodiment of the application, a two-classification vector machine SVM is adopted as a classification model of the ADHD characteristics of the attention deficit hyperactivity disorder. Before application, electroencephalogram signals of a patient with attention deficit hyperactivity disorder and a patient without attention deficit hyperactivity disorder are respectively collected and labeled with corresponding labels, so that sample data for training a binary classification vector machine (SVM) are obtained. In the training process, the sample can be divided into a training sample and a testing sample until the training is completed, so as to obtain the attention deficit hyperactivity disorder ADHD screening model.
Specifically, the output result of the classification model for the characteristics of attention deficit hyperactivity disorder ADHD is generally labeled information representing whether the user is ill or not, and whether the user is ill or not is queried through the labeled information. For example, if the annotation information is X, it is determined that the user has attention deficit hyperactivity disorder ADHD, otherwise the user is normal.
In some embodiments, step S105 comprises:
encrypting the ADHD characteristics of the attention deficit hyperactivity disorder to obtain a corresponding encrypted value;
and inquiring the encrypted values in a preset screening result table to obtain a classification result aiming at the detected user, wherein the screening result table comprises a plurality of encrypted values and classification results of the encrypted values respectively corresponding to the attention defect hyperactivity disorder ADHD characteristics.
Specifically, a hash function may be used to perform encryption processing on the attention deficit hyperactivity disorder ADHD feature to obtain a hash value, and the hash value is used as a key value for querying in the screening result table, so as to obtain a final classification result.
According to the embodiment of the application, the problem that the attention deficit hyperactivity disorder ADHD features are maliciously stolen can be effectively solved through the encryption processing, the effect of shortening the classifying time of the attention deficit hyperactivity disorder ADHD features is achieved, the classifying efficiency of the attention deficit hyperactivity disorder ADHD is improved, and an auxiliary basis is provided for diagnosis of the attention deficit hyperactivity disorder ADHD.
In some embodiments, step S101 comprises:
preprocessing an original electroencephalogram signal aiming at a detected user;
and performing wavelet decomposition and reconstruction on the preprocessed original electroencephalogram signal to obtain an electroencephalogram signal to be analyzed in a preset frequency band.
Specifically, the preprocessing includes filtering, drying, artifact removal, and the like. The original electroencephalogram signal of the user to be detected can be filtered by adopting a preset high-pass filter and a preset low-pass filter, so that the electroencephalogram signal to be analyzed which meets the requirements can be obtained. For example, a preset high-pass filter and a preset low-pass filter obtain 0.5-35Hz electroencephalogram signals to be analyzed.
Since the children with attention deficit hyperactivity disorder ADHD have more theta wave activity and weaker beta wave activity, the predetermined frequency band may be set to a frequency band to which the theta wave belongs, or set to frequency bands to which two kinds of waves, theta wave and beta wave, respectively, belong; meanwhile, in order to comprehensively analyze the health state of the patient, frequency bands corresponding to a plurality of waves such as alpha waves, beta waves and theta waves can be preselectively set at the same time, so that the signals are filtered by performing wavelet decomposition and reconstruction on the mechanical energy of the original brain electrical signals, and the signals conforming to the preset frequency bands are obtained. For example, the theta wave is taken as the electroencephalogram signal to be analyzed through wavelet decomposition and reconstruction.
In some embodiments, the method further comprises:
acquiring personal information of a tested user;
and the treatment information determining module is used for inputting the personal information and the classification result of the attention deficit hyperactivity disorder ADHD characteristics aiming at the detected user into a preset database to obtain a treatment guidance scheme aiming at the detected user, wherein the database comprises the corresponding relations of different personal information, the classification results of different attention deficit hyperactivity disorder ADHD characteristics and different treatment guidance schemes.
Specifically, the personal information may include age, gender, home address, contact, lifestyle, and the like.
