CN106388780A - A sleep state detection method and system based on fusion of two classifiers and detectors - Google Patents

A sleep state detection method and system based on fusion of two classifiers and detectors Download PDF

Info

Publication number
CN106388780A
CN106388780A CN201610843527.XA CN201610843527A CN106388780A CN 106388780 A CN106388780 A CN 106388780A CN 201610843527 A CN201610843527 A CN 201610843527A CN 106388780 A CN106388780 A CN 106388780A
Authority
CN
China
Prior art keywords
detector
sleep state
user
characteristic
grader
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
Application number
CN201610843527.XA
Other languages
Chinese (zh)
Inventor
赵巍
胡静
韩志
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Shiyuan Electronics Thecnology Co Ltd
Original Assignee
Guangzhou Shiyuan Electronics Thecnology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Shiyuan Electronics Thecnology Co Ltd filed Critical Guangzhou Shiyuan Electronics Thecnology Co Ltd
Priority to CN201610843527.XA priority Critical patent/CN106388780A/en
Publication of CN106388780A publication Critical patent/CN106388780A/en
Pending legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
    • 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
    • A61B5/4815—Sleep quality
    • 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

Abstract

The invention relates to a sleep state detection method and system based on fusion of two classifiers and detectors. The method comprises the steps of collecting electroencephalogram signals of a user and extracting corresponding characteristic data; inputting the characteristic data into a preset classifier, a first detector and a second detector separately for detection; if the output results of the first detector and the second detector are not consistent, detecting the sleep state of the user according to the output results of the first detector and the second detector and performing type marking on characteristic data output by the first detector and the second detector separately; if the output results of the first detector and the second detector are consistent, detecting the sleep state of the user according to the output result of the preset classifier; training the preset classifier with the marked characteristic data to obtain a new classifier, replacing the preset classifier with the new classifier and detecting the sleep state of the user. The method and the system can improve the accuracy of classifiers and the accuracy of sleep state detection.

