CN106388812A - A marking method and system for the data types of electroencephalogram signals in a waking state - Google Patents
A marking method and system for the data types of electroencephalogram signals in a waking state Download PDFInfo
- Publication number
- CN106388812A CN106388812A CN201610840458.7A CN201610840458A CN106388812A CN 106388812 A CN106388812 A CN 106388812A CN 201610840458 A CN201610840458 A CN 201610840458A CN 106388812 A CN106388812 A CN 106388812A
- Authority
- CN
- China
- Prior art keywords
- eeg signals
- electro
- area
- spike
- sample
- 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
- A61B5/369—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
- A61B5/316—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
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
-
- 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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Psychology (AREA)
- Ophthalmology & Optometry (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention relates to a marking method and system for the data types of electroencephalogram signals in a waking state. The method comprises the steps of: after a user starts a sleep process, collecting real-time electrooculogram signal and electroencephalogram signal samples of a user according to a set frame length and performing wavelet decomposition and low frequency range reconstruction to obtain electrooculogram signals and electroencephalogram signals; according to electroencephalogram signals and electrooculogram signals at the same moment, detecting blinking activities on the electrooculogram signals, and performing threshold value judgment on the sample entropy; if blinking activities exist or the sample entropy is greater than the threshold valve, marking the signal type of the current electroencephalogram signal samples as a waking state. The method can protect electroencephalogram signals against interference, can detect the waking state of the electroencephalogram signals accurately, and can perform effective data type marking; the identification accuracy of an individual classifier obtained by training electroencephalogram signal samples marked by using the method is improved and the reliability of individual sleep state detection results in a later period can be improved.
Description
Technical field
The present invention relates to assisting sleep technical field, the EEG signals data type under more particularly to a kind of waking state
Mask method and system.
Background technology
Some auxiliary equipments have been had to carry out assisting people to fall asleep at present on the market, i.e. assisting sleep, to improve user
Sleep quality.Sleep state analysis is the important means that auxiliary equipment understands user's sleep quality, and in the process, needs
User's sleep state is detected, accurately to know that user is clear-headed or asleep state, then can carry out corresponding
Intervening measure.
Polysomnogram (Polysomnography, PSG), also known as sleep electroencephalogram, is clinically to examine for sleep at present
" goldstandard " breaking and analyzing.Polysomnogram is analyzed to sleep using multiple vital signs, in these sign,
Brain electricity is in core status;Using brain wave 4 species rhythm:δ ripple (1-3Hz), θ ripple (4-7Hz), α ripple (8-12Hz), β ripple (14-
Frequency characteristic 30Hz).Brain wave according to the different rhythm and pace of moving things and ocular movement feature, in addition to the clear-headed stage, sleep is permissible
It is divided into non-dynamic sleep (No Rapid Eye Movement Sleep, NREM sleep) and the dynamic sleep (Rapid that is sharp-eyed of being sharp-eyed
Eye Movement Sleep, REM sleep) cycle.Wherein non-dynamic sleep of being sharp-eyed can be divided into 4 periods again:The S1 phase is (completely
The transition stage regained consciousness to sleep), the S2 phase (shallow sleep the stage), the S3 phase (middle deep sleep), the S4 phase (sound sleep phase).
Generally, whether detection user is in waking state, is the signal (δ by using brain wave in 4 frequency ranges
Wave frequency section, θ wave frequency section, α wave frequency section and β wave frequency section) train the identification model (grader) of waking state EEG signals are entered
Row identification, the universal identification model that these identification models are often trained using other people brain wave, but due to brain electricity
The individual human specific of signal is very strong, and the intensity of brain electricity very weak (brain electricity is microvolt rank, and electrocardio is millivolt rank), in signal
Easily disturbed by outer signals during collection.
In the process, when needing the personal grader of training it is necessary to the number of personal EEG signals sample to collection
It is labeled according to type, so just can carry out self study and test to the data of marking types, train and be more applicable for
The personal grader of people, and when EEG signals are carried out detection mark using universal identification model, as previously described, due to brain
The very weak type being easily interfered, marking eeg signal sample using universal identification model of the intensity of the signal of telecommunication, easily
It is mixed into interference component, leads to the recognition accuracy of personal grader training out relatively low, have impact on the later stage to personal sleep shape
The reliability of state testing result.
Content of the invention
Based on this it is necessary to be directed to the problems referred to above, provide a kind of mark of the EEG signals data type under waking state
Method and system, can detect the EEG signals under waking state exactly, and carry out the mark of data type.
A kind of mask method of the EEG signals data type under waking state, including:
After user starts sleep procedure, according to the real-time electro-ocular signal setting frame length collection user and EEG signals sample
This;
Respectively described real-time electro-ocular signal and EEG signals sample are carried out with wavelet decomposition, and little according to setting low-frequency range
Wave system number carries out signal reconstruction and obtains electro-ocular signal and EEG signals;
Dependency according to synchronization EEG signals and electro-ocular signal and the feature of nictation eye electrical waveform, in eye telecommunications
Detection nictation activity on number;And the Sample Entropy of described EEG signals is compared with default sample entropy threshold;
When the movable or described Sample Entropy of nictation being detected on electro-ocular signal more than described sample entropy threshold, forebrain electricity will be worked as
The signal type of sample of signal is labeled as waking state.
A kind of labeling system of the EEG signals data type under waking state, including:
Signal acquisition module, for after user starts sleep procedure, according to the real-time eye setting frame length collection user
The signal of telecommunication and EEG signals sample;
Signal reconstruction module, for respectively wavelet decomposition being carried out to described real-time electro-ocular signal and EEG signals sample, and
Wavelet coefficient according to setting low-frequency range carries out signal reconstruction and obtains electro-ocular signal and EEG signals;
Detection comparison module, for the dependency according to synchronization EEG signals and electro-ocular signal and nictation eye electric wave
The feature of shape, detects nictation activity on electro-ocular signal;And by the Sample Entropy of described EEG signals and default sample entropy threshold
It is compared;
Sample labeling module, for when detect on electro-ocular signal the movable or described Sample Entropy of nictation be more than described Sample Entropy
During threshold value, the signal type of current EEG signals sample is labeled as waking state.
The mask method of EEG signals data type under above-mentioned waking state and system, start sleep procedure in user
Afterwards, according to the real-time electro-ocular signal setting frame length collection user and EEG signals sample, wavelet decomposition and low-frequency range weight are carried out
Build and obtain electro-ocular signal and EEG signals;According to synchronization EEG signals and electro-ocular signal, detection nictation on electro-ocular signal
Activity, and threshold decision is carried out to Sample Entropy, when there is nictation activity or Sample Entropy more than threshold value, by current EEG signals sample
Signal type be labeled as waking state.Mark the type of eeg signal sample by the program, brain telecommunications can be avoided
Number it is interfered, detects the waking state of EEG signals exactly, and carry out effective data type mark so that utilizing this mark
The recognition accuracy of the EEG signals sample training of note personal grader out is higher, also improves the later stage to personal sleep shape
The reliability of state testing result.
Brief description
Fig. 1 is the flow chart of the mask method of EEG signals data type under the waking state of an embodiment;
Fig. 2 is one section of common EEG signals in clear-headed period and electro-ocular signal schematic diagram;
Fig. 3 is electro-ocular signal waveform spike area schematic diagram in sliding window;
Fig. 4 is result schematic diagram nictation activity is detected;
Fig. 5 is the waking state detector concept figure that the mask method based on the present invention is realized;
Fig. 6 is the labeling system structural representation of the EEG signals data type under the waking state of an embodiment.
Specific embodiment
Illustrate the mask method of EEG signals data type under the waking state of the present invention and system below in conjunction with the accompanying drawings
Embodiment.
With reference to shown in Fig. 1, Fig. 1 is the mask method of the EEG signals data type under the waking state of an embodiment
Flow chart, including:
Step S101, after user starts sleep procedure, according to set frame length gather user real-time electro-ocular signal and
EEG signals sample;
In this step, in this step, can be user to be carried out with assisting sleep, during the personal identification model of training, true
In the state of warranty family is clear-headed, starts to carry out EEG signals sample collection to user, related brain fax sense is worn by user
Equipment, the EEG signals that collection user produces in sleep procedure, during collection EEG signals sample, wear phase using user simultaneously
Close eye electricity sensing equipment the real-time electro-ocular signal of user is acquired.
When gathering signal, can be acquired with 30s for a frame, every frame EEG signals are as a sample, subsequently right
Every frame electro-ocular signal and EEG signals are analyzed processing.
Generally, it is contemplated being 10~15 minutes to the normal time for falling asleep of people, when tired/tired out, time for falling asleep is very
To shortening, therefore, start to gather the EEG signals of user under the wide-awake state of user it is believed that starting to gather
It is believed that user is in waking state in setting time section T afterwards.
In one embodiment, if starting to gather the time span of EEG signals sample and real-time electro-ocular signal less than setting
Time T, the EEG signals sample of all collections is labeled as waking state;, that is, user starts taking T=300s (5 minutes) as a example
The EEG signals sample in 300 seconds after collection EEG signals is judged as waking state;As described above, EEG signals sample is
With 30s for a frame, then getting final product Direct Mark in the data type of front 10 brains electricity sample is waking state.
Step S102, carries out wavelet decomposition to described real-time electro-ocular signal and EEG signals sample respectively, and according to setting
The wavelet coefficient of low-frequency range carries out signal reconstruction and obtains electro-ocular signal and EEG signals;
Respectively real-time electro-ocular signal and EEG signals sample are carried out with wavelet decomposition first, and little according to setting low-frequency range
Ripple coefficient reconstruction electro-ocular signal and EEG signals, in order to avoid the essential information of the interference stick signal simultaneously of high-frequency noise, I
Compared with being analyzed to EEG signals in low-frequency range.For the convenience calculating, the upper frequency limit (0~8Hz) of θ ripple can be selected
Carry out wavelet decomposition and reconstruction.
For the convenience calculating, the upper frequency limit of the θ ripple (mainly 4-7Hz) of EEG signals can be selected to be rebuild,
I.e. 0~8Hz.
Step S103, the spy of the dependency according to synchronization EEG signals and electro-ocular signal and nictation eye electrical waveform
Levy, nictation activity is detected on electro-ocular signal;And the Sample Entropy of described EEG signals is compared with default sample entropy threshold
Relatively;
For detection nictation activity:
In the sleep cycle of normal person, nictation is an activity specific to lucid interval, due to electro-ocular signal during nictation
Amplitude higher, EEG signals can be interfered.
With reference to Fig. 2, Fig. 2 is one section of common EEG signals in clear-headed period and electro-ocular signal schematic diagram;In figure solid line is
EEG signals, dotted line is electro-ocular signal.By in figure as can be seen that nictation activity all produces in EEG signals and electro-ocular signal
Downward spike, nictation activity shows as the waveform with the high peak of short time on electroencephalogram, and this is also nictation eye electricity
The feature of waveform.
In above-mentioned detection process, using the dependency between the EEG signals of synchronization and electro-ocular signal, in conjunction with blinking
The wave character of eye electro-ocular signal is judged.
In an embodiment, the method for detection nictation activity on electro-ocular signal, can be as follows:
(1) intercept described low frequency eye signal using the sliding window with setting signal amplitude range and time span;
The present invention utilizes the similarity degree of the signal amplitude, electro-ocular signal and EEG signals in a sliding window, spike
Acuity and spike duration detecting in sliding window whether there is nictation activity, during this sliding window checking electroencephalogram
Slide on countershaft, intercept electro-ocular signal waveform.
Because the time of nictation is generally less than 0.4 second, therefore can be in the interior detection nictation letter of a slightly larger sliding window
Number, the such as sampling time length of 0.6 times of setting, i.e. n=0.6 fs, n are sliding window length, and fs is adopting of electro-ocular signal
Sample rate.
The amplitude of electro-ocular signal can deduct minima (p by the maximum of electro-ocular signal in sliding windowmax-pmin)
Mode is obtained, and generally, the amplitude of sliding window could be arranged between 75 microvolts to 300 microvolts.
(2) calculate electro-ocular signal and the correlation coefficient of the waveform of synchronization EEG signals in sliding window respectively, slide
The persistent period of the acuity parameter of electro-ocular signal waveform spike and spike in window;
Here acuity parameter be characterize spike feature meet the high peak of short time during nictation waveform strong and weak
Parameter.
In one embodiment, calculate the acuity parameter of electro-ocular signal waveform spike in sliding window, can include
As follows:
A () calculates upper area area in sliding window for the electro-ocular signal waveform and lower area area respectively, calculate
Formula is as follows:
In formula, piFor the electro-ocular signal in sliding window, pmaxFor the maximum of electro-ocular signal in sliding window, pminFor cunning
The minima of electro-ocular signal, area in dynamic windowupRepresent upper area area, areadownRepresent lower area area;
(b) according to the area of described upper area area and electro-ocular signal waveform spike described in lower area areal calculation,
Computing formula is as follows:
In formula, blinkareaRepresent the area of spike, if represents and meets condition;
With reference to shown in Fig. 3, Fig. 3 is electro-ocular signal waveform spike area schematic diagram in sliding window, the spike in two kinds of directions
Upper and lower part region area as illustrated, left figure spike direction upwards, the spike direction of right figure is downward.
C (), according to spike areal calculation acuity parameter, computing formula is as follows:
blinkratio=blinkarea/in-blinkarea
In formula, blinkratioRepresent acuity parameter, in-blinkareaRepresent the area of non-peak position, here point
It is ratio between upper area area and lower area area that sharp extent index can also be converted into.
The method calculating the persistent period of electro-ocular signal waveform spike in sliding window, can include as follows:
(d) according to the direction of described upper area area and electro-ocular signal waveform spike described in lower area areal calculation,
Computing formula is as follows:
In formula, blinkdirectionRepresent spike direction, be labeled as 1 expression spike downwards, be labeled as -1 expression spike to
On;
E (), when spike is downward, the Local modulus maxima according to spike both sides calculates the persistent period of spike;Or in point
Peak upwards when, calculate the persistent period of spike according to the local local minizing point of spike both sides;Computing formula is as follows:
blinkts=vertexright-vertexleft,
In formula, blinktsRepresent the persistent period of spike, vertexrightRepresent the right side summit moment of spike, represent point
In the leftmost vertices moment at peak, right_min_loca represents the local minizing point on the right side of spike, and right_max_loca represents
Local modulus maxima on the right side of spike, left_min_loca represents the local minizing point on the left of spike, left_max_loca
Represent the Local modulus maxima on the left of spike, s.t. represents constraints.
(3) if described correlation coefficient, acuity parameter and persistent period respectively meet default correlation coefficient threshold,
Acuity parameter threshold and duration threshold, judge that in this sliding window, electro-ocular signal has nictation activity;
Specifically, when the area of the similarity degree of the signal amplitude in sliding window, electro-ocular signal and EEG signals, spike
When all meeting condition with the persistent period, that is, think that current sliding window mouth has nictation activity;
For correlation coefficient threshold it is considered that, correlation coefficient be more than 0.7 two vectors just substantially may be considered
Related it is contemplated that the interference to EEG signals for electro-ocular signal during nictation, the phase between electro-ocular signal and EEG signals during nictation
Close coefficient threshold and can be set to 0.9;For acuity parameter threshold, typically could be arranged to 0.3;For spike lasting when
Between threshold value, according to wink time be usually the 0.3-0.4 second, therefore, duration threshold can be set to 0.3 second.
Sample Entropy is compared with default sample entropy threshold:
Calculate the Sample Entropy of described EEG signals first, then this Sample Entropy is compared with default sample entropy threshold
Relatively;
Sample Entropy is a kind of tolerance of time serieses complexity, is widely used in the detection of epilepsy.In sleep cycle
6 stages in, the Sample Entropy highest of the EEG signals in clear-headed stage, the present invention utilize EEG signals Sample Entropy size Lai
Judge whether user is waking state, by setting sample entropy threshold, be compared with the Sample Entropy of EEG signals.
In above-mentioned comparison procedure, the selection of sample entropy threshold is also it is critical that a ring.Detection in current epilepsy
Etc. the empirical data that obtains of aspect, be not appropriate for used in sleep state analyze in accurate judgement to waking state.
In one embodiment, calculating sample entropy threshold with the following method can be adopted, including:
First the EEG signals in setting time are divided into multiple samples, and calculate the sample of each EEG signals sample respectively
This entropy, obtains Sample Entropy set;
In the process it is assumed that using 30s be a frame, collection 300 seconds EEG signals processed, then just have 10 here
Individual sample, now can calculate the Sample Entropy set including 10 Sample Entropy.
Then sample entropy threshold is calculated according to described Sample Entropy set;As embodiment, the computing formula of sample entropy threshold
Can be as follows:
sampen_vali=sampen (y [p_start:p_end])
P_start=(i-1) * time_length*fs+1
P_end=t_start+time_length*fs-1
P_end < T fs
In formula, wherein sampen_thre is sample entropy threshold, sampen_valiFor i-th sample in Sample Entropy set
Sample Entropy, sampen is the computing seeking Sample Entropy, and it inputs y [p_start:P_end] it is EEG signals y in pth _ start point
Start the part to pth _ end point, time_length is the time span of each sample calculating Sample Entropy, fs is brain
The sample rate of the signal of telecommunication, T is to start the setting time after gathering EEG signals, and v is setup parameter.
In above-mentioned numerical procedure, the value of parameter v is extremely important, can control recognition accuracy by parameter v;Cause
This, in order to improve recognition accuracy, can be calculated by equation below for parameter v value:
Assume that the set X of Sample Entropy during the clear-headed stage obeys standard normal distribution, in set X, i-th element representation is:
Wherein,
Now, x=v
Integration according to Standard Normal Distribution:
Wherein, P (X≤x) represents that the value in the set X of Sample Entropy is less than the probability of x, thus can calculate, with T=
As a example 300s, time_length=30s, when parameter v=2.58, the probability that the value of Sample Entropy set X is less than x is 99.5%.
Sample Entropy in view of the EEG signals in clear-headed stage is maximum, the sample entropy threshold being calculated based on above-described embodiment
Sampen_thre is it is known that the EEG signals that Sample Entropy is more than sampen_thre are judged as that waking state can obtain compared with Gao Zhun
Really rate.
Step S104, when the movable or described Sample Entropy of nictation being detected on electro-ocular signal more than described sample entropy threshold,
The signal type of current EEG signals sample is labeled as waking state;
In the sleep cycle of normal person, nictation is an activity specific to lucid interval, and therefore, sleep state was analyzed
Cheng Zhong, if within certain a period of time, detected nictation activity, you can thinks that current EEG signals sample is belonging to clear-headed shape
State.
Compared with sample entropy threshold by the Sample Entropy calculating the EEG signals of present frame, if Sample Entropy is more than sample
Entropy threshold, you can judge current EEG signals sample as waking state.
The arbitrary establishment of two above condition, you can judge that current EEG signals sample belongs to the brain telecommunications under waking state
Number, therefore the signal type of this EEG signals sample is labeled as waking state.
With reference to Fig. 4, Fig. 4 is result schematic diagram nictation activity is detected, and in figure solid line and dotted line are respectively through small echo
EEG signals after transform reconstruction and electro-ocular signal.On electro-ocular signal, circle has marked the spike that nictation activity is formed, can
To find although the nictation amount of activity detecting is less, but false drop rate is extremely low.In actual applications, in order to avoid flase drop
Go out nictation activity and bring mistake when data type is marked, taking 30 seconds electro-ocular signals of a frame as a example, when in a frame signal extremely
When will detect the nictation activity of 2 or more than 2 less, just confirm this data type, by the signal type mark of EEG signals sample
Note as waking state, this makes it possible to mark accuracy is greatly improved.
The scheme of above-described embodiment, is judged by detecting nictation activity or EEG signals Sample Entropy, to judge EEG signals
The type of sample and carry out EEG signals data type mark, there is higher accuracy rate.The technology of the present invention is for part
Disturb more serious signal, recall rate may be affected, but not interfere with accuracy rate, go for sleep state analysis
In, in the personal identification model of training, as detector, the EEG signals data type under waking state is labeled.
With reference to shown in Fig. 5, Fig. 5 is the waking state detector concept figure that the mask method based on the present invention is realized, collection
After EEG signals sample and real-time electro-ocular signal, wavelet decomposition and low-frequency range are rebuild, lived by detecting the nictation in electro-ocular signal
Dynamic, and EEG signals are carried out with calculating and the threshold decision of Sample Entropy;If acquisition time in setting time T, detect and blink
Eye activity or if Sample Entropy exceedes threshold value, the arbitrary establishment of three, then EEG signals sample is carried out with the mark of data type.
The mask method of the EEG signals data type under the waking state of the embodiment of the present invention, utilizes brain telecommunications in many cases
In number waking state test experience carrying out, the data type of EEG signals sample has obtained accurate judgement, by waking state
Accurate judgement, waking state detector can be formed, if this detector output result is "Yes", that is, be labeled as clear-headed shape
State, if output result is "No", due to neither waking state, but nor be considered sleep state, then abandon this sample.
With reference to shown in Fig. 6, Fig. 6 is the labeling system knot of the EEG signals data type under the waking state of an embodiment
Structure schematic diagram, including:
Signal acquisition module 101, for, after user starts sleep procedure, gathering the real-time of user according to setting frame length
Electro-ocular signal and EEG signals sample;
Signal reconstruction module 102, for respectively wavelet decomposition being carried out to described real-time electro-ocular signal and EEG signals sample,
And carry out signal reconstruction and obtain electro-ocular signal and EEG signals according to the wavelet coefficient setting low-frequency range;
Detection comparison module 103, for the dependency according to synchronization EEG signals and electro-ocular signal and nictation eye
The feature of electrical waveform, detects nictation activity on electro-ocular signal;And by the Sample Entropy of described EEG signals and default Sample Entropy
Threshold value is compared;
Sample labeling module 104, for when detect on electro-ocular signal the movable or described Sample Entropy of nictation be more than described sample
During this entropy threshold, the signal type of current EEG signals sample is labeled as waking state.
Under the labeling system of EEG signals data type under the waking state of the present invention and the waking state of the present invention
The mask method of EEG signals data type corresponds, the mark side of the EEG signals data type under above-mentioned waking state
Technical characteristic that the embodiment of method illustrates and its advantage are all applied to the mark of the EEG signals data type under waking state
In the embodiment of injection system, 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 mask method of the EEG signals data type under waking state is it is characterised in that include:
After user starts sleep procedure, according to the real-time electro-ocular signal setting frame length collection user and EEG signals sample;
Respectively described real-time electro-ocular signal and EEG signals sample are carried out with wavelet decomposition, and the wavelet systems according to setting low-frequency range
Number carries out signal reconstruction and obtains electro-ocular signal and EEG signals;
Dependency according to synchronization EEG signals and electro-ocular signal and the feature of nictation eye electrical waveform, on electro-ocular signal
Detection nictation activity;And the Sample Entropy of described EEG signals is compared with default sample entropy threshold;
When the movable or described Sample Entropy of nictation being detected on electro-ocular signal more than described sample entropy threshold, by current EEG signals
The signal type of sample is labeled as waking state.
2. the mask method of the EEG signals data type under waking state according to claim 1 is it is characterised in that go back
Including:
If starting to gather EEG signals sample and the time span of real-time electro-ocular signal being less than setting time T, by all collections
EEG signals sample is labeled as waking state.
3. the mask method of the EEG signals data type under waking state according to claim 1 is it is characterised in that institute
State the dependency according to synchronization EEG signals and electro-ocular signal and the feature of eye electrical waveform of blinking, electro-ocular signal is examined
The step surveying nictation activity includes:
Intercept described low frequency eye signal using the sliding window with setting signal amplitude range and time span;
Calculate the correlation coefficient of the waveform of electro-ocular signal and synchronization EEG signals in sliding window, eye in sliding window respectively
The acuity parameter of electric signal waveform spike and the persistent period of spike;
If described correlation coefficient, acuity parameter and persistent period respectively meet default correlation coefficient threshold, sharp journey
Degree parameter threshold and duration threshold, judge that in this sliding window, electro-ocular signal has nictation activity.
4. the mask method of the EEG signals data type under waking state according to claim 3 is it is characterised in that institute
The step stating the acuity parameter of electro-ocular signal waveform spike in calculating sliding window includes:
Calculate upper area area in sliding window for the electro-ocular signal waveform and lower area area respectively, computing formula is such as
Under:
In formula, piFor the electro-ocular signal in sliding window, pmaxFor the maximum of electro-ocular signal in sliding window, pminFor sliding window
The minima of electro-ocular signal, area in mouthfulupRepresent upper area area, areadownRepresent lower area area;
Area according to described upper area area and electro-ocular signal waveform spike described in lower area areal calculation, computing formula
As follows:
In formula, blinkareaRepresent the area of spike, if represents and meets condition;
According to spike areal calculation acuity parameter, computing formula is as follows:
blinkratio=blinkarea/in-blinkarea
In formula, blinkratioRepresent acuity parameter, in-blinkareaRepresent the area of non-peak position.
5. the mask method of the EEG signals data type under waking state according to claim 4 is it is characterised in that institute
The step stating the persistent period of electro-ocular signal waveform spike in calculating sliding window includes:
Direction according to described upper area area and electro-ocular signal waveform spike described in lower area areal calculation, computing formula
As follows:
In formula, blinkdirectionRepresent spike direction, be labeled as 1 expression spike downwards, be labeled as -1 expression spike upwards;
When spike is downward, the Local modulus maxima according to spike both sides calculates the persistent period of spike;Or in spike upwards
When, the local local minizing point according to spike both sides calculates the persistent period of spike;Computing formula is as follows:
blinkts=vertexright-vertexleft,
In formula, blinktsRepresent the persistent period of spike, vertexrightRepresent the right side summit moment of spike, represent spike
In the leftmost vertices moment, right_min_loca represents the local minizing point on the right side of spike, and right_max_loca represents spike
The Local modulus maxima on right side, left_min_loca represents the local minizing point on the left of spike, and left_max_loca represents
Local modulus maxima on the left of spike, s.t. represents constraints.
6. the mask method of the EEG signals data type under waking state according to claim 5 is it is characterised in that institute
The amplitude stating sliding window is 75 microvolts to 300 microvolts, the correlation coefficient between electro-ocular signal and EEG signals during described nictation
Threshold value is 0.9, and described acuity parameter threshold is 0.3, and described duration threshold is 0.3 second.
7. the mask method of the EEG signals data type under waking state according to claim 1 is it is characterised in that institute
The computing formula stating sample entropy threshold is as follows:
sampen_vali=sampen (y [p_start:p_end])
P_start=(i-1) * time_length*fs+1
P_end=t_start+time_length*fs-1
P_end < T fs
In formula, wherein sampen_thre is sample entropy threshold, sampen_valiSample for i-th sample in Sample Entropy set
Entropy, sampen is the computing seeking Sample Entropy, and it inputs y [p_start:P_end] start in pth _ start point for EEG signals y
Part to pth _ end point, time_length is the time span of each sample calculating Sample Entropy, and fs is brain telecommunications
Number sample rate, T be start gather EEG signals after setting time, v be setup parameter.
8. the mask method of the EEG signals data type under waking state according to claim 7 is it is characterised in that institute
The value stating parameter v is as follows:
Wherein,
X=v
In formula, X represents Sample Entropy set, XiRepresent i-th element in Sample Entropy set X, Φ (x) represents standard normal distribution letter
The integration of number, P (X≤x) represents that the value in the set X of Sample Entropy is less than the probability of x.
9. the mask method of the EEG signals data type under waking state according to claim 8 is it is characterised in that institute
State T=300s, time_length=30s, v=2.58.
10. a kind of labeling system of the EEG signals data type under waking state is it is characterised in that include:
Signal acquisition module, for after user starts sleep procedure, according to the real-time eye telecommunications setting frame length collection user
Number and EEG signals sample;
Signal reconstruction module, for respectively wavelet decomposition being carried out to described real-time electro-ocular signal and EEG signals sample, and according to
The wavelet coefficient of setting low-frequency range carries out signal reconstruction and obtains electro-ocular signal and EEG signals;
Detection comparison module, for the dependency according to synchronization EEG signals and electro-ocular signal and eye electrical waveform of blinking
Feature, detects nictation activity on electro-ocular signal;And the Sample Entropy of described EEG signals is carried out with default sample entropy threshold
Relatively;
Sample labeling module, for when detect on electro-ocular signal the movable or described Sample Entropy of nictation be more than described sample entropy threshold
When, the signal type of current EEG signals sample is labeled as waking state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610840458.7A CN106388812B (en) | 2016-09-21 | 2016-09-21 | The mask method and system of EEG signals data type under waking state |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610840458.7A CN106388812B (en) | 2016-09-21 | 2016-09-21 | The mask method and system of EEG signals data type under waking state |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106388812A true CN106388812A (en) | 2017-02-15 |
CN106388812B CN106388812B (en) | 2019-06-11 |
Family
ID=57998304
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610840458.7A Active CN106388812B (en) | 2016-09-21 | 2016-09-21 | The mask method and system of EEG signals data type under waking state |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106388812B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110232976A (en) * | 2019-07-01 | 2019-09-13 | 上海电机学院 | A kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105105714A (en) * | 2015-08-26 | 2015-12-02 | 吴建平 | Sleep period separating method and system |
-
2016
- 2016-09-21 CN CN201610840458.7A patent/CN106388812B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105105714A (en) * | 2015-08-26 | 2015-12-02 | 吴建平 | Sleep period separating method and system |
Non-Patent Citations (1)
Title |
---|
和卫星等: "基于样本熵的睡眠脑电分期", 《江苏大学学报》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110232976A (en) * | 2019-07-01 | 2019-09-13 | 上海电机学院 | A kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric |
Also Published As
Publication number | Publication date |
---|---|
CN106388812B (en) | 2019-06-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200367800A1 (en) | Method for identifying driving fatigue based on cnn-lstm deep learning model | |
CN106175754B (en) | Waking state detection device in sleep state analysis | |
CN104173064B (en) | Lie detecting method based on analysis of heart rate variability and device of detecting a lie | |
US20220280096A1 (en) | Ssvep-based attention evaluation method, training method, and brain-computer interface | |
CN110135285B (en) | Electroencephalogram resting state identity authentication method and device using single-lead equipment | |
CN103610447A (en) | Mental workload online detection method based on forehead electroencephalogram signals | |
CN104461007A (en) | Driver-car interactive system assisting driver based on electroencephalograms | |
CN104173046A (en) | Method for extracting color marked amplitude-integrated electroencephalogram | |
CN106333676B (en) | The annotation equipment of EEG signals data type under waking state | |
CN113349780A (en) | Method for evaluating influence of emotional design on online learning cognitive load | |
CN101382837B (en) | Computer mouse control device of compound motion mode | |
CN111067513B (en) | Sleep quality detection key brain area judgment method based on characteristic weight self-learning | |
Qin et al. | Stress level evaluation using BP neural network based on time-frequency analysis of HRV | |
CN109009098A (en) | A kind of EEG signals characteristic recognition method under Mental imagery state | |
CN106344008B (en) | Waking state detection method and system in sleep state analysis | |
CN106333677A (en) | Blinking activity detection method and blinking activity detection system in sleep state analysis | |
CN106175698B (en) | Sleep cycle detection device in sleep state analysis | |
CN106361327B (en) | Waking state detection method and system in sleep state analysis | |
CN106388812B (en) | The mask method and system of EEG signals data type under waking state | |
CN106333678A (en) | Method and system for detecting brain wave at sleep state in electroencephalogram | |
CN106333675B (en) | The mask method and system of EEG signals data type under waking state | |
CN106333674A (en) | Sleep cycle detection method and sleep cycle detection system in sleep state analysis | |
CN106377250B (en) | The tagging equipment of EEG signals data type under sleep state | |
Cecotti et al. | Suboptimal sensor subset evaluation in a p300 brain-computer interface | |
Rezaee et al. | EEG-Based Driving Fatigue Recognition Using Hybrid Deep Transfer Learning Approach |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |