CN113576492A - Machine learning algorithm for sleep staging by applying forehead single-channel electroencephalogram signals - Google Patents
Machine learning algorithm for sleep staging by applying forehead single-channel electroencephalogram signals Download PDFInfo
- Publication number
- CN113576492A CN113576492A CN202110901251.7A CN202110901251A CN113576492A CN 113576492 A CN113576492 A CN 113576492A CN 202110901251 A CN202110901251 A CN 202110901251A CN 113576492 A CN113576492 A CN 113576492A
- Authority
- CN
- China
- Prior art keywords
- forehead
- signals
- machine learning
- learning algorithm
- filtering
- 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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/25—Bioelectric electrodes therefor
- A61B5/251—Means for maintaining electrode contact with the body
- A61B5/257—Means for maintaining electrode contact with the body using adhesive means, e.g. adhesive pads or tapes
-
- 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
- A61B5/25—Bioelectric electrodes therefor
- A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
- A61B5/291—Bioelectric electrodes therefor specially adapted for particular uses for electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—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
- A61B5/374—Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- 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
-
- 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
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- 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
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychology (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 machine learning algorithm for sleep stage by applying a forehead leaf single-channel electroencephalogram signal, which comprises the steps of establishing a training model and finally outputting and predicting, wherein the establishing of the training model comprises four stages of acquiring, filtering and removing artifacts, processing in 30s segments and extracting features of Fp1-Fp2 electroencephalogram data, and finally establishing the training model; and finally, acquiring, filtering and removing artifacts of the Fp1-Fp2 electroencephalogram data, performing 30s segmentation processing and extracting features, and finally sending the extracted features into an established training model to obtain the final output prediction, wherein the acquisition of the Fp1-Fp2 electroencephalogram data is realized by placing flexible patch electrodes at the positions of the prefrontal lobes Fp1-Fp2 of the human brain to acquire electroencephalogram signals. The invention has the beneficial effects that: the Fp1-Fp2 forehead single-channel brain electricity adopted by the invention is positioned at the forehead of the brain, the collection electrode uses a flexible patch electrode, the collection and the wearing are very convenient, and the wearing which is nearly non-inductive can not influence the night sleep of a wearer.
Description
Technical Field
The invention relates to a sleep stage machine learning algorithm, in particular to a sleep stage machine learning algorithm applying forehead single-channel electroencephalogram signals, and belongs to the technical field of sleep stage.
Background
Sleep monitoring is one of the very important daily monitoring items as well as daily physiological index monitoring such as heart rate, blood oxygen and blood pressure, and the sleep monitoring is not only required by people suffering from sleep disorder, but also comprises a plurality of common people and some chronic patients. Sleep staging based on electroencephalogram is much more accurate than methods based on electrocardio or pulse rate, body movement and the like. At present, a method for sleep monitoring based on electroencephalogram signals is mainly based on multiple channels, such as electroencephalogram signals (EEG), electro-oculogram signals (EOG), electromyogram signals (EMG) and the like, or single channels based on the position of a parietal middle axis, such as single-channel electroencephalogram signals of Fpz-Oz, Pz-Cz and the like. The two methods have inconvenience for sleep monitoring of ordinary people, are complicated in wearing mode and even influence sleep.
Disclosure of Invention
The invention aims to provide a machine learning algorithm for sleep staging by applying a forehead single-channel electroencephalogram signal to solve the problems.
The invention realizes the purpose through the following technical scheme, a machine learning algorithm of a prefrontal single-channel electroencephalogram signal to sleep stage is applied, the method comprises the steps of establishing a training model and final output prediction, the establishment of the training model comprises four stages of acquisition of Fp1-Fp2 electroencephalogram data, filtering and artifact removal, 30s segmentation processing and feature extraction, and finally the training model is established;
the final output prediction also needs to be subjected to four stages of acquisition, filtering and artifact removal, 30s segmentation processing and feature extraction of the Fp1-Fp2 electroencephalogram data, and finally the extracted features are sent to the established training model to obtain the final output prediction.
Preferably, the Fp1-Fp2 electroencephalogram data are acquired by placing flexible patch electrodes at the positions of Fp1-Fp2 of the prefrontal lobes of the human brain to acquire electroencephalogram signals; and meanwhile, the PSG equipment is worn to collect data, and then the data collected by the PSG equipment is labeled, and the label is used as a label for model training.
Preferably, the signal acquired by the PSG device is divided into: four categories of waking, rapid eye movement periods, light sleep and deep sleep.
Preferably, the method for filtering and removing the artifacts is to calculate the slope, the difference between the maximum and minimum values and the peak value of the signal in the time window of N milliseconds, and the numerical characteristics obtained by calculation are used as the determination conditions, and the signal exceeding a certain condition is judged to be the artifact signal to be removed;
and then, carrying out high-low pass filtering and 50Hz power frequency notch filtering on the electroencephalogram signals without the artifacts.
Preferably, the 30s segmentation processing is to perform 30s signal segmentation processing on each segment of the filtered data, and extract the corresponding labeled tag.
Preferably, the extracting features are feature extraction on 30s of segmented data;
firstly, decomposing signals in the ranges of 0.5-3Hz of delta wave, 4-7Hz of theta wave, 8-13Hz of alpha wave, 12-16Hz of spindles wave and 13-30Hz of beta wave;
secondly, performing median filtering on the signals, and then performing band-pass filtering of 0.5-3Hz to obtain signals related to eye movement; then, high-pass filtering of 40Hz is carried out to obtain signals related to myoelectricity.
Preferably, the decomposed signal is respectively extracted with six signal features of sigma _ beta _ index, delta _ beta _ index, eye _ movement _ index, beta _ EMG _ index, average _ beta _ envelope, and average _ EMG _ envelope.
Preferably, after the features are extracted, the extracted features and the corresponding labels are sent to an XGboost model for training; a target function is set in the XGboost model as a softmax function, meanwhile, in the training process, grid searching is used to find the optimal parameter setting until the optimal kappa value is reached, and at the moment, the model is stored.
Preferably, the stored model is the established training model and is used for carrying out automatic sleep stage classification on new data;
and then, carrying out filtering and artifact removing processing on newly acquired Fp1-Fp2 electroencephalogram data, then carrying out 30-second segmentation processing, extracting features, and finally sending the features into a stored training model for final output prediction.
The invention has the beneficial effects that: 1. the Fp1-Fp2 forehead single-channel brain electricity adopted by the invention is positioned at the forehead of the brain, the collection electrode uses a flexible patch electrode, and is very light and thin, so that the collection and wearing are very convenient for a wearer, and the wearing is almost senseless and cannot influence the night sleep of the wearer.
2. The invention provides an artifact removing method, which can effectively remove noise in signals, and simultaneously uses a light-weight and effective machine learning algorithm to extract a series of six characteristics including sigma _ beta _ index, delta _ beta _ index, eye _ movement _ EMG _ index, beta _ index, average _ beta _ envelope and average _ EMG _ envelope from the collected brain electrical signals of the forehead leaves, and the XGboost algorithm is used for learning and training by applying the six characteristics, so that the effect better than that of other machine learning models can be finally achieved, and the accuracy can reach more than 80%.
Drawings
FIG. 1 is a schematic diagram of a model training process according to the present invention;
FIG. 2 is a schematic diagram illustrating a sleep stage prediction process according to the present invention;
FIG. 3 is a graph of the results of sleep staging according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, the machine learning algorithm for sleep staging by applying the prefrontal single-channel electroencephalogram signal comprises the steps of establishing a training model and final output prediction, wherein the establishing of the training model comprises four stages of acquiring, filtering and removing artifacts of Fp1-Fp2 electroencephalogram data, performing 30s segmentation processing and extracting features, and finally establishing the training model;
and finally, the final output prediction also needs to be obtained through four stages of acquisition, filtering and artifact removal of Fp1-Fp2 electroencephalogram data, 30s segmentation processing and feature extraction, and finally the extracted features are sent to the established training model.
The acquisition of Fp1-Fp2 electroencephalogram data is that a flexible patch electrode is placed at the position of Fp1-Fp2 of the forehead of a human brain to acquire an electroencephalogram signal; and meanwhile, the PSG equipment is worn to collect data, and then the data collected by the PSG equipment is labeled, and the label is used as a label for model training.
The signals acquired by the PSG equipment are divided into the following parts according to the labels correspondingly marked: four categories of waking, rapid eye movement periods, light sleep and deep sleep.
The method for filtering and removing the artifacts comprises the steps of firstly calculating the slope, the difference value of the maximum value and the minimum value and the peak value of signals in a time window of N milliseconds, taking the numerical characteristics obtained by calculation as judgment conditions, and judging the signals exceeding certain conditions as artifact signals to be removed;
and then, carrying out high-low pass filtering and 50Hz power frequency notch filtering on the electroencephalogram signals without the artifacts.
The 30s segmentation processing is to perform 30s signal segmentation processing on the filtered data, and extract the corresponding labeled tag.
The characteristic extraction is carried out on the segmented data of 30 s;
firstly, decomposing signals in the ranges of 0.5-3Hz of delta wave, 4-7Hz of theta wave, 8-13Hz of alpha wave, 12-16Hz of spindles wave and 13-30Hz of beta wave;
secondly, performing median filtering on the signals, and then performing band-pass filtering of 0.5-3Hz to obtain signals related to eye movement; then, high-pass filtering of 40Hz is carried out to obtain signals related to myoelectricity.
As a technical optimization scheme of the invention, for decomposed signals, six signal characteristics of sigma _ beta _ index, delta _ beta _ index, eye _ movement _ index, beta _ EMG _ index, average _ beta _ envelope and average _ EMG _ envelope are respectively extracted;
the sigma _ beta _ index is the ratio of the average value of the envelope (envelope) of the spindles frequency band signal to the average value of the envelope of the beta frequency band signal; delta _ beta _ index is the ratio of the envelope mean value of the delta frequency band signal to the envelope mean value of the beta frequency band signal; eye _ movement _ index is the ratio of the mean value of the envelope of the theta band signal to the mean value of the envelope of the delta band signal; the beta _ EMG _ index is the ratio of the mean value of the envelope of the beta frequency band signal to the mean value of the envelope of the EMG frequency band signal; the average _ beta _ envelope is the average value of the signal envelope of the beta frequency band; average _ EMG _ envelope is the mean value of the EMG frequency band signal envelope.
As a technical optimization scheme of the invention, after the characteristics are extracted, the extracted characteristics and corresponding labels are sent to an XGboost model for training; setting a target function in the XGboost model as a softmax function, and simultaneously using grid search to find out the optimal parameter setting in the training process until the optimal kappa value is reached, and storing the model at the moment;
the XGboost is a limit gradient lifting algorithm in machine learning, the algorithm belongs to one of ensemble learning, the effect is good for data with unbalanced sleep stage categories, and the kappa value is an index for measuring the classification accuracy.
As a technical optimization scheme of the invention, the stored model is the established training model and is used for carrying out automatic sleep stage classification on new data;
then, filtering and artifact removing processing are carried out on newly acquired Fp1-Fp2 electroencephalogram data, then 30-second segmentation processing is carried out, characteristics are extracted, and finally the characteristics are sent to a stored training model for final output prediction;
according to the prediction result given by the model, the sleep stage chart can be drawn, so that the sleep stage chart is helpful for learning and researching how to improve the sleep quality.
Example (b): the flexible patch electrode is attached to the Fp1-Fp2 position of the forehead of a monitor, then data signal acquisition is carried out by utilizing PSG equipment, and then the flexible patch electrode is divided into the following parts according to the label of corresponding label obtained by acquisition: the method comprises the following steps of (1) filtering and removing artifacts of acquired signals, performing 30s segmentation processing and extracting a series of processing on the acquired signals, and then sending extracted features and corresponding labels into an XGboost model for training; setting a target function in the XGboost model as a softmax function, and drawing a sleep stage chart according to a prediction result given by the model, wherein the sleep stage chart is shown in FIG. 3;
wherein the monitoring time period is 00:50-06:30, Wake is waking stage, REM is rapid eye movement stage, Light is Light sleep stage, Deep sleep stage.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (9)
1. The machine learning algorithm for sleep staging by applying the prefrontal single-channel electroencephalogram signal comprises the establishment of a training model and the final output prediction, and is characterized in that: the establishment of the training model comprises four stages of Fp1-Fp2 electroencephalogram data acquisition, filtering and artifact removal, 30s segmentation processing and feature extraction, and finally the establishment of the training model;
the final output prediction also needs to be subjected to four stages of acquisition, filtering and artifact removal, 30s segmentation processing and feature extraction of the Fp1-Fp2 electroencephalogram data, and finally the extracted features are sent to the established training model to obtain the final output prediction.
2. The machine learning algorithm for sleep staging using forehead single-channel electroencephalogram signal according to claim 1, characterized in that: the Fp1-Fp2 electroencephalogram data are acquired by placing flexible patch electrodes at the positions of Fp1-Fp2 of the forehead of a human brain to acquire electroencephalogram signals; and meanwhile, the PSG equipment is worn to collect data, and then the data collected by the PSG equipment is labeled, and the label is used as a label for model training.
3. The machine learning algorithm for sleep staging using forehead single-channel electroencephalogram signal according to claim 2, characterized in that: the signals acquired by the PSG equipment are divided into the following parts according to the labels correspondingly marked: four categories of waking, rapid eye movement periods, light sleep and deep sleep.
4. The machine learning algorithm for sleep staging using forehead single-channel electroencephalogram signal according to claim 1, characterized in that: the method for filtering and removing the artifacts comprises the steps of firstly calculating the slope, the difference value of the maximum value and the minimum value and the peak value of signals in a time window of N milliseconds, taking the numerical characteristics obtained by calculation as judgment conditions, and judging the signals exceeding certain conditions as artifact signals to be removed;
and then, carrying out high-low pass filtering and 50Hz power frequency notch filtering on the electroencephalogram signals without the artifacts.
5. The machine learning algorithm for sleep staging using forehead single-channel electroencephalogram signal according to claim 1, characterized in that: the 30s segmentation processing is to perform 30s signal segmentation processing on the filtered data and extract the corresponding labeled tag.
6. The machine learning algorithm for sleep staging using forehead single-channel electroencephalogram signal according to claim 1, characterized in that: the extraction features are extracted on 30s of segmented data;
firstly, decomposing signals in the ranges of 0.5-3Hz of delta wave, 4-7Hz of theta wave, 8-13Hz of alpha wave, 12-16Hz of spindles wave and 13-30Hz of beta wave;
secondly, performing median filtering on the signals, and then performing band-pass filtering of 0.5-3Hz to obtain signals related to eye movement; then, high-pass filtering of 40Hz is carried out to obtain signals related to myoelectricity.
7. The machine learning algorithm for sleep staging using forehead single-channel electroencephalogram signal according to claim 6, characterized by: and for the decomposed signals, respectively extracting six signal characteristics of sigma _ beta _ index, delta _ beta _ index, eye _ movement _ index, beta _ EMG _ index, average _ beta _ envelope and average _ EMG _ envelope.
8. The machine learning algorithm for sleep staging using forehead single-channel electroencephalogram signal according to claim 7, characterized by: after the features are extracted, the extracted features and the corresponding labels are sent to an XGboost model for training; a target function is set in the XGboost model as a softmax function, meanwhile, in the training process, grid searching is used to find the optimal parameter setting until the optimal kappa value is reached, and at the moment, the model is stored.
9. The machine learning algorithm for sleep staging using forehead single-channel electroencephalogram signal according to claim 8, characterized by: the stored model is the established training model and is used for carrying out automatic sleep stage classification on new data;
and then, carrying out filtering and artifact removing processing on newly acquired Fp1-Fp2 electroencephalogram data, then carrying out 30-second segmentation processing, extracting features, and finally sending the features into a stored training model for final output prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901251.7A CN113576492A (en) | 2021-08-06 | 2021-08-06 | Machine learning algorithm for sleep staging by applying forehead single-channel electroencephalogram signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901251.7A CN113576492A (en) | 2021-08-06 | 2021-08-06 | Machine learning algorithm for sleep staging by applying forehead single-channel electroencephalogram signals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113576492A true CN113576492A (en) | 2021-11-02 |
Family
ID=78255820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110901251.7A Pending CN113576492A (en) | 2021-08-06 | 2021-08-06 | Machine learning algorithm for sleep staging by applying forehead single-channel electroencephalogram signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113576492A (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110897639A (en) * | 2020-01-02 | 2020-03-24 | 清华大学深圳国际研究生院 | Electroencephalogram sleep staging method based on deep convolutional neural network |
-
2021
- 2021-08-06 CN CN202110901251.7A patent/CN113576492A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110897639A (en) * | 2020-01-02 | 2020-03-24 | 清华大学深圳国际研究生院 | Electroencephalogram sleep staging method based on deep convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111012341B (en) | Artifact removal and electroencephalogram signal quality evaluation method based on wearable electroencephalogram equipment | |
| CN107495962B (en) | Sleep automatic staging method for single-lead electroencephalogram | |
| CN105496363A (en) | Method for classifying sleep stages on basis of sleep EGG (electroencephalogram) signal detection | |
| CN107007291A (en) | Intense strain intensity identifying system and information processing method based on multi-physiological-parameter | |
| CN108888280A (en) | Student based on electroencephalogramsignal signal analyzing listens to the teacher attention evaluation method | |
| CN111616682B (en) | Epileptic seizure early warning system based on portable electroencephalogram acquisition equipment and application | |
| CN107361745B (en) | Supervised sleep electroencephalogram and electrooculogram mixed signal stage interpretation method | |
| US20220265218A1 (en) | Real-time evaluation method and evaluation system for group emotion homogeneity | |
| CN110135285B (en) | Electroencephalogram resting state identity authentication method and device using single-lead equipment | |
| CN110353704B (en) | Emotion evaluation method and device based on wearable electrocardiogram monitoring | |
| CN106175754B (en) | Waking state detection device in sleep state analysis | |
| CN109481164B (en) | Electric wheelchair control system based on electroencephalogram signals | |
| CN111012345A (en) | Eye fatigue degree detection system and method | |
| CN109091141A (en) | A kind of sleep quality monitor and its monitoring method based on brain electricity and eye electricity | |
| CN106388778A (en) | A method and a system for electroencephalogram signal preprocessing in sleep state analysis | |
| CN114081439A (en) | Brain-like algorithm for sleep staging by applying prefrontal single-channel electroencephalogram signals | |
| CN115153463A (en) | Training method of sleep state recognition model, and sleep state recognition method and device | |
| CN113303814A (en) | Single-channel ear electroencephalogram automatic sleep staging method based on deep transfer learning | |
| CN114246593A (en) | Electroencephalogram, electrooculogram and heart rate fused fatigue detection method and system | |
| TWI288875B (en) | Multiple long term auto-processing system and method thereof | |
| CN114533089A (en) | Lower limb action recognition and classification method based on surface electromyographic signals | |
| CN113662558A (en) | Intelligent classification method for distinguishing electroencephalogram blink artifact and frontal epilepsy-like discharge | |
| CN116784860B (en) | Electrocardiosignal characteristic extraction system based on morphological heart beat template clustering | |
| CN106618486B (en) | Sleep state identification method and system in intelligent sleep assistance | |
| CN115969330B (en) | Method, system and device for detecting and quantifying sleep emotion activity level |
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 |