CN112717253A - Acousto-optic combined awakening device based on brain wave monitoring - Google Patents
Acousto-optic combined awakening device based on brain wave monitoring Download PDFInfo
- Publication number
- CN112717253A CN112717253A CN202011556862.4A CN202011556862A CN112717253A CN 112717253 A CN112717253 A CN 112717253A CN 202011556862 A CN202011556862 A CN 202011556862A CN 112717253 A CN112717253 A CN 112717253A
- Authority
- CN
- China
- Prior art keywords
- sleep
- user
- brain wave
- module
- rhythm
- 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
- 210000004556 brain Anatomy 0.000 title claims abstract description 50
- 238000012544 monitoring process Methods 0.000 title claims abstract description 18
- 230000007958 sleep Effects 0.000 claims abstract description 134
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 230000009466 transformation Effects 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 230000033764 rhythmic process Effects 0.000 claims description 41
- 230000008667 sleep stage Effects 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 14
- 210000001061 forehead Anatomy 0.000 claims description 12
- 206010062519 Poor quality sleep Diseases 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 239000007772 electrode material Substances 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 230000004461 rapid eye movement Effects 0.000 claims description 3
- 230000036385 rapid eye movement (rem) sleep Effects 0.000 claims description 3
- 241001669679 Eleotris Species 0.000 abstract description 9
- 230000002618 waking effect Effects 0.000 abstract description 6
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 14
- 230000000694 effects Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 206010042265 Sturge-Weber Syndrome Diseases 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000003860 sleep quality Effects 0.000 description 4
- 230000004622 sleep time Effects 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 3
- 230000001020 rhythmical effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 210000000988 bone and bone Anatomy 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000000147 hypnotic effect Effects 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 208000020401 Depressive disease Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 206010041349 Somnolence Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000037326 chronic stress Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 201000003102 mental depression Diseases 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000002040 relaxant effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 210000003625 skull Anatomy 0.000 description 1
- 230000037322 slow-wave sleep Effects 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
-
- 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
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
- A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
- A61M2021/0027—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the hearing sense
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
- A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
- A61M2021/0044—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the sight sense
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
- A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
- A61M2021/0083—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus especially for waking up
Abstract
The invention discloses a sound and light combined awakening device based on brain wave monitoring, which comprises a wearing front end: for signal acquisition and adaptive sleep regulation; cloud platform: the sleep parameter calculation module is used for calculating the sleep parameters of the user by adopting an electroencephalogram signal processing algorithm based on wavelet transformation according to the electroencephalogram signals collected by the wearing front end; the sleep parameters and the personal characteristic information of the user are output to the sleep state of the user through the personalized sleep staging system, and the sleep state is sent to the control module and the mobile terminal; a mobile terminal: for receiving and displaying the sleep state of the user. The invention can avoid the influence on the sleeper caused by directly waking up the sleeper, can improve the sleeping quality of the sleeper and meets the requirements of user groups.
Description
Technical Field
The invention relates to the technical field of life electronic equipment, in particular to a sound and light combined awakening device based on brain wave monitoring.
Background
The existing earphone awakening products are mostly awakening modes directly by applying interference such as an alarm, the working mode is simple and fast, but the specialty is not strong, and the health of the ears of a user can be influenced to a certain extent by wearing the earphone for a long time. In addition, directly applying interference wakes the user from a deep sleep state, greatly reducing the user's sleep experience and sleep quality. The study shows that the sudden awakening of the alarm clock in the sleep is equivalent to one drunk. Long-term awakening will cause chronic stress and increase the risk of mental depression, hypertension and heart disease. Especially in the state of deep sleep, if the alarm clock wakes up, the damage to the body is very large, and particularly the influence on the heart and blood vessels is large.
Scientific experiments prove that due to the action of the biological rhythm of the human body, the gradual change light is used for simulating the natural light to effectively and harmlessly wake up, the external light source is used for stimulating as an alarm clock signal to well wake up a user under the condition of not influencing the sleep of other people, and the sleep quality of other people is guaranteed to the maximum extent.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides the acousto-optic combination awakening device based on brain wave monitoring, which can avoid the influence on a sleeper caused by directly awakening the sleeper, improve the sleeping quality of the sleeper and meet the requirements of user groups.
In order to achieve the above object, the invention provides a combined sound and light waking device based on brain wave monitoring, which is characterized in that the device comprises:
wearing the front end: the system comprises a brain wave signal acquisition module for acquiring brain wave signals, a control module for processing data and sending out a control instruction according to a sleep state, a sound awakening module for outputting audio data according to the control instruction, a light awakening module for emitting light according to the control instruction, a Wi-Fi communication module for remotely transmitting data and a power supply for supplying power to the system, wherein the sound awakening module is used for outputting audio data according to the control instruction;
cloud platform: the sleep parameter calculation module is used for calculating the sleep parameters of the user by adopting an electroencephalogram signal processing algorithm based on wavelet transformation according to the electroencephalogram signals collected by the wearing front end; the sleep parameters and the personal characteristic information of the user are output to the sleep state of the user through the personalized sleep staging system, and the sleep state is sent to the control module and the mobile terminal;
a mobile terminal: for receiving and displaying the sleep state of the user.
Furthermore, the brain wave signal acquisition module is positioned above the inner side of the front end of the wearing front end and is tightly attached to the forehead of the user; the brain wave signal acquisition module is used for acquiring electroencephalogram signals of the right forehead or the left forehead, a middle electrode of the forehead is used as a reference electrode, and an electroencephalogram signal acquisition dry electrode is selected as an electrode material; the brain wave signal acquisition module performs pre-stage amplification on the acquired signals and adopts a trap circuit for filtering; and after the filtering is finished, converting the signal into a digital signal through the ADC.
Furthermore, the acoustic awakening module comprises an audio decoding module and a vibrator, wherein an ARM processor of the control module reads music data from the SD card through an SPI protocol and sends the music data to a decoding chip for decoding; when the sound awakening module works, the soothing music loaded with white noise is played, so that the sleep state of the user at the moment is changed from deep sleep to light sleep.
Furthermore, the light awakening module is arranged on the inner side of the front end of the wearing front end, surrounds the periphery of the eyes of the user and comprises an LED aperture; the light awakening module adopts an LED aperture, and soft warm light with adjustable brightness is emitted to a user during working; the ARM processor of the control module drives the warm light LED lamp of the light awakening module to work through the power amplifier circuit, and brightness is adjusted through PWM waves to simulate natural light awakening.
Furthermore, the electroencephalogram signal processing algorithm based on the wavelet transformation extracts the energy ratio of each rhythm wave of the electroencephalogram signal, and the energy components of different characteristic waves are used as the basis for distinguishing sleep stages to obtain the sleep parameters of the user.
Further, the personalized sleep staging system is a sample-trained convolutional neural network model, which takes the sleep parameters and personal characteristic information of the user as input vectors and takes the sleep states as output values, wherein the sleep states comprise an awake period WAKE, a sleep 1 period N1, a sleep 2 period N2, a deep sleep period SWS and a rapid eye movement sleep period REM.
Further, the sleep parameter E 'of the user'χThe calculation method comprises the following steps:
wherein Ex ∈ (E)α,Eβ,Eθ,Eδ),EallIs a total energy value; eα、Eβ、Eθ、 EδThe rhythm wave energy of alpha, beta, theta and delta of the user is respectively, n is the type of the rhythm wave and represents the rhythm waves of alpha, beta, theta and delta in sequence.
Furthermore, the wavelet transform-based electroencephalogram signal processing algorithm has the following frequency band ranges of alpha, beta, theta and delta rhythm waves: 6.25-12.5Hz, 12.5-25Hz, 3.906-7.813Hz and 2.344-4.688 Hz.
Still further, the personalized sleep staging system outputting the rule of the user's sleep state includes:
a) and (3) during the wake period: the method comprises the steps of mixing alpha rhythm waves and beta rhythm waves, and judging the alpha rhythm waves as wake periods when more than 50 percent of the alpha rhythm waves are alpha rhythm waves;
b) NREM sleep stage I: comprises mixed alpha and theta rhythm waves, the alpha rhythm wave occupies less than 50% of the time;
c) NREM sleep phase II: the brain wave amplitude is increased;
d) deep sleep period: delta rhythm wave accounts for 20% -50% of the signal, and the peak-to-peak value of brain wave amplitude is above 75 uV;
e) rapid eye movement period: including alpha and beta rhythm waves, with a sawtooth wave.
Furthermore, the mobile terminal stores and processes user data, including system setting, user information entry, working parameter entry, real-time sleep staging result display and historical sleep state change curve display.
Compared with the prior art, the invention has the beneficial effects that: according to rhythm wave characteristics of electroencephalogram signals, real-time sleep staging is carried out by combining age, gender and historical data of a user, working parameters are transmitted back to a wearing front end to carry out self-adaptive sleep regulation, and meanwhile, sleep state changes in the sleep process are presented to the user through the mobile phone APP by the system; when the preset awakening time is reached, the control module firstly drives the sound awakening module to play the soothing music loaded with the white noise, guides the sleep state of the user from deep sleep to light sleep, then controls the LED aperture to simulate gradually-bright natural light, and awakens the user from the light sleep; the invention can avoid the influence on the sleeper caused by directly waking up the sleeper, can improve the sleeping quality of the sleeper and meets the requirements of user groups.
Drawings
Fig. 1 is a schematic structural diagram of a combined sound and light awakening device based on brain wave monitoring according to the invention; the list of components represented by each reference number is as follows: 1. a brain wave sensor; 2. an embedded system board; 3. a lithium battery; 4. an audio decoding module; 5. a Wi-Fi communication module; 6. a power source; 7. an LED aperture; 8. and a vibrator.
Fig. 2 is a schematic diagram of data transmission between a wearing front end, a cloud platform, and a mobile phone APP according to the present invention.
Fig. 3 is an external view of the wearing tip according to the present invention.