In particular, the database may be stored in a server or locally. For example, if the database is stored in the server, the user terminal may send the personal information and the screening result to the server as a query request, so that the server matches the query request in the database, and send the queried treatment guidance plan for the user to be tested to the user terminal.
In the embodiment of the application, the treatment guidance scheme for the tested user generally comprises prompt information for learning, life, diet, treatment and the like.
To further illustrate the method provided by the embodiments of the present application, the following description is made with reference to the flowcharts shown in fig. 3 and 4.
The application system provided by the embodiment comprises a brain-computer interface 100 for acquiring EEG signals, a mobile phone 200 and a server 300. In the embodiment of the present application, the brain-computer interface 100 is a wearable brain-computer EEG acquisition cap, and the brain-computer signal acquisition cap is tightly attached to the head of the user to be tested, so that the electrodes on the brain-computer signal acquisition cap are attached to the forehead of the user to be tested, thereby achieving the purpose of acquiring brain-computer EEG signals. The electroencephalogram EEG acquisition cap is connected with the mobile phone 200 through Bluetooth. When the electroencephalogram and EEG detection system is applied, the mobile phone 200 acquires and analyzes electroencephalogram and EEG signals acquired by the electroencephalogram and EEG acquisition cap so as to judge whether a detected user is ill, and then the mobile phone 200 stores the electroencephalogram and EEG signals and detection results into the server 300 so that the user can remotely inquire the electroencephalogram and EEG signals and the detection results.
As shown in fig. 3, the analysis flow of the mobile phone 200 is as follows: firstly, acquiring an EEG signal, and carrying out pretreatment of filtering and drying on the EEG signal; when the method is applied, a notch filtering algorithm and a band-pass filtering algorithm can be adopted to execute preprocessing operation, so that a preprocessing signal is obtained; secondly, performing wavelet decomposition on the preprocessed signals to obtain brain waves which are decomposed into different frequency bands, such as delta frequency bands, theta frequency bands, alpha frequency bands, beta frequency bands and the like; thirdly, selecting wavelets obtained by decomposition, performing empirical mode decomposition on the selected wavelets (namely brain waves to be analyzed) to obtain an eigenmode function, performing Hilbert transform on the eigenmode function to obtain a first Hilbert spectrum representing the corresponding relation between time and instantaneous amplitude and a second Hilbert spectrum representing the corresponding relation between time and instantaneous frequency, wherein the selected wavelets can be all wavelets or one of the wavelets, such as brain waves of theta frequency; thirdly, feature extraction is performed on the first hilbert spectrum and the second hilbert spectrum, and the extraction result may include: a first type of feature, kurtosis, skewness, standard deviation, median, and mean obtained by statistical analysis; the method comprises the steps of presetting an amplitude mean value of instantaneous amplitude in first unit time length to obtain a first change trend aiming at the amplitude mean value and presetting a frequency mean value of instantaneous frequency in second unit time length to obtain a second change trend aiming at the frequency mean value, and therefore, the first type of features can be used as the attention defect multi-movement obstacle features, and the result obtained by fusing the first type of features and the second type of features can be used as the attention defect multi-movement obstacle features; and finally, identifying the attention deficit hyperactivity disorder characteristics, and judging whether the detected user is sick, wherein the specific identification mode is as follows: the method comprises the steps of firstly, identifying through a pre-constructed attention deficit hyperactivity disorder ADHD screening model; and secondly, encrypting the ADHD screening model of the attention deficit hyperactivity disorder, and then performing matching query in a preset screening result table by using the encrypted value. The attention deficit hyperactivity disorder ADHD screening model provided in the first mode may be identified according to the first type of features (i.e., kurtosis, skewness, standard deviation, median, and mean), and may also be identified according to the second type of features (i.e., kurtosis, skewness, standard deviation, median, mean, a change trend for an amplitude mean, and a change trend for a frequency mean).
It should be noted that, the screening of the attention deficit hyperactivity disorder ADHD can also be completed on the brain-computer interface 100, that is, the brain-computer interface 100 is a device integrating signal acquisition and signal analysis, and the failure problem of analysis caused by bluetooth or network interruption is avoided by the arrangement of the device.
Another embodiment of the present application provides a terminal, including: the device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the processing method of the electroencephalogram signals.
In particular, the processor may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. A processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, a DSP and a microprocessor, or the like.
In particular, the processor is coupled to the memory via a bus, which may include a path for communicating information. The bus may be a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc.
The memory may be, but is not limited to, a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an EEPROM, a CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Optionally, the memory is used for storing codes of computer programs for executing the scheme of the application, and the processor is used for controlling the execution. The processor is used for executing the application program codes stored in the memory so as to realize the actions of the electroencephalogram signal processing device provided by the embodiment.
Yet another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the above-described method for processing an electroencephalogram signal.
The application further provides a chip for executing the method for processing the electroencephalogram signals.
Another embodiment of the present application provides a brain-computer interface, including a wearable device applying a chip for executing the above-mentioned processing method for electroencephalogram signals.
In particular, the brain-computer interface may be configured as a headband, a helmet, or the like, which is worn on a wearable device capable of contacting the forehead, or the forehead and the scalp, and is not listed here.
The above-described embodiments of the apparatus are merely illustrative, and the units illustrated as separate components may or may not be physically separate, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
While the present invention has been described with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (12)
1. A processing device for electroencephalogram signals, comprising:
the analysis-waiting signal determining module is used for determining the electroencephalogram signals to be analyzed for the detected user;
the eigenmode function determining module is used for carrying out empirical mode decomposition on the electroencephalogram signal to be analyzed to obtain a plurality of eigenmode functions;
the Hilbert conversion module is used for converting the plurality of eigenmode functions into a first Hilbert spectrum representing the corresponding relation between time and instantaneous amplitude and a second Hilbert spectrum representing the corresponding relation between time and instantaneous frequency;
an obstacle feature determination module for determining an attention deficit hyperactivity disorder, ADHD, feature based on the first Hilbert spectrum and the second Hilbert spectrum;
and the feature classification determining module is used for classifying the attention deficit hyperactivity disorder ADHD features to obtain the feature classification of the detected user.
2. The apparatus of claim 1, wherein the obstacle feature determination module comprises:
the statistical characteristic extraction submodule is used for respectively carrying out statistical analysis on the first Hilbert spectrum and the second Hilbert spectrum to obtain statistical characteristics;
an obstacle feature determination submodule for using the statistical features as Attention Deficit Hyperactivity Disorder (ADHD) features;
wherein the statistical features include at least kurtosis, skewness, standard deviation, median, and mean.
3. The apparatus according to claim 2, wherein the obstacle feature determination module further comprises, before the step of characterizing the statistical features as attention deficit hyperactivity disorder, ADHD:
the first trend determining submodule is used for determining an amplitude mean value of instantaneous amplitude within preset first unit time length based on the first Hilbert spectrum so as to obtain a first variation trend aiming at the amplitude mean value;
the first trend determining submodule is used for determining a frequency mean value of instantaneous frequency within preset second unit time length based on the second Hilbert spectrum so as to obtain a second variation trend aiming at the frequency mean value;
the obstacle feature determination submodule includes:
an obstacle feature determination unit configured to use the statistical feature, the first variation tendency, and the second variation tendency as the attention deficit hyperactivity disorder ADHD feature.
4. The apparatus of claim 1, wherein the feature classification determination module comprises:
and the first screening submodule is used for determining a classification result for the tested user according to a pre-constructed classification model for the attention deficit hyperactivity disorder ADHD characteristics and the attention deficit hyperactivity disorder ADHD characteristics.
5. The apparatus of claim 1, wherein the feature classification determination module comprises:
the encryption processing submodule is used for encrypting the attention deficit hyperactivity disorder ADHD characteristics to obtain a corresponding encryption value;
and the second screening submodule is used for inquiring the encrypted values in a preset screening result table to obtain a classification result aiming at the detected user, wherein the screening result table comprises a plurality of encrypted values and classification results which are respectively corresponding to the encrypted values and aim at the attention defect hyperactivity disorder ADHD characteristics.
6. The apparatus of claim 1, wherein the means for determining the signal to be analyzed comprises:
the preprocessing submodule is used for preprocessing the original electroencephalogram signal of the tested user;
and the wavelet processing sub-module is used for performing wavelet decomposition and reconstruction on the preprocessed original electroencephalogram signal to obtain the electroencephalogram signal to be analyzed in a preset frequency band.
7. The apparatus of claim 1, further comprising:
the personal information acquisition module is used for acquiring the personal information of the tested user;
and the treatment information determining module is used for inputting the personal information and the classification result of the attention deficit hyperactivity disorder ADHD characteristics aiming at the detected user into a preset database to obtain a treatment guidance scheme aiming at the detected user, wherein the database comprises the corresponding relations of different personal information, the classification results of different attention deficit hyperactivity disorder ADHD characteristics and different treatment guidance schemes.
8. A method for processing an electroencephalogram signal, comprising:
determining an electroencephalogram signal to be analyzed for a detected user;
performing empirical mode decomposition on the electroencephalogram signal to be analyzed to obtain a plurality of eigenmode functions;
converting the plurality of eigenmode functions into a first Hilbert spectrum representing the corresponding relation between time and instantaneous amplitude and a second Hilbert spectrum representing the corresponding relation between time and instantaneous frequency;
determining an Attention Deficit Hyperactivity Disorder (ADHD) feature based on the first Hilbert spectrum and the second Hilbert spectrum;
and classifying the ADHD characteristics to obtain a classification result aiming at the detected user.
9. An electronic device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured for execution by the one or more processors, the one or more programs configured to: the method of claim 8 is performed.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of claim 8.
11. A chip for carrying out the method according to claim 8.
12. A brain-computer interface comprising a wearable device applying a chip for performing the method of claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210141615.0A CN114403901A (en) | 2022-02-16 | 2022-02-16 | Electroencephalogram signal processing device, method and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210141615.0A CN114403901A (en) | 2022-02-16 | 2022-02-16 | Electroencephalogram signal processing device, method and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114403901A true CN114403901A (en) | 2022-04-29 |
Family
ID=81262186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210141615.0A Pending CN114403901A (en) | 2022-02-16 | 2022-02-16 | Electroencephalogram signal processing device, method and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114403901A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116421187A (en) * | 2023-03-30 | 2023-07-14 | 之江实验室 | Attention deficit hyperactivity disorder analysis system based on speech hierarchy sequence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6097980A (en) * | 1998-12-24 | 2000-08-01 | Monastra; Vincent J. | Quantitative electroencephalographic (QEEG) process and apparatus for assessing attention deficit hyperactivity disorder |
| US20050020930A1 (en) * | 2003-07-24 | 2005-01-27 | Salisbury John I. | Apparatus and method for identifying sleep disordered breathing |
| CN102824173A (en) * | 2012-09-17 | 2012-12-19 | 北京理工大学 | Classification method of electroencephalogram signal |
| US20170311870A1 (en) * | 2014-11-14 | 2017-11-02 | Neurochip Corporation, C/O Zbx Corporation | Method and apparatus for processing electroencephalogram (eeg) signals |
| US20190175041A1 (en) * | 2017-12-11 | 2019-06-13 | Adaptive, Intelligent And Dynamic Brain Corporation (Aidbrain) | Method, module and system for analysis of physiological signal |
| US20200368491A1 (en) * | 2019-05-24 | 2020-11-26 | Neuroenhancement Lab, LLC | Device, method, and app for facilitating sleep |
-
2022
- 2022-02-16 CN CN202210141615.0A patent/CN114403901A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6097980A (en) * | 1998-12-24 | 2000-08-01 | Monastra; Vincent J. | Quantitative electroencephalographic (QEEG) process and apparatus for assessing attention deficit hyperactivity disorder |
| US20050020930A1 (en) * | 2003-07-24 | 2005-01-27 | Salisbury John I. | Apparatus and method for identifying sleep disordered breathing |
| CN102824173A (en) * | 2012-09-17 | 2012-12-19 | 北京理工大学 | Classification method of electroencephalogram signal |
| US20170311870A1 (en) * | 2014-11-14 | 2017-11-02 | Neurochip Corporation, C/O Zbx Corporation | Method and apparatus for processing electroencephalogram (eeg) signals |
| US20190175041A1 (en) * | 2017-12-11 | 2019-06-13 | Adaptive, Intelligent And Dynamic Brain Corporation (Aidbrain) | Method, module and system for analysis of physiological signal |
| US20200368491A1 (en) * | 2019-05-24 | 2020-11-26 | Neuroenhancement Lab, LLC | Device, method, and app for facilitating sleep |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116421187A (en) * | 2023-03-30 | 2023-07-14 | 之江实验室 | Attention deficit hyperactivity disorder analysis system based on speech hierarchy sequence |
| CN116421187B (en) * | 2023-03-30 | 2023-10-13 | 之江实验室 | Attention deficit hyperactivity disorder analysis system based on speech hierarchy sequence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tiwari et al. | Automated diagnosis of epilepsy using key-point-based local binary pattern of EEG signals | |
| Singh et al. | Classification of focal and nonfocal EEG signals using features derived from Fourier-based rhythms | |
| CN107233103B (en) | High-speed rail dispatcher fatigue state evaluation method and system | |
| Guo et al. | Epileptic seizure detection by cascading isolation forest-based anomaly screening and EasyEnsemble | |
| Roy et al. | Effective EEG motion artifacts elimination based on comparative interpolation analysis | |
| CN114403901A (en) | Electroencephalogram signal processing device, method and medium | |
| Liu et al. | Classification of EEG signals for epileptic seizures using feature dimension reduction algorithm based on LPP | |
| Saccá et al. | On the classification of EEG signal by using an SVM based algorithm | |
| Khasawneh et al. | Detection of K-complexes in EEG signals using deep transfer learning and YOLOv3 | |
| Prabhakar et al. | Factor analysis, Hessian Local Linear Embedding and Isomap for epilepsy classification from EEG | |
| CN111671420A (en) | Method for extracting features from resting electroencephalogram data and terminal equipment | |
| Cleatus et al. | Epileptic seizure detection using spectral transformation and convolutional neural networks | |
| Callegari et al. | EpiCare—A home care platform based on mobile cloud computing to assist epilepsy diagnosis | |
| Afzali et al. | Automated major depressive disorder diagnosis using a dual-input deep learning model and image generation from EEG signals | |
| Taghavi et al. | Usefulness of approximate entropy in the diagnosis of schizophrenia | |
| CN112383829A (en) | Experience quality evaluation method and device | |
| CN116543878A (en) | Big data monitoring method and system for 24-hour online inquiry | |
| Mehla et al. | An Efficient Classification of Focal and Non-Focal EEG Signals Using Adaptive DCT Filter Bank | |
| CN113925517A (en) | Cognitive disorder recognition method, device and medium based on electroencephalogram signals | |
| CN115670480A (en) | Biological characteristic analysis method and device, electronic equipment and storage medium | |
| AlSharabi et al. | EEG-based clinical decision support system for Alzheimer's disorders diagnosis using EMD and deep learning techniques | |
| CN113679386A (en) | Method, device, terminal and medium for recognizing attention | |
| Pinto-Orellana et al. | Patient-specific epilepsy seizure detection using random forest classification over one-dimension transformed EEG data | |
| CN113476058B (en) | Intervention treatment method, device, terminal and medium for depression patients | |
| Bagheri et al. | Classifier cascade to aid in detection of epileptiform transients in interictal EEG |
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 |