CN110327040A - Sleep stage method and system based on cloud platform - Google Patents
Sleep stage method and system based on cloud platform Download PDFInfo
- Publication number
- CN110327040A CN110327040A CN201910331566.5A CN201910331566A CN110327040A CN 110327040 A CN110327040 A CN 110327040A CN 201910331566 A CN201910331566 A CN 201910331566A CN 110327040 A CN110327040 A CN 110327040A
- Authority
- CN
- China
- Prior art keywords
- sleep
- cloud platform
- user
- eeg signals
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- A61B5/48—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
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Psychology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The sleep stage method and system based on cloud platform that the present invention provides a kind of, comprising: obtain the personal information that user inputs on mobile terminals, and the input parameter as personalized sleep by stages；The corresponding EEG signals for wearing front-end collection user are controlled, and EEG signals are sent to cloud platform；Cloud platform application Algorithms of Discrete Wavelet Transform pre-processes the eeg data of acquisition, obtains the rhythm and pace of moving things wave characteristic of user's EEG signals, and as one of the input feature vector amount of personalized sleep Staging System based on convolutional neural networks；According to the rhythm and pace of moving things wave characteristic of the EEG signals of input, real-time sleep stage is carried out in conjunction with age of user, gender and historical data, while corresponding running parameter being transmitted back to and wears front end, carry out adaptive sleep regulation；Cloud platform records the sleep state delta data of user in real time, and after the completion of entire sleep stage process, mobile terminal will obtain the sleep state data of record from cloud platform.
Description
Technical field
The invention belongs to medical security technical fields, and in particular to a kind of sleep stage method based on cloud platform and be
System.
Background technique
Insomnia can not only make one to occur that absent minded, working efficiency is low, growth hormone synthesis is disorderly with secreting function
The symptoms such as random, serious insomnia also results in human body memory and declines with brain function remodelling capability, under resistance and self-rehabilitation ability
It is the problems such as drop, very big to Health Impact.
With the acceleration of people's life rhythm, it has a sleepless night along with pressure with deeply worried without stopping pregnancy life, has seriously affected people
Mental attitude and physically and mentally healthy, have resulted in more and more crowds and be in sub-health state, at the same time, people also gradually anticipate
The importance of sleep quality is known, people improve the unrest that mistaken ideas existing for aspect result in assisting sleep means to sleep quality
With with abuse phenomenon.Therefore, demand of the people to intelligentized auxiliary sleeping device is growing day by day.
Currently, correlation assisting sleep class product category is a lot of both at home and abroad, each products characteristics are summarized as follows:
It is that collected eeg signal is transmitted by Bluetooth technology to user APP mostly in system design aspect.Its
The course of work is: after collecting eeg signal, being transferred to APP by Bluetooth technology, the processing of signal is carried out on APP and is divided
Analysis.Its system structure is simple, low in cost, but since function algorithm is limited by mobile phone storage space and arithmetic speed,
Its expansibility is low, and since this kind of APP is mostly to work offline, cannot achieve the personalized sleep with individual subscriber feature point
Phase system.
In terms of sleep stage system, seen sleep stage system is divided only in accordance with universality index mostly on the market
Phase, staging scale is single, and evaluating result lacks individual specific aim.And in fact, the sleep state of people is by age, gender, body
The influence of body factor etc., staging scale should vary with each individual.
Summary of the invention
The present invention status growing day by day for demand of the people to intelligentized auxiliary sleeping device, the invention proposes
A kind of high targetedly personalized sleep method by stages, can not only provide high specific aim in conjunction with user information and its historical data
Sleep stage, moreover it is possible to sleep stage result is supplied to assisting sleep system to carry out high auxiliary adjustment of targetedly sleeping.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of sleep stage method based on cloud platform is provided, comprising the following steps:
Step 1: obtaining the personal information that inputs on mobile terminals of user, and as personalized sleep by stages defeated
Enter parameter；
Step 2: the corresponding EEG signals for wearing front-end collection user of control, and by EEG signals real-time transmission to Yun Ping
Platform；
Step 3: cloud platform pre-processes the eeg data of acquisition, obtains the rhythm and pace of moving things wave characteristic of user's EEG signals,
And as one of the input feature vector amount of personalized sleep Staging System based on convolutional neural networks；
Step 4: personalized sleep Staging System according to the rhythm and pace of moving things wave characteristics of the EEG signals of input, in conjunction with age of user,
Gender and historical data carry out real-time sleep stage, while corresponding running parameter being transmitted back to and wears front end, to carry out
Adaptive sleep regulation；
Step 5: cloud platform records the sleep state delta data of user in real time, after the completion of entire sleep stage process,
Mobile terminal will obtain the sleep state data of record from cloud platform, and be presented to user.
Above-mentioned technical proposal is connect, the sleep procedure of people was divided into for 6 phases: awakening by the sleep stage criterion of the cloud platform
Phase WAKE, rapid-eye-movement sleep phase REM and 4 NREM sleep phase NREM, wherein NREM is divided into 1 phase N1 of sleep again, sleeps
Sleep 2 phase N2,3 phase N3 of sleep and 4 phase N4 of sleep, and 1,2 phases of sleep are shallowly to sleep phase LS, and 3,4 phases of sleep are sound sleep phase SWS.
Connect above-mentioned technical proposal, the pretreated detailed process of eeg data are as follows: selection small wave converting method is to EEG signals
Characteristic wave extract, and using the energy feature of characteristic wave as distinguish sleep period temporal signatures；In wavelet transform procedure
In, use db4 wavelet function to carry out the preprocessing process that scale realizes EEG signals for 8 wavelet transformation.
Above-mentioned technical proposal is connect, personal information includes personal gender, the age, height, weight, occupies ground long.
Above-mentioned technical proposal is connect, the EEG signals acquired in step 2 are the simulation EEG signals for wearing front-end collection.
Connect above-mentioned technical proposal, personalized sleep method by stages passes through the personal characteristic information and process user
Input vector of the EEG signals as convolutional neural networks of prime processing, by 5 sleep state values (WAKE, N1, N2, SWS,
REM output vector of the evaluation result) as neural network, with enough sample trainings network, by real output value with
Desired output is compared, and when its error is less than setting value, this group of weight and threshold value that neural network is held are nets
Network passes through the obtained correct internal representation of adaptive learning.
Above-mentioned technical proposal is connect, the algorithm model by stages in the cloud platform sleep stage method includes to use discrete wavelet
Time-frequency characteristics matrix extract layer, convolutional neural networks input layer, convolutional layer Conv1, the pond layer Pool1, convolutional layer of transformation
Conv2, pond layer Pool2, convolutional layer Conv3, full articulamentum FC and output layer.
The sleep stage system based on cloud platform that the present invention also provides a kind of, comprising:
Front end is worn, user's head is worn on, acquires the EEG signals of user, EEG signals are sent to cloud platform；Together
When receive the control parameter that is sent by cloud platform, adaptive sleep regulation is realized with cooperation supplementary module of sleeping.
Mobile terminal obtains the personal information that user inputs on mobile terminals, and as based on convolutional Neural net
One of the input characteristic parameter of the personalized sleep Staging System of network；After the completion of sleep procedure, acquisition is recorded in cloud platform
Sleep state data, and by analysis sleep state data, comparison historical data generate sleep adjustment suggest, then will sleep
The adjustment suggestion that the sleep state of process changes and generates is shown；
Cloud platform is obtained to react and be slept for pre-processing to the eeg data application wavelet transform of acquisition
The rhythm and pace of moving things wave characteristic of user's EEG signals of dormancy state changing features, and slept as the personalization based on convolutional neural networks
One of input feature vector amount of dormancy Staging System；Real-time sleep state data are obtained by sleep stage method, while record in real time
The data of record are sent to mobile terminal after the completion of entire sleep procedure by sleep state data.
Personalized sleep Staging System, for the rhythm and pace of moving things wave characteristic according to the EEG signals of input, in conjunction with age of user, property
Not and historical data application convolutional neural networks carry out real-time sleep stage, while corresponding running parameter being put down by cloud
Platform, which is transmitted back to, wears front end, to carry out adaptive sleep regulation.
Above-mentioned technical proposal is connect, the mobile terminal is also used to obtain the sleep state data of record from cloud platform, and is in
Now give user.
Above-mentioned technical proposal is connect, original eeg data is sent to cloud platform by Wi-Fi by the acquisition front end.
The beneficial effect comprise that: cloud platform of the invention being capable of brain wave data to a large number of users and institute
Corresponding information, index are collected, and carry out self-optimizing to itself using a large amount of data, so that staging scale is more accurate,
And suggest the sleep state for obtaining user and sleep adjustment to be sent respectively to mobile terminal.
Further, the present invention combines assisting sleep process with development of Mobile Internet technology, complicated data processing
Algorithm is transferred in cloud platform and completes, and while meeting user demand, reduces the complexity that user wears front end.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the sleep stage method flow diagram the present invention is based on cloud platform；
Fig. 2 is that the present invention is based on the sleep stage method and system structure charts of cloud platform；
Fig. 3 is that the present invention is based on the sleep stage method and system technologies of cloud platform to realize block diagram；
Fig. 4 is personalized sleep of the present invention algorithm model figure by stages.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, the present invention is based on the sleep stage method of cloud platform the following steps are included:
S1: the personal information that user inputs in mobile terminal (cell phone application) is obtained, and as personalized sleep point
The input parameter of phase；
S2: the EEG signals of the corresponding acquisition front-end collection user of control, and transmitted EEG signals by Wi-Fi technology
To cloud platform；
S3: cloud platform pre-processes the eeg data of acquisition, obtains the rhythm and pace of moving things wave characteristic of user's EEG signals, and will
It is as one of the input feature vector amount of personalized sleep Staging System based on convolutional neural networks；
S4: personalized sleep Staging System is according to the rhythm and pace of moving things wave characteristics of the EEG signals of input, in conjunction with age of user, gender
And historical data carries out real-time sleep stage, while corresponding running parameter being transmitted back to and wears front end, it is adaptive to carry out
The sleep regulation answered；
S5: cloud platform records the sleep state delta data of user, after the completion of entire sleep procedure, mobile terminal in real time
The sleep state data of record will be obtained from cloud platform, and be presented to user.
The sleep procedure of people was divided into for 6 phases by the sleep stage criterion of cloud platform: awakening phase WAKE, rapid-eye-movement sleep phase
REM and 4 NREM sleep phase NREM, wherein NREM is divided into 1 phase N1 of sleep, Sleep Stage 2 N2,3 phase N3 of sleep again and sleeps
Sleep 4 phase N4, and 1,2 phases of sleep are shallowly to sleep phase LS, and 3,4 phases of sleep are sound sleep phase SWS.
In S3, eeg data preprocess method essentially consists in and uses Algorithms of Discrete Wavelet Transform to original EEG signals, with
Extract the time-frequency spectrum matrix with different sleep period rhythm and pace of moving things wave characteristics.In wavelet transform procedure, for wavelet function and change
The selection for changing scale directly affects the accuracy of EEG feature extraction.When use db4 wavelet function, the small echo that scale is 8
Transformation, the amplitude-frequency characteristic of each rhythm and pace of moving things wave are the most obvious.Therefore this method uses db4 wavelet function to carry out scale as 8 wavelet transformation
Realize the preprocessing process of EEG signals.
Personalized sleep by stages believe by algorithm, the brain electrical feature for passing through the personal characteristic information user and passing through prime processing
Input vector number as convolutional neural networks makees the evaluation result of 5 sleep state values (WAKE, N1, N2, SWS, REM)
Real output value and desired output are compared with enough sample trainings network for the output vector of neural network
Compared with when its error is less than setting value, this group of weight and threshold value that neural network is held are networks by adaptive learning
Obtained correct internal representation.
The EEG Processing algorithm for sleep stage in cloud platform by the EEG signals based on wavelet transformation in advance
Adjustment method and personalized sleep based on convolutional neural networks Algorithm constitution by stages.Personalized sleep algorithm model by stages, according to
The secondary time-frequency characteristics matrix extract layer comprising wavelet transform (DWT), convolutional neural networks (CNN) input layer, convolutional layer 1
(Conv1), pond layer 1 (Pool1), convolutional layer 2 (Conv2), pond layer 2 (Pool2), convolutional layer 3 (Conv3), full articulamentum
(FC) and output layer.
The personalized sleep based on convolutional neural networks in cloud platform by stages sleep in EEG signals special by algorithm, the algorithm
Sign extract on the basis of method by stages, use can effecting reaction sleep period time-frequency and nonlinear characteristic wavelet energy as sleeping
The fusion feature in dormancy stage, using convolutional neural networks as the analysis model of sleep stage, in conjunction with age of user, gender, history
The individualized features such as data are realized to five stage sleep spies of Wake, SWS, N1, N2, REM in R&K sleep stage model
The identification of sign is classified, accuracy rate and stability with higher.
EEG Processing algorithm for sleep stage is by EEG signals Preprocessing Algorithm and base based on wavelet transformation
In the personalized sleep Algorithm constitution by stages of convolutional neural networks.Algorithm model is illustrated in fig. 4 shown below by stages for this, successively comprising discrete
Time-frequency characteristics matrix extract layer, convolutional neural networks (CNN) input layer, convolutional layer 1 (Conv1), Chi Hua of wavelet transformation (DWT)
1 (Pool1) of layer, convolutional layer 2 (Conv2), pond layer 2 (Pool2), convolutional layer 3 (Conv3), full articulamentum (FC) and output layer.
The training of convolutional neural networks uses the AdamOptimizer optimizer based on tensorflow, and learning rate is initial
It is set as 0.001, and the parameter of neural network is optimized using cross entropy loss function.
The core function of cloud platform includes EEG signals Preprocessing Algorithm and the sleep stage system based on convolutional neural networks
System.Real-time eeg data is uploaded to cloud platform via eeg signal acquisition device, and cloud platform utilizes the brain electricity based on wavelet transformation
Signal processing algorithm extracts each rhythm and pace of moving things wave characteristic information of original EEG signals, and the index and user information, environmental factor are total
With the personalized sleep Staging System for being input to the convolutional neural networks model based on R&K sleep stage standard, system can be defeated
Real-time sleep state out.In addition cloud platform can brain wave data to a large number of users and corresponding information, index carry out
It collects, self-optimizing is carried out to itself using a large amount of data, so that staging scale is more accurate, and the sleep shape of user will be obtained
State and sleep adjustment are suggested being sent respectively to mobile terminal.
Personal information includes personal gender, the age, height, weight, nationality, occupies the information such as ground long.
As shown in figure 3, the sleep stage system of the invention based on cloud platform, including mobile terminal 1, wearing 2 and of front end
Cloud platform 3；
The mobile terminal 1 installs corresponding APP in the mobile terminal, is mainly used for obtaining the personal letter of user's input
It ceases and is transferred to cloud platform；Data record and analysis sleep state to this sleep procedure got from cloud platform
Data and the sleep for comparing historical data generation, which adjust, to be suggested being shown；
Eeg data, is sent to by the wearing front end 2 for acquiring the eeg data of user, and by Wi-Fi technology
Cloud platform；
The cloud platform 3, real-time EEG signals data are uploaded to cloud platform via eeg signal acquisition device, and cloud platform mentions
After getting the feature of EEG signals, personalized sleep is carried out by stages in conjunction with age of user, gender, historical data etc., is slept in real time
State will be used to adjust the working condition positioned at the sleep supplementary module for wearing front end as feedback parameter.
Personalized sleep Staging System, which can be separately provided, may also be arranged in cloud platform 3.The cloud of the embodiment of the present invention
Platform is equipped with personalized sleep Staging System, for the rhythm and pace of moving things wave characteristic according to the EEG signals of input, in conjunction with age of user,
Gender and historical data application convolutional neural networks carry out real-time sleep stage, while corresponding running parameter is passed through cloud
Platform, which is transmitted back to, wears front end, to carry out adaptive sleep regulation.
In addition cloud platform can brain wave data to a large number of users and corresponding information, index be collected, benefit
Self-optimizing is carried out to itself with a large amount of data, so that staging scale is more accurate, and by the sleep state for obtaining user and is slept
Adjustment of sleeping is suggested being sent respectively to mobile terminal.
In specific implementation, present invention combination age of user, gender, historical data carry out personalized sleep by stages, in real time
Sleep state will adjust the working condition of sleeping-assisting system as feedback parameter.In addition cloud platform can be to a large number of users
Brain wave data and corresponding information, index are collected, and are carried out self-optimizing to itself using a large amount of data, are made score
Phase standard is more accurate.
User the end APP fill in personal gender, the age, height, weight, long occupy etc. information；
The eeg data of acquisition is uploaded to cloud by hardware device (wearing front end).
Every time before sleep, user can carry out sleep pattern selection and the setting of sleeping time, Zhi Houdian at cell phone application end
Start-up operation button is hit, using cloud platform and wears front end as the adaptive sleep regulation system starts of core.Adaptively sleep
After dormancy regulating system is started to work, cloud platform can analyze the real-time sleep state data of the user obtained in real time and record, and then make
It is located at the assisting sleep module work for wearing front end for feedback parameter real-time control.After entire sleep procedure, cloud platform meeting
The sleep state data recorded are sent to APP, user can see that oneself is whole at the sleep state interface on APP
Dormant variation in a sleep procedure.Sleep quality variation tendency and system also can transmit the evaluation and recommendations of oneself
It is presented to the user to the end APP.
The present invention combines EEG Processing technology with mobile Internet, is transmitted using APP as data and man-machine
Interactive medium, design the personalized sleep based on wavelet transform and convolutional neural networks model in cloud platform is by stages
System, fusion EEG signals and the medical knowledge of sleep state by stages, can complete accurate sleep stage.Based on the above design side
Case, this system can detect user's sleep state, further improve the sleep quality of user, and terminal device at
This lower, high reliablity, convenient for promoting.
Cloud platform can automatically save user each time in sleep procedure sleep state variation data.Sleep quality assessment system
System can go out the sleep quality variation tendency of user according to the historical sleep status analysis of record, and provide rational evaluation and suggestion.
With the acquisition of long-term a large amount of eeg datas, the change curve for obtaining EEG signals can be counted, so as to give
It gives the stronger suggestion of specific aim and makes health early warning in time.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (10)
1. a kind of sleep stage method based on cloud platform, which comprises the following steps:
Step 1: obtaining the personal information that user inputs on mobile terminals, and join as the input of personalized sleep by stages
Number；
Step 2: the corresponding EEG signals for wearing front-end collection user of control, and by EEG signals real-time transmission to cloud platform；
Step 3: cloud platform pre-processes the eeg data of acquisition, obtains the rhythm and pace of moving things wave characteristic of user's EEG signals, and will
It is as one of the input feature vector amount of personalized sleep Staging System based on convolutional neural networks；
Step 4: personalized sleep Staging System is according to the rhythm and pace of moving things wave characteristics of the EEG signals of input, in conjunction with age of user, gender
And historical data carries out real-time sleep stage, while corresponding running parameter being transmitted back to and wears front end, it is adaptive to carry out
The sleep regulation answered；
Step 5: cloud platform records the sleep state delta data of user in real time, mobile after the completion of entire sleep stage process
Terminal will obtain the sleep state data of record from cloud platform, and be presented to user.
2. the sleep stage method according to claim 1 based on cloud platform, which is characterized in that the cloud platform is slept
It sleeps criterion by stages, the sleep procedure of people was divided into for 6 phases: awakening phase WAKE, rapid-eye-movement sleep phase REM and 4 non-rapid eye movements
Sleep period NREM, wherein NREM be divided into again sleep 1 phase N1, Sleep Stage 2 N2, sleep 3 phase N3 and sleep 4 phase N4, sleep 1,2 phases be
Phase LS is shallowly slept, 3,4 phases of sleep are sound sleep phase SWS.
3. the sleep stage method according to claim 1 based on cloud platform, which is characterized in that eeg data is pretreated
Detailed process are as follows: selection small wave converting method extracts the characteristic wave of EEG signals, and the energy feature of characteristic wave is made
For the temporal signatures for distinguishing sleep period；In wavelet transform procedure, db4 wavelet function is used to carry out scale as 8 wavelet transformation
Realize the preprocessing process of EEG signals.
4. the sleep stage method according to claim 1 based on cloud platform, which is characterized in that personal information includes individual
Gender, height, weight, occupies ground long at the age.
5. the sleep stage method according to claim 1 based on cloud platform, which is characterized in that the brain acquired in step 2
Electric signal is the simulation EEG signals for wearing front-end collection.
6. the sleep stage method according to claim 2 based on cloud platform, which is characterized in that the personalized sleep point
Phase method, by the EEG signals using the personal characteristic information of user and by prime processing as the input of convolutional neural networks
Vector, the output vector by the evaluation result of 5 sleep state values (WAKE, N1, N2, SWS, REM) as neural network, with foot
Real output value is compared by enough sample trainings network with desired output, when its error is less than setting value, mind
This group of weight and threshold value held through network are networks by the obtained correct internal representation of adaptive learning.
7. the sleep stage method according to claim 6 based on cloud platform, which is characterized in that the cloud platform sleep point
Algorithm model by stages in phase method includes defeated using time-frequency characteristics matrix extract layer, the convolutional neural networks of wavelet transform
Enter layer, convolutional layer Conv1, pond layer Pool1, convolutional layer Conv2, pond layer Pool2, convolutional layer Conv3, full articulamentum FC and
Output layer.
8. a kind of sleep stage system based on cloud platform characterized by comprising
Front end is worn, user's head is worn on, acquires the EEG signals of user, EEG signals are sent to cloud platform；It connects simultaneously
The control parameter sent by cloud platform is received, adaptive sleep regulation is realized with cooperation sleep supplementary module；
Mobile terminal obtains the personal information that user inputs on mobile terminals, and as based on convolutional neural networks
One of the input characteristic parameter of personalized sleep Staging System；After the completion of sleep procedure, acquisition is recorded in sleeping in cloud platform
Dormancy status data, and sleep adjustment is generated by analysis sleep state data, comparison historical data and is suggested, then by sleep procedure
Sleep state variation and generate adjustment suggestion shown；
Cloud platform for pre-processing the eeg data application wavelet transform of acquisition obtains that sleep shape can be reacted
The rhythm and pace of moving things wave characteristic of user's EEG signals of state changing features, and as the personalized sleep based on convolutional neural networks point
One of input feature vector amount of phase system；Real-time sleep state data are obtained by sleep stage method, while record sleep in real time
The data of record are sent to mobile terminal after the completion of entire sleep procedure by status data；
Personalized sleep Staging System, for the rhythm and pace of moving things wave characteristic according to the EEG signals of input, in conjunction with age of user, gender with
And historical data application convolutional neural networks carry out real-time sleep stage, while corresponding running parameter being passed by cloud platform
It is back to and wears front end, to carry out adaptive sleep regulation.
9. the sleep stage system according to claim 8 based on cloud platform, which is characterized in that the mobile terminal is also used
In the sleep state data from cloud platform acquisition record, and it is presented to the user.
10. the sleep stage system according to claim 8 based on cloud platform, which is characterized in that the acquisition front end is logical
It crosses Wi-Fi and original eeg data is sent to cloud platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910331566.5A CN110327040A (en) | 2019-04-24 | 2019-04-24 | Sleep stage method and system based on cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910331566.5A CN110327040A (en) | 2019-04-24 | 2019-04-24 | Sleep stage method and system based on cloud platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110327040A true CN110327040A (en) | 2019-10-15 |
Family
ID=68139754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910331566.5A Pending CN110327040A (en) | 2019-04-24 | 2019-04-24 | Sleep stage method and system based on cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110327040A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111973177A (en) * | 2020-07-23 | 2020-11-24 | 山东师范大学 | Sleep assisting system and method based on portable electroencephalogram equipment |
| CN112717253A (en) * | 2020-12-25 | 2021-04-30 | 武汉理工大学 | Acousto-optic combined awakening device based on brain wave monitoring |
| CN112932501A (en) * | 2021-01-25 | 2021-06-11 | 上海海事大学 | Method for automatically identifying insomnia based on one-dimensional convolutional neural network |
| CN113080864A (en) * | 2021-04-07 | 2021-07-09 | 电子科技大学 | Common sleep disease detection method through automatic sleep staging results |
| CN113208623A (en) * | 2021-04-07 | 2021-08-06 | 北京脑陆科技有限公司 | Sleep staging method and system based on convolutional neural network |
| CN113812965A (en) * | 2021-08-19 | 2021-12-21 | 杭州回车电子科技有限公司 | Sleep state recognition method, device, electronic device and storage medium |
| CN116058805A (en) * | 2023-03-29 | 2023-05-05 | 安徽星辰智跃科技有限责任公司 | Method, system and device for dynamically adjusting sleep memory activity level |
| CN116504357A (en) * | 2023-06-28 | 2023-07-28 | 安徽星辰智跃科技有限责任公司 | Sleep periodicity detection and adjustment method, system and device based on wavelet analysis |
| CN116671867A (en) * | 2023-06-06 | 2023-09-01 | 中国人民解放军海军特色医学中心 | Sleep quality evaluation method and system for underwater operators |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105748070A (en) * | 2016-04-26 | 2016-07-13 | 深圳市思立普科技有限公司 | Sleep intervention method for improving sleep quality |
| WO2018027141A1 (en) * | 2016-08-05 | 2018-02-08 | The Regents Of The University Of Colorado, A Body Corporate | In-ear sensing systems and methods for biological signal monitoring |
| CN107788976A (en) * | 2017-09-22 | 2018-03-13 | 复旦大学 | Sleep monitor system based on Amplitude integrated electroencephalogram |
| CN108742517A (en) * | 2018-03-27 | 2018-11-06 | 重庆邮电大学 | One kind is based on the mono- lead brain electrosleep of Stacking method by stages automatically |
| CN109363670A (en) * | 2018-11-13 | 2019-02-22 | 杭州电子科技大学 | A kind of depression intelligent detecting method based on sleep monitor |
| CN109567748A (en) * | 2018-11-09 | 2019-04-05 | 速眠创新科技（深圳）有限公司 | Determination method, apparatus, computer equipment and the storage medium of sleep stage |
-
2019
- 2019-04-24 CN CN201910331566.5A patent/CN110327040A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105748070A (en) * | 2016-04-26 | 2016-07-13 | 深圳市思立普科技有限公司 | Sleep intervention method for improving sleep quality |
| WO2018027141A1 (en) * | 2016-08-05 | 2018-02-08 | The Regents Of The University Of Colorado, A Body Corporate | In-ear sensing systems and methods for biological signal monitoring |
| CN107788976A (en) * | 2017-09-22 | 2018-03-13 | 复旦大学 | Sleep monitor system based on Amplitude integrated electroencephalogram |
| CN108742517A (en) * | 2018-03-27 | 2018-11-06 | 重庆邮电大学 | One kind is based on the mono- lead brain electrosleep of Stacking method by stages automatically |
| CN109567748A (en) * | 2018-11-09 | 2019-04-05 | 速眠创新科技（深圳）有限公司 | Determination method, apparatus, computer equipment and the storage medium of sleep stage |
| CN109363670A (en) * | 2018-11-13 | 2019-02-22 | 杭州电子科技大学 | A kind of depression intelligent detecting method based on sleep monitor |
Non-Patent Citations (1)
| Title |
|---|
| 张熙: "《现代睡眠学》", 31 December 2007 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111973177A (en) * | 2020-07-23 | 2020-11-24 | 山东师范大学 | Sleep assisting system and method based on portable electroencephalogram equipment |
| CN112717253A (en) * | 2020-12-25 | 2021-04-30 | 武汉理工大学 | Acousto-optic combined awakening device based on brain wave monitoring |
| CN112932501A (en) * | 2021-01-25 | 2021-06-11 | 上海海事大学 | Method for automatically identifying insomnia based on one-dimensional convolutional neural network |
| CN113080864B (en) * | 2021-04-07 | 2022-02-01 | 电子科技大学 | Common sleep disease detection method through automatic sleep staging results |
| CN113208623A (en) * | 2021-04-07 | 2021-08-06 | 北京脑陆科技有限公司 | Sleep staging method and system based on convolutional neural network |
| CN113080864A (en) * | 2021-04-07 | 2021-07-09 | 电子科技大学 | Common sleep disease detection method through automatic sleep staging results |
| CN113812965A (en) * | 2021-08-19 | 2021-12-21 | 杭州回车电子科技有限公司 | Sleep state recognition method, device, electronic device and storage medium |
| CN113812965B (en) * | 2021-08-19 | 2024-04-09 | 杭州回车电子科技有限公司 | Sleep state identification method, sleep state identification device, electronic device and storage medium |
| CN116058805A (en) * | 2023-03-29 | 2023-05-05 | 安徽星辰智跃科技有限责任公司 | Method, system and device for dynamically adjusting sleep memory activity level |
| CN116671867A (en) * | 2023-06-06 | 2023-09-01 | 中国人民解放军海军特色医学中心 | Sleep quality evaluation method and system for underwater operators |
| CN116671867B (en) * | 2023-06-06 | 2024-02-20 | 中国人民解放军海军特色医学中心 | Sleep quality evaluation method and system for underwater operators |
| CN116504357A (en) * | 2023-06-28 | 2023-07-28 | 安徽星辰智跃科技有限责任公司 | Sleep periodicity detection and adjustment method, system and device based on wavelet analysis |
| CN116504357B (en) * | 2023-06-28 | 2024-05-10 | 安徽星辰智跃科技有限责任公司 | Sleep periodicity detection and adjustment method, system and device based on wavelet analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110327040A (en) | Sleep stage method and system based on cloud platform | |
| CN105748043B (en) | Sleep quality monitoring method and device, wearable device | |
| KR102356890B1 (en) | Method and Apparatus for controlling temperature adjustment device | |
| JP4192127B2 (en) | Sleep state management device and sleep state management method | |
| CN108577343B (en) | User interaction system and method for soft and hard adjustable mattress realized by mobile phone terminal | |
| CN106267514B (en) | Feeling control system based on brain electricity feedback | |
| CN106137130B (en) | A kind of sleep period recognition methods based on audio processing | |
| CN107126615A (en) | Music induced hypnotic method and system based on EEG signals | |
| CN108310587A (en) | A kind of sleep control device and method | |
| CN206045144U (en) | A kind of novel intelligent sleeping and the device for waking up naturally | |
| CN108308942A (en) | The soft or hard adjustable bed mattess of intelligence and its control method of a kind of fusion family Internet of Things | |
| CN106730812A (en) | A kind of game regulator control system estimated based on multi-physiological-parameter mood amount and regulation and control method | |
| CN107080546A (en) | Electroencephalogram-based emotion perception system and method for environmental psychology of teenagers and stimulation sample selection method | |
| EP2846683A2 (en) | System and method for monitoring the health of a user | |
| US11383130B2 (en) | Pelvic floor muscle training device and system | |
| CN102715902A (en) | Emotion monitoring method for special people | |
| CN109730658A (en) | A kind of artificial intelligence mattress system | |
| CN105411580A (en) | Brain control wheelchair system based on touch and auditory evoked potential | |
| CN116400800B (en) | ALS patient human-computer interaction system and method based on brain-computer interface and artificial intelligence algorithm | |
| CN110491498A (en) | A kind of data receiver and processing method of brain wave signal | |
| CN108491792A (en) | Office scene human-computer interaction Activity recognition method based on electro-ocular signal | |
| CN106650243A (en) | Relaxation activity system of preventing injury to athlete muscle | |
| CN109432567A (en) | A kind of Feeling control system based on adaptive virtual reality scenario | |
| CN106250685B (en) | Method and device for displaying user health parameters | |
| CN113261929B (en) | Mobile phone bad use behavior risk early warning system based on heart rate variability index |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191015 |
|
| RJ01 | Rejection of invention patent application after publication |