CN112641449A - EEG signal-based rapid evaluation method for cranial nerve functional state detection - Google Patents
EEG signal-based rapid evaluation method for cranial nerve functional state detection Download PDFInfo
- Publication number
- CN112641449A CN112641449A CN202011504403.1A CN202011504403A CN112641449A CN 112641449 A CN112641449 A CN 112641449A CN 202011504403 A CN202011504403 A CN 202011504403A CN 112641449 A CN112641449 A CN 112641449A
- Authority
- CN
- China
- Prior art keywords
- subject
- eeg signal
- cranial nerve
- frequency range
- function state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—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
- A61B5/7207—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
-
- 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)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a rapid evaluation method for detecting the brain nerve function state based on an EEG signal, which comprises the steps of collecting resting state electroencephalogram data of a subject, extracting time domain and frequency domain characteristic parameters through windowing, constructing a characteristic matrix after independently normalizing each characteristic, putting into a brain nerve function state detection model trained in the early stage, and rapidly evaluating the brain function state of the subject. The brain function state evaluation method is high in expansibility, applicable to evaluation of various brain function states, simple to operate, high in accuracy and quite wide in application prospect.
Description
Technical Field
The invention belongs to the field of biomedicine, and particularly relates to a rapid evaluation method for detecting a cranial nerve functional state based on an EEG signal.
Background
In recent years, the phenomenon of drug abuse is increasingly prominent, and the statistical data of the world health organization shows that the number of drug abuse people in the world breaks through ten million at present, and the drug abuse exists in different degrees in developed countries and developing countries. In China, the phenomenon is very severe. The abuse of drugs seriously damages the physical health of abusers, causes pathological damage to multiple systems and multiple organs of organisms, and also seriously influences the cranial nerve functional state of the abusers, thereby causing serious harm to the society. Therefore, the potential social hazard can be well avoided by rapidly screening the drug abusers.
The traditional method for screening drug abusers is to sample saliva, urine and the like of a tested person and then screen the saliva, urine and the like by combining a biochemical analysis method. If the duration of the drug withdrawal is to be traced, hair or blood detection methods can be used. However, the methods cannot achieve rapid screening, and are very inconvenient in certain application occasions, such as the situation of temporary inspection of poison drivers. Meanwhile, if the tested person suffers from some infectious diseases, the sampling process of saliva, urine and blood samples is likely to cause secondary infection of the inspectors, so that the risk is high.
In addition, a biomedical company, FingerPrinting, abroad, developed a device for screening drugs of abuse by analyzing metabolites in fingerprint sweat, which is also a biochemical analysis mode, but is safer than saliva, urine and blood tests, and can analyze and detect up to four drugs of abuse in one test by only collecting one fingerprint sample in the whole process, and can give positive or negative results in less than 10 minutes and give simple pass or fail readings according to a preset drug detection cut-off level. However, this method is also not easy to apply in the scene of a poisonous drive near inspection, and traffic jam is likely to be caused due to the limitation of the inspection time, and the screening accuracy may be affected if a drug abuser applies some special solvent to the finger.
In addition, chinese patent CN 205144519 proposes a system for detecting dynamic changes in skin light absorption rate, which is suitable for drug abuse, i.e. whether a human body takes drugs or not, because after the human body takes drugs or injects drugs, the drugs will affect the endocrine system of the human body, change the secretion of dopamine, epinephrine and other substances, destroy the interaction between these substances and receptors, change the blood flow dynamics of the skin and subcutaneous tissues, thereby changing the absorption rate of incident light beams, and thus, the drug absorption screening can be realized by detecting the dynamic changes in skin light absorption rate. However, the patent does not provide specific setting of system parameters and calculation of the absorption rate of the incident light beam, and does not describe the effectiveness of the method in practical use, and the absorption rate of the incident light beam of the human body is still easily interfered by the environment, and the patent does not mention how to remove the interference of the ambient light.
For example, chinese patent CN2080002774 and chinese patent CN111278351A both propose similar methods, but the detection criteria of the principle is that dynamic changes of pupils of detection personnel are compared with the ordinary non-toxic experience values, but each detection personnel has individual difference, so that a mismatch condition may occur. Although some methods using this principle can also obtain data on the dynamic changes of the pupil before and after light stimulation, there is no clear indication on the method and the measurement criteria for screening drug addicts by using the dynamic changes of the pupil before and after light stimulation.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses a rapid evaluation method for detecting the cranial nerve functional state based on an EEG signal, and the detection method can be used for rapidly evaluating the cranial nerve functional state.
The purpose of the invention is realized by the following technical scheme:
a rapid evaluation method for detecting the cranial nerve functional state based on EEG signals specifically comprises the following steps:
s1, placing the electroencephalogram acquisition equipment on the scalp surface of the subject for a certain time, keeping the head of the subject relatively still, and acquiring stable electroencephalogram EEG signals;
s2: preprocessing the collected EEG signal to remove the interference of muscle activity and other nerve electrophysiological signals;
s3: windowing the collected EEG signals of each channel, setting step length, and calculating frequency domain parameters and time domain parameters in the EEG signals in each window; wherein the frequency domain parameters include power spectral densities of the delta, theta, alpha, beta, gamma rhythms; the time domain parameters are Hjorth parameters, including activity, mobility and complexity;
s4: independently normalizing each time domain parameter and frequency domain parameter of each subject obtained in S3, and constructing a feature matrix;
s5: repeating S1-S4, constructing training set data according to the obtained feature matrix and the corresponding classification label, putting the training set data into an algorithm frame of a random forest, and training the training set data to obtain an optimized evaluation model;
s6: and according to S1-S4, acquiring data of a new subject, and putting the acquired data into the optimized evaluation model obtained in S5 to obtain the classification result of the current subject, namely the cranial nerve function state of the subject.
Further, the frequency range of delta is 1-3 Hz, the frequency range of theta is 4-7 Hz, the frequency range of alpha is 8-13 Hz, the frequency range of beta is 14-30 Hz, and the frequency range of gamma is 30-80 Hz.
Further, the time to acquire a new subject' S electroencephalogram EEG signal is not shorter than the window time in S3.
Further, in S2, the interference of the head movement artifact is removed by wavelet transform, and the interference of the eye movement and the myoelectric artifact is removed by the independent component analysis method.
Compared with the prior art, the invention has the beneficial effects that:
(1) the evaluation method of the invention has simple sampling, does not relate to the sampling of saliva, urine, blood and the like of a subject, thereby avoiding the secondary infection of inspectors;
(2) EEG signals are acquired for a short time, and the acquisition portability and efficiency are high;
(3) the head movement, muscle activity and other nerve electrophysiological signals in the acquired signals are removed in a targeted manner, and frequency domain parameters and time domain parameters can be extracted more accurately;
(4) the method provided by the invention can be used for simultaneously extracting frequency domain parameters and time domain parameters, and combining a machine learning algorithm, so that the generalization capability of the evaluation model is better, and the classification accuracy is higher.
Drawings
FIG. 1 is a flowchart illustrating an evaluation method according to an embodiment of the present invention;
FIG. 2 is a waveform of an EEG signal containing motion artifacts, eye movement and myoelectrical artifacts measured when the subject is a human;
FIG. 3 is a waveform of an EEG signal with motion artifacts, eye movement and myoelectrical artifacts removed, as measured when the subject is a human;
FIG. 4 is a plot of the power spectral density of EEG signals for drug abuse versus normal controls measured when the subject is a mouse;
FIG. 5 is a graph of a time domain Activity parameter waveform of EEG signals for drug abuse versus normal controls measured when the subject is a mouse;
FIG. 6 is a graph of a time domain Mobility parameter waveform of EEG signals for drug abuse versus normal controls measured when the subject is a mouse;
FIG. 7 is a graph of time domain complete parameter waveforms of EEG signals for drug abuse versus normal controls measured when the subject is a mouse;
FIG. 8 is a bar graph of the degree of contribution of measured characteristic parameters to classification accuracy in the evaluation model training when the subject is a mouse;
fig. 9 is a schematic diagram of evaluation indexes of the evaluation model trained by a random forest algorithm when the subject is a mouse.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments, and the objects and effects of the present invention will become more apparent, it being understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.
As shown in fig. 1, the method for rapidly evaluating the cranial nerve functional state detection based on the EEG signal of the present invention specifically includes the following steps:
s1, placing the electroencephalogram acquisition equipment on the scalp surface of the subject for a certain time, keeping the head of the subject relatively still, keeping the eye closing state or the eye opening state continuously, reducing the blinking action as much as possible, and acquiring stable electroencephalogram EEG signals;
s2: preprocessing the collected EEG signal to remove the interference of muscle activity and other nerve electrophysiological signals, which specifically comprises the following steps: the interference of the head motion artifact is removed through Wavelet transformation (Wavelet-Methods), and the interference of the eye movement and the myoelectricity artifact is removed through an Independent Component Analysis (ICA). Waveforms of EEG signals before and after the removal of interference are shown in fig. 2 and 3.
S3: windowing the collected EEG signals of each channel, setting step length, and calculating frequency domain parameters and time domain parameters in the EEG signals in each window; wherein the frequency domain parameters include power spectral densities of the delta, theta, alpha, beta, gamma rhythms; the frequency range of delta is 1-3 Hz, the frequency range of theta is 4-7 Hz, the frequency range of alpha is 8-13 Hz, the frequency range of beta is 14-30 Hz, and the frequency range of gamma is 30-80 Hz. The time domain parameters are Hjorth parameters including Activity (Activity), Mobility (Mobility) and Complexity (Complexity);
s4: normalizing each characteristic parameter of each subject obtained in S3 independently, and constructing a characteristic matrix;
here, instead of normalizing all the feature parameters in the entire data set or all the feature parameters of a certain subject, the influence on the evaluation model due to too much individual difference or too much individual single feature difference when normalizing with all the feature parameters in the entire data set or all the feature parameters of a single subject can be avoided.
S5: repeating S1-S4, constructing training set data according to the obtained feature matrix and the corresponding classification label, putting the training set data into an algorithm frame of a random forest, and training the training set data to obtain an optimized evaluation model;
s6: according to S1-S4, data acquisition is carried out on a new subject, and the time for acquiring the EEG signal of the new subject is not shorter than the window time in S3; and putting the collected data into the optimized evaluation model obtained in the step S5 to obtain the classification result of the current subject, namely the cranial nerve function state of the subject.
The evaluation method of the present invention is verified in the mouse experiment as follows. All experiments have passed ethical scrutiny in animal experiments. The electrode is implanted into the head of a mouse, and electroencephalogram data of the mouse in a relatively quiet period in a waking state are collected.
The collected EEG signals are processed in steps S2-S3, and the EEG signal power spectral density of a certain normal mouse and a certain experimental mouse is obtained, as shown in FIG. 4. The total power spectral density value and the average power spectral density value of the frequency bands of the five electroencephalogram rhythms are extracted from the five electroencephalogram rhythms and are used as characteristic parameters of the five electroencephalogram rhythms. As can be seen, at certain brain electrical rhythms, such as in the theta (4Hz-7Hz), beta (14Hz-30Hz) frequency bands, the log power spectral density (LogPSD) of cocaine-injected mice is lower than that of saline.
Time domain parameters of the EEG signals of a certain normal mouse and a certain experimental mouse, namely Hjorth parameters, including Activity (Activity), Mobility (Mobility) and Complexity (Complexity) are calculated by the formulas (1) - (3), as shown in FIGS. 5-7. As can be seen from the figure, the time domain Activity parameter Activity and complexity parameter Complex of the mice injected with saline is higher than those of the mice injected with cocaine, while the time domain Mobility parameter Mobility is lower. The above fig. 4 to 7 only show that the 8 characteristic parameters extracted by the evaluation method of the present invention make certain contribution to the classification result, and are not used to limit the determinacy of a single factor on the classification result.
Activity＝var(y(t)) (1)
Where var () represents the variance function and y (t) represents the electroencephalographic EEG time-domain signal of the subject over a window time.
The experiment has 28 mice, 16 experimental mice and 12 control mice, and the drug addiction experiment is carried out for 5 days, the total time for collecting single-channel EEG signals of each mouse is 10 minutes, the set window length is 30s, and the step length is 1s, so that the data set has 79940 records.
28*5*(10*60-30+1)＝79940 (4)
Table 1 shows the evaluation indexes of the evaluation model trained by the random forest algorithm, which are obtained by a ten-fold cross-validation method. The ten-fold cross-validation method divides the data set into ten parts, and tests are carried out by taking 9 parts as training data and 1 part as test data in turn. As can be seen from Table 1, in the ten-fold cross validation, the average values of 4 evaluation indexes all reach more than 90%, which indicates that the evaluation model achieves a good classification effect.
Table 1 evaluation indexes of the evaluation model trained by random forest algorithm
| Evaluation run | Recall rate | Rate of accuracy | F1 index | Rate of |
| 1 | 0.93346 | 0.96333 | 0.96073 | 0.96184 |
| 2 | 1 | 0.9714 | 0.97056 | 0.96967 |
| 3 | 1 | 0.96881 | 0.9678 | 0.96673 |
| 4 | 1 | 0.85144 | 0.82553 | 0.78865 |
| 5 | 0.94129 | 0.86907 | 0.8698 | 0.8591 |
| 6 | 1 | 1 | 1 | 1 |
| 7 | 0.96183 | 1 | 0.98054 | 0.96184 |
| 8 | 0.97652 | 1 | 0.98812 | 0.97652 |
| 9 | 0.98924 | 1 | 0.99459 | 0.98927 |
| 10 | 1 | 1 | 1 | 1 |
| Mean value of | 0.980234 | 0.962405 | 0.955767 | 0.947362 |
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and although the invention has been described in detail with reference to the foregoing examples, it will be apparent to those skilled in the art that various changes in the form and details of the embodiments may be made and equivalents may be substituted for elements thereof. All modifications, equivalents and the like which come within the spirit and principle of the invention are intended to be included within the scope of the invention.
Claims (4)
1. A rapid evaluation method for detecting the cranial nerve functional state based on EEG signals is characterized by comprising the following steps:
s1, placing the electroencephalogram acquisition equipment on the scalp surface of the subject for a certain time, keeping the head of the subject relatively still, and acquiring stable electroencephalogram EEG signals;
s2: preprocessing the collected EEG signal to remove the interference of muscle activity and other nerve electrophysiological signals;
s3: windowing the collected EEG signals of each channel, setting step length, and calculating frequency domain parameters and time domain parameters in the EEG signals in each window; wherein the frequency domain parameters include power spectral densities of the delta, theta, alpha, beta, gamma rhythms; the time domain parameters are Hjorth parameters, including activity, mobility and complexity;
s4: independently normalizing each time domain parameter and frequency domain parameter of each subject obtained in S3, and constructing a feature matrix;
s5: repeating S1-S4, constructing training set data according to the obtained feature matrix and the corresponding classification label, putting the training set data into an algorithm frame of a random forest, and training the training set data to obtain an optimized evaluation model;
s6: and according to S1-S4, acquiring data of a new subject, and putting the acquired data into the optimized evaluation model obtained in S5 to obtain the classification result of the current subject, namely the cranial nerve function state of the subject.
2. The method for rapid assessment of EEG signal based cranial nerve function state detection according to claim 1, wherein δ is in the frequency range of 1-3 Hz, θ is in the frequency range of 4-7 Hz, α is in the frequency range of 8-13 Hz, β is in the frequency range of 14-30 Hz, γ is in the frequency range of 30-80 Hz.
3. The method for rapid evaluation of EEG signal-based cranial nerve function state detection according to claim 1, wherein the time to acquire a new subject' S EEG signal is not shorter than the window time in S3.
4. The method for rapidly evaluating the EEG signal-based cranial nerve function state detection according to claim 1, wherein the interference of the head movement artifact is removed by wavelet transform and the interference of the eye movement and myoelectric artifact is removed by independent component analysis in S2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011504403.1A CN112641449A (en) | 2020-12-18 | 2020-12-18 | EEG signal-based rapid evaluation method for cranial nerve functional state detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011504403.1A CN112641449A (en) | 2020-12-18 | 2020-12-18 | EEG signal-based rapid evaluation method for cranial nerve functional state detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112641449A true CN112641449A (en) | 2021-04-13 |
Family
ID=75355273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011504403.1A Pending CN112641449A (en) | 2020-12-18 | 2020-12-18 | EEG signal-based rapid evaluation method for cranial nerve functional state detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112641449A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113208594A (en) * | 2021-05-12 | 2021-08-06 | 海南热带海洋学院 | Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram |
| CN114169366A (en) * | 2021-11-19 | 2022-03-11 | 北京师范大学 | Neurofeedback training system and method |
| CN114533066A (en) * | 2022-04-28 | 2022-05-27 | 之江实验室 | Social anxiety assessment method and system based on composite expression processing brain network |
| CN114587385A (en) * | 2022-02-25 | 2022-06-07 | 之江实验室 | Method for constructing post-stroke rehabilitation assessment deep learning model based on brain muscle network graph theory characteristics |
| CN114886388A (en) * | 2022-07-12 | 2022-08-12 | 浙江普可医疗科技有限公司 | Evaluation method and device for quality of electroencephalogram signal in anesthesia depth monitoring process |
| CN118576216A (en) * | 2024-08-06 | 2024-09-03 | 江西杰联医疗设备有限公司 | Artifact suppression capability evaluation method, device, electronic equipment and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4576184A (en) * | 1981-08-31 | 1986-03-18 | Pharmometrics Corporation | Drug abuse detection |
| CN102184415A (en) * | 2011-05-17 | 2011-09-14 | 重庆大学 | Electroencephalographic-signal-based fatigue state recognizing method |
| CN107106006A (en) * | 2014-08-04 | 2017-08-29 | 纽约大学 | For diagnosing, evaluating or quantifying medicine use, drug abuse and anesthesia, internuclear ophthalmoplegia, attention deficit hyperactivity disorder (ADHD), chronic traumatic encephalopathic, schizophrenia pedigree obstacle and the method and kit of alcohol consumption |
| CN108563324A (en) * | 2018-03-04 | 2018-09-21 | 天津大学 | A kind of Mental imagery brain-computer interface design method of procedure-oriented control |
| CN108564039A (en) * | 2018-04-16 | 2018-09-21 | 北京工业大学 | A kind of epileptic seizure prediction method generating confrontation network based on semi-supervised deep layer |
| CN109171753A (en) * | 2018-08-16 | 2019-01-11 | 广东工业大学 | A kind of EEG signals EEG personal identification method encoding neural network certainly based on depth |
| CN109299647A (en) * | 2018-07-24 | 2019-02-01 | 东南大学 | A kind of extraction of multitask Mental imagery brain electrical feature and mode identification method towards vehicle control |
| CN109602417A (en) * | 2018-11-23 | 2019-04-12 | 杭州妞诺科技有限公司 | Sleep stage method and system based on random forest |
| CN109674468A (en) * | 2019-01-30 | 2019-04-26 | 大连理工大学 | It is a kind of singly to lead brain electricity sleep mode automatically method by stages |
| CN110811609A (en) * | 2019-10-28 | 2020-02-21 | 杭州电子科技大学 | Intelligent epileptic spike detection method based on fusion of adaptive template matching and machine learning algorithm |
| CN111476158A (en) * | 2020-04-07 | 2020-07-31 | 金陵科技学院 | Multi-channel physiological signal somatosensory gesture recognition method based on PSO-PCA-SVM |
| CN111657935A (en) * | 2020-05-11 | 2020-09-15 | 浙江大学 | Epilepsia electroencephalogram recognition system based on hierarchical graph convolutional neural network, terminal and storage medium |
| CN112006696A (en) * | 2019-05-29 | 2020-12-01 | 北京入思技术有限公司 | Emotion recognition method based on skin electric signal |
-
2020
- 2020-12-18 CN CN202011504403.1A patent/CN112641449A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4576184A (en) * | 1981-08-31 | 1986-03-18 | Pharmometrics Corporation | Drug abuse detection |
| CN102184415A (en) * | 2011-05-17 | 2011-09-14 | 重庆大学 | Electroencephalographic-signal-based fatigue state recognizing method |
| CN107106006A (en) * | 2014-08-04 | 2017-08-29 | 纽约大学 | For diagnosing, evaluating or quantifying medicine use, drug abuse and anesthesia, internuclear ophthalmoplegia, attention deficit hyperactivity disorder (ADHD), chronic traumatic encephalopathic, schizophrenia pedigree obstacle and the method and kit of alcohol consumption |
| CN108563324A (en) * | 2018-03-04 | 2018-09-21 | 天津大学 | A kind of Mental imagery brain-computer interface design method of procedure-oriented control |
| CN108564039A (en) * | 2018-04-16 | 2018-09-21 | 北京工业大学 | A kind of epileptic seizure prediction method generating confrontation network based on semi-supervised deep layer |
| CN109299647A (en) * | 2018-07-24 | 2019-02-01 | 东南大学 | A kind of extraction of multitask Mental imagery brain electrical feature and mode identification method towards vehicle control |
| CN109171753A (en) * | 2018-08-16 | 2019-01-11 | 广东工业大学 | A kind of EEG signals EEG personal identification method encoding neural network certainly based on depth |
| CN109602417A (en) * | 2018-11-23 | 2019-04-12 | 杭州妞诺科技有限公司 | Sleep stage method and system based on random forest |
| CN109674468A (en) * | 2019-01-30 | 2019-04-26 | 大连理工大学 | It is a kind of singly to lead brain electricity sleep mode automatically method by stages |
| CN112006696A (en) * | 2019-05-29 | 2020-12-01 | 北京入思技术有限公司 | Emotion recognition method based on skin electric signal |
| CN110811609A (en) * | 2019-10-28 | 2020-02-21 | 杭州电子科技大学 | Intelligent epileptic spike detection method based on fusion of adaptive template matching and machine learning algorithm |
| CN111476158A (en) * | 2020-04-07 | 2020-07-31 | 金陵科技学院 | Multi-channel physiological signal somatosensory gesture recognition method based on PSO-PCA-SVM |
| CN111657935A (en) * | 2020-05-11 | 2020-09-15 | 浙江大学 | Epilepsia electroencephalogram recognition system based on hierarchical graph convolutional neural network, terminal and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| KARINA P. ABRAHAO 等: "Dose-dependent alcohol effects on electroencephalogram: Sedation/anesthesia is qualitatively distinct from sleep", 《NEUROPHARMACOLOGY》 * |
| N. PANDRIA 等: "Advances in biofeedback and neurofeedback studies on smoking", 《NEUROIMAGE: CLINICAL》 * |
| 刘彦斌: "吗啡依赖与猕猴前额叶皮质EEG活动相关性研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
| 郭肖瑜: "基于脑电信号的海洛因成瘾戒断者的识别", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113208594A (en) * | 2021-05-12 | 2021-08-06 | 海南热带海洋学院 | Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram |
| CN114169366A (en) * | 2021-11-19 | 2022-03-11 | 北京师范大学 | Neurofeedback training system and method |
| CN114169366B (en) * | 2021-11-19 | 2023-10-20 | 北京师范大学 | Neural feedback training system and method |
| CN114587385A (en) * | 2022-02-25 | 2022-06-07 | 之江实验室 | Method for constructing post-stroke rehabilitation assessment deep learning model based on brain muscle network graph theory characteristics |
| CN114533066A (en) * | 2022-04-28 | 2022-05-27 | 之江实验室 | Social anxiety assessment method and system based on composite expression processing brain network |
| CN114533066B (en) * | 2022-04-28 | 2022-08-19 | 之江实验室 | Social anxiety assessment method and system based on composite expression processing brain network |
| CN114886388A (en) * | 2022-07-12 | 2022-08-12 | 浙江普可医疗科技有限公司 | Evaluation method and device for quality of electroencephalogram signal in anesthesia depth monitoring process |
| CN118576216A (en) * | 2024-08-06 | 2024-09-03 | 江西杰联医疗设备有限公司 | Artifact suppression capability evaluation method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112641449A (en) | EEG signal-based rapid evaluation method for cranial nerve functional state detection | |
| Liu et al. | A consensus statement on detection of hippocampal sharp wave ripples and differentiation from other fast oscillations | |
| CN101690659B (en) | Brain wave analysis method | |
| Zhou et al. | Characterizing the complexity of spontaneous motor unit patterns of amyotrophic lateral sclerosis using approximate entropy | |
| CN110135285B (en) | Electroencephalogram resting state identity authentication method and device using single-lead equipment | |
| CN110192874B (en) | Lie detection method based on multi-lead electroencephalogram signal margin factors | |
| CN103405225B (en) | A kind of pain that obtains feels the method for evaluation metrics, device and equipment | |
| CN105147281A (en) | Portable stimulating, awaking and evaluating system for disturbance of consciousness | |
| Gonzalez-Carabarin et al. | Machine Learning for personalised stress detection: Inter-individual variability of EEG-ECG markers for acute-stress response | |
| JP2015504764A (en) | Association of intentional and unintentional changes in brain state with brain signals | |
| CN110123342B (en) | Internet addiction detection method and system based on brain waves | |
| CN105512500A (en) | Method for rapidly screening characteristic of schizophrenia and evaluating therapeutic effect | |
| Anwar et al. | Use of portable EEG sensors to detect meditation | |
| CN113598790A (en) | Consciousness disturbance brain function network consciousness assessment method based on auditory stimulation | |
| CN112244767A (en) | Cognitive function assessment method based on electroencephalogram | |
| Barraco et al. | An approach based on wavelet analysis for feature extraction in the a-wave of the electroretinogram | |
| Kumar et al. | Fuzzy entropy as a measure of EEG complexity during Rajayoga practice in long-term meditators | |
| CN110192875B (en) | Lie detection method based on multi-lead electroencephalogram signal form factor | |
| Chu et al. | Physiological signals based quantitative evaluation method of the pain | |
| Sulistyono et al. | Analysis of EEG-based stroke severity groups clustering using k-means | |
| US11944445B2 (en) | Method for detecting elements of interest in electrophysiological signals and detector | |
| Lin et al. | Neurophysiological markers of identifying regret by 64 channels EEG signal | |
| CN101856221A (en) | Detection system for determining damage degree and damage positions of spinal cord | |
| CN110192878A (en) | Based on the lie detecting method for more leading EEG signals orientation transfer function | |
| Gholamipour et al. | Estimation of the independent components reliability of EEG signal in a clinical application |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210413 |