Description

The sleep state detection method being merged with detector based on two graders and system
Technical field
The present invention relates to assisting sleep technical field, more particularly to a kind of based on two graders and sleeping that detector merges Dormancy condition detection method and system.
Background technology
In sleep, human body has carried out the process self loosened and recover, and therefore good sleep is to maintain healthy A primary condition；But due to the reason such as operating pressure is big, daily life system is irregular, result in the sleep matter of part population Amount is not good enough, shows as insomnia, midnight wakes up with a start.
There are some equipment at present on the market to help people to fall asleep, improved sleep quality.For example specific sleep a certain Pass through the manual intervention such as sound, optical signal, it is to avoid wake user etc. under the state of sleeping soundly under dormancy state.Assisting sleep is set For standby, in order to be really achieved the purpose improving user's sleep quality, the sleep state of correct detection user is extremely important 's.
Clinically mainly adopt at present polysomnogram to identify sleep state, mainly use EEG signals come to sleep into Row analysis, by training sleep state model to identify, measured is belonging to sleep or waking state, but due to EEG signals Individual human specific is very strong, and intensity is very weak, is easily disturbed by outer signals in signals collecting.Therefore general training in advance There is error to the detection of a lot of users in grader out, accuracy is difficult to be guaranteed.
Content of the invention
Based on this it is necessary to be directed to the problems referred to above, provide a kind of sleep state merging based on two graders with detector Detection method and system, effectively improve the accuracy of default grader identification.
A kind of sleep state detection method being merged with detector based on two graders, including：
The EEG signals that collection user produces in sleep procedure, the identification mission according to sleep state identification is from described brain Corresponding characteristic is extracted in the signal of telecommunication；
Described characteristic is inputted default grader, the first detector and the second detector respectively detected；Its In, default grader is used for detecting the clear-headed of user or sleep state, the first detector is used for detecting the waking state of user, the Two detectors are used for detecting the sleep state of user；
If the first detector is inconsistent with the output result of the second detector, with the first detector and the second detector Output result detects the sleep state of user, and carries out class to the characteristic of the first detector and the output of the second detector respectively Type marks；If the first detector is consistent with the output result of the second detector, used with the output result detection of default grader The sleep state at family；
Characteristic using mark is trained obtaining new grader to described default grader, and new using this Grader replaces described default grader, the sleep state of detection user.
A kind of sleep state detecting system being merged with detector based on two graders, including：
Characteristic extraction module, for gathering the EEG signals that user produces in sleep procedure, according to sleep state The identification mission of identification extracts corresponding characteristic from described EEG signals；
Multiple Classifier Fusion detection module, for by described characteristic input respectively default grader, the first detector with And second detector detected；Wherein, default grader is used for detecting the clear-headed of user or sleep state, the first detector is used In the waking state of detection user, the second detector is used for detecting the sleep state of user；
Result judges data labeling module, if inconsistent with the output result of the second detector for the first detector, The sleep state of user is then detected with the output result of the first detector and the second detector, and respectively to the first detector and the The characteristic of two detector outputs carries out type mark；If the first detector is consistent with the output result of the second detector, Detect the sleep state of user with the output result of default grader；
Classifier training and update module, for being trained to described default grader using the characteristic of mark To new grader, and replace described default grader, the sleep state of detection user using this new grader.
The above-mentioned sleep state detection method based on two graders and detector fusion and system, the spy based on EEG signals Levy data, on the basis of default grader, be provided with waking state and dormant two classification and Detection devices further, merge and divide Class device testing result and detector output result carry out type mark to characteristic, then by the characteristic of marking types The default classifier training of input goes out new grader, replaces former default grader, the sleep state of detection user.The program is permissible Train in use and be closer to the specific grader of individual subscriber, the accuracy rate of grader can be improved, increase The accuracy of strong sleep state detection.
Brief description
Fig. 1 is the flow chart of the sleep state detection method being merged with detector based on two graders of an embodiment；
Fig. 2 is the EEG signals schematic diagram before and after Filtering Processing；
Fig. 3 is that two Multiple Classifier Fusion detectors detect dormant schematic diagram；
Fig. 4 is the sleep state detecting system structural representation merged with detector based on two graders of an embodiment Figure.
Specific embodiment
Illustrate below in conjunction with the accompanying drawings the present invention the sleep state detection method being merged based on two graders and detector and The embodiment of system.
With reference to shown in Fig. 1, Fig. 1 is the sleep state detection side merged with detector based on two graders of an embodiment The flow chart of method, including：
Step S101, the EEG signals that collection user produces in sleep procedure, appointed according to the identification of sleep state identification Corresponding characteristic is extracted in business from described EEG signals；
In this step, as when assisting sleep is carried out to user, related transducer equipment is worn by user, detect user EEG signals, gather EEG signals when, can be acquired with 30s for a frame.
Carry out the task of sleep state identification as needed, determine feature data types, extract therewith from EEG signals Corresponding characteristic；For example, waking state to be identified or sleep state, extracts the feature for carrying out both state recognitions Data.
In one embodiment, before extracting characteristic, the EEG signals that be gathered can also be filtered process, filter Except high-frequency noise and Hz noise.For example, the useful information of EEG signals focuses mostly in the range of 0-100Hz, is gathering Cheng Zhonghui mixes frequency in this extraneous noise, therefore, it can be filtered by means of filtering.Can same band filter Filter high-frequency noise, and design a wave trap (50/60Hz) to filter Hz noise.
With reference to shown in Fig. 2, Fig. 2 is the EEG signals schematic diagram before and after Filtering Processing, and upper figure is primary signal, figure below be through Cross the signal after Filtering Processing, it can be found that most high-frequency noise is filtered out.
For the scheme extracting characteristic, the present invention provides some embodiments, and detailed process includes as follows：
(1) extract the baseline of EEG signals, calculate the amplitude of variation of described baseline；Wherein, described amplitude of variation is baseline Maximum deducts minima；
(2) after removing baseline, described EEG signals are carried out with wavelet decomposition, obtain wavelet coefficient, and according to wavelet systems Number calculates the characteristic parameter of wavelet coefficient；Wherein, described characteristic parameter include the average of wavelet coefficient, variance, kurtosis coefficient and/ Or gradient coefficient；
In order to preferably decomposite described various frequency waveform, the number of plies of wavelet decomposition is full with the sample frequency of EEG signals The following relation of foot：F=2N+2, wherein, f is the sample frequency of EEG signals, and N is the number of plies of wavelet decomposition；For example, when signal When down-sampled rate is 128Hz, 4 layers of decomposition can be selected, when the sample rate of signal is 256Hz, then can carry out 5 layers of decomposition.
(3) LZ complexity and the Sample Entropy of EEG signals after removing baseline, are calculated；
The amplitude of variation of described baseline, the characteristic parameter of wavelet coefficient, LZ complexity and Sample Entropy are set to described feature Data；
By the scheme of above-described embodiment, the data as signal characteristic includes the amplitude of variation of baseline, wavelet coefficient Characteristic parameter, LZ complexity and Sample Entropy etc..
Further, can also be identified using the waveform of multiple wave bands of EEG signals, carry in wavelet reconstruction Take described EEG signals δ wave frequency section, the signal of θ wave frequency section, α wave frequency section and β wave frequency section；According to the difference of frequency, EEG signals It is to be divided into 4 species rhythm brain waves：δ ripple (1-3Hz), θ ripple (4-7Hz), α ripple (8-12Hz), β ripple (14-30Hz), here, After these four brain waves can be extracted, calculate correlated characteristic using these brain waves, concrete scheme can be as follows：
(4) δ wave frequency section in EEG signals, θ wave frequency section, α wave frequency section are calculated respectively, the energy of β wave frequency section is in gross energy Ratio；This ratio is also served as characteristic input grader be identified；Computational methods can include equation below：
rδ=∑ (yδ)2/ptotal
rθ=∑ (yθ)2/ptotal
rα=∑ (yα)2/ptotal
rβ=∑ (yβ)2/ptotal
Wherein ptotal=∑ (yδ)2+∑(yθ)2+∑(yα)2+∑(yβ)2, yδ, yθ, yαAnd yβRepresent the δ frequency after reconstruct respectively Section, the signal of θ frequency range, α frequency range and β frequency range, rδ, rθ, rαAnd rβRepresent δ frequency range, the signal of θ frequency range, α frequency range and β frequency range respectively Energy gross energy ratio.
(5) calculate respectively within the time of a frame, δ wave frequency section in EEG signals, θ wave frequency section, α wave frequency section, β wave frequency section energy The maximum time span of amount；This time also served as characteristic input grader be identified, computational methods can include as Lower formula：
1st, a kind of mask method of sleep state sample data type is it is characterised in that include：
The EEG signals that collection user produces in sleep state analysis, obtain sample data；
Build the cluster center that the characteristic vector of sample data of multiple sleep state types and characteristic vector are assembled, Object function is set up according to described characteristic vector and its cluster center；Wherein, described object function characterizes and minimizes same type Sample data and the distance of dictionary atom, and maximize the distance between different types of atom；
Select several characteristic vectors as the initial value of atom from the sample data of multiple sleep state types respectively, Each sample data is distributed to described atom and solves described object function, obtain classifying dictionary；
Sample data is inputted classifying dictionary, compares type and the distance of the atom nearest with sample data, if apart from little In default threshold value, then the type of this sample data is labeled as consistent with the type of this atom.
2nd, the mask method of sleep state sample data type according to claim 1 is it is characterised in that described mesh Scalar functions are：
In formula, it is provided with the sample data of t kind sleep state type,P=1 ..., t are characterized vector,P=1 ..., t are characterized the cluster center of vector gathering.
3rd, the mask method of sleep state sample data type according to claim 2 is it is characterised in that described sleep Dormancy Status Type includes clear-headed type and sleep pattern；
Described object function is：
In formula,I=1 ..., nwakeFor the characteristic vector of clear-headed type,J=1 ..., kwakeFor type of regaining consciousness In formula, cδ, cθ, cαAnd cβThe signal representing δ frequency range, θ frequency range, α frequency range and β frequency range is in energy proportion maximum shared by current frame in Time span,Represent that in i-th second, δ frequency range, the energy of the signal of θ frequency range, α frequency range and β frequency range are in total energy respectively The ratio of amount.
Step S102, described characteristic is inputted default grader, the first detector and the second detector respectively and enters Row detection；Wherein, default grader is used for detecting the clear-headed of user or sleep state, the first detector is used for detecting that user's is clear Awake state, the second detector is used for detecting the sleep state of user；
For above-mentioned default grader, can be using RBF core SVM (Support Vector Machin, support to Amount machine) grader, it would however also be possible to employ neutral net, the grader of decision tree.This grader is to be trained by other sample datas Obtain.
Training process can be as follows：
(1) obtain the characteristic of described user, randomly draw equal number from two kinds of characteristic respectively Sample as training data, remaining is as test data；
(2) described training data is inputted support vector machine classifier or neutral net carries out self study, using grid- Test algorithm finds discrimination highest parameter, and this parameter is set to optimized parameter；
For support vector machine classifier, adopt in training process the optimum penalty factor of grid software test method choice and Parameter σ of RBF core；Adjust described penalty factor and parameter σ, corresponding parameter during discrimination highest is set to optimized parameter；Its In, the span of penalty factor can be [2-2, 212], the span of described parameter σ can be [2-2, 210]；Above-mentioned instruction During white silk, because training data is randomly drawed from gathered data, therefore this process can be with repeated several times；
(3) reruned in training data once using described optimized parameter, obtain grader；
(4) carry out test accuracy rate using described test data on this grader, after the completion of test, obtain default classification Device.
Because the individual human specific of EEG signals is very strong, and the intensity of EEG signals is very weak, in signals collecting, easily Disturbed by outer signals.Therefore, the grader that in advance collection training data trains out, for partial test data its Effect is unsatisfactory.
Based on above-mentioned phenomenon, in this step, it is provided with waking state and dormant two detectors classified with right Characteristic is labeled, and then trains, by the characteristic of mark, the new grader meeting personal characteristics, pre- to update If grader, replace it for the sleep state detecting user.
On the premise of above-mentioned detector typically chooses certain sensitivity (sensitivity), there is higher accuracy (precision) detector.
In addition, in order to obtain ideal detector, the first detector and the second detector can be using preferable detections Device, the method using the penalty factor of the corresponding sample of adjustment trains described first detector and the second detector.
Test result indicate that, the sensitivity of both detectors is above 70%, and accuracy is above 95%.
For above-mentioned two detector, according to the evaluation index of classification task, overall accuracy (over accuracy), Sensitivity rate (sensitivity, sometimes referred to as recall rate, recall) and accurate rate (precision).For above-mentioned waking state With sleep state two classification problem, its confusion matrix see table：
Overall accuracyReflect is total classification accuracy of all types sample.Sensitive Degree refers to the ratio in all 1st class samples, being accurately identified.Degree of accuracy refers in all samples being identified as the 1st class In this, truly belong to the sample proportion of the 1st class.
In one embodiment, for default grader, the first detector and the second detector, function setting can be as Under：
Described default grader is used for detecting whether user is in clear-headed or sleep state, output result be " regaining consciousness " or " sleep ".
Described first detector is used for detecting whether user is in waking state, if judging, user is in waking state, defeated Going out result is "true", otherwise then output result is "false"；This detector can relatively accurately detect waking state；
Described second detector is used for detecting whether user is in sleep state, if judging, user is in sleep state, defeated Going out result is "true", otherwise then output result is "false"；This detector can relatively accurately detect sleep state.
Step S103, if the first detector is inconsistent with the output result of the second detector, with the first detector and The output result of two detectors detects the sleep state of user, and the feature to the first detector and the output of the second detector respectively Data carries out type mark；If the first detector is consistent with the output result of the second detector, with the output of default grader Result detects the sleep state of user；
This step is the recognition result based on default grader, the first detector and the second detector, sleeps to residing for user The judgement scheme of dormancy state.
Further, judged according to following inspection policies：
(1) if the first detector output result be "true", the second detector output result be "false", respectively by first examine The feature data types that survey device is exported with the second detector are labeled as regaining consciousness；If the first detector output result be "false", second The output result of detector is "true", and the feature data types exporting the first detector with the second detector respectively are labeled as sleeping Sleep；
In such scheme, after the mark of feature data types, these characteristics can be used for training default classification Device, thus the dormant accuracy of detection improving grader.
(2) if the first detector, the second detector output result are all "true" or are all "false", abandon the first detector, The output result of the second detector, and the characteristic of the first detector, the second detector output is not labeled；
In such scheme, because detector cannot detect, therefore can determine according to the testing result of default grader and work as The sleep state of front user, now the first detector, the output characteristic data of the second detector cannot be used for improving default classification The training sample of device, is therefore abandoned.
Step S104, the characteristic using mark is trained obtaining new grader to described default grader, and Replace described default grader, the sleep state of detection user using this new grader.
In this step, the characteristic based on mark in abovementioned steps S103, is input to default as sample It is trained in grader obtaining new grader, replace default grader with this new grader, pre- such that it is able to improve If the detection sleep state accuracy of grader.
In actual applications, continuing on with user, can persistently trigger, and constantly update grader, such that it is able to Constantly accuracy, and when being applied to other users it is also possible to re -training goes out grader, obtain being more suitable for dividing of this user Class device.
In one embodiment, when training new grader, first determine whether the quantity of the characteristic of marking types, When quantity reaches given threshold, the characteristic of mark is trained obtaining as the default grader of sample data input New grader；
By with given threshold, when the characteristic of the marking types collected reaches some, default point of input Class device is trained, it is to avoid sample size is too low, and training effect is not good.
With reference to shown in Fig. 3, Fig. 3 is that two Multiple Classifier Fusion detectors detect dormant schematic diagram.Remove in annotation process Outside the default grader of more balance of other sample datas, also design two detectors, the first detector is used for Whether monitoring user is in waking state, and the second detector is used for monitoring user's whether sleep state.
Default grader, the first detector and the second detector is respectively enterd after characteristic input；By above-mentioned detection Strategy is judged, the input current sleep state testing result of user, for the characteristic of labeled data type, input to Default grader is trained new grader, for the characteristic of unlabeled data type, is abandoned after detection.
With reference to shown in Fig. 4, Fig. 4 is the sleep state detection system merged with detector based on two graders of an embodiment System structural representation, including：
Characteristic extraction module 101, for gathering the EEG signals that user produces in sleep procedure, according to sleep shape The identification mission of state identification extracts corresponding characteristic from described EEG signals；
Multiple Classifier Fusion detection module 102, for inputting default grader, the first detector respectively by described characteristic And second detector detected；Wherein, default grader is used for detecting the clear-headed of user or sleep state, the first detector For detecting the waking state of user, the second detector is used for detecting the sleep state of user；
Result judges data labeling module 103, if the output result for the first detector and the second detector differs Cause, then detect the sleep state of user with the output result of the first detector and the second detector, and respectively to the first detector Carry out type mark with the characteristic of the second detector output；If the output result one of the first detector and the second detector Cause, then detect the sleep state of user with the output result of default grader；
Classifier training and update module 104, for being instructed to described default grader using the characteristic of mark Get new grader, and replace described default grader, the sleep state of detection user using this new grader.
The sleep state detecting system based on two graders and detector fusion of the present invention is with the present invention based on two points The sleep state detection method that class device and detector merge corresponds, above-mentioned based on two graders and sleeping that detector merges The technical characteristic that the embodiment of dormancy condition detection method illustrates and its advantage are all applied to based on two graders and detector In the embodiment of sleep state detecting system merging, hereby give notice that.
Each technical characteristic of embodiment described above can arbitrarily be combined, for making description succinct, not to above-mentioned reality The all possible combination of each technical characteristic applied in example is all described, as long as however, the combination of these technical characteristics is not deposited In contradiction, all it is considered to be the scope of this specification record.
Embodiment described above only have expressed the several embodiments of the present invention, and its description is more concrete and detailed, but simultaneously Can not therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art Say, without departing from the inventive concept of the premise, some deformation can also be made and improve, these broadly fall into the protection of the present invention Scope.Therefore, the protection domain of patent of the present invention should be defined by claims.

Claims (10)

1. a kind of sleep state detection method being merged with detector based on two graders is it is characterised in that include：
The EEG signals that collection user produces in sleep procedure, the identification mission according to sleep state identification is from described brain telecommunications Corresponding characteristic is extracted in number；
Described characteristic is inputted default grader, the first detector and the second detector respectively detected；Wherein, in advance If grader is used for detecting the clear-headed of user or sleep state, the first detector is used for detecting the waking state of user, the second inspection Survey device to be used for detecting the sleep state of user；
If the first detector is inconsistent with the output result of the second detector, with the output of the first detector and the second detector Result detects the sleep state of user, and carries out type mark to the characteristic of the first detector and the output of the second detector respectively Note；If the first detector is consistent with the output result of the second detector, detect user's with the output result of default grader Sleep state；
Characteristic using mark is trained obtaining new grader to described default grader, and utilizes this new classification Device replaces described default grader, the sleep state of detection user.
2. the sleep state detection method being merged with detector based on two graders according to claim 1, its feature exists In described default grader is used for detecting whether user is in clear-headed or sleep state, and output result is " regaining consciousness " or " sleep "；
Described first detector is used for detecting whether user is in waking state, if judging, user is in waking state, output knot Fruit is "true", otherwise then output result is "false"；
Described second detector is used for detecting whether user is in sleep state, if judging, user is in sleep state, output knot Fruit is "true", otherwise then output result is "false".
3. the sleep state detection method being merged with detector based on two graders according to claim 2, its feature exists In, if the first detector output result be "true", the output result of the second detector be "false", respectively by the first detector and the The feature data types of two detector outputs are labeled as regaining consciousness；If the first detector output result is "false", the second detector Output result is "true", is labeled as sleeping by the feature data types of the first detector and the output of the second detector respectively.
4. the sleep state detection method being merged with detector based on two graders according to claim 2, its feature exists In, if the first detector, the second detector output result are all "true" or are all "false", abandon the first detector, second detection The output result of device, and the characteristic of the first detector, the second detector output is not labeled.
5. the sleep state detection method being merged with detector based on two graders according to claim 1, its feature exists In the characteristic step that is trained obtaining new grader to described default grader using mark includes：
Judge the quantity of the characteristic of marking types, when quantity reaches given threshold, the characteristic of mark is made It is trained obtaining new grader for the default grader of sample data input.
6. the sleep state detection method being merged with detector based on two graders according to claim 1, its feature exists In the described step extracting corresponding characteristic from described EEG signals includes：
Extract the baseline of EEG signals, calculate the amplitude of variation of described baseline；Wherein, described amplitude of variation subtracts for baseline maximum Go minima；
After removing baseline, described EEG signals are carried out with wavelet decomposition, obtain wavelet coefficient, and calculated according to wavelet coefficient little The characteristic parameter of wave system number；Wherein, described characteristic parameter includes average, variance, kurtosis coefficient and/or the gradient system of wavelet coefficient Number；
After removing baseline, calculate LZ complexity and the Sample Entropy of EEG signals；
The amplitude of variation of described baseline, the characteristic parameter of wavelet coefficient, LZ complexity and Sample Entropy are set to described characteristic.
7. the sleep state detection method being merged with detector based on two graders according to claim 6, its feature exists In also including：
Described EEG signals δ wave frequency section, the signal of θ wave frequency section, α wave frequency section and β wave frequency section is extracted in wavelet reconstruction；
Calculate δ wave frequency section in EEG signals, θ wave frequency section, α wave frequency section, the energy of the β wave frequency section ratio in gross energy respectively；
Calculate respectively within the time of a frame, δ wave frequency section in EEG signals, θ wave frequency section, α wave frequency section, β ripple band energy is maximum Time span；
Described ratio and time are set to described characteristic.
8. the sleep state detection method being merged with detector based on two graders according to claim 7, its feature exists In described calculating δ wave frequency section in EEG signals, θ wave frequency section, α wave frequency section, the energy of the β wave frequency section ratio in gross energy respectively The step of example includes equation below：
rδ=∑ (yδ)2/ptotal
rθ=∑ (yθ)2/ptotal
rα=∑ (yα)2/ptotal
rβ=∑ (yβ)2/ptotal
Wherein ptotal=∑ (yδ)2+∑(yθ)2+∑(yα)2+∑(yβ)2, yδ, yθ, yαAnd yβRepresent the δ frequency range after reconstruct, θ respectively The signal of frequency range, α frequency range and β frequency range, rδ, rθ, rαAnd rβRepresent δ frequency range, the energy of the signal of θ frequency range, α frequency range and β frequency range respectively Amount is in the ratio of gross energy.
9. the sleep state detection method being merged with detector based on two graders according to claim 7, its feature exists In, described calculate respectively within the time of a frame, δ wave frequency section in EEG signals, θ wave frequency section, α wave frequency section, β ripple band energy is The step of big time span includes equation below：
c δ = Σ i = 1 30 f δ i , f δ i = 1 , i f r δ i = m a x ( r δ i , r θ i , r α i , r β i ) 0 , i f r δ i ≠ m a x ( r δ i , r θ i , r α i , r β i )
c θ = Σ i = 1 30 f θ i , f θ i = 1 , i f r θ i = m a x ( r δ i , r θ i , r α i , r β i ) 0 , i f r θ i ≠ m a x ( r δ i , r θ i , r α i , r β i )
c α = Σ i = 1 30 f α i , f α i = 1 , i f r α i = m a x ( r δ i , r θ i , r α i , r β i ) 0 , i f r α i ≠ m a x ( r δ i , r θ i , r α i , r β i )
c β = Σ i = 1 30 f β i , f β i = 1 , i f r β i = m a x ( r δ i , r θ i , r α i , r β i ) 0 , i f r β i ≠ m a x ( r δ i , r θ i , r α i , r β i )
In formula, cδ, cθ, cαAnd cβRepresent δ frequency range, θ frequency range, α frequency range and β frequency range signal in energy proportion shared by current frame in Big time span,Represent that in i-th second, δ frequency range, the energy of the signal of θ frequency range, α frequency range and β frequency range are total respectively The ratio of energy.
10. a kind of sleep state detecting system being merged with detector based on two graders is it is characterised in that include：
Characteristic extraction module, for gathering the EEG signals that user produces in sleep procedure, identifies according to sleep state Identification mission extract corresponding characteristic from described EEG signals；
Multiple Classifier Fusion detection module, for inputting default grader, the first detector and respectively by described characteristic Two detectors are detected；Wherein, default grader is used for detecting the clear-headed of user or sleep state, the first detector is used for examining Survey the waking state of user, the second detector is used for detecting the sleep state of user；
Result judges data labeling module, if inconsistent with the output result of the second detector for the first detector, with The output result of the first detector and the second detector detects the sleep state of user, and respectively to the first detector and the second inspection The characteristic surveying device output carries out type mark；If the first detector is consistent with the output result of the second detector, with pre- If the output result of grader detects the sleep state of user；
Classifier training and update module, for being trained to described default grader obtaining newly using the characteristic of mark Grader, and replace described default grader, the sleep state of detection user using this new grader.
CN201610843527.XA 2016-09-21 2016-09-21 A sleep state detection method and system based on fusion of two classifiers and detectors Pending CN106388780A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610843527.XA CN106388780A (en) 2016-09-21 2016-09-21 A sleep state detection method and system based on fusion of two classifiers and detectors

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610843527.XA CN106388780A (en) 2016-09-21 2016-09-21 A sleep state detection method and system based on fusion of two classifiers and detectors

Publications (1)

Publication Number Publication Date
CN106388780A true CN106388780A (en) 2017-02-15

Family

ID=57997988

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610843527.XA Pending CN106388780A (en) 2016-09-21 2016-09-21 A sleep state detection method and system based on fusion of two classifiers and detectors

Country Status (1)

Country Link
CN (1) CN106388780A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107708191A (en) * 2017-09-30 2018-02-16 北京小米移动软件有限公司 Terminal control method, device and computer-readable recording medium
CN107861605A (en) * 2017-11-06 2018-03-30 北京小米移动软件有限公司 Data processing method and device
CN108903936A (en) * 2018-07-03 2018-11-30 西安科技大学 The Intelligent mining helmet control method merged based on human body information and environmental information
CN111356401A (en) * 2017-11-29 2020-06-30 威里利生命科学有限责任公司 Continuous detection and monitoring of cardiac arrhythmias using wearable sensors and cloud residency analysis
CN112545525A (en) * 2020-11-30 2021-03-26 中国科学技术大学 Electrocardiogram data classification method, device and system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102438515A (en) * 2008-11-14 2012-05-02 索尔克生物学研究所 Methods of identifying sleep and waking patterns and uses
CN104573630A (en) * 2014-12-05 2015-04-29 杭州电子科技大学 Multiclass brain electrical mode online identification method based on probability output of twin support vector machine
CN104834946A (en) * 2015-04-09 2015-08-12 清华大学 Method and system for non-contact sleep monitoring
CN105286890A (en) * 2015-09-22 2016-02-03 江西科技学院 Driver sleepy state monitoring method based on electroencephalogram signal

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102438515A (en) * 2008-11-14 2012-05-02 索尔克生物学研究所 Methods of identifying sleep and waking patterns and uses
CN104573630A (en) * 2014-12-05 2015-04-29 杭州电子科技大学 Multiclass brain electrical mode online identification method based on probability output of twin support vector machine
CN104834946A (en) * 2015-04-09 2015-08-12 清华大学 Method and system for non-contact sleep monitoring
CN105286890A (en) * 2015-09-22 2016-02-03 江西科技学院 Driver sleepy state monitoring method based on electroencephalogram signal

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107708191A (en) * 2017-09-30 2018-02-16 北京小米移动软件有限公司 Terminal control method, device and computer-readable recording medium
CN107861605A (en) * 2017-11-06 2018-03-30 北京小米移动软件有限公司 Data processing method and device
CN111356401A (en) * 2017-11-29 2020-06-30 威里利生命科学有限责任公司 Continuous detection and monitoring of cardiac arrhythmias using wearable sensors and cloud residency analysis
CN111356401B (en) * 2017-11-29 2024-03-26 威里利生命科学有限责任公司 Continuous detection and monitoring of cardiac arrhythmias using wearable sensors and cloud-resident analysis
CN108903936A (en) * 2018-07-03 2018-11-30 西安科技大学 The Intelligent mining helmet control method merged based on human body information and environmental information
CN108903936B (en) * 2018-07-03 2021-01-26 西安科技大学 Intelligent mining helmet control method based on human body information and environment information fusion
CN112545525A (en) * 2020-11-30 2021-03-26 中国科学技术大学 Electrocardiogram data classification method, device and system
CN112545525B (en) * 2020-11-30 2022-05-13 中国科学技术大学 Electrocardiogram data classification method, device and system

Similar Documents

Publication Publication Date Title
CN106388780A (en) A sleep state detection method and system based on fusion of two classifiers and detectors
CN110811609B (en) Epileptic spike intelligent detection device based on self-adaptive template matching and machine learning algorithm fusion
CN111340142B (en) Epilepsia magnetoencephalogram spike automatic detection method and tracing positioning system
CN109843163A (en) For marking dormant method and system
CN110432898A (en) A kind of epileptic attack eeg signal classification system based on Nonlinear Dynamical Characteristics
CN104173046B (en) A kind of extracting method of color indicia Amplitude integrated electroencephalogram
CN113180691B (en) Three-channel sleep apnea and hypopnea syndrome recognition device
CN103405225B (en) A kind of pain that obtains feels the method for evaluation metrics, device and equipment
CN107887032A (en) A kind of data processing method and device
CN106473705A (en) Brain-electrical signal processing method for sleep state monitoring and system
CN107205652A (en) The sleep analysis system with automatic mapping is generated with feature
CN110123342A (en) A kind of network addiction detection method and system based on brain wave
Paisarnsrisomsuk et al. Deep Sleep: Convolutional neural networks for predictive modeling of human sleep time-signals
CN113768519A (en) Method for analyzing consciousness level of patient based on deep learning and resting state electroencephalogram data
CN106333676B (en) The annotation equipment of EEG signals data type under waking state
CN111513675A (en) Amplitude-integrated electroencephalogram-based neonatal sleep-wake cycle detection method
CN114886388A (en) Evaluation method and device for quality of electroencephalogram signal in anesthesia depth monitoring process
CN106333681A (en) Sleep state monitoring method and system based on self learning
CN111067513A (en) Sleep quality detection key brain area judgment method based on characteristic weight self-learning
CN106388813A (en) A sleep state identification model training method and system based on electroencephalogram signals
CN106618486A (en) Sleep state recognition method and system in intelligent assistant sleep
CN106333680A (en) Sleep state detection method and system based on fusion of multiple classifiers
CN106333678A (en) Method and system for detecting brain wave at sleep state in electroencephalogram
CN106377251A (en) Sleep state identification model training method and sleep state identification model training system based on electroencephalogram
CN106175698B (en) Sleep cycle detection device in sleep state analysis

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20170215

RJ01 Rejection of invention patent application after publication