Fig. 4 is a flow chart of energy feature extraction according to the present invention.
Fig. 5 is a table showing the correspondence between wavelet coefficients and frequency bands after decomposition of 8-layer db4 according to the present invention.
Fig. 6 is a diagram of a personalized sleep staging model according to the present invention.
Fig. 7 is a table showing the relationship between rhythmic waves included in different sleep stages according to the present invention.
Fig. 8 is a table of sleep staging effects according to the present invention.
Fig. 9 is a flowchart of the operation of the closed-loop feedback hypnosis system according to the present invention.
Fig. 10 is a flowchart of the first phase wake-up procedure according to the present invention.
Fig. 11 is a flowchart illustrating a second phase wake-up procedure according to the present invention.
Detailed Description
In order to make the technical scheme and the beneficial effects of the invention more clearly understood, the invention is further described in detail below with reference to the accompanying drawings and the embodiments.
The invention provides a brain wave monitoring-based acousto-optic combined awakening device which comprises a wearing front end, a cloud platform and a mobile end. Wherein the content of the first and second substances,
wearing the front end: the system comprises a brain wave signal acquisition module for acquiring brain wave signals, a control module for processing data and sending out a control instruction according to a sleep state, a sound awakening module for outputting audio data according to the control instruction, a light awakening module for emitting light according to the control instruction, a Wi-Fi communication module for remotely transmitting data and a power supply for supplying power to the system, wherein the sound awakening module is used for outputting audio data according to the control instruction;
cloud platform: the sleep parameter calculation module is used for calculating the sleep parameters of the user by adopting an electroencephalogram signal processing algorithm based on wavelet transformation according to the electroencephalogram signals collected by the wearing front end; the sleep parameters and the personal characteristic information of the user are output to the sleep state of the user through the personalized sleep staging system, and the sleep state is sent to the control module and the mobile terminal;
a mobile terminal: the sleep state of the user is received and displayed, and the user is interacted with.
The front end is worn to collect electroencephalogram signals, the electroencephalogram signals are transmitted to the cloud platform through the Wi-Fi communication module, the cloud platform processes data to obtain rhythm wave characteristics of the electroencephalogram signals of a user, the personalized sleep staging system of the cloud platform carries out real-time sleep staging by combining age, gender and historical data of the user according to the rhythm wave characteristics of the electroencephalogram signals, meanwhile, working parameters are transmitted back to the front end to be worn, self-adaptive sleep regulation is carried out, and meanwhile, the system can enable sleep state changes in the sleep process to be presented to the user through the mobile phone APP. Fig. 2 is a schematic diagram of data transmission between a wearable front end, a cloud platform, and a mobile end.
In this embodiment, the appearance diagram of the wearing front end is as shown in fig. 3, and includes a brain wave signal acquisition module, a control module, an acoustic wake-up module, a light wake-up module, a Wi-Fi communication module, and a power supply.
The brain wave signal acquisition module is used for acquiring brain wave signals in real time and transmitting the brain wave signals to the control module; the control module is used for processing the collected brain wave signals and controlling the whole system; the voice awakening module is used for playing the soothing music loaded with white noise, so that the sleep state of the user at the moment is changed from deep sleep to light sleep; the light awakening module is used for emitting soft warm light with adjustable brightness to a user; the Wi-Fi communication module is used for transmitting the acquired electroencephalogram digital signals to the cloud in real time; the power supply is used for supplying power to the system.
The cloud platform comprises an electroencephalogram signal processing algorithm based on wavelet transformation and an individualized sleep stage system, wherein the electroencephalogram signal processing algorithm based on wavelet transformation is used for extracting characteristics of electroencephalogram signals; the personalized sleep staging system is used for performing personalized sleep staging by combining the age, the gender and historical data of the user. The electroencephalogram data of a large number of users, corresponding information and indexes are collected together by the wavelet transform-based electroencephalogram signal processing algorithm and the personalized sleep stage system, self-optimization is carried out on the electroencephalogram data by utilizing a large amount of data, and the stage standard is more accurate.
The mobile terminal APP can realize the functions of system setting, user information input, working parameter input, real-time sleep staging result display, historical sleep state change curve display and the like. During work, the APP uploads the basic information of the user and the relevant parameters set by the working mode to the cloud platform, and the sleep staging result is obtained from the cloud platform.
In this embodiment, the brain wave signal collecting module is located above the inner side of the front end of the wearing front end and is tightly attached to the forehead of the user, and comprises a brain wave sensor 1. The brain wave signal acquisition module is used for acquiring electroencephalogram signals of the right forehead or the left forehead, a middle electrode of the forehead is used as a reference electrode, and an electroencephalogram signal acquisition dry electrode is selected as an electrode material. The brain wave signal acquisition module firstly performs preceding stage amplification on the acquired signals to enable the acquired signals to reach the magnitude of voltage, and prepares for the subsequent stage signal processing; because of the power frequency interference of 50Hz, a trap circuit is also needed for filtering; and after the filtering is finished, the digital signals are converted into digital signals through the ADC and then sent to the cloud platform through the Wi-Fi communication module.
The control module is located in an intermediate position within the wearing front end, not in contact with the user, and comprises an embedded system board 2.
The acoustic awakening module is positioned at the front wearing end close to the skull and comprises an audio decoding module 4 and a vibrator 8. The sound awakening module consists of a VS1053 audio decoding chip, an SD memory card and a bone conduction vibrator, and an ARM processor of the control module reads music data from the SD card through an SPI protocol and sends the music data to the decoding chip for decoding. When the sound awakening module works, the soothing music loaded with white noise is played, so that the sleep state of the user at the moment is changed from deep sleep to light sleep.
The light awakening module is positioned at the inner side of the front end of the wearing front end, surrounds the eye of the user and comprises an LED aperture 7. The light awakening module mainly adopts an LED aperture, and soft warm light with adjustable brightness is emitted to a user during working. The ARM processor of the control module drives the warm light LED lamp of the light awakening module to work through a power discharge circuit, and the brightness of the warm light LED lamp can be adjusted through the PWM wave to simulate natural light awakening.
Wi-Fi communication module 5 is located under the audio decoding module of the wearing front end, including ESP-8266. The ESP-8266 sends the acquired electroencephalogram digital signals to the cloud platform in real time, the cloud platform sends feedback control signals to the ESP-8266 after signal processing and analysis are carried out on the signals, and the ESP-8266 sends the received data to the control module, so that the relevant modules are controlled to wake up or hypnotize.
The power supply 6 is located at the left lower part of the wearing front end and comprises a lithium battery and a DC-DC conversion module controlled by a TPS63020 chip, the output voltage of the TPS63020 is adjustable, and the range can reach 1.2-5.5V, so that the output voltage can be divided into two paths, one path of the output voltage is boosted to 5V for stable output, the output voltage supplies power for the brain wave signal acquisition module, and the other path of the output voltage is stabilized and output by 3.3V for supplying power for other modules.
The electroencephalogram signal processing algorithm based on wavelet transformation extracts the energy ratio of each rhythm wave of the electroencephalogram signal. The EEG signals in different sleep stages are mainly distinguished in the time-frequency domain by different characteristic waves, the energy can be concentrated to represent the characteristics of the time-frequency domain of the signals, and the energy components of the different characteristic waves can be used as the basis for distinguishing the sleep stages, so that the characteristic waves of the EEG signals are extracted by using a wavelet transform method, and the energy characteristics of the characteristic waves are input into an individualized sleep stage system to be used as time domain characteristics for distinguishing the sleep stages.
The wavelet transform method is selected to extract the EEG characteristic waves and calculate the relative energy, and the flow of the energy characteristic extraction method is shown in FIG. 4. The basic method of wavelet transformation is to select a function meeting the condition of compatibility as a basic wavelet, to generate a function family by expanding and translating the basic wavelet, the function family forms a space model of the function, to map the signal to be processed on the function space model (namely decomposition and reconstruction), to obtain a new signal which is the same as the original time domain, and to obtain the time-scale characteristics of the signal by decomposition on a plurality of scales.
The Discrete Wavelet Transform (DWT) calculation formula for the discrete-time signal f (t) is:
in the formula 2jIs a scale factor, 2jk is a translation variable, #*(t) is the conjugate function of the orthogonal wavelet function ψ (t).
In signal processing studies, the principle of DWT is to decompose a signal into approximation coefficients (a) and detail coefficients (D) by passing the signal sequentially through sets of low-pass and high-pass filter banks using discrete, binary, orthogonal wavelet functions ψ (t). Mallat results for DWT:
wherein N is the number of discrete time series, N is 0,1, 2, …, N, A0f (n) is the original signal after sampling; j is 1, 2, …, N, j is the number of layers, k is the translation,are the filter coefficients.
In the wavelet transformation process, the selection of wavelet functions and transformation scales directly influences the accuracy of EEG signal feature extraction. When the db4 wavelet function is used, the amplitude-frequency characteristics of each rhythm wave are most obvious when the wavelet transform with the scale of 8 is used, and the wavelet coefficients and the corresponding frequency ranges after the DWT decomposition of 8 layers of db4 are shown in FIG. 5.
The distribution of the energy of the wavelet coefficient in the time domain and the frequency domain has obvious difference, and the energy can be used as the characteristic distribution information of each rhythm wave. From the correspondence relationship between wavelet coefficients and frequency ranges in fig. 5, in the present embodiment, wavelet coefficients D3 (band range: 6.25-12.5Hz), D2 (band range: 12.5-25Hz), D4+ D6 (band range: 3.906-7.813Hz), and D5+ D6 (band range: 2.344-4.688Hz) are selected to represent the α, β, θ, and δ rhythm waves, and energy characteristics are processed.
According to the Pasaval theorem, the total energy of the signals can be formed by adding the fractional energies of the signals in each orthogonal function set, and the energy of different signals can be used as characteristic parameters for distinguishing the waveforms of the signals. Because the EEG signals in different sleep periods have different energies and contain different rhythmic wave energies, the ratio of each rhythmic wave energy to the total energy can be used as a characteristic parameter for distinguishing the sleep periods. The EEG sleep stage derives energy in the time domain as: total energy E of signalallRelative energy E of each characteristic waveα、Eβ、Eθ、Eδ。
The energy of wavelet analysis of signal f (t) can be represented by:
in the above formula, EχRepresenting the reconstructed signal fχ(t) a band energy value; χ represents a rhythm wave; x is the number ofiRepresenting the reconstructed signal fχ(t) the corresponding amplitudes of the discrete points; and i is 0,1, …, m and represents the number of i sampling points of the electroencephalogram signal.
The relative energy (characteristic parameter for distinguishing sleep periods) is the ratio of wave energy of each rhythm to total energy, and the sleep parameter E 'of the user is obtained'χThe calculation method comprises the following steps:
wherein Ex ∈ (E)α,Eβ,Eθ,Eδ),EallIs a total energy value; eα、Eβ、Eθ、 EδThe rhythm wave energy of alpha, beta, theta and delta of the user is respectively, n is the type of the rhythm wave and represents the rhythm waves of alpha, beta, theta and delta in sequence.
The characteristic parameter is input into the personalized sleep staging system.
Personal characteristic information of a user and electroencephalogram signals (characteristic parameters) processed by a preceding stage are used as input vectors of a neural network, the output vector of the neural network is the evaluation result of 5 sleep state values (WAKE, N1, N2, SWS, REM), the network is trained by using enough samples, the actual output value is compared with an expected output value, and when the error is smaller than a set value, the set of weight values and threshold values held by the neural network are correct internal representation obtained by the network through self-adaptive learning. Two processes are involved:
a) a forward process: transmitting the input network through each unit until the output unit obtains the output result of the network;
b) and (3) reversing the process: the error between the actual output value and the desired output value is gradually returned to the input layer through the output layer, and the connection weight and the bias weight are adjusted until the error between the actual output value and the desired output value of the sample is less than a predetermined value.
As shown in fig. 6, the personalized sleep staging model sequentially includes a DWT time-frequency matrix extraction layer, a CNN input layer, a convolutional layer 1(Conv1), a convolutional layer 2(Conv2), a pooling layer 1(Pool1), a convolutional layer 3(Conv3), a fully-connected layer 1(FC1), a fully-connected layer 2(FC2), and an output layer.
The convolutional neural network was trained using an adammoptimizer optimizer based on tensorflow, with the learning rate initially set to 0.001, and the parameters of the neural network were optimized using a cross-entropy loss function as shown below:
wherein w and b represent the current weight and bias of the neural network; x represents an input sample; j represents an output layer neuron; y represents the output layer neuron expected output value; and a represents the actual output value of the neuron of the output layer.
The main difference in the time-frequency domain between different sleep stage EEG signals is the difference in the characteristic waves involved, as shown in fig. 7. The rule for the personalized sleep staging system to output the sleep state of the user includes:
a) WAKE period WAKE: the brain is completely conscious in the wake period, and brain waves in the wake period are mainly mixed alpha waves and beta waves. When more than 50% of a frame is alpha-waves, the frame can be determined as an awake period.
b) NREM sleep stage I: this phase is also called the dozing phase or the sleepy period, which is the transition period from the awake state to sleep. The main characteristic of this phase is that the alpha wave is gradually reduced, occupying less than 50% of the time, and the alpha wave is gradually replaced by the theta wave. K-complexes and fusiform waves do not occur.
c) NREM sleep phase II: this stage is generally considered to be the beginning of true sleep. In this stage, the brain wave amplitude becomes larger by the sleep fusiform wave and the k-complex wave.
Both NREM sleep stage I and NREM sleep stage II are LS stage
d) NREM sleep stage III: the period is mainly delta wave, the delta wave accounts for about 20% -50% of the EEG signal, and the peak-peak value of the brain wave amplitude is generally over 75 uV. At the moment, the sleep degree is deepened and the sleep is not easy to be awaken.
e) NREM sleep stage IV: this phase is a high deep sleep phase, with the same waveform as NREM sleep phase III, also dominated by the delta rhythm wave, but with more than 50% slow waves and a larger average amplitude. Since both NREM sleep stages III and IV are mainly characterized by S-waves having a low frequency, these two stages are collectively referred to as a slow wave sleep stage (SWS stage).
f) REM sleep period: the biggest characteristic of this stage is the unprecedented rapid eye movement. The REM and NREM sleep I phases are very similar in waveform, both being a mixed frequency wave containing an alpha wave and a beta wave, but the REM spike is not significant and is usually accompanied by a sawtooth wave. The REM phase is closely related to human memory, and most dreams occur at this stage. Different age groups have different optimal sleep times, and the proportion of REM in the total sleep time is also different. Generally, the smaller the age, the higher the proportion of REM.
In the embodiment, 8 groups of measured data of Sleep-EDF database in MIT-BIH physiological information base are used as EEG simulation data. Four of the data, sc4002e0, sc4012e0, sc4102e0, sc4112e0, were sleep data from healthy volunteers; the other 4 groups of data st7022j0, st7052j0, st7121j0 and st7132j0 are sleep data of the person with slight difficulty in falling asleep. During the data collection procedure, the subjects did not use any drugs and included both males and females, with ages between 21-35 years. EEG signals mainly adopt single-channel sleep data with Fpz-Cz as a lead mode and 100Hz sampling frequency. According to the R & K sleep stage standard, every 30s of EEG data is used as a sleep stage, all EEG sample data is divided into segments by every 30s of data (3000 data), each database has corresponding information for recording the sleep stage, the information is manually marked as a single sleep stage by a sleep specialist with abundant experience, and the information can be used as a verification result of the accuracy of the sleep stage.
Then, the sample data and the label data are input into the sleep staging model of the experiment for training, and a better sleep staging effect is obtained through continuous parameter adjustment. The optimal sleep stage classification effect obtained by us is shown in fig. 8, the global classification accuracy of the model is 81.9%, and the macro-average F1 value is 76.4%. Among all sleep stage classes, class W achieves the best classification effect, with an F1 value of 86.7%; the values of N2 and SWS F1 are more than 83%, and the classification effect of the two types is good; of all classes, stage N1 achieved the worst classification effect with an F1 value of only 43.7%.
Combining the data in the table of fig. 8, the experimental model has better resolution for most sleep stage categories.
The work flow of assisting sleep and awakening by the acousto-optic combined awakening device based on brain wave detection provided by the invention is shown in fig. 9. In the sleep assisting process, when the user is detected to be in a waking state, the cloud platform plays the sleep promoting music mixed with white noise through the remote control single chip microcomputer to guide the user to enter a light sleep state; once the user is detected to be in light sleep, the single chip microcomputer is controlled to play the hypnosis music mixed with pink noise, the user is guided to deep sleep step by step, and the volume of the played music is gradually reduced along with the deepening of the deep sleep. The invention provides two sleep mode selections for a user, wherein one sleep mode is a comfortable sleep mode, namely, the sleep time can be prolonged to a deep sleep time and the sleep quality can be improved when the user sleeps at night; the other mode is a afternoon nap mode, which is suitable for middle-noon nap and only goes into light sleep without leading to deep sleep, so that the mental state after waking up is improved.
Fig. 10 is a flowchart of the first phase wake-up procedure according to the present invention. In the awakening process, after the user sets the alarm clock time through the mobile phone APP, the system calculates the latest work starting time of the awakening system which can successfully awaken the user, the time that the user is in a deep sleep state is prolonged to the maximum degree when a better awakening effect is achieved, and the sleep quality of the user is improved. The working process is as follows: firstly, according to the preset alarm clock time, the time point of starting playing and awakening music is calculated, the relaxing music loaded with white noise is applied to the user through the bone conduction module, and meanwhile, the sleep state of the user is continuously identified. And if the sleep state of the person is detected to be changed from deep sleep to light sleep, the sound awakening part stops working.
Fig. 11 is a flowchart illustrating a second phase wake-up procedure according to the present invention. After the sound awakening is finished, the light awakening starts to work, and the working process is as follows: when the system starts the light awakening function, the system controls the LED lamp set to emit gradually bright light to simulate the awakening process of the human body by natural light and continuously identify the sleeping state of the user. And if the sleep state of the person is detected to be converted into the waking state, the light awakening part stops working.
If the awakening time set by the user is about to reach, and the sleep state identification system detects that the sleep state of the person is still in the non-awakening period, an emergency mechanism is started, and the user APP is used for alarm awakening.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Details not described in this specification are within the skill of the art that are well known to those skilled in the art.
Claims (10)
1. Reputation combines awakening device based on brain wave monitoring, its characterized in that: the device comprises:
wearing the front end: the system comprises a brain wave signal acquisition module for acquiring brain wave signals, a control module for processing data and sending control instructions according to sleep states, an acoustic awakening module for outputting audio data according to the control instructions, a light awakening module for emitting light according to the control instructions, a Wi-Fi communication module for remotely transmitting data and a power supply for supplying power to the system, wherein the sound awakening module is used for outputting audio data according to the control instructions;
cloud platform: the sleep parameter calculation module is used for calculating the sleep parameters of the user by adopting an electroencephalogram signal processing algorithm based on wavelet transformation according to the electroencephalogram signals collected by the wearing front end; the sleep parameters and the personal characteristic information of the user are output to the sleep state of the user through the personalized sleep staging system, and the sleep state is sent to the control module and the mobile terminal;
a mobile terminal: for receiving and displaying the sleep state of the user.
2. The acousto-optic combined wake-up device based on brain wave monitoring according to claim 1, characterized in that: the brain wave signal acquisition module is positioned above the inner side of the front end of the wearing front end and is tightly attached to the forehead of a user; the brain wave signal acquisition module is used for acquiring electroencephalogram signals of the right forehead or the left forehead, a middle electrode of the forehead is used as a reference electrode, and an electroencephalogram signal acquisition dry electrode is selected as an electrode material; the brain wave signal acquisition module performs pre-stage amplification on the acquired signals and adopts a trap circuit for filtering; and after the filtering is finished, converting the signal into a digital signal through the ADC.
3. The acousto-optic combined wake-up device based on brain wave monitoring according to claim 1, characterized in that: the sound awakening module comprises an audio decoding module (4) and a vibrator (8), and an ARM processor of the control module reads music data from the SD card through an SPI protocol and sends the music data to a decoding chip for decoding; when the sound awakening module works, the soothing music loaded with white noise is played, so that the sleep state of the user at the moment is changed from deep sleep to light sleep.
4. The acousto-optic combined wake-up device based on brain wave monitoring according to claim 1, characterized in that: the light awakening module is arranged on the inner side of the front end of the wearing front end, surrounds the periphery of the eyes of a user and comprises an LED aperture (7); the light awakening module adopts an LED aperture, and soft warm light with adjustable brightness is emitted to a user during working; the ARM processor of the control module drives the warm light LED lamp of the light awakening module to work through the power amplifier circuit, and the brightness is adjusted through the PWM wave to simulate natural light awakening.
5. The acousto-optic combined wake-up device based on brain wave monitoring according to claim 1, characterized in that: the electroencephalogram signal processing algorithm based on wavelet transformation extracts the energy ratio of each rhythm wave of the electroencephalogram signal, and obtains the sleep parameters of the user by taking the energy components of different characteristic waves as the basis for distinguishing the sleep stages.
6. The acousto-optic combined wake-up device based on brain wave monitoring according to claim 1, characterized in that: the personalized sleep staging system is a convolutional neural network model trained by samples, takes the sleep parameters and personal characteristic information of a user as input vectors and takes the sleep states as output values, wherein the sleep states comprise a WAKE period, a sleep 1 period N1, a sleep 2 period N2, a deep sleep period SWS and a rapid eye movement sleep period REM.
7. The acousto-optic combined wake-up device based on brain wave monitoring according to claim 5, characterized in that: sleep parameter E 'of the user'χThe calculation method comprises the following steps:
wherein Ex ∈ (E)α,Eβ,Eθ,Eδ),EallIs a total energy value; eα、Eβ、Eθ、EδThe rhythm wave energy of alpha, beta, theta and delta of the user is respectively, n is the type of the rhythm wave and sequentially represents the rhythm waves of alpha, beta, theta and delta.
8. The acousto-optic combined wake-up device based on brain wave monitoring according to claim 7, characterized in that: the wavelet transform-based electroencephalogram signal processing algorithm is characterized in that the frequency band ranges of alpha, beta, theta and delta rhythm waves in the electroencephalogram signal processing algorithm are respectively as follows: 6.25-12.5Hz, 12.5-25Hz, 3.906-7.813Hz and 2.344-4.688 Hz.
9. The acousto-optic combined wake-up device based on brain wave monitoring according to claim 8, characterized in that: the personalized sleep staging system outputs the rules of the sleep state of the user including:
a) and (3) during the wake period: comprises alpha and beta rhythm waves which are mixed, and when more than 50 percent of the alpha rhythm waves are alpha rhythm waves, the alpha rhythm waves are judged as a wake period;
b) NREM sleep stage I: comprises mixed alpha and theta rhythm waves, the alpha rhythm wave occupying less than 50% of time;
c) NREM sleep phase II: the brain wave amplitude is increased;
d) deep sleep period: delta rhythm wave accounts for 20% -50% of the signal, and the peak-to-peak value of brain wave amplitude is above 75 uV;
e) rapid eye movement period: including alpha and beta rhythm waves, with a sawtooth wave.
10. The acousto-optic combined wake-up device based on brain wave monitoring according to claim 1, characterized in that: and the mobile terminal stores and processes user data, including system setting, user information input, working parameter input, real-time sleep staging result display and historical sleep state change curve display.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011556862.4A CN112717253A (en) | 2020-12-25 | 2020-12-25 | Acousto-optic combined awakening device based on brain wave monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011556862.4A CN112717253A (en) | 2020-12-25 | 2020-12-25 | Acousto-optic combined awakening device based on brain wave monitoring |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112717253A true CN112717253A (en) | 2021-04-30 |
Family
ID=75615678
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011556862.4A Pending CN112717253A (en) | 2020-12-25 | 2020-12-25 | Acousto-optic combined awakening device based on brain wave monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112717253A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113397566A (en) * | 2021-07-29 | 2021-09-17 | 杭州云睡吧健康管理有限公司 | Sleep environment database establishing method and using method |
CN114569863A (en) * | 2022-05-07 | 2022-06-03 | 深圳市心流科技有限公司 | Sleep-assisted awakening method and system, electronic equipment and storage medium |
TWI806295B (en) * | 2021-12-17 | 2023-06-21 | 財團法人亞洲大學 | Improve insomnia training equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160015315A1 (en) * | 2014-07-21 | 2016-01-21 | Withings | System and method to monitor and assist individual's sleep |
US20160015314A1 (en) * | 2014-07-21 | 2016-01-21 | Withings | System and Method to Monitor and Assist Individual's Sleep |
CN106178222A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Based on magnetic intelligence assisting sleep method and system |
CN109316170A (en) * | 2018-11-16 | 2019-02-12 | 武汉理工大学 | Brain wave assisting sleep and wake-up system based on deep learning |
US20190251858A1 (en) * | 2018-02-12 | 2019-08-15 | Hypnocore Ltd. | Systems and methods for generating a presentation of an energy level based on sleep and daily activity |
CN110327040A (en) * | 2019-04-24 | 2019-10-15 | 武汉理工大学 | Sleep stage method and system based on cloud platform |
-
2020
- 2020-12-25 CN CN202011556862.4A patent/CN112717253A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160015315A1 (en) * | 2014-07-21 | 2016-01-21 | Withings | System and method to monitor and assist individual's sleep |
US20160015314A1 (en) * | 2014-07-21 | 2016-01-21 | Withings | System and Method to Monitor and Assist Individual's Sleep |
CN106178222A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Based on magnetic intelligence assisting sleep method and system |
US20190251858A1 (en) * | 2018-02-12 | 2019-08-15 | Hypnocore Ltd. | Systems and methods for generating a presentation of an energy level based on sleep and daily activity |
CN109316170A (en) * | 2018-11-16 | 2019-02-12 | 武汉理工大学 | Brain wave assisting sleep and wake-up system based on deep learning |
CN110327040A (en) * | 2019-04-24 | 2019-10-15 | 武汉理工大学 | Sleep stage method and system based on cloud platform |
Non-Patent Citations (2)
Title |
---|
朱双: "《流域水文分析与中长期预报方法》", 31 August 2020 * |
由育阳: "《机器学习智能诊断理论与应用》", 30 September 2020 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113397566A (en) * | 2021-07-29 | 2021-09-17 | 杭州云睡吧健康管理有限公司 | Sleep environment database establishing method and using method |
CN113397566B (en) * | 2021-07-29 | 2022-06-10 | 杭州云睡吧健康管理有限公司 | Sleep environment database establishing method and using method |
TWI806295B (en) * | 2021-12-17 | 2023-06-21 | 財團法人亞洲大學 | Improve insomnia training equipment |
CN114569863A (en) * | 2022-05-07 | 2022-06-03 | 深圳市心流科技有限公司 | Sleep-assisted awakening method and system, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108310587B (en) | Sleep control device and method | |
CN110841169B (en) | Deep learning sound stimulation system and method for sleep regulation | |
CN112717253A (en) | Acousto-optic combined awakening device based on brain wave monitoring | |
CN104257381A (en) | Voice frequency sleep assisting device based on brain wave signals | |
CN105833411A (en) | Novel intelligent sleeping-aiding and natural wakening method and device | |
US11185281B2 (en) | System and method for delivering sensory stimulation to a user based on a sleep architecture model | |
EP1886707A1 (en) | Sleep enhancing device | |
CN1882372A (en) | Sleep guidance system and related methods | |
CN206045144U (en) | A kind of novel intelligent sleeping and the device for waking up naturally | |
JP2016539758A (en) | MULTIPHASE SLEEP MANAGEMENT SYSTEM, ITS OPERATION METHOD, SLEEP ANALYSIS DEVICE, CURRENT SLEEP PHASE CLASSIFICATION METHOD, MULTIPHASE SLEEP MANAGEMENT SYSTEM, AND USE OF SLEEP ANALYSIS DEVICE IN MULTIPHASE SLEEP MANAGEMENT | |
CN105476631A (en) | EEG (electroencephalogram) based sleep detection and sleep aid method and device | |
CN102715902A (en) | Emotion monitoring method for special people | |
KR102114373B1 (en) | System and method for inducing sleep based on auditory stimulation | |
CN110947075A (en) | Personalized mental state adjusting system and method based on brainwave music | |
CN1739817A (en) | Personalized stereo health training method and equipment | |
CN107463646A (en) | A kind of sleeping music intelligent recommendation method and device | |
CN110167424A (en) | For exporting the system and method for indicating to be supplied to the indicator of the effect of stimulation of object during sleep period | |
CN211884899U (en) | Sleep-aiding instrument | |
CN106681123A (en) | Intelligent alarm clock adaptive control wake-up method and sleep monitoring system | |
CN107233653A (en) | Decompression method is loosened based on brain wave context aware and cloud platform storage technology | |
Shi et al. | A smart detection method of sleep quality using EEG signal and long short-term memory model | |
JP2022525985A (en) | Enhanced deep sleep based on information from frontal brain activity monitoring sensors | |
TWI524885B (en) | Pressure relief apparatus with brain entrainment | |
CN202802459U (en) | Musical device used for psychological regulation | |
CN115645707B (en) | Sleep stimulus control method based on sleep mode and related equipment |
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: 20210430 |
|
RJ01 | Rejection of invention patent application after publication |