CN111631711B - Method for analyzing and processing brain electrical data of schizophrenia and auditory hallucination symptoms - Google Patents
Method for analyzing and processing brain electrical data of schizophrenia and auditory hallucination symptoms Download PDFInfo
- Publication number
- CN111631711B CN111631711B CN202010576351.2A CN202010576351A CN111631711B CN 111631711 B CN111631711 B CN 111631711B CN 202010576351 A CN202010576351 A CN 202010576351A CN 111631711 B CN111631711 B CN 111631711B
- Authority
- CN
- China
- Prior art keywords
- brain
- electroencephalogram
- signals
- data
- wavelet packet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 23
- 201000000980 schizophrenia Diseases 0.000 title claims abstract description 15
- 208000004547 Hallucinations Diseases 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 title claims abstract description 11
- 208000024891 symptom Diseases 0.000 title abstract description 10
- 208000020016 psychiatric disease Diseases 0.000 claims abstract description 6
- 208000019901 Anxiety disease Diseases 0.000 claims abstract description 4
- 230000036506 anxiety Effects 0.000 claims abstract description 4
- 239000013598 vector Substances 0.000 claims description 14
- 238000001228 spectrum Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- 230000000698 schizophrenic effect Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 208000028017 Psychotic disease Diseases 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 2
- 206010019070 Hallucination, auditory Diseases 0.000 claims 4
- 238000002203 pretreatment Methods 0.000 claims 1
- 238000000605 extraction Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 230000033764 rhythmic process Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 101150104012 TOP2 gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007177 brain activity Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Neurology (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Physiology (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Neurosurgery (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention relates to the field of medical signal processing, and discloses a method for analyzing and processing electroencephalogram data of schizophrenia and auditory symptoms thereof, which is based on the asymmetric rate extraction characteristics of multi-band wavelet packet entropy, a multi-classifier system is constructed on auditory symptoms of schizophrenia, non-auditory symptoms of schizophrenia, suspicion, depression, easy impulse, easy anxiety and electroencephalogram signals in a normal state, and finally probability values of auditory symptoms of the electroencephalogram signals to be detected can be output to obtain decision suggestions. The invention can predict the auditory hallucination symptom of the schizophrenia and various mental disease conditions by utilizing the brain electrical signals of the independent individuals, and has practical application significance.
Description
Technical Field
The invention belongs to the field of medical signal processing, and particularly relates to a method for analyzing and processing brain electrical data of schizophrenia and auditory hallucination thereof.
Background
Currently, brain electrical signals of mental diseases play an increasingly important role in basic research and clinical applications concerning brain activities. The current research method of the electroencephalogram signals is mainly divided into a linear method and a nonlinear analysis, wherein the linear method comprises a time domain analysis, a frequency domain analysis and a frequency domain analysis, the time domain analysis mainly takes waveform characteristics as a main factor, only the resolution of the electroencephalogram signals in a time domain can be reflected, the frequency domain analysis mainly converts the electroencephalogram signals into electroencephalogram power information through time-frequency transformation, the change condition along with the frequency and the rhythm distribution condition are explored, the typical representative of the time-frequency domain analysis method is wavelet analysis, the electroencephalogram signals can be processed in the time domain and the frequency domain at the same time, and the nonlinear analysis method of the electroencephalogram signals usually comprises a correlation dimension, a Lyapunov index, an entropy-based analysis method and the like.
Because the electroencephalogram signal is a time-varying and non-stable nonlinear dynamic signal, the linear analysis method cannot effectively extract electroencephalogram data characteristics, has certain limitation, in the electroencephalogram nonlinear analysis method based on the information theory, wavelet packet entropy is an effective characteristic extraction mode, the wavelet packet entropy is based on wavelet packet transformation, the wavelet packet transformation can extract rhythm signals and achieve better frequency resolution than the wavelet transformation, almost no requirement is met on the stability of the signals, the electroencephalogram signal is decomposed through the wavelet packet to obtain different rhythm signals, the spectral entropy of the electroencephalogram signal is calculated through the energy spectrum, the concentration or dispersion degree of the electroencephalogram signal power spectrum can be reflected, and each rhythm of the electroencephalogram is effectively extracted and the local complexity of the electroencephalogram signal is estimated.
The mental diseases comprise various subclasses, a large number of researches only aim at individual symptoms to carry out electroencephalogram analysis, the practical application is limited, and a multi-classification prediction model aiming at various represented mental diseases is built, so that the method has profound research significance and wide application value.
Disclosure of Invention
The invention aims to provide a method for analyzing and processing brain electrical data of schizophrenia and auditory hallucination symptoms thereof, so as to solve the problems in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a method of analyzing and processing electroencephalogram data for schizophrenia and auditory hallucination thereof, comprising the steps of:
collecting brain electricity data;
preprocessing the acquired data;
acquiring a multi-scale wavelet energy spectrum of segmented electroencephalogram signals of all leads of an individual;
calculating the asymmetry ratio among the leads to obtain a characteristic mode vector of the individual segmented electroencephalogram signals;
constructing a classifier based on wavelet packet entropy according to the characteristic mode vector of the segmented electroencephalogram signals;
the classifier is used to analyze and predict brain electrical signals of schizophrenic patients or mental diseases with phantom hearing, non-phantom hearing.
As still further aspects of the invention: the pretreatment comprises the following steps: positioning an electrode; re-referencing; artifact correction; filtering; segmentation; deleting errors to be tested, deleting and reconstructing bad guides; removing artifacts; removing the bad section; baseline correction and normalization.
As still further aspects of the invention: the step of obtaining the multi-scale wavelet energy spectrum of the segmented electroencephalogram signals of all leads of the individual comprises the following steps:
carrying out wavelet packet decomposition on individual segmented electroencephalogram signals one by one to obtain a multi-layer decomposition tree;
and (5) calculating wavelet packet entropy of nodes in the tree to obtain a multi-scale wavelet energy spectrum.
As still further aspects of the invention: and carrying out wavelet packet decomposition on the electroencephalogram signal data to obtain information of different frequency bands.
As still further aspects of the invention: the calculating of the asymmetry ratio between the leads comprises:
the individual segmented brain electrical data comprises multi-lead signals, wherein one lead is from the left half brain, and the other lead is from the right lead;
and calculating the asymmetry ratio by using the combination of leads of the left and right half brains as characteristic values to form a characteristic mode vector of the brain electrical signal.
As still further aspects of the invention: and constructing a multi-classifier model based on the classification accuracy maximization criterion.
As still further aspects of the invention: the brain electrical characteristic pattern vector similarity or variability of different individuals can be measured by any Euclidean distance.
As still further aspects of the invention: the multi-classifier is trained and debugged based on data of schizophrenic patients, schizophrenic non-auditory patients, suspicion, depression, easy impulse, easy anxiety and normal control.
As still further aspects of the invention: and predicting and analyzing the brain electrical signal information of the test individual to obtain the characteristics of the psychotic diseases, the auditory hallucination characteristics of the schizophrenia and the classification information.
Compared with the prior art, the invention has the beneficial effects that: the system comprises a general preprocessing flow, a data extraction flow, model construction and classification prediction output, and the interactive interface can realize the functions of self-defined preprocessing, signal segmentation selection processing and data analysis.
Detailed Description
The following describes in detail the various details involved in the technical solution of the present invention. It should be noted that the described embodiments are only intended to facilitate an understanding of the invention and are not intended to be in any way limiting.
The invention collects multi-lead electroencephalogram data, and the electroencephalogram data of each individual is a 2-dimensional signal comprising lead information (1-dimensional) and time information (1-dimensional);
the acquisition of the electroencephalogram signals is completed on an electroencephalogram signal acquisition instrument with a multi-lead electrode cap;
the specific parameters are not required, the sampling time is preferably 2-4 minutes, and the head is kept as motionless as possible during the data acquisition process.
Preprocessing electroencephalogram data, wherein the method mainly comprises the following steps of: positioning an electrode; re-referencing; artifact correction is carried out on continuous data; filtering; segmentation; deleting errors to be tested, deleting and reconstructing bad guides; removing artifacts; removing the bad section; baseline correction and normalization.
The preprocessed electroencephalogram signals are segmented signals, namely, electroencephalogram data of the same individual are divided into a plurality of equal-length multi-lead signals, the data volume is amplified, and the electroencephalogram signals have dynamic characteristics;
performing wavelet packet decomposition on each lead data of the segmented signal;
the wavelet packet transformation can decompose the non-stationary signal into weighted sums of wavelets with different scale bases, and can ensure higher frequency resolution of a high frequency band;
the wavelet packet function is expressed as:
wherein, is a psi (t) mother wavelet, and h (t) and g (k) are weight coefficients.
The recurrence relation of the j and j+1 th stages is:
wavelet coefficientsThe method comprises the following steps:
thus, the electroencephalogram signal can be represented as a plurality of wavelet packet sets, which correspond to different frequency ranges and can be changed according to actual needs.
Defining brain electrical signal components using wavelet packet nodesThe energy of (a) is as follows:
the total energy of the brain electrical signals is as follows:
defining the energy of a specific frequency band (signal sub-band) as E s Which is the sum of the energies of the contained signal components, normalized to be expressed as:
the final definition wavelet packet entropy is:
S wp =-∑p s ln[p s ]
therefore, assuming that an electroencephalogram signal of an individual is expressed as P (number of leads) ×m (number of signals in a segment short time window) ×n (number of segments), the wavelet packet entropy thereof is characterized as P (number of leads) ×n (number of segments), the leads in each segment of data are derived from left and right half brain signals, assuming that 3 leads are derived from left half brain (A1, A2, A3), 3 leads are derived from right half brain (B1, B2, B3), the asymmetry ratio rate of the wavelet packet entropy values is found by the permutation and combination of the left and right half brains (A1, B1), (A1, B2), (A1, B3), (A2, B2), (A2, B3), (A3, B1), (A3, B2), (A3, B3):
wherein R represents a lead from the right brain half and L represents a lead from the left brain half.
The data used for modeling is 16-lead brain electrical signals, and each of left and right half brains is 8-lead, so that 64 eigenvalues can be obtained to form eigenvectors of signals in a certain frequency band of a corresponding data segment, wavelet packet entropy and asymmetry ratio are repeatedly calculated in different frequency bands, and the corresponding eigenvectors are obtained;
the segmented electroencephalogram signals of the final individual can be represented by this F (frequency band number) ×64 vector.
Constructing an optimal multi-classification model based on a classifier of pattern recognition, straightening the multi-band feature vectors into one-dimensional feature vectors in the training process, and inputting the one-dimensional feature vectors into the classifier; considering the influence of the feature dimension on the classifier, the method adopts a principal component analysis method to reduce dimension in the implementation process, and ensures that the contribution rate of the selected components reaches 99 percent; then, utilizing a Support Vector Machine (SVM) to carry out multi-category training on the segmented data of the training individuals;
the SVM kernel function can select radial basis kernel function, linear kernel function and the like to define distance measurement, and output the distance measurement as posterior probability value and classification label;
the classification result of the classifier is determined by selecting corresponding parameters and carrying out ten-fold cross validation on a data set to generate a multi-classifier, and classification labels are schizophrenic auditory data, schizophrenic non-auditory data, multi-suspicion, depression, easy impulse, easy anxiety and normal control data.
For new test data, firstly, obtaining segmented data of an electroencephalogram signal to be predicted through preprocessing, and then, predicting all the segmented data through a built multi-classifier model system in sequence;
because the test data comprises a plurality of segmentation results, the classifier also generates a plurality of segmentation prediction conditions, and statistical analysis is carried out on all the prediction results;
finally, the system outputs probability values of the categories to which the segmented signals belong and top2 decision suggestions, and in practical application, different segmented prediction results can be comprehensively considered and the psychotic symptoms of the independent individuals can be predicted.
The foregoing description is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical solution of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (6)
1. A method for analyzing and processing electroencephalogram data of schizophrenia and auditory hallucination thereof, comprising the steps of:
collecting brain electricity data;
preprocessing the acquired data, wherein the preprocessed electroencephalogram signals are segmented signals, and the electroencephalogram data of the same individual
A plurality of equal length multi-lead signals, which are divided into a plurality of equal length multi-lead signals, amplify the data volume, and have dynamic characteristics;
acquiring a multi-scale wavelet energy spectrum of segmented electroencephalogram signals of all leads of an individual;
calculating the asymmetry ratio among the leads to obtain a characteristic mode vector of the individual segmented electroencephalogram signals;
constructing a classifier based on wavelet packet entropy according to the characteristic mode vector of the segmented electroencephalogram signals;
analyzing and predicting brain electrical signals of patients with auditory hallucinations, non-auditory hallucinations, or mental diseases by using a classifier;
the step of obtaining the multi-scale wavelet energy spectrum of the segmented electroencephalogram signals of all leads of the individual comprises the following steps:
carrying out wavelet packet decomposition on individual segmented electroencephalogram signals one by one to obtain a multi-layer decomposition tree;
performing wavelet packet entropy calculation on nodes in the tree to obtain a multi-scale wavelet energy spectrum;
carrying out wavelet packet decomposition on the electroencephalogram signal data to obtain information of different frequency bands;
wherein the wavelet packet function is expressed as:
wherein, is a psi (t) mother wavelet, h (k) and g (k) are weight coefficients;
the recurrence relation of the j and j+1 th stages is:
wavelet coefficientsThe method comprises the following steps:
therefore, the electroencephalogram signals are expressed as a plurality of wavelet packet sets, and the wavelet packet sets correspond to different frequency ranges and can be changed according to actual needs;
defining brain electrical signal components using wavelet packet nodesThe energy of (a) is as follows:
the total energy of the brain electrical signals is as follows:
defining the energy of a specific frequency band as E s Which is the sum of the energies of the contained signal components, normalized to be expressed as:
the final definition wavelet packet entropy is:
S wp =-∑p s ln[p s ]
the calculating of the asymmetry ratio between the leads comprises:
the individual segmented brain electrical data comprises multi-lead signals, wherein one lead is from the left half brain, and one lead is from the right half brain;
the asymmetry ratio is obtained by utilizing the combination of leads of the left half brain and the right half brain to be used as a characteristic value to form a characteristic mode vector of the brain electrical signal;
the characteristic mode vector of the electroencephalogram signal is a vector formed by the asymmetric rate of wavelet packet entropy of the left brain lead and the right brain lead in the segmentation and the specific frequency band component;
assuming that an electroencephalogram signal of an individual is expressed as P multiplied by M multiplied by N, wherein P is the number of leads, M is the number of signals in a segmented short time window, and N is the number of segments; the wavelet packet entropy is characterized by p×n, the leads in each segment of data are derived from left and right brain signals, assuming that 3 leads are derived from left brain (A1, A2, A3), 3 leads are derived from right brain (B1, B2, B3), and the asymmetry ratio rate of the wavelet packet entropy values is calculated according to the permutation and combination (A1, B1), (A1, B2), (A1, B3), (A2, B2), (A2, B3), (A3, B1), (A3, B2), (A3, B3) of the left and right brain:
wherein R represents a lead from the right brain half and L represents a lead from the left brain half.
2. A method of analysing electroencephalogram data for schizophrenia and its auditory hallucinations as claimed in claim 1, wherein said pre-treatment comprises: positioning an electrode; re-referencing; artifact correction; filtering; segmentation; deleting errors to be tested, deleting and reconstructing bad guides; removing artifacts; removing the bad section; baseline correction and normalization.
3. The method of claim 2, further comprising constructing a multi-classifier model based on classification accuracy maximization criteria.
4. A method of analysing brain electrical data for schizophrenia and its auditory hallucinations according to claim 3, wherein the similarity or difference of brain electrical characteristic pattern vectors of different individuals can be measured by any euclidean distance.
5. The method of claim 4, wherein the multi-classifier is based on training and debugging of schizophrenic auditory patients, schizophrenic non-auditory patients, suspicion, depression, impulsivity, anxiety, normal control data.
6. The method for analyzing and processing the electroencephalogram data of the schizophrenia and the auditory hallucination thereof according to claim 5, further comprising predicting and analyzing the electroencephalogram information of the test individual to obtain the characteristics of the psychotic disorder, the auditory hallucination of the schizophrenia and the classification information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010576351.2A CN111631711B (en) | 2020-06-22 | 2020-06-22 | Method for analyzing and processing brain electrical data of schizophrenia and auditory hallucination symptoms |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010576351.2A CN111631711B (en) | 2020-06-22 | 2020-06-22 | Method for analyzing and processing brain electrical data of schizophrenia and auditory hallucination symptoms |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111631711A CN111631711A (en) | 2020-09-08 |
CN111631711B true CN111631711B (en) | 2024-03-15 |
Family
ID=72323964
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010576351.2A Active CN111631711B (en) | 2020-06-22 | 2020-06-22 | Method for analyzing and processing brain electrical data of schizophrenia and auditory hallucination symptoms |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111631711B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102715903A (en) * | 2012-07-09 | 2012-10-10 | 天津市人民医院 | Method for extracting electroencephalogram characteristic based on quantitative electroencephalogram |
CN110338820A (en) * | 2019-06-13 | 2019-10-18 | 四川大学 | A kind of depression and schizophrenia recognition methods |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110112426A1 (en) * | 2009-11-10 | 2011-05-12 | Brainscope Company, Inc. | Brain Activity as a Marker of Disease |
-
2020
- 2020-06-22 CN CN202010576351.2A patent/CN111631711B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102715903A (en) * | 2012-07-09 | 2012-10-10 | 天津市人民医院 | Method for extracting electroencephalogram characteristic based on quantitative electroencephalogram |
CN110338820A (en) * | 2019-06-13 | 2019-10-18 | 四川大学 | A kind of depression and schizophrenia recognition methods |
Non-Patent Citations (2)
Title |
---|
冯静雯 等.精神分裂症和抑郁症患者静息态脑电功率谱熵的对照研究.《中国生物医学工程学报》.2019,第38卷(第38期),第385-390页. * |
许慰玲 等.基于小波包分解的精神分裂症脑电信号分析.《电子测量与仪器学报》.2004,第18卷(第18期),第35-39页. * |
Also Published As
Publication number | Publication date |
---|---|
CN111631711A (en) | 2020-09-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Hussein et al. | Epileptic seizure detection: A deep learning approach | |
CN110811609B (en) | Epileptic spike intelligent detection device based on self-adaptive template matching and machine learning algorithm fusion | |
Li et al. | Seizure onset detection using empirical mode decomposition and common spatial pattern | |
US10433752B2 (en) | Method for the real-time identification of seizures in an electroencephalogram (EEG) signal | |
Guo et al. | Epileptic seizure detection by cascading isolation forest-based anomaly screening and EasyEnsemble | |
Kalaivani et al. | Analysis of EEG signal for the detection of brain abnormalities | |
CN111310570B (en) | Electroencephalogram signal emotion recognition method and system based on VMD and WPD | |
CN110781945A (en) | Electroencephalogram signal emotion recognition method and system integrating multiple features | |
CN112741638B (en) | Medical diagnosis auxiliary system based on EEG signal | |
CN110598676B (en) | Deep learning gesture electromyographic signal identification method based on confidence score model | |
CN111956221B (en) | Temporal lobe epilepsy classification method based on wavelet scattering factor and LSTM neural network model | |
CN110840432A (en) | Multichannel electroencephalogram epilepsy automatic detection device based on one-dimensional CNN-LSTM | |
Yuan et al. | A novel wavelet-based model for eeg epileptic seizure detection using multi-context learning | |
CN108567418A (en) | A kind of pulse signal inferior health detection method and detecting system based on PCANet | |
Al-Qazzaz et al. | Classification enhancement for post-stroke dementia using fuzzy neighborhood preserving analysis with QR-decomposition | |
CN107045624B (en) | Electroencephalogram signal preprocessing and classifying method based on maximum weighted cluster | |
CN113069117A (en) | Electroencephalogram emotion recognition method and system based on time convolution neural network | |
Talukdar et al. | Motor imagery EEG signal classification scheme based on autoregressive reflection coefficients | |
CN113011330B (en) | Electroencephalogram signal classification method based on multi-scale neural network and cavity convolution | |
CN116807496B (en) | Method, device, equipment and medium for positioning epileptic interval brain wave abnormal signals | |
CN111631711B (en) | Method for analyzing and processing brain electrical data of schizophrenia and auditory hallucination symptoms | |
Jaffino et al. | Expectation-maximization extreme machine learning classifier for epileptic seizure detection | |
CN111631709B (en) | Method for distinguishing auditory hallucination symptoms of schizophrenia from auditory hallucination symptoms of other diseases | |
CN110327043B (en) | Event-related potential waveform map solving method based on sparse modeling | |
Ferariu et al. | Using Hand-Crafted and Learned EEG Features for the Detection of Epileptic Seizures |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |