CN107361745A - One kind has supervised sleep cerebral electricity eye electricity mixed signal interpretation method by stages - Google Patents
One kind has supervised sleep cerebral electricity eye electricity mixed signal interpretation method by stages Download PDFInfo
- Publication number
- CN107361745A CN107361745A CN201710671649.XA CN201710671649A CN107361745A CN 107361745 A CN107361745 A CN 107361745A CN 201710671649 A CN201710671649 A CN 201710671649A CN 107361745 A CN107361745 A CN 107361745A
- Authority
- CN
- China
- Prior art keywords
- sleep
- signal
- electricity
- gross energy
- eye
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- A61B5/398—Electrooculography [EOG], e.g. detecting nystagmus; Electroretinography [ERG]
-
- 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
-
- 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
- A61B5/48—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
- A61B5/7253—Details of waveform analysis characterised by using transforms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
Abstract
Having supervised sleep cerebral electricity eye electricity mixed signal the invention discloses one kind, interpretation method, this method include by stages:Multiple sleep cerebral electricity eye electricity mixed signal fragment epoch are marked by stages;Removal interference is filtered to epoch, characteristic parameter extraction is carried out using filtered epoch, obtains characteristic parameter;Statistical disposition is carried out to characteristic parameter, builds decision tree;Un-marked sleep all night signal is obtained, sleep stage interpretation is carried out using decision tree, obtains sleep stage intermediate result;Sleep stage intermediate result is modified, obtains sleep stage result.This method, which is realized, improves sleep stage discrimination.
Description
Technical field
The present invention relates to sleep stage interpretation technical field, has the electricity mixing of supervised sleep cerebral electricity eye more particularly to one kind
Signal interpretation method by stages.
Background technology
At present, in paper " Virkkala J, Velin R, Himanen S L, et al.Automatic sleep
stage classification using two facial electrodes[J].Conf Proc IEEE Eng Med
Biol Soc,2008,2008:Sleep stage interpretation method in 1643-1646 " uses FP1 and FP2 lead brain electricity EEG signals,
Eye electricity EOG signal and lower jaw muscle electricity EMG signal are not used.The algorithm uses the difference for FP1 and FP2 lead signals to believe
Number, FFT is carried out, obtains the gross energy of each frequency range, tries to achieve delta frequency ranges gross energy, theta frequency ranges gross energy, alpha frequencies
Section gross energy, sigma frequency ranges gross energy, beta frequency ranges gross energy, muscle electricity frequency range gross energy.Slept by three layers of decision tree
The interpretation by stages of dormancy signal obtains result by stages.
Existing sleep stage interpretation method, sleep cerebral electricity eye electricity mixed signal fragment epoch record are limited to hardware
Equipment acquisition noise, influence sleep signal and differentiate result, and part epoch characteristic parameter and unobvious, independent uses spy
Sign parameter and decision tree this kind of epoch is carried out interpretation can cause it is very big misread, and characteristic parameter dimension is not abundant enough, only
It is confined among EEG signals, so causes sleep stage discrimination relatively low, the utilization ratio of sleep signal is relatively low.
The content of the invention
It is an object of the invention to provide one kind supervised sleep cerebral electricity eye electricity mixed signal interpretation method by stages, to realize
Improve sleep stage discrimination.
In order to solve the above technical problems, the present invention, which provides one kind, the interpretation by stages of supervised sleep cerebral electricity eye electricity mixed signal
Method, this method include:
Multiple sleep cerebral electricity eye electricity mixed signal fragment epoch are marked by stages;
Removal interference is filtered to epoch, characteristic parameter extraction is carried out using filtered epoch, obtains feature ginseng
Amount;
Statistical disposition is carried out to characteristic parameter, builds decision tree;
Un-marked sleep all night signal is obtained, sleep stage interpretation is carried out using decision tree, obtains in sleep stage
Between result;
Sleep stage intermediate result is modified, obtains sleep stage result.
Preferably, the characteristic parameter includes:Delta frequency ranges gross energy, theta frequency ranges gross energy, alpha frequency range total energys
Amount, sigma frequency ranges gross energy, beta frequency ranges gross energy, muscle electricity frequency range gross energy, electro-ocular signal gross energy, rejecting eye electricity are pseudo-
Sleep signal gross energy, sleep signal approximate entropy after mark.
Preferably, rejecting the acquisition process of the sleep signal gross energy after eye electricity artefact includes:
Wavelet analysis and reconstruct are carried out using sym3 small-wave cores, removes the eye electricity artefact in sleep signal, removes eye electricity
After artefact, the sleep after rejecting eye electricity artefact is calculated using Fast Fourier Transform (FFT) method or adaptive AR analysis methods and is believed
Number gross energy.
Preferably, the decision tree is three layers of decision tree.
Preferably, it is described that sleep stage intermediate result is modified, including:
Sleep stage intermediate result is modified using special event.
Preferably, before the special event of the use is modified to sleep stage intermediate result, in addition to:
Sleep stage intermediate result is smoothly post-processed using average value filtering.
Preferably, the special event includes:Shuttle-type of sleeping ripple, microarousal event, K-complex ripples, fast quick-action eye thing
Part.
One kind provided by the present invention has supervised sleep cerebral electricity eye electricity mixed signal interpretation method by stages, to multiple sleeps
Brain electric eye electricity mixed signal fragment epoch is marked by stages;Removal interference is filtered to epoch, utilization is filtered
Epoch carries out characteristic parameter extraction, obtains characteristic parameter;Statistical disposition is carried out to characteristic parameter, builds decision tree;Obtain without
The sleep all night signal of mark, sleep stage interpretation is carried out using decision tree, obtains sleep stage intermediate result;To sleep stage
Intermediate result is modified, and obtains sleep stage result.It can be seen that being filtered removal interference to epoch, and use sleep event
The post processing of result by stages has been carried out with statistical method, i.e., sleep stage intermediate result has been modified, obtains sleep stage
As a result, preliminary filtering process is carried out before interpretation particularly for sleep signal and sleep event amendment and rear place are carried out after interpretation
Reason, to obtain higher sleep stage discrimination, and improve the utilization ratio of sleep signal.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of flow for having supervised sleep cerebral electricity eye electricity mixed signal interpretation method by stages provided by the present invention
Figure;
Fig. 2 is decision tree of the present invention structure and algorithm using process diagram;
Fig. 3 is decision tree detailed schematic;
Fig. 4 is sleep event and sleep post processing schematic flow sheet.
Embodiment
The core of the present invention, which is to provide one kind, supervised sleep cerebral electricity eye electricity mixed signal interpretation method by stages, to realize
Improve sleep stage discrimination.
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Term is explained as follows:
Sleep cerebral electricity eye electricity mixed signal:Sample rate be 100Hz to 250Hz FP1FP2 leads brain electricity with electro-ocular signal with
And muscle electric signal, abbreviation sleep signal in the text.
Sleep cerebral electricity eye electricity mixed signal fragment:Referred to as epoch, the sleep cerebral electricity eye electricity mixed signal of 30 seconds is represented,
The fragment is the chronomere of sleep stage.It that is to say title:" certain epoch belong to sleep certain by stages ", in the text abbreviation epoch;
Sleep stage:According to AASM sleep rules, sleep epoch may belong to five kinds by stages, awaken phase abbreviation Weak or
Abbreviation W, fast quick-action eye phase abbreviation REM or abbreviation R, phase no rapid eye movement phase one or abbreviation N1, no rapid eye movement phase are the second stage of or simple
Claim N2, phase no rapid eye movement phase three or abbreviation N3;
Fast Fourier Transform (FFT):Abbreviation FFT;
Adaptive AR is analyzed:Abbreviation AR spectrum analyses.
Fig. 1 is refer to, Fig. 1 is that one kind provided by the present invention has the interpretation by stages of supervised sleep cerebral electricity eye electricity mixed signal
The flow chart of method, this method include:
S11:Multiple sleep cerebral electricity eye electricity mixed signal fragment epoch are marked by stages;
S12:Removal interference is filtered to epoch, characteristic parameter extraction is carried out using filtered epoch, is obtained special
Levy parameter;
S13:Statistical disposition is carried out to characteristic parameter, builds decision tree;
S14:Un-marked sleep all night signal is obtained, sleep stage interpretation is carried out using decision tree, obtains sleep point
Phase intermediate result;
S15:Sleep stage intermediate result is modified, obtains sleep stage result.
It can be seen that being filtered removal interference to epoch, and result by stages is carried out using sleep event and statistical method
Post processing, i.e., sleep stage intermediate result is modified, sleep stage result is obtained, particularly for sleep signal in interpretation
It is preceding to carry out preliminary filtering process and sleep event amendment and post processing are carried out after interpretation, identified with obtaining higher sleep stage
Rate, and improve the utilization ratio of sleep signal.
Based on the above method, detailed, the characteristic parameter includes:Delta frequency ranges gross energy, theta frequency ranges gross energy,
Alpha frequency ranges gross energy, sigma frequency ranges gross energy, beta frequency ranges gross energy, muscle electricity frequency range gross energy, electro-ocular signal total energy
Sleep signal gross energy, sleep signal approximate entropy after amount, rejecting eye electricity artefact.So carried out for epoch characteristic parameters
Supplement, is supplemented:Muscle electricity frequency range gross energy, electro-ocular signal gross energy, reject eye electricity artefact after sleep signal gross energy and
Sleep signal approximate entropy, so adds the characteristic parameter species that feature extraction is carried out for sleep signal, and use is more
More stable sleep signal can be obtained and differentiate result.
Wherein, rejecting the acquisition process of the sleep signal gross energy after eye electricity artefact includes:Entered using sym3 small-wave cores
Row wavelet analysis and reconstruct, the eye electricity artefact in sleep signal is removed, after removing eye electricity artefact, utilize Fast Fourier Transform (FFT)
Method or adaptive AR analysis methods calculate the sleep signal gross energy after rejecting eye electricity artefact.
Wherein, the acquisition process of sleep signal approximate entropy:For certain epoch signal, the FFT of the signal is calculated first
The part for being less than power spectrum average among power spectrum is removed and carries out IFFT Fourier's contravariant to signal by power spectrum, second step
Change, the 3rd calculates signal that second step obtains and original signal summed after difference, the 4th step, by signal total value and the
The calculating of three steps and value carry out ratio and obtain approximate entropy, to characterize the complexity of signal, how to divide in this, as judging that epoch belongs to
The characteristic parameter of phase.
Wherein, the decision tree is three layers of decision tree.Build in decision tree, sleep signal is carried out using three layers of decision tree
Differentiate by stages, each node threshold parameter of decision tree is to optimize calculating using marked epoch data and obtain.
Wherein, the process that is modified to sleep stage intermediate result is specially:Using special event to sleep point
Phase intermediate result is modified.
Wherein, before the special event of the use is modified to sleep stage intermediate result, in addition to:Using average value
Filtering is smoothly post-processed to sleep stage intermediate result.
Specifically, the special event includes:Shuttle-type of sleeping ripple, microarousal event, K-complex ripples, fast quick-action eye thing
Part.By being recorded to the generation frequency of this four classes special event among certain epoch, the sentence read result by stages of the epoch is corrected.
Wherein, certain epoch is believed by using the time window that length is 2 seconds for shuttle-type ripple of sleeping, sleep shuttle-type ripple
It is the scanning of 1 second number to carry out stepping, and observes the shuttle-type wave frequency section total energy value of signal in time window under each stepping, and is set
Put thresholding and carry out interpretation, a shuttle-type ripple is recorded if the thresholding is more than and is occurred.
For microarousal event, microarousal event is by epoch of the gross energy higher than certain thresholding being identified as that micro- feel occurs
Wake up.
For K-complex ripples, K-complex ripples use matched filtering algorithm, first by a typical K-complex ripple
Signal is stored, and convolution is carried out to certain epoch signal with the upset of this signal, and convolution results record once if certain thresholding is more than
K-complex ripples.
For fast quick-action eye event, fast quick-action eye event is by the gross energy to eye electricity EOG signal and more than 0.75Hz's
Frequency band energy carries out thresholding interpretation, identifies fast quick-action eye event.
Wherein, sleep post processing refers to is quantified as 1,2,3,4,5 respectively by sleep stage W, N1, N2, N3, R, then to whole night
Epoch sleep stage result carries out the average value filtering that length is 5, to reach the effect of smooth sleep stage burr.
In addition, except technical solution of the present invention, sleep signal characteristic parameter can also be entered using rear Feedback Neural Network
Row neural network learning, and obtain and stablize available neutral net, reuse neutral net and sleep signal is entered instead of decision tree
Row sleep stage, it can also complete the purpose of the present invention.The partial parameters structure of the characteristic parameter of sleep signal can also be used to determine
Plan tree, sleep stage is carried out to sleep signal.
This method is using there is supervision amendment decision tree, to the brain wave EEG signal using the collection of FP1, FP2 lead, eye electricity
EOG and muscle electricity EMG signal carry out sleep stage interpretation.This method characteristic parameter is tried to achieve to signal before preliminary filtering at
Reason, increased to the characteristic parameter extraction dimension of sleep signal, supplemented with muscle electricity frequency range gross energy, electro-ocular signal total energy
Amount, sleep signal are using gross energy, sleep signal approximate entropy after wavelet reconstruction rejecting eye electricity artefact, for sentencing by decision tree
Result is read, the post processing of result by stages has been carried out using sleep event and statistical method.It is with reference to figure 2, Fig. 3 and Fig. 4, Fig. 2
Decision tree structure of the present invention and algorithm using process diagram, Fig. 3 are decision tree detailed schematic, and Fig. 4 is sleep event and slept
Sleep and post-process schematic flow sheet, wherein, six node J1 to J6 of decision tree decision parameter is by decision-making among Fig. 2 in Fig. 3
Tree structure optimization, and determined concrete numerical value, are subsequently still required for adjusting.
It is as follows based on this method, specific implementation process:
1. a couple a large amount of epoch manually mark by stages;
2. first passing around 50Hz power frequency quadravalence Butterworth notch filters, remove 50Hz interference, then using marked
Epoch carries out characteristic parameter extraction, and principal character parameter includes:Delta frequency ranges gross energy, theta frequency ranges gross energy, alpha
Frequency range gross energy, sigma frequency ranges gross energy, beta frequency ranges gross energy, muscle electricity frequency range gross energy, electro-ocular signal gross energy, sleep
Dormancy signal uses gross energy after wavelet reconstruction rejecting eye electricity artefact, sleep signal approximate entropy;
Wherein, extracted for characteristic parameter, used FFT Fast Fourier Transform (FFT)s and AR to compose analysis and obtain certain afterwards
Epoch energy spectrum, each frequency range total energy value is tried to achieve for characteristic spectra;
3. pair characteristic parameter extracted carries out statistical procedures, artificial constructed decision tree, so as to for un-marked
Epoch characteristic parameter is judged;
4. after obtaining un-marked sleep all night signal, sleep stage interpretation is carried out using the decision tree of structure, will
All epoch interpretations of the sleep all night signal are five by stages some, obtain middle conclusion;
5. pair middle conclusion obtained post-processes, some by average value filtering and special event amendment, corrigendum
Epoch conclusion by stages, obtain final conclusion by stages.
This method is augmented for epoch characteristic parameters, supplemented with muscle electricity frequency range gross energy, electro-ocular signal total energy
Amount, sleep signal use gross energy after wavelet reconstruction rejecting eye electricity artefact, sleep signal approximate entropy.And for sleep signal point
The middle conclusion of phase carries out sleep event amendment and post processing, employ sleep shuttle-type ripple, microarousal event, K-complex ripples,
Fast quick-action eye event is corrected by stages to sleep signal, result by stages is carried out using the average value filtering by optimization smooth
Post processing.
Invention increases the characteristic parameter species that feature extraction is carried out for sleep signal, can be obtained using more
More stable sleep signal differentiates result, and preliminary filtering process is carried out before interpretation for sleep signal and in interpretation
Sleep event amendment and post processing are carried out afterwards, to obtain higher sleep stage discrimination, and are improved utilizing for sleep signal and are imitated
Rate.
Having supervised sleep cerebral electricity eye electricity mixed signal to one kind provided by the present invention above, interpretation method is carried out by stages
It is discussed in detail.Specific case used herein is set forth to the principle and embodiment of the present invention, above example
Explanation be only intended to help understand the present invention method and its core concept.It should be pointed out that for the common of the art
For technical staff, under the premise without departing from the principles of the invention, some improvement and modification can also be carried out to the present invention, these
Improve and modification is also fallen into the protection domain of the claims in the present invention.
Claims (7)
1. one kind has supervised sleep cerebral electricity eye electricity mixed signal interpretation method by stages, it is characterised in that including:
Multiple sleep cerebral electricity eye electricity mixed signal fragment epoch are marked by stages;
Removal interference is filtered to epoch, characteristic parameter extraction is carried out using filtered epoch, obtains characteristic parameter;
Statistical disposition is carried out to characteristic parameter, builds decision tree;
Un-marked sleep all night signal is obtained, sleep stage interpretation is carried out using decision tree, obtains tying among sleep stage
Fruit;
Sleep stage intermediate result is modified, obtains sleep stage result.
2. the method as described in claim 1, it is characterised in that the characteristic parameter includes:Delta frequency ranges gross energy, theta
Frequency range gross energy, alpha frequency ranges gross energy, sigma frequency ranges gross energy, beta frequency ranges gross energy, muscle electricity frequency range gross energy, eye
Sleep signal gross energy, sleep signal approximate entropy after electric signal gross energy, rejecting eye electricity artefact.
3. method as claimed in claim 2, it is characterised in that reject the acquisition of the sleep signal gross energy after eye electricity artefact
Journey includes:
Wavelet analysis and reconstruct are carried out using sym3 small-wave cores, removes the eye electricity artefact in sleep signal, removes eye electricity artefact
Afterwards, the sleep signal calculated using Fast Fourier Transform (FFT) method or adaptive AR analysis methods after rejecting eye electricity artefact is total
Energy.
4. the method as described in claim 1, it is characterised in that the decision tree is three layers of decision tree.
5. the method as described in claim 1, it is characterised in that it is described that sleep stage intermediate result is modified, including:
Sleep stage intermediate result is modified using special event.
6. method as claimed in claim 5, it is characterised in that described to be carried out using special event to sleep stage intermediate result
Before amendment, in addition to:
Sleep stage intermediate result is smoothly post-processed using average value filtering.
7. method as claimed in claim 5, it is characterised in that the special event includes:Shuttle-type of sleeping ripple, microarousal thing
Part, K-complex ripples, fast quick-action eye event.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710671649.XA CN107361745B (en) | 2017-08-08 | 2017-08-08 | Supervised sleep electroencephalogram and electrooculogram mixed signal stage interpretation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710671649.XA CN107361745B (en) | 2017-08-08 | 2017-08-08 | Supervised sleep electroencephalogram and electrooculogram mixed signal stage interpretation method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107361745A true CN107361745A (en) | 2017-11-21 |
CN107361745B CN107361745B (en) | 2021-01-01 |
Family
ID=60309057
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710671649.XA Active CN107361745B (en) | 2017-08-08 | 2017-08-08 | Supervised sleep electroencephalogram and electrooculogram mixed signal stage interpretation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107361745B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108403086A (en) * | 2018-03-09 | 2018-08-17 | 浙江纽若思医疗科技有限公司 | A kind of intelligence headring |
CN108451505A (en) * | 2018-04-19 | 2018-08-28 | 广西欣歌拉科技有限公司 | The In-Ear sleep stage system of light weight |
CN108553084A (en) * | 2018-03-09 | 2018-09-21 | 浙江纽若思医疗科技有限公司 | A kind of recognition methods, device and the equipment of sleep stage event |
CN108968915A (en) * | 2018-06-12 | 2018-12-11 | 山东大学 | Sleep state classification method and system based on entropy feature and support vector machines |
CN109044280A (en) * | 2018-08-20 | 2018-12-21 | 深圳和而泰数据资源与云技术有限公司 | A kind of sleep stage method and relevant device |
CN109758145A (en) * | 2018-12-15 | 2019-05-17 | 北京交通大学 | Based on the causal sleep mode automatically of EEG signals method by stages |
CN110179459A (en) * | 2019-06-17 | 2019-08-30 | 清华大学深圳研究生院 | A kind of recognition methods of sleep arousal, equipment and system |
CN110432870A (en) * | 2019-08-13 | 2019-11-12 | 重庆邮电大学 | A kind of sleep signal based on 1D CNN-LSTM method by stages automatically |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012018157A1 (en) * | 2010-08-01 | 2012-02-09 | 연세대학교 산학협력단 | System for automatically classifying sleep stages on the basis of biosignals |
CN104970773A (en) * | 2015-07-21 | 2015-10-14 | 西安交通大学 | Automatic sleep stage classification method based on dual character filtering |
CN105105714A (en) * | 2015-08-26 | 2015-12-02 | 吴建平 | Sleep period separating method and system |
CN105496363A (en) * | 2015-12-15 | 2016-04-20 | 浙江神灯生物科技有限公司 | Method for classifying sleep stages on basis of sleep EGG (electroencephalogram) signal detection |
CN106236079A (en) * | 2016-08-18 | 2016-12-21 | 中山衡思健康科技有限公司 | Electric and the sleep monitor eyeshield of eye electricity compound detection and sleep monitor method for brain |
CN106333674A (en) * | 2016-09-21 | 2017-01-18 | 广州视源电子科技股份有限公司 | Sleep cycle detection method and sleep cycle detection system in sleep state analysis |
CN106344008A (en) * | 2016-09-21 | 2017-01-25 | 广州视源电子科技股份有限公司 | Method and system for detecting waking state in sleep state analysis |
CN106388778A (en) * | 2016-09-21 | 2017-02-15 | 广州视源电子科技股份有限公司 | A method and a system for electroencephalogram signal preprocessing in sleep state analysis |
CN106413541A (en) * | 2014-01-08 | 2017-02-15 | 拉斯洛·奥斯瓦特 | Systems and methods for diagnosing sleep |
CN106618611A (en) * | 2017-03-06 | 2017-05-10 | 兰州大学 | Sleeping multichannel physiological signal-based depression auxiliary diagnosis method and system |
CN106709469A (en) * | 2017-01-03 | 2017-05-24 | 中国科学院苏州生物医学工程技术研究所 | Automatic sleep staging method based on multiple electroencephalogram and electromyography characteristics |
CN107007278A (en) * | 2017-04-25 | 2017-08-04 | 中国科学院苏州生物医学工程技术研究所 | Sleep mode automatically based on multi-parameter Fusion Features method by stages |
-
2017
- 2017-08-08 CN CN201710671649.XA patent/CN107361745B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012018157A1 (en) * | 2010-08-01 | 2012-02-09 | 연세대학교 산학협력단 | System for automatically classifying sleep stages on the basis of biosignals |
CN106413541A (en) * | 2014-01-08 | 2017-02-15 | 拉斯洛·奥斯瓦特 | Systems and methods for diagnosing sleep |
CN104970773A (en) * | 2015-07-21 | 2015-10-14 | 西安交通大学 | Automatic sleep stage classification method based on dual character filtering |
CN105105714A (en) * | 2015-08-26 | 2015-12-02 | 吴建平 | Sleep period separating method and system |
CN105496363A (en) * | 2015-12-15 | 2016-04-20 | 浙江神灯生物科技有限公司 | Method for classifying sleep stages on basis of sleep EGG (electroencephalogram) signal detection |
CN106236079A (en) * | 2016-08-18 | 2016-12-21 | 中山衡思健康科技有限公司 | Electric and the sleep monitor eyeshield of eye electricity compound detection and sleep monitor method for brain |
CN106333674A (en) * | 2016-09-21 | 2017-01-18 | 广州视源电子科技股份有限公司 | Sleep cycle detection method and sleep cycle detection system in sleep state analysis |
CN106344008A (en) * | 2016-09-21 | 2017-01-25 | 广州视源电子科技股份有限公司 | Method and system for detecting waking state in sleep state analysis |
CN106388778A (en) * | 2016-09-21 | 2017-02-15 | 广州视源电子科技股份有限公司 | A method and a system for electroencephalogram signal preprocessing in sleep state analysis |
CN106709469A (en) * | 2017-01-03 | 2017-05-24 | 中国科学院苏州生物医学工程技术研究所 | Automatic sleep staging method based on multiple electroencephalogram and electromyography characteristics |
CN106618611A (en) * | 2017-03-06 | 2017-05-10 | 兰州大学 | Sleeping multichannel physiological signal-based depression auxiliary diagnosis method and system |
CN107007278A (en) * | 2017-04-25 | 2017-08-04 | 中国科学院苏州生物医学工程技术研究所 | Sleep mode automatically based on multi-parameter Fusion Features method by stages |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108403086A (en) * | 2018-03-09 | 2018-08-17 | 浙江纽若思医疗科技有限公司 | A kind of intelligence headring |
CN108553084A (en) * | 2018-03-09 | 2018-09-21 | 浙江纽若思医疗科技有限公司 | A kind of recognition methods, device and the equipment of sleep stage event |
CN108403086B (en) * | 2018-03-09 | 2021-09-28 | 浙江纽若思医疗科技有限公司 | Intelligent head ring |
CN108451505A (en) * | 2018-04-19 | 2018-08-28 | 广西欣歌拉科技有限公司 | The In-Ear sleep stage system of light weight |
CN108968915A (en) * | 2018-06-12 | 2018-12-11 | 山东大学 | Sleep state classification method and system based on entropy feature and support vector machines |
CN109044280A (en) * | 2018-08-20 | 2018-12-21 | 深圳和而泰数据资源与云技术有限公司 | A kind of sleep stage method and relevant device |
CN109044280B (en) * | 2018-08-20 | 2021-12-17 | 深圳和而泰数据资源与云技术有限公司 | Sleep staging method and related equipment |
CN109758145A (en) * | 2018-12-15 | 2019-05-17 | 北京交通大学 | Based on the causal sleep mode automatically of EEG signals method by stages |
CN109758145B (en) * | 2018-12-15 | 2021-05-11 | 北京交通大学 | Automatic sleep staging method based on electroencephalogram causal relationship |
CN110179459A (en) * | 2019-06-17 | 2019-08-30 | 清华大学深圳研究生院 | A kind of recognition methods of sleep arousal, equipment and system |
CN110179459B (en) * | 2019-06-17 | 2022-07-26 | 清华大学深圳研究生院 | Method, device and system for identifying sleep arousal |
CN110432870A (en) * | 2019-08-13 | 2019-11-12 | 重庆邮电大学 | A kind of sleep signal based on 1D CNN-LSTM method by stages automatically |
Also Published As
Publication number | Publication date |
---|---|
CN107361745B (en) | 2021-01-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107361745A (en) | One kind has supervised sleep cerebral electricity eye electricity mixed signal interpretation method by stages | |
CN104809434B (en) | A kind of sleep stage method removed based on single channel EEG signals eye electricity artefact | |
CN102824172B (en) | EEG (electroencephalogram) feature extraction method | |
CN106709469B (en) | Automatic sleep staging method based on electroencephalogram and myoelectricity multiple characteristics | |
CN110353672A (en) | Eye artefact removal system and minimizing technology in a kind of EEG signals | |
CN106963369B (en) | Electroencephalogram relaxation degree identification method and device based on neural network model | |
CN102058413B (en) | Method for detecting EEG (electroencephalogram) alertness based on continuous wavelet transform | |
CN104173045A (en) | Epileptic seizure prewarning system | |
CN109657642A (en) | A kind of Mental imagery Method of EEG signals classification and system based on Riemann's distance | |
CN110321783A (en) | A kind of MEG spike detection method and system based on 1D convolutional neural networks | |
CN108280414A (en) | A kind of recognition methods of the Mental imagery EEG signals based on energy feature | |
CN107411739A (en) | EEG signals Emotion identification feature extracting method based on dual-tree complex wavelet | |
AlSharabi et al. | A DWT-entropy-ANN based architecture for epilepsy diagnosis using EEG signals | |
CN107612865A (en) | A kind of signal de-noising method applied to low-voltage powerline carrier communication | |
CN113065526A (en) | Electroencephalogram signal classification method based on improved depth residual error grouping convolution network | |
CN113116361A (en) | Sleep staging method based on single-lead electroencephalogram | |
Vijayasankar et al. | Correction of blink artifacts from single channel EEG by EMD-IMF thresholding | |
CN113576495B (en) | Motor imagery assessment method combined with EEG data quality | |
Lasefr et al. | An efficient automated technique for epilepsy seizure detection using EEG signals | |
CN110477909B (en) | Gender classification method based on resting electroencephalogram data | |
CN115736944A (en) | Atrial fibrillation detection model MCNN-BLSTM based on short-time single lead electrocardiosignal | |
CN113180659B (en) | Electroencephalogram emotion recognition method based on three-dimensional feature and cavity full convolution network | |
CN114081503A (en) | Method for removing ocular artifacts in electroencephalogram signals | |
Park et al. | Hybrid neural-network and rule-based expert system for automatic sleep stage scoring | |
Chai et al. | Classification of driver fatigue in an electroencephalography-based countermeasure system with source separation module |
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 | ||
CP02 | Change in the address of a patent holder |
Address after: 311222 301y, No. 22, Xinyan Road, Yuhang Economic and Technological Development Zone, Linping District, Hangzhou, Zhejiang Province Patentee after: ZHEJIANG NEURONS MEDICAL TECHNOLOGY CO.,LTD. Address before: Room 348, building 3, No.1 luting Road, Cangqian street, Yuhang District, Hangzhou City, Zhejiang Province Patentee before: ZHEJIANG NEURONS MEDICAL TECHNOLOGY CO.,LTD. |
|
CP02 | Change in the address of a patent holder |