CN113925517A - Cognitive disorder recognition method, device and medium based on electroencephalogram signals - Google Patents
Cognitive disorder recognition method, device and medium based on electroencephalogram signals Download PDFInfo
- Publication number
- CN113925517A CN113925517A CN202111106232.1A CN202111106232A CN113925517A CN 113925517 A CN113925517 A CN 113925517A CN 202111106232 A CN202111106232 A CN 202111106232A CN 113925517 A CN113925517 A CN 113925517A
- Authority
- CN
- China
- Prior art keywords
- analysis
- result
- time domain
- determining
- feature
- 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.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/372—Analysis of electroencephalograms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4088—Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Neurology (AREA)
- Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Psychology (AREA)
- Animal Behavior & Ethology (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Psychiatry (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Child & Adolescent Psychology (AREA)
- Neurosurgery (AREA)
- Physiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The application discloses a cognitive impairment recognition method, a device and a medium based on electroencephalogram signals. The method comprises the following steps: acquiring an electroencephalogram signal of a user; determining time domain characteristics, frequency domain characteristics and synchronization characteristics of the electroencephalogram signals; performing dimensionality reduction processing on the synchronization characteristic, the time domain characteristic and the frequency domain characteristic to obtain dimensionality reduction data; respectively inputting the dimension reduction data into at least two pre-constructed cognitive disorder recognition models to obtain at least two first analysis results; determining a second analysis result based on the time domain features; and determining a cognitive disorder recognition result aiming at the user according to at least two first analysis results and second analysis results. The method and the device achieve the purposes of quickly identifying the cognitive disorder, reducing diagnosis cost and improving the accuracy of identifying the cognitive disorder, and avoid the problem of poor accuracy of the identification result caused by the fact that the analysis result is obtained by only performing one-time analysis in the related technology.
Description
Technical Field
The application relates to the technical field of electroencephalogram signals, in particular to a cognitive impairment recognition method, a device and a medium based on electroencephalogram signals.
Background
Mild Cognitive Impairment (Mild Cognitive Impairment MCI) is a disease state intermediate between normal senile brain decline and alzheimer's disease. Clinical findings show that the medicine intervention on patients in the early stage of mild cognitive impairment can improve symptoms and delay the disease development to a certain extent. The current diagnosis of depression is mainly based on the history, clinical symptoms, course of disease, physical examination and laboratory examination. Therefore, the diagnosis method is susceptible to subjective factors, and misdiagnosis and missed diagnosis are easily caused. The brain wave signals of the patients with cognitive disorder and the healthy contrast persons are different. Therefore, in order to overcome the problem that the diagnosis of the cognitive disorder is easily affected by subjective factors, the cognitive disorder is mainly identified by analyzing the electroencephalogram signals in the related art. However, this identification method has problems of long analysis time and low efficiency.
Disclosure of Invention
The application provides a cognitive impairment recognition method and device based on electroencephalogram signals, electronic equipment and a computer-readable storage medium, which can solve at least one problem. The technical scheme is as follows:
in a first aspect, a cognitive impairment recognition method based on electroencephalogram signals is provided, and the method includes:
acquiring an electroencephalogram signal of a user;
determining time domain characteristics, frequency domain characteristics and synchronization characteristics of the electroencephalogram signals;
performing dimensionality reduction processing on the synchronization characteristic, the time domain characteristic and the frequency domain characteristic to obtain dimensionality reduction data;
respectively inputting the dimension reduction data into at least two pre-constructed cognitive disorder recognition models to obtain at least two first analysis results;
determining a second analysis result based on the time domain features;
and determining a cognitive disorder recognition result aiming at the user according to at least two first analysis results and second analysis results.
In a second aspect, a cognitive impairment recognition apparatus based on electroencephalogram signals is provided, the apparatus comprising:
the signal acquisition module is used for acquiring an electroencephalogram signal of a user;
the characteristic determining module is used for determining time domain characteristics, frequency domain characteristics and synchronous characteristics of the electroencephalogram signals;
the dimensionality reduction processing module is used for carrying out dimensionality reduction processing on the synchronous characteristic, the time domain characteristic and the frequency domain characteristic to obtain dimensionality reduction data;
the first analysis module is used for respectively inputting the dimension reduction data to at least two pre-constructed cognitive disorder recognition models to obtain at least two first analysis results;
the second analysis module is used for determining a second analysis result based on the time domain characteristics;
and the obstacle identification module is used for determining a cognitive obstacle identification result aiming at the user according to at least two first analysis results and second analysis results.
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: and executing the cognitive disorder identification method based on the electroencephalogram signals.
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 cognitive impairment recognition method based on electroencephalogram signals.
The technical scheme provided by the embodiment of the application has the following beneficial effects: the method comprises the steps of obtaining electroencephalogram signals of a user, determining time domain characteristics, frequency domain characteristics and synchronous characteristics of the electroencephalogram signals, carrying out dimensionality reduction processing on the synchronous characteristics, the time domain characteristics and the frequency domain characteristics to obtain dimensionality reduction data, inputting the dimensionality reduction data to at least two pre-constructed cognitive impairment recognition models respectively to obtain at least two first analysis results, determining a second analysis result based on the time domain characteristics, and further determining a cognitive impairment recognition result for the user according to the at least two first analysis results and the second analysis result, wherein the electroencephalogram signals are analyzed through the time domain, the frequency domain and the space domain, so that the effect of enriching the characteristic quantity of the electroencephalogram signals is achieved, the cognitive impairment is recognized through a large number of characteristics of the electroencephalogram signals, and the recognition accuracy of the cognitive impairment is improved; meanwhile, at least two first analysis results and at least two second analysis results are obtained by respectively identifying the dimension reduction data and the time domain characteristics, so that the cognitive disorder is identified for many times in a mode of analyzing the at least two first analysis results and the at least two second analysis results, the purpose of improving the accuracy of identifying the cognitive disorder is achieved, and the problem of poor accuracy of the identification result caused by the fact that the analysis result is obtained by only performing one-time analysis in the related technology is solved.
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 cognitive impairment recognition method based on electroencephalogram signals according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a cognitive impairment recognition device based on electroencephalogram signals 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.
The embodiment of the application provides a cognitive impairment recognition method based on electroencephalogram signals, and as shown in fig. 1, the method comprises the following steps: step S101 to step S106.
Step S101: and acquiring the electroencephalogram signals of the user.
Specifically, the electronic device acquires an electroencephalogram signal of the user. When the brain wave EEG electronic equipment is applied, the electronic equipment can be brain computer interface BCI equipment for brain wave EEG, and can also be equipment such as a mobile phone, a tablet, a PC (personal computer) and a server which are connected with the brain computer interface BCI equipment.
Specifically, the electroencephalogram signals may be data which is cached locally in advance, or may be data which is acquired from a brain-computer interface BCI device according to a preset acquisition cycle. When the method is applied, the electronic equipment can read the data cached locally according to the preset length, so that the electroencephalogram signals meeting the preset length are obtained.
Specifically, the electroencephalogram signal may be a multi-channel signal or a single-channel signal.
Step S102: and determining the time domain characteristic, the frequency domain characteristic and the synchronization characteristic of the electroencephalogram signal.
Specifically, the electroencephalogram signal may be preprocessed according to a pre-configured algorithm before the step is performed. For example, the electroencephalogram signal is filtered, dessicated, and the like.
Step S103: and performing dimensionality reduction processing on the synchronization characteristic, the time domain characteristic and the frequency domain characteristic to obtain dimensionality reduction data.
Specifically, a variety of dimension reduction processing tools may be preconfigured for selection by the user. When the method is applied, one of the plurality of dimension reduction processing tools configured in advance can be selected as a default dimension reduction processing tool. The number of features is reduced through dimension reduction processing so as to quicken the recognition of the cognitive disorder of the user.
In particular, the time-domain features may include one or more features, i.e., one or more features by which the distribution of the brain electrical signal in the time domain is characterized. In the case where the time domain features include multiple features, one or more of them may be subjected to dimensionality reduction processing with respect to the synchronization features and the frequency domain features.
Specifically, if the electroencephalogram signal is a single-channel signal, the synchronization feature may be null; if the electroencephalogram signals are multi-channel signals, the correlation and other synchronization characteristics of different acquisition channels are analyzed.
Step S104: and respectively inputting the dimension reduction data into at least two pre-constructed cognitive disorder recognition models to obtain at least two first analysis results.
In an embodiment of the application, the first analysis result is used for characterizing the identification result of whether the user belongs to the cognitive disorder patient. Specifically, the first analysis result may be a result of positive existence of cognitive disorder, a result of negative existence of cognitive disorder, or a severity indicating existence of cognitive disorder, such as mild cognitive disorder, moderate cognitive disorder, severe cognitive disorder, and the like.
Specifically, the dimension reduction data may be analyzed through a preset algorithm model.
Specifically, the cognitive impairment recognition model may include a support vector machine SVM, a CNN convolutional neural network, a LightGBM model, and the like.
Step S105: based on the time domain features, a second analysis result is determined.
Specifically, the second analysis result may be determined according to all the time domain features, or according to one or more of the time domain features.
In an embodiment of the application, the second analysis result is used for characterizing the identification result of whether the user belongs to the cognitive disorder patient. Specifically, the second analysis result may be a result of positive existence of cognitive disorder, a result of negative existence of cognitive disorder, or a severity characterizing existence of cognitive disorder, such as mild cognitive disorder, moderate cognitive disorder, severe cognitive disorder, and the like.
Specifically, the time domain characteristics may be analyzed through a preset algorithm to obtain a second analysis result; the time domain features can be compared with the pre-stored time domain features corresponding to various cognitive disorders respectively, so that a second analysis result can be obtained according to the matching result.
Step S106: and determining a cognitive disorder recognition result aiming at the user according to at least two first analysis results and second analysis results.
Specifically, at least two first analysis results and two second analysis results can be analyzed through a preset voting algorithm, so that a cognitive disorder recognition result of the user is obtained.
According to the method, the electroencephalogram signals of a user are obtained, so that the time domain characteristics, the frequency domain characteristics and the synchronous characteristics of the electroencephalogram signals are determined, dimension reduction processing is performed on the synchronous characteristics, the time domain characteristics and the frequency domain characteristics, dimension reduction data are obtained, the dimension reduction data are respectively input into at least two pre-constructed cognitive disorder recognition models, at least two first analysis results are obtained, a second analysis result is determined based on the time domain characteristics, and the cognitive disorder recognition results for the user are determined according to the at least two first analysis results and the second analysis result, so that the electroencephalogram signals are analyzed in the time domain, the frequency domain and the synchronous dimensions, the effect of enriching the characteristic quantity of the electroencephalogram signals is achieved, the cognitive disorders are recognized through the characteristics of a large number of electroencephalogram signals, and the recognition accuracy of the cognitive disorders is improved; meanwhile, at least two first analysis results and second analysis results are obtained by respectively identifying the dimension reduction data and the time domain characteristics, so that the mode of analyzing the at least two first analysis results and the second analysis results plays a role in identifying the cognitive disorder for many times, the cognitive disorder is quickly identified, the diagnosis cost is reduced, the cognitive disorder identification precision is improved, and the problem of poor identification result precision caused by the fact that the analysis results are obtained by only performing analysis once in the related technology is solved.
In some embodiments, the synchronization features include at least:
phase delay index PLI, correlation parameter for between channels and coherence parameter.
In an embodiment of the present application, the correlation parameter is used to characterize the relation of different acquisition channels in time.
In an embodiment of the present application, the coherence parameters are used to characterize the relationship of the different acquisition channels in the frequency domain.
In some embodiments, the time domain feature comprises an Hjorth parameter, as shown in fig. 1, step S103 further comprises:
step S1031 (not shown in the figure): reducing the dimension of the phase delay index PLI, the correlation parameter and the coherence parameter to obtain dimension reduction characteristics;
step S1032 (not shown in the figure): and splicing the dimensionality reduction feature, the frequency domain feature and the Hjorth parameter to obtain dimensionality reduction data.
Specifically, a dimensionality reduction tool NetworkX can be used to perform dimensionality reduction processing on the phase delay index PLI, the correlation parameter and the coherence parameter to obtain a dimensionality reduction feature.
Specifically, the dimension reduction feature, the frequency domain feature and the Hjorth parameter are spliced together to obtain dimension reduction data, namely, the dimension reduction data comprises three kinds of data of the dimension reduction feature, the frequency domain feature and the Hjorth parameter, and the splicing process has the effect of reserving time domain, frequency domain and synchronization feature, so that the accuracy of subsequent recognition of the cognitive disorder can be improved.
In some embodiments, the frequency domain features include a power spectral density PSD feature and a bispectral BiS feature, and before step S1032, step S103 further includes: step S1033 (not shown in the figure): carrying out principal component analysis on the PSD characteristic and the BiS characteristic to obtain principal component analysis characteristic; step S1032 further includes: and splicing the dimensionality reduction characteristic, the principal component analysis characteristic and the Hjorth parameter to obtain dimensionality reduction data.
By analyzing the principal components of the frequency domain features, the method and the device aim to extract the key information of the electroencephalogram signals with influence on the recognition of the cognitive disorder in the frequency domain dimension, filter the factors with no influence or weak influence in the recognition of the cognitive disorder in the frequency domain features, reduce the number of the frequency domain features, and achieve the purpose of improving the precision of the first analysis result in the step S104.
In some embodiments, step S104 further comprises:
inputting the dimension reduction data into a preset classifier to obtain a first classification result;
determining a second classification result aiming at the dimensionality reduction data based on a preset XGboost algorithm;
and taking the first classification result and the second classification result as a first analysis result.
In particular, the support vector machine SVM may be used as a preset classifier. Before applying the support vector machine SVM, the support vector machine SVM may be trained according to steps S101 to S104.
According to the method and the device, the dimensionality reduction data are processed through the classifier and the XGboost algorithm respectively, so that more features are extracted, the purpose of improving the classification result is achieved by combining the classifier, and the purpose of screening the subsequent classification result and the second classification result is facilitated.
In some embodiments, the time domain features include wavelet transform features, and step S105 further includes:
sampling the wavelet transformation characteristics according to a preset sliding window algorithm to obtain a plurality of sliding window characteristics;
determining a first output result for a plurality of sliding window features based on a pre-constructed CNN model;
classifying the output result according to a pre-constructed LSTM model to obtain a second output result;
and determining a second analysis result according to the second output result.
Specifically, the CNN model includes an input layer, several convolutional layers, and an output layer, wherein the number of convolutional layers may be set according to business needs. For example, the number of convolutional layers of the CNN model may be set to 3.
Specifically, the output result of the CNN model is processed by the LSTM, so that the valid information of the disappearance function is reduced, and the invalid information is removed, thereby obtaining a second analysis result.
Specifically, the single moving distance of the window can be controlled by pre-configured sliding window parameters to sample wavelet transformation characteristics, so that a plurality of characteristics with the same length are obtained, and the effect of enriching the quantity of the wavelet transformation characteristics is achieved.
Specifically, the second output result may be identified by using a preset neural network model, for example, using a fully-connected neural network MLP, so as to obtain a second output result; and querying a second analysis result corresponding to the second output result according to a preset comparison table of the output result and the analysis result.
In some embodiments, step S106 further comprises:
voting at least two first analysis results and second analysis results;
and determining a cognitive disorder recognition result aiming at the user according to the voting result.
Specifically, the three analysis results are calculated through a preconfigured voting algorithm to obtain respective probabilities of the three analysis results, and the analysis result with the highest probability is used as a final category, namely a recognition result of the cognitive disorder.
Still another embodiment of the present application provides a cognitive impairment recognition apparatus based on electroencephalogram signals, as shown in fig. 2, the apparatus 20 including: a signal acquisition module 201, a feature determination module 202, a dimension reduction processing module 203, a first analysis module 204, a second analysis module 205, and an obstacle identification module 206.
A signal obtaining module 201, configured to obtain an electroencephalogram signal of a user;
the characteristic determining module 202 is used for determining time domain characteristics, frequency domain characteristics and synchronization characteristics of the electroencephalogram signals;
the dimension reduction processing module 203 is configured to perform dimension reduction processing on the synchronization feature, the time domain feature and the frequency domain feature to obtain dimension reduction data;
the first analysis module 204 is configured to analyze the dimension reduction data to obtain a first analysis result;
a second analysis module 205, configured to determine a second analysis result based on the time domain feature;
and the obstacle recognition module 206 is configured to determine a cognitive obstacle recognition result for the user according to the first analysis result and the second analysis result.
According to the method, the electroencephalogram signals of a user are obtained, so that time domain characteristics, frequency domain characteristics and synchronous characteristics of the electroencephalogram signals are determined, dimension reduction processing is performed on the synchronous characteristics, the time domain characteristics and the frequency domain characteristics, dimension reduction data are obtained, the dimension reduction data are respectively input to at least two pre-constructed cognitive disorder recognition models, at least two first analysis results are obtained, a second analysis result is determined based on the time domain characteristics, and then the cognitive disorder recognition results for the user are determined according to the at least two first analysis results and the second analysis result, so that the electroencephalogram signals are analyzed through the time domain, the frequency domain and the synchronization, the effect of enriching the characteristic quantity of the electroencephalogram signals is achieved, the cognitive disorders are recognized through the characteristics of a large number of electroencephalogram signals, and the recognition accuracy of the cognitive disorders is improved; meanwhile, at least two first analysis results and at least two second analysis results are obtained by respectively identifying the dimension reduction data and the time domain characteristics, so that the cognitive disorder is identified for many times in a mode of analyzing the at least two first analysis results and the at least two second analysis results, the purpose of improving the accuracy of identifying the cognitive disorder is achieved, and the problem of poor accuracy of the identification result caused by the fact that the analysis result is obtained by only performing one-time analysis in the related technology is solved.
Further, the synchronization feature includes at least:
phase delay index PLI, correlation parameter for between channels and coherence parameter.
Further, the time domain feature includes an Hjorth parameter, and the dimension reduction processing module includes:
the dimension reduction processing submodule is used for reducing the dimension of the phase delay index PLI, the correlation parameter and the coherence parameter to obtain dimension reduction characteristics;
and the characteristic splicing submodule is used for splicing the dimensionality reduction characteristic, the frequency domain characteristic and the Hjorth parameter to obtain the dimensionality reduction data.
Further, the frequency domain features include a Power Spectral Density (PSD) feature and a Bispectral (BiS) feature;
before the step of splicing the dimension reduction feature, the frequency domain feature and the Hjorth parameter, the feature splicing sub-module further comprises: the principal component analysis unit is used for carrying out principal component analysis on the power spectral density PSD characteristics and the bispectral BiS characteristics to obtain principal component analysis characteristics; the characteristic concatenation submodule includes: and the splicing processing unit is used for splicing the dimensionality reduction feature, the principal component analysis feature and the Hjorth parameter to obtain the dimensionality reduction data.
Further, the first analysis module comprises:
the first classification submodule is used for inputting the dimension reduction data into a preset classifier to obtain a first classification result;
the second classification submodule is used for determining a second classification result aiming at the dimensionality reduction data based on a preset XGboost algorithm;
and the result determination submodule is used for taking the first classification result and the second classification result as the first analysis result.
Further, the time domain features include wavelet transform features, and the second analysis module includes:
the sliding window processing submodule is used for sampling the wavelet transformation characteristics according to a preset sliding window algorithm to obtain a plurality of sliding window characteristics;
the first-stage model processing submodule is used for determining output results aiming at a plurality of sliding window features on the basis of a pre-constructed CNN model;
and the second-stage model processing submodule is used for classifying the output result according to the pre-constructed LSTM model by the second recognition to obtain a second analysis result.
Further, the obstacle identification module includes:
the voting identification submodule is used for voting the first analysis result and the second analysis result;
and the result determining submodule is used for determining a cognitive disorder recognition result aiming at the user according to the voting result.
The cognitive impairment recognition device based on the electroencephalogram signals can execute the cognitive impairment recognition method based on the electroencephalogram signals, which is similar to the implementation principle, and is not described herein again.
Another embodiment of the present application provides a terminal, including: the cognitive impairment recognition method based on the electroencephalogram signals 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 cognitive impairment recognition method based on 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 action of the cognitive disorder recognition device based on the electroencephalogram signals 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 being executed by a processor, implements the above-mentioned cognitive impairment recognition method based on electroencephalogram signals.
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 (10)
1. A cognitive impairment recognition method based on electroencephalogram signals is characterized by comprising the following steps:
acquiring an electroencephalogram signal of a user;
determining time domain characteristics, frequency domain characteristics and synchronization characteristics of the electroencephalogram signals;
performing dimensionality reduction processing on the synchronization feature, the time domain feature and the frequency domain feature to obtain dimensionality reduction data;
inputting the dimensionality reduction data into at least two pre-constructed cognitive disorder recognition models respectively to obtain at least two first analysis results;
determining a second analysis result based on the time domain feature;
determining a cognitive impairment recognition result for the user in dependence on at least two of the first analysis result and the second analysis result.
2. The method according to claim 1, characterized in that said synchronization features comprise at least:
phase delay index PLI, correlation parameter for between channels and coherence parameter.
3. The method of claim 2, wherein the time domain features comprise Hjorth parameters, and the step of performing dimension reduction processing on the synchronization features, the time domain features and the frequency domain features to obtain dimension reduction data comprises:
reducing the dimension of the phase delay index PLI, the correlation parameter and the coherence parameter to obtain dimension reduction characteristics;
and splicing the dimensionality reduction feature, the frequency domain feature and the Hjorth parameter to obtain the dimensionality reduction data.
4. The method of claim 3, wherein the frequency domain features comprise a Power Spectral Density (PSD) feature and a Bispectral (BiS) feature;
before the step of splicing the dimension reduction feature, the frequency domain feature and the Hjorth parameter, the method further comprises:
performing principal component analysis on the power spectral density PSD characteristic and the bispectral BiS characteristic to obtain a principal component analysis characteristic;
the step of splicing the dimensionality reduction feature, the frequency domain feature and the Hjorth parameter comprises the following steps:
and splicing the dimensionality reduction feature, the principal component analysis feature and the Hjorth parameter to obtain the dimensionality reduction data.
5. The method of claim 1, wherein the step of analyzing the dimension-reduced data to obtain a first analysis result comprises:
inputting the dimension reduction data into a preset classifier to obtain a first classification result;
determining a second classification result aiming at the dimensionality reduction data based on a preset XGboost algorithm;
and taking the first classification result and the second classification result as the first analysis result.
6. The method of claim 1, wherein the time domain features include wavelet transform features, and wherein the step of determining a second analysis result based on the time domain features comprises:
sampling the wavelet transformation characteristics according to a preset sliding window algorithm to obtain a plurality of sliding window characteristics;
determining output results for a plurality of the sliding window features based on a pre-constructed CNN model;
and classifying the output result according to the pre-constructed LSTM model to obtain a second analysis result.
7. The method according to claim 1, wherein the step of determining the cognitive impairment recognition result for the user based on the first analysis result and the second analysis result comprises:
voting on at least two of the first analysis result and the second analysis result;
and determining a cognitive disorder recognition result aiming at the user according to the voting result.
8. A cognitive impairment recognition device based on electroencephalogram signals, comprising:
the signal acquisition module is used for acquiring an electroencephalogram signal of a user;
the characteristic determination module is used for determining time domain characteristics, frequency domain characteristics and synchronous characteristics of the electroencephalogram signals;
the dimensionality reduction processing module is used for carrying out dimensionality reduction processing on the synchronous characteristic, the time domain characteristic and the frequency domain characteristic to obtain dimensionality reduction data;
the first analysis module is used for respectively inputting the dimensionality reduction data to at least two pre-constructed cognitive disorder recognition models to obtain at least two first analysis results;
the second analysis module is used for determining a second analysis result based on the time domain characteristics;
and the obstacle identification module is used for determining a cognitive obstacle identification result aiming at the user according to at least two first analysis results and second analysis results.
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 to be executed by the one or more processors, the one or more programs configured to: performing the brain electrical signal-based cognitive impairment recognition method of any one of claims 1-7.
10. A computer-readable storage medium on which a computer program is stored, the program being characterized by implementing the method for brain electrical signal-based cognitive impairment recognition of any one of claims 1-7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111106232.1A CN113925517B (en) | 2021-09-22 | 2021-09-22 | Cognitive disorder recognition method, device and medium based on electroencephalogram signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111106232.1A CN113925517B (en) | 2021-09-22 | 2021-09-22 | Cognitive disorder recognition method, device and medium based on electroencephalogram signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113925517A true CN113925517A (en) | 2022-01-14 |
| CN113925517B CN113925517B (en) | 2022-08-26 |
Family
ID=79276199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111106232.1A Active CN113925517B (en) | 2021-09-22 | 2021-09-22 | Cognitive disorder recognition method, device and medium based on electroencephalogram signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113925517B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116048282A (en) * | 2023-03-06 | 2023-05-02 | 中国医学科学院生物医学工程研究所 | Data processing method, system, device, equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101862194A (en) * | 2010-06-17 | 2010-10-20 | 天津大学 | Imagination action EEG identification method based on fusion feature |
| CN104586387A (en) * | 2015-01-19 | 2015-05-06 | 秦皇岛市惠斯安普医学系统有限公司 | Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters |
| WO2016146265A1 (en) * | 2015-03-17 | 2016-09-22 | Zynaptiq Gmbh | Methods for extending frequency transforms to resolve features in the spatio-temporal domain |
| CN106384364A (en) * | 2016-08-31 | 2017-02-08 | 天津大学 | LPP-ELM based objective stereoscopic image quality evaluation method |
| CN108836327A (en) * | 2018-09-06 | 2018-11-20 | 电子科技大学 | Intelligent outlet terminal and EEG signal identification method based on brain-computer interface |
| WO2019041202A1 (en) * | 2017-08-30 | 2019-03-07 | Vita-Course Technologies Co., Ltd. | System and method for identifying user |
| US20190246927A1 (en) * | 2018-02-14 | 2019-08-15 | Cerenion Oy | Apparatus and method for electroencephalographic measurement |
| CN110200626A (en) * | 2019-06-14 | 2019-09-06 | 重庆大学 | A kind of vision induction motion sickness detection method based on ballot classifier |
| CN110859616A (en) * | 2019-12-12 | 2020-03-06 | 科大讯飞股份有限公司 | Cognitive assessment method, device and equipment of object and storage medium |
| WO2020081609A1 (en) * | 2018-10-15 | 2020-04-23 | The Board Of Trustees Of The Leland Stanford Junior University | Treatment of depression using machine learning |
| CN112784892A (en) * | 2021-01-14 | 2021-05-11 | 重庆兆琨智医科技有限公司 | Electroencephalogram movement intention identification method and system |
| CN113017627A (en) * | 2020-12-31 | 2021-06-25 | 北京工业大学 | Depression and bipolar disorder brain network analysis method based on two-channel phase synchronization feature fusion |
| CN113208620A (en) * | 2021-04-06 | 2021-08-06 | 北京脑陆科技有限公司 | Sleep stage based Alzheimer disease screening method and system |
| CN113397559A (en) * | 2021-06-17 | 2021-09-17 | 深圳大学 | Stereotactic electroencephalogram analysis method, stereotactic electroencephalogram analysis device, computer equipment and storage medium |
-
2021
- 2021-09-22 CN CN202111106232.1A patent/CN113925517B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101862194A (en) * | 2010-06-17 | 2010-10-20 | 天津大学 | Imagination action EEG identification method based on fusion feature |
| CN104586387A (en) * | 2015-01-19 | 2015-05-06 | 秦皇岛市惠斯安普医学系统有限公司 | Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters |
| WO2016146265A1 (en) * | 2015-03-17 | 2016-09-22 | Zynaptiq Gmbh | Methods for extending frequency transforms to resolve features in the spatio-temporal domain |
| CN106384364A (en) * | 2016-08-31 | 2017-02-08 | 天津大学 | LPP-ELM based objective stereoscopic image quality evaluation method |
| WO2019041202A1 (en) * | 2017-08-30 | 2019-03-07 | Vita-Course Technologies Co., Ltd. | System and method for identifying user |
| US20190246927A1 (en) * | 2018-02-14 | 2019-08-15 | Cerenion Oy | Apparatus and method for electroencephalographic measurement |
| CN108836327A (en) * | 2018-09-06 | 2018-11-20 | 电子科技大学 | Intelligent outlet terminal and EEG signal identification method based on brain-computer interface |
| WO2020081609A1 (en) * | 2018-10-15 | 2020-04-23 | The Board Of Trustees Of The Leland Stanford Junior University | Treatment of depression using machine learning |
| CN110200626A (en) * | 2019-06-14 | 2019-09-06 | 重庆大学 | A kind of vision induction motion sickness detection method based on ballot classifier |
| CN110859616A (en) * | 2019-12-12 | 2020-03-06 | 科大讯飞股份有限公司 | Cognitive assessment method, device and equipment of object and storage medium |
| CN113017627A (en) * | 2020-12-31 | 2021-06-25 | 北京工业大学 | Depression and bipolar disorder brain network analysis method based on two-channel phase synchronization feature fusion |
| CN112784892A (en) * | 2021-01-14 | 2021-05-11 | 重庆兆琨智医科技有限公司 | Electroencephalogram movement intention identification method and system |
| CN113208620A (en) * | 2021-04-06 | 2021-08-06 | 北京脑陆科技有限公司 | Sleep stage based Alzheimer disease screening method and system |
| CN113397559A (en) * | 2021-06-17 | 2021-09-17 | 深圳大学 | Stereotactic electroencephalogram analysis method, stereotactic electroencephalogram analysis device, computer equipment and storage medium |
Non-Patent Citations (14)
| Title |
|---|
| XIAO-AN WANG等: "Extended Hamming and BCH soft decision decoders for mobile data applications", 《IEEE TRANSACTIONS ON COMMUNICATIONS》 * |
| XIAO-AN WANG等: "Extended Hamming and BCH soft decision decoders for mobile data applications", 《IEEE TRANSACTIONS ON COMMUNICATIONS》, vol. 47, no. 3, 31 March 1999 (1999-03-31), pages 333 - 337, XP011009375 * |
| YULING LI等: "Classification of Mild Cognitive Impairment from multi-domain features of resting-state EEG", 《2020 42ND ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC)》 * |
| YULING LI等: "Classification of Mild Cognitive Impairment from multi-domain features of resting-state EEG", 《2020 42ND ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC)》, 30 June 2020 (2020-06-30) * |
| 侯璐璐等: "经前期综合征与奖赏进程失调——来自脑电的证据", 《心理学报》 * |
| 侯璐璐等: "经前期综合征与奖赏进程失调——来自脑电的证据", 《心理学报》, vol. 52, no. 6, 30 June 2020 (2020-06-30), pages 742 - 757 * |
| 孟迪: "用户需求分析在产品族设计中的应用", 《工业设计》 * |
| 孟迪: "用户需求分析在产品族设计中的应用", 《工业设计》, no. 8, 31 August 2016 (2016-08-31), pages 146 - 147 * |
| 尹钟: "基于生理特征与支持向量机的认知任务负荷瞬时识别", 《中国博士学位论文全文数据库 (信息科技辑)》 * |
| 尹钟: "基于生理特征与支持向量机的认知任务负荷瞬时识别", 《中国博士学位论文全文数据库 (信息科技辑)》, no. 1, 31 January 2016 (2016-01-31), pages 138 - 98 * |
| 杨舒涵: "基于脑电信号的分析算法研究及其在癫痫检测方面的应用", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
| 杨舒涵: "基于脑电信号的分析算法研究及其在癫痫检测方面的应用", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》, no. 8, 15 August 2020 (2020-08-15), pages 070 - 19 * |
| 王晓岸等: "基于递归神经网络人工智能技术的音乐创作", 《电子技术与软件工程》 * |
| 王晓岸等: "基于递归神经网络人工智能技术的音乐创作", 《电子技术与软件工程》, no. 3, 31 March 2020 (2020-03-31), pages 176 - 180 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116048282A (en) * | 2023-03-06 | 2023-05-02 | 中国医学科学院生物医学工程研究所 | Data processing method, system, device, equipment and storage medium |
| CN116048282B (en) * | 2023-03-06 | 2023-08-04 | 中国医学科学院生物医学工程研究所 | Data processing method, system, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113925517B (en) | 2022-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hossain et al. | Healthcare big data voice pathology assessment framework | |
| Krishnan et al. | Emotion classification from speech signal based on empirical mode decomposition and non-linear features: Speech emotion recognition | |
| EP3839942A1 (en) | Quality inspection method, apparatus, device and computer storage medium for insurance recording | |
| Asghar et al. | AI inspired EEG-based spatial feature selection method using multivariate empirical mode decomposition for emotion classification | |
| CN109087670A (en) | Mood analysis method, system, server and storage medium | |
| JP2020525908A (en) | Image search method, device, device and readable storage medium | |
| WO2021159571A1 (en) | Method and device for constructing and identifying multiple mood states using directed dynamic functional brain network | |
| US11133022B2 (en) | Method and device for audio recognition using sample audio and a voting matrix | |
| Song et al. | Speech emotion recognition based on robust discriminative sparse regression | |
| CN113925517B (en) | Cognitive disorder recognition method, device and medium based on electroencephalogram signals | |
| Banerjee et al. | Using complex networks towards information retrieval and diagnostics in multidimensional imaging | |
| Tigga et al. | Efficacy of novel attention-based gated recurrent units transformer for depression detection using electroencephalogram signals | |
| CN111671420A (en) | Method for extracting features from resting electroencephalogram data and terminal equipment | |
| TW202123026A (en) | Data archiving method, device, computer device and storage medium | |
| CN117557941A (en) | Video intelligent analysis system and method based on multi-mode data fusion | |
| CN111190902A (en) | Medical data structuring method, device, equipment and storage medium | |
| CN113397563A (en) | Training method, device, terminal and medium for depression classification model | |
| CN114795247A (en) | Electroencephalogram signal analysis method and device, electronic equipment and storage medium | |
| CN108288068A (en) | Electroencephalogram signal data classification method under complex emotion scene | |
| CN109614854B (en) | Video data processing method and device, computer device and readable storage medium | |
| CN114373539A (en) | Method and system for processing traditional Chinese and western medicine clinical data, storage medium and terminal | |
| CN113723519A (en) | Electrocardio data processing method and device based on contrast learning and storage medium | |
| CN114664325A (en) | Abnormal sound identification method, system, terminal equipment and computer readable storage medium | |
| CN113476058B (en) | Intervention treatment method, device, terminal and medium for depression patients | |
| Wang et al. | MSFNet: A Multi-Scale Space-Time Frequency Fusion Network for Motor Imagery EEG Classification |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220114 Assignee: Beijing Xinnao Medical Technology Co.,Ltd. Assignor: BEIJING BRAIN UP TECHNOLOGY Co.,Ltd. Contract record no.: X2022990000129 Denomination of invention: Cognitive impairment recognition method, device and medium based on EEG signal License type: Common License Record date: 20220304 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |