CN111814830B - Sleep state detection model construction and sleep state detection method and device - Google Patents
Sleep state detection model construction and sleep state detection method and device Download PDFInfo
- Publication number
- CN111814830B CN111814830B CN202010517041.3A CN202010517041A CN111814830B CN 111814830 B CN111814830 B CN 111814830B CN 202010517041 A CN202010517041 A CN 202010517041A CN 111814830 B CN111814830 B CN 111814830B
- Authority
- CN
- China
- Prior art keywords
- sleep state
- respiratory
- signals
- user
- signal
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 112
- 238000010276 construction Methods 0.000 title claims abstract description 16
- 230000000241 respiratory effect Effects 0.000 claims abstract description 130
- 239000013598 vector Substances 0.000 claims abstract description 86
- 230000029058 respiratory gaseous exchange Effects 0.000 claims abstract description 77
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 28
- 238000013135 deep learning Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 38
- 230000015654 memory Effects 0.000 claims description 37
- 230000036391 respiratory frequency Effects 0.000 claims description 22
- 206010041235 Snoring Diseases 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 208000008784 apnea Diseases 0.000 claims description 6
- 230000036387 respiratory rate Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000002618 waking effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000035565 breathing frequency Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000004549 pulsed laser deposition Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Measuring devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Measuring devices for evaluating the respiratory organs
- A61B5/0826—Detecting or evaluating apnoea events
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4818—Sleep apnoea
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Pulmonology (AREA)
- Theoretical Computer Science (AREA)
- Psychiatry (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Anesthesiology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The embodiment of the invention relates to a sleep state detection model construction method, a sleep state detection method and a sleep state detection device, wherein the method comprises the following steps: acquiring a plurality of first respiration signals of a user in a sleep state and labels corresponding to the sleep state; determining a multidimensional feature vector corresponding to each first respiratory signal according to a plurality of parameter information in each first respiratory signal, and obtaining a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals; and inputting a plurality of the multidimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model, thereby accurately judging the sleep state of the human body.
Description
Technical Field
The embodiment of the invention relates to the field of intelligent bedrooms, in particular to a sleep state detection model construction method and a sleep state detection method and device.
Background
Along with the continuous progress of scientific technology, the Internet of things and intelligent home development are rapid, meanwhile, people pay more attention to life of people and convenience brought to health monitoring of people in an intelligent era, so that the development of intelligent bedrooms focusing on the sleep state of a human body is greatly focused, and meanwhile, the analysis of sleep data is also very important for doctors to diagnose sleep-related diseases.
In the prior art, the method for judging the snoring behavior of the human body is to judge the snoring behavior based on the signal characteristics extracted by the acoustic sensor, but the snoring signal is overlapped with the breathing signal in frequency and is similar to the amplitude of the human body motion signal, so that various signals are difficult to distinguish in the prior art, and the judgment of the sleep state of the human body is inaccurate.
Disclosure of Invention
In view of this, in order to solve the above-mentioned technical problem that the sleep state of the human body cannot be accurately determined, the embodiment of the invention provides a sleep state detection model construction method and a sleep state detection device.
In a first aspect, an embodiment of the present invention provides a method for constructing a sleep state detection model, including:
Acquiring a plurality of first respiration signals of a user in a sleep state and labels corresponding to the sleep state;
Determining a multidimensional feature vector corresponding to each first respiratory signal according to a plurality of parameter information in each first respiratory signal, and obtaining a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals;
and inputting the multi-dimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model.
In one possible embodiment, the method further comprises:
acquiring a sleep electric signal of a user in a sleep state;
Intercepting a plurality of first electrical signals with preset duration from the sleep electrical signals;
and acquiring corresponding first respiratory signals from each first electric signal to obtain a plurality of first respiratory signals corresponding to the first electric signals.
In one possible embodiment, the method further comprises:
And acquiring a sleep electric signal of the user in a sleep state through the piezoelectric sensor.
In one possible embodiment, the method further comprises:
And filtering each first electric signal according to the frequency range of the first electric signal to obtain a plurality of first respiration signals corresponding to the respiration of the user.
In one possible embodiment, the method further comprises:
Processing a plurality of first respiration signals according to time domain characteristics of signals generated during respiration of a user, and removing Gaussian errors of each first respiration signal to obtain a plurality of processed first respiration signals;
performing short-time Fourier transform on each processed first respiratory signal, and determining corresponding frequency domain characteristics;
determining a corresponding respiratory frequency of the user based on each of the frequency domain features;
Determining a plurality of parameter information for the corresponding first respiratory signal from each of the respiratory frequencies;
And carrying out vectorization processing on a plurality of parameter information of each first respiratory signal to obtain a multi-dimensional feature vector corresponding to each first respiratory signal, and further obtaining a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals.
In a second aspect, an embodiment of the present invention provides a method for detecting a sleep state of a user, including:
acquiring a sleep electric signal of a user in a sleep state;
Extracting a plurality of first respiratory signals from the sleep electrical signals;
Determining a plurality of parameter information from each first respiratory signal, and generating a multi-dimensional feature vector corresponding to each first respiratory signal based on a plurality of parameter information, so as to obtain a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals;
Inputting a plurality of the multi-dimensional feature vectors into the sleep state detection model constructed in any one of the first aspects, so that the sleep state detection model outputs the sleep state of the user.
In one possible embodiment, the method further comprises:
and sending the sleep state to a terminal device so that the terminal device can display the sleep state.
In a third aspect, an embodiment of the present invention provides an apparatus for constructing a sleep state detection model, including:
the acquisition module is used for acquiring a plurality of first breathing signals of a user in a sleep state and labels corresponding to the sleep state;
The data processing module is used for determining a multi-dimensional feature vector corresponding to each first respiration signal according to a plurality of parameter information in each first respiration signal to obtain a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiration signals;
And the training module is used for inputting a plurality of the multidimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model.
In a fourth aspect, an embodiment of the present invention provides a user sleep state detection apparatus, including:
the acquisition module is used for acquiring sleep electric signals of the user in a sleep state;
A data processing module for extracting a plurality of first respiration signals from the sleep electrical signals;
the data processing module is further configured to determine a plurality of parameter information from each first respiratory signal, and generate a multidimensional feature vector corresponding to each first respiratory signal based on the plurality of parameter information, so as to obtain a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals;
and the determining module is used for inputting a plurality of the multidimensional feature vectors into a sleep state detection model so that the sleep state detection model outputs the sleep state of the user.
In a fifth aspect, an embodiment of the present invention provides a sleep detection apparatus, including: the sleep state detection system comprises a processor and a memory, wherein the processor is used for executing a sleep state detection model construction and user sleep state detection program stored in the memory to realize the sleep state detection model construction method according to any one of the first aspect and the user sleep state detection method according to any one of the second aspect.
In a sixth aspect, an embodiment of the present invention provides a storage medium, including: the storage medium stores one or more programs executable by one or more processors to implement the sleep state detection model construction method of any one of the first aspects and the user sleep state detection method of any one of the second aspects.
According to the scheme for constructing the sleep state detection model, a plurality of first respiration signals of a user in a sleep state and labels corresponding to the sleep state are obtained; determining a multidimensional feature vector corresponding to each first respiratory signal according to a plurality of parameter information in each first respiratory signal, and obtaining a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals; and inputting a plurality of the multidimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model.
Drawings
Fig. 1 is a schematic flow chart of a method for constructing a sleep state detection model according to an embodiment of the present invention;
FIG. 2 is a flowchart of another method for constructing a sleep state detection model according to an embodiment of the present invention;
fig. 3 is a flow chart of a method for detecting sleep states of a user according to an embodiment of the present invention;
Fig. 4 is a schematic structural diagram of a sleep state detection model building device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a sleep state detection device for a user according to an embodiment of the present invention;
Fig. 6 is a schematic structural diagram of a sleep detection apparatus according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
For the purpose of facilitating an understanding of the embodiments of the present invention, reference will now be made to the following description of specific embodiments, taken in conjunction with the accompanying drawings, which are not intended to limit the embodiments of the invention.
Fig. 1 is a flow chart of a method for constructing a sleep state detection model according to an embodiment of the present invention, as shown in fig. 1, where the method specifically includes:
S11, acquiring a plurality of first respiration signals of a user in a sleep state and labels corresponding to the sleep state.
And in the piezoelectric signals of the user in the sleep state, which are acquired from the piezoelectric sensor, extracting a plurality of first respiration signals for a plurality of times according to the preset duration and the respiration frequency range, and recording a plurality of sleep states of the user represented by the plurality of first respiration signals into a sleep state label, wherein the state label at least comprises snoring conditions and apnea conditions.
S12, determining a multi-dimensional feature vector corresponding to each first respiratory signal according to the plurality of parameter information in each first respiratory signal, and obtaining a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals.
And carrying out data processing on each first respiration signal to obtain a plurality of parameter information corresponding to each first respiration signal, and forming a multi-dimensional feature vector by the plurality of parameter information corresponding to each first respiration signal so as to obtain a plurality of multi-dimensional feature vectors corresponding to the plurality of first respiration signals.
S13, inputting a plurality of multidimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model.
The method comprises the steps that a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals are input into an initial model, the model calculates and obtains an output user sleep state result according to input data, the result possibly does not accord with a pre-recorded state label, so that deep learning training is needed to be conducted on the model until the similarity between the user sleep state result output by the model and the state label is greater than or equal to a set threshold (for example, 90%), training of the model is considered to be completed, and the model trained at the moment is used as a sleep state detection model.
The scheme provides a sleep state detection model construction method, which comprises the steps of obtaining a plurality of first respiration signals of a user in a sleep state and labels corresponding to the sleep state; determining a multidimensional feature vector corresponding to each first respiratory signal according to a plurality of parameter information in each first respiratory signal, and obtaining a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals; and inputting a plurality of the multidimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model, so that analysis and prediction of the sleep state of a human body by collecting human body physiological signals can be realized.
Fig. 2 is a flow chart of another method for constructing a sleep state detection model according to an embodiment of the present invention, as shown in fig. 2, where the method specifically includes:
S21, acquiring a sleep electric signal of the user in a sleep state through a piezoelectric sensor.
The sleep detection equipment is arranged below the mattress, in a daily non-detection stage, the sleep detection equipment is in a standby mode, after a user gets on bed, a piezoelectric sensor arranged on the sleep detection equipment senses signal mutation, the sleep detection equipment starts a normal working mode, the piezoelectric sensor arranged on the sleep detection equipment starts to collect piezoelectric signals, and the collected piezoelectric signals comprise signals of all periods when the user is in a waking state and a sleeping state.
Further, the electric signal of the user in the awake state needs to be removed from the collected electric signals according to the respiratory frequency, heart rate and other parameters in the awake state, and the sleeping electric signal of the user in the sleeping state is reserved.
S22, intercepting a plurality of first electric signals with preset duration from the sleep electric signals.
From the reserved sleep electric signals, intercepting the sleep electric signals for a plurality of times according to a preset time length to obtain a plurality of first electric signals, wherein the interval time between intercepting the first electric signals for each two times is used for data processing of the first electric signals intercepted last time, in order to ensure the sampling effectiveness of the signals, the single measurement error is removed, and each measurement value needs to be weighted, and the following formula 1 is adopted:
(equation 1)
Where x is the signal measurement, n is the width of the sliding weighting process,Is the corresponding weight, and the sum is 1.
The preset time length can be 30s, 40 or 45s, and the scheme is adjusted according to the actual use process and is not particularly limited herein.
S23, filtering each first electric signal according to the frequency range of the first electric signal to obtain a plurality of first respiration signals corresponding to the respiration of the user.
According to the known respiratory rate of a general person, an IIR multi-order filter is preset, each first electric signal of the intercepted first electric signals is subjected to filtering processing, and a corresponding first respiratory signal is separated from each first electric signal.
S24, processing the plurality of first respiration signals according to the time domain characteristics of signals generated during respiration of the user, and removing Gaussian errors of each first respiration signal to obtain a plurality of processed first respiration signals.
Because the sensitivity of the piezoelectric sensor is higher, a large jump signal can be generated by slight touch, the acquired first respiratory signal data is required to be processed according to the time domain characteristics of signals generated during respiration of a user, jump values are filtered, namely Gaussian errors of each first respiratory signal are removed, missing values in the signal processing process are filled through polynomial fitting and interpolation operation, signal continuity is guaranteed, and a plurality of processed first respiratory signals are obtained.
S25, performing short-time Fourier transform on each processed first respiratory signal, and determining corresponding frequency domain characteristics.
S26, determining the breathing frequency of the corresponding user based on each frequency domain feature.
And performing short-time Fourier transform on the processed first respiration signals, and decomposing each first respiration signal into a frequency spectrum to further obtain the frequency domain characteristic corresponding to each first respiration signal.
Further, a plurality of corresponding respiratory frequencies are determined according to the obtained frequency domain characteristics corresponding to each first respiratory signal.
S27, determining a plurality of parameter information of the corresponding first respiratory signals from each respiratory frequency.
And obtaining a plurality of parameter information of the first respiratory signal according to the respiratory frequency, wherein the parameter information at least comprises parameters such as high frequency, low frequency, amplitude, energy, mean value, variance, root mean square error or median value of the respiratory frequency.
S28, vectorizing the multiple parameter information of each first respiratory signal to obtain a multidimensional feature vector corresponding to each first respiratory signal, and further obtaining multiple multidimensional feature vectors corresponding to the multiple first respiratory signals.
And forming a multidimensional feature vector by the parameter information of each first respiratory signal, so as to obtain a plurality of multidimensional feature vectors corresponding to the first respiratory signals.
Further, according to the parallel particle swarm optimization algorithm, the accuracy of the output result of the sleep state detection model is used as fitness, the parameter information is subjected to optimization processing, one or more unnecessary parameters are removed, and therefore the training convergence speed of the sleep state detection model is increased, and the accuracy of the prediction result of the sleep state detection model is improved.
According to the scheme for constructing the sleep state detection model, the piezoelectric sensor is used for acquiring the sleep electric signal of the user in the sleep state, the sleep electric signal is processed, the breathing signal is separated, the breathing signal is further processed to obtain a plurality of signal parameter information, a plurality of multidimensional feature vectors are formed, the multidimensional feature vectors are input into the sleep state detection model, and the sleep state of the user is predicted.
Fig. 3 is a flow chart of a method for detecting a sleep state of a user according to an embodiment of the present invention, as shown in fig. 3, where the method specifically includes:
S31, acquiring a sleep electric signal of the user in a sleep state.
The sleep detection equipment is arranged below the mattress, in a daily non-detection stage, the sleep detection equipment is in a standby mode, after a user gets on bed, a piezoelectric sensor arranged on the sleep detection equipment senses signal mutation, the sleep detection equipment starts a normal working mode, the piezoelectric sensor arranged on the sleep detection equipment starts to collect piezoelectric signals, the collected piezoelectric signals comprise signals of all periods of the user in a waking state and a sleeping state, further, the electric signals of the user in the waking state are removed from the collected electric signals according to the respiratory frequency, heart rate and other parameters of the user in the waking state, and the sleeping electric signals of the user in the sleeping state are reserved.
S32, extracting a plurality of first respiration signals from the sleep electric signals.
And intercepting the sleep electric signals from the reserved sleep electric signals for a plurality of times to obtain a plurality of first electric signals, presetting an IIR multi-order filter according to the known respiratory frequency of a common person, filtering each intercepted first electric signal of the plurality of first electric signals, and separating a corresponding first respiratory signal from each first electric signal.
S33, determining a plurality of parameter information from each first respiratory signal, and generating a multi-dimensional feature vector corresponding to each first respiratory signal based on the plurality of parameter information, so as to obtain a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals.
In the embodiment of the invention, firstly, because the sensitivity of the piezoelectric sensor is higher, a large jump signal can be generated by slight touch, the acquired first respiratory signal data is required to be processed according to the time domain characteristics of the signals generated during respiration of a user, the Gaussian error of each first respiratory signal is removed, the missing value in the signal processing process is filled through polynomial fitting and interpolation operation, the signal continuity is ensured, a plurality of processed first respiratory signals are further obtained, the processed first respiratory signals are subjected to short-time Fourier transform, each first respiratory signal is decomposed into frequency spectrums, the frequency domain characteristics corresponding to each first respiratory signal are further obtained, a plurality of corresponding respiratory frequencies are determined according to the frequency domain characteristics corresponding to each first respiratory signal, and a plurality of parameter information of the first respiratory signal is obtained according to the respiratory frequencies.
Further, the multi-dimensional feature vector is formed by the parameter information of each first respiratory signal, and a plurality of multi-dimensional feature vectors corresponding to the first respiratory signals are obtained.
S34, inputting a plurality of the multidimensional feature vectors into the sleep state detection model constructed according to any one of claims 1 to 5, so that the sleep state detection model outputs the sleep state of the user.
And S35, sending the sleep state to a terminal device so that the terminal device displays the sleep state.
And inputting the obtained multiple multidimensional feature vectors into a trained sleep state detection model, and outputting the detected sleep state of the user.
The sleep state includes respiratory rate (times/minutes), snoring period and apnea period.
Further, the output result is fed back to the app of the mobile terminal held by the user, so that the user can conveniently check the sleep state.
According to the user sleep state detection method provided by the embodiment of the invention, the sleep electric signal of the user in the sleep state is obtained; extracting a plurality of first respiratory signals from the sleep electrical signals; determining a plurality of parameter information from each first respiratory signal, and generating a multi-dimensional feature vector corresponding to each first respiratory signal based on a plurality of parameter information, so as to obtain a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals; the multi-dimensional feature vectors are input into the sleep state detection model, so that the sleep state detection model outputs the sleep state of the user, and the method can accurately judge the sleep state of the human body by detecting the physiological signals of the human body and provides convenience for a doctor to diagnose the sleep-related diseases.
Fig. 4 is a schematic structural diagram of a sleep state detection model building device according to an embodiment of the present invention, which specifically includes:
An obtaining module 401, configured to obtain a plurality of first respiratory signals of a user in a sleep state, and a tag corresponding to the sleep state;
the data processing module 402 is configured to determine a multidimensional feature vector corresponding to each first respiratory signal according to a plurality of parameter information in each first respiratory signal, so as to obtain a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals;
The training module 403 is configured to input a plurality of the multidimensional feature vectors into an initial model, perform deep learning training, and determine that the training of the initial model is completed when the similarity between the output result of the initial model and the label is greater than or equal to a set threshold, and use the trained initial model as a sleep state detection model.
The acquisition module is specifically used for acquiring sleep electric signals of the user in a sleep state; intercepting a plurality of first electrical signals with preset duration from the sleep electrical signals; and acquiring corresponding first respiratory signals from each first electric signal to obtain a plurality of first respiratory signals corresponding to the first electric signals.
In a possible implementation manner, the acquisition module is further used for acquiring the sleeping electric signal of the user in a sleeping state through the piezoelectric sensor.
In one possible implementation manner, the obtaining module is further configured to perform filtering processing on each of the first electrical signals according to the frequency range of the first electrical signals, so as to obtain a plurality of first respiration signals corresponding to respiration of the user.
The data processing module is specifically used for processing a plurality of first respiration signals according to time domain characteristics of signals generated during respiration of a user, removing Gaussian errors of each first respiration signal and obtaining a plurality of processed first respiration signals; performing short-time Fourier transform on each processed first respiratory signal, and determining corresponding frequency domain characteristics; determining a corresponding respiratory frequency of the user based on each of the frequency domain features; determining a plurality of parameter information for the corresponding first respiratory signal from each of the respiratory frequencies; and carrying out vectorization processing on a plurality of parameter information of each first respiratory signal to obtain a multi-dimensional feature vector corresponding to each first respiratory signal, and further obtaining a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals.
The device for constructing the sleep state detection model provided in this embodiment may be a device for constructing the sleep state detection model as shown in fig. 4, and may perform all steps of the method for constructing the sleep state detection model as shown in fig. 1-2, so as to achieve the technical effects of the method for constructing the sleep state detection model as shown in fig. 1-2, and the detailed description is omitted herein for brevity.
Fig. 5 is a schematic structural diagram of a user sleep state detection apparatus according to an embodiment of the present invention, which specifically includes:
an acquisition module 501, configured to acquire a sleep electric signal when a user is in a sleep state;
a data processing module 502 for extracting a plurality of first respiration signals from the sleep electrical signals;
The data processing module 502 is further configured to determine a plurality of parameter information from each of the first respiratory signals, and generate a multidimensional feature vector corresponding to each of the first respiratory signals based on the plurality of parameter information, so as to obtain a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals;
A determining module 503, configured to input a plurality of the multidimensional feature vectors into a sleep state detection model, so that the sleep state detection model outputs a sleep state of the user.
The user sleep state detection apparatus provided in this embodiment may be a user sleep state detection apparatus as shown in fig. 5, and may perform all steps of the method for constructing the sleep state detection model as shown in fig. 3, so as to achieve the technical effects of the user sleep state detection method as shown in fig. 3, and the description thereof will be specifically referred to in fig. 3, and is omitted herein for brevity.
Fig. 6 is a schematic structural diagram of a sleep detection apparatus according to an embodiment of the present invention, and an electronic apparatus 600 shown in fig. 6 includes: at least one processor 601, memory 602, at least one network interface 604, and other user interfaces 603. The various components in the sleep detection apparatus 600 are coupled together by a bus system 605. It is understood that the bus system 605 is used to enable connected communications between these components. The bus system 605 includes a power bus, a control bus, and a status signal bus in addition to a data bus. But for clarity of illustration the various buses are labeled as bus system 605 in fig. 6.
The user interface 603 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, a trackball, a touch pad, or a touch screen, etc.).
It is to be appreciated that the memory 602 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate Synchronous dynamic random access memory (Double DATA RATE SDRAM, DDRSDRAM), enhanced Synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCH LINK DRAM, SLDRAM), and Direct memory bus random access memory (DRRAM). The memory 602 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some implementations, the memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 6021 and application programs 6022.
The operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. Application 6022 includes various applications such as a media player (MEDIA PLAYER), browser (Browser), etc. for implementing various application services. The program for implementing the method of the embodiment of the present invention may be included in the application 6022.
In the embodiment of the present invention, the processor 601 is configured to execute the method steps provided by the method embodiments by calling a program or an instruction stored in the memory 602, specifically, a program or an instruction stored in the application 6022, for example, including:
Acquiring a plurality of first respiration signals of a user in a sleep state and labels corresponding to the sleep state; determining a multidimensional feature vector corresponding to each first respiratory signal according to a plurality of parameter information in each first respiratory signal, and obtaining a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals; and inputting the multi-dimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model.
In one possible implementation, acquiring a sleep electrical signal of a user in a sleep state; intercepting a plurality of first electrical signals with preset duration from the sleep electrical signals; and acquiring corresponding first respiratory signals from each first electric signal to obtain a plurality of first respiratory signals corresponding to the first electric signals.
In one possible embodiment, the sleep electric signal of the user in the sleep state is acquired by the piezoelectric sensor.
In one possible implementation manner, each first electric signal is subjected to filtering processing according to the frequency range of the first electric signal, so as to obtain a plurality of first respiration signals corresponding to respiration of the user.
In one possible implementation manner, processing a plurality of first respiration signals according to the time domain characteristics of signals generated when a user breathes, and removing the gaussian error of each first respiration signal to obtain a plurality of processed first respiration signals; performing short-time Fourier transform on each processed first respiratory signal, and determining corresponding frequency domain characteristics; determining a corresponding respiratory frequency of the user based on each of the frequency domain features; determining a plurality of parameter information for the corresponding first respiratory signal from each of the respiratory frequencies; and carrying out vectorization processing on a plurality of parameter information of each first respiratory signal to obtain a multi-dimensional feature vector corresponding to each first respiratory signal, and further obtaining a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals.
Or alternatively, the first and second heat exchangers may be,
Acquiring a sleep electric signal of a user in a sleep state; extracting a plurality of first respiratory signals from the sleep electrical signals; determining a plurality of parameter information from each first respiratory signal, and generating a multi-dimensional feature vector corresponding to each first respiratory signal based on a plurality of parameter information, so as to obtain a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals; and inputting a plurality of the multidimensional feature vectors into a sleep state detection model so that the sleep state detection model outputs the sleep state of the user.
In one possible implementation, the sleep state is sent to a terminal device, so that the terminal device en displays the sleep state.
The method disclosed in the above embodiment of the present invention may be applied to the processor 601 or implemented by the processor 601. The processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 601 or instructions in the form of software. The Processor 601 may be a general purpose Processor, a digital signal Processor (DIGITAL SIGNAL Processor, DSP), an Application SPECIFIC INTEGRATED Circuit (ASIC), an off-the-shelf programmable gate array (Field Programmable GATE ARRAY, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software elements in a decoding processor. The software elements may be located in a random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 602, and the processor 601 reads information in the memory 602 and performs the steps of the above method in combination with its hardware.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the Processing units may be implemented within one or more Application SPECIFIC INTEGRATED Circuits (ASICs), digital signal processors (DIGITAL SIGNAL Processing, DSPs), digital signal Processing devices (DSPDEVICE, DSPD), programmable logic devices (Programmable Logic Device, PLDs), field-Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units for performing the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
The sleep detection apparatus provided in this embodiment may be a sleep detection apparatus as shown in fig. 6, and may perform all steps of the method for constructing the sleep state detection model shown in fig. 1-2 and the method for detecting the user sleep state shown in fig. 3, so as to further implement the technical effects of the method for constructing the sleep state detection model shown in fig. 1-2 and the method for detecting the user sleep state shown in fig. 3, and specifically please refer to the related descriptions in fig. 1-2 and fig. 3, which are not repeated herein for brevity.
The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium here stores one or more programs. Wherein the storage medium may comprise volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid state disk; the memory may also comprise a combination of the above types of memories.
When one or more programs in the storage medium are executable by one or more processors, the automatic printing method executed on the sleep detection apparatus side is realized.
The processor is used for executing a sleep state detection model construction and user sleep state detection program stored in the memory to realize the following steps of a sleep state detection model construction method and a user sleep state detection method executed on the sleep detection equipment side:
Acquiring a plurality of first respiration signals of a user in a sleep state and labels corresponding to the sleep state; determining a multidimensional feature vector corresponding to each first respiratory signal according to a plurality of parameter information in each first respiratory signal, and obtaining a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals; and inputting the multi-dimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model.
In one possible implementation, acquiring a sleep electrical signal of a user in a sleep state; intercepting a plurality of first electrical signals with preset duration from the sleep electrical signals; and acquiring corresponding first respiratory signals from each first electric signal to obtain a plurality of first respiratory signals corresponding to the first electric signals.
In one possible embodiment, the sleep electric signal of the user in the sleep state is acquired by the piezoelectric sensor.
In one possible implementation manner, each first electric signal is subjected to filtering processing according to the frequency range of the first electric signal, so as to obtain a plurality of first respiration signals corresponding to respiration of the user.
In one possible implementation manner, processing a plurality of first respiration signals according to the time domain characteristics of signals generated when a user breathes, and removing the gaussian error of each first respiration signal to obtain a plurality of processed first respiration signals; performing short-time Fourier transform on each processed first respiratory signal, and determining corresponding frequency domain characteristics; determining a corresponding respiratory frequency of the user based on each of the frequency domain features; determining a plurality of parameter information for the corresponding first respiratory signal from each of the respiratory frequencies; and carrying out vectorization processing on a plurality of parameter information of each first respiratory signal to obtain a multi-dimensional feature vector corresponding to each first respiratory signal, and further obtaining a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals.
Or alternatively, the first and second heat exchangers may be,
Acquiring a sleep electric signal of a user in a sleep state; extracting a plurality of first respiratory signals from the sleep electrical signals; determining a plurality of parameter information from each first respiratory signal, and generating a multi-dimensional feature vector corresponding to each first respiratory signal based on a plurality of parameter information, so as to obtain a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals; and inputting a plurality of the multidimensional feature vectors into a sleep state detection model so that the sleep state detection model outputs the sleep state of the user.
In one possible implementation, the sleep state is sent to a terminal device, so that the terminal device en displays the sleep state.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of function in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. A method of sleep state detection model construction, comprising:
acquiring a plurality of first respiration signals of a user in a sleep state and a label corresponding to the sleep state, wherein the label at least comprises snoring conditions and apnea conditions;
Determining a multidimensional feature vector corresponding to each first respiratory signal according to a plurality of parameter information in each first respiratory signal to obtain a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals, wherein the parameter information at least comprises high frequency, low frequency, amplitude, energy, mean, variance, root mean square error or median of respiratory frequency;
Inputting a plurality of multidimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model, wherein the sleep state comprises respiratory rate, snoring time period and apnea time period;
Wherein the acquiring the plurality of first respiration signals of the user in the sleep state includes:
acquiring a sleep electric signal of a user in a sleep state;
Intercepting a plurality of first electrical signals with preset duration from the sleep electrical signals;
Acquiring corresponding first respiratory signals from each first electric signal to obtain a plurality of first respiratory signals corresponding to a plurality of first electric signals;
determining a multidimensional feature vector corresponding to each first respiratory signal according to a plurality of parameter information in each first respiratory signal to obtain a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals, including:
Processing a plurality of first respiration signals according to time domain characteristics of signals generated during respiration of a user, and removing Gaussian errors of each first respiration signal to obtain a plurality of processed first respiration signals;
performing short-time Fourier transform on each processed first respiratory signal, and determining corresponding frequency domain characteristics;
determining a corresponding respiratory frequency of the user based on each of the frequency domain features;
Determining a plurality of parameter information for the corresponding first respiratory signal from each of the respiratory frequencies;
And carrying out vectorization processing on a plurality of parameter information of each first respiratory signal to obtain a multi-dimensional feature vector corresponding to each first respiratory signal, and further obtaining a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals.
2. The method of claim 1, wherein the acquiring the sleep electrical signal of the user in the sleep state comprises:
And acquiring a sleep electric signal of the user in a sleep state through the piezoelectric sensor.
3. The method according to claim 2, wherein said obtaining a corresponding first respiration signal from each of the first electrical signals, to obtain a plurality of first respiration signals corresponding to a plurality of the first electrical signals, comprises:
And filtering each first electric signal according to the frequency range of the first electric signal to obtain a plurality of first respiration signals corresponding to the respiration of the user.
4.A method for detecting a sleep state of a user, comprising:
acquiring a sleep electric signal of a user in a sleep state;
Extracting a plurality of first respiratory signals from the sleep electrical signals;
Determining a plurality of parameter information from each first respiratory signal, and generating a multi-dimensional feature vector corresponding to each first respiratory signal based on a plurality of parameter information, so as to obtain a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals; inputting a plurality of the multi-dimensional feature vectors into the sleep state detection model constructed as claimed in any one of claims 1 to 3, so that the sleep state detection model outputs the sleep state of the user.
5. The method according to claim 4, wherein the method further comprises:
and sending the sleep state to a terminal device so that the terminal device displays the sleep state.
6. A device for sleep state detection model construction, comprising:
The device comprises an acquisition module, a detection module and a display module, wherein the acquisition module is used for acquiring a plurality of first breathing signals of a user in a sleep state and labels corresponding to the sleep state, and the labels at least comprise snoring conditions and apnea conditions;
The data processing module is used for determining a multidimensional feature vector corresponding to each first respiration signal according to a plurality of parameter information in each first respiration signal to obtain a plurality of multidimensional feature vectors corresponding to a plurality of first respiration signals, wherein the parameter information at least comprises high frequency, low frequency, amplitude, energy, mean value, variance, root mean square error or median value of respiration frequency;
The training module is used for inputting a plurality of the multidimensional feature vectors into an initial model, performing deep learning training until the similarity between the output result of the initial model and the label is greater than or equal to a set threshold value, determining that the training of the initial model is completed, and taking the trained initial model as a sleep state detection model, wherein the sleep state comprises respiratory rate, snoring time period and apnea time period;
The acquisition module is also used for acquiring a sleep electric signal of the user in a sleep state; intercepting a plurality of first electrical signals with preset duration from the sleep electrical signals; acquiring corresponding first respiratory signals from each first electric signal to obtain a plurality of first respiratory signals corresponding to a plurality of first electric signals;
The data processing module is further used for processing a plurality of first respiration signals according to time domain characteristics of signals generated during respiration of a user, removing Gaussian errors of each first respiration signal and obtaining a plurality of processed first respiration signals; performing short-time Fourier transform on each processed first respiratory signal, and determining corresponding frequency domain characteristics; determining a corresponding respiratory frequency of the user based on each of the frequency domain features; determining a plurality of parameter information for the corresponding first respiratory signal from each of the respiratory frequencies; and carrying out vectorization processing on a plurality of parameter information of each first respiratory signal to obtain a multi-dimensional feature vector corresponding to each first respiratory signal, and further obtaining a plurality of multi-dimensional feature vectors corresponding to a plurality of first respiratory signals.
7. A user sleep state detection apparatus applied to the user sleep state detection method as claimed in any one of claims 4-5, characterized by comprising:
the acquisition module is used for acquiring sleep electric signals of the user in a sleep state;
A data processing module for extracting a plurality of first respiration signals from the sleep electrical signals;
the data processing module is further configured to determine a plurality of parameter information from each first respiratory signal, and generate a multidimensional feature vector corresponding to each first respiratory signal based on the plurality of parameter information, so as to obtain a plurality of multidimensional feature vectors corresponding to a plurality of first respiratory signals;
and the determining module is used for inputting a plurality of the multidimensional feature vectors into a sleep state detection model so that the sleep state detection model outputs the sleep state of the user.
8. A sleep detection apparatus, comprising: the sleep state detection system comprises a processor and a memory, wherein the processor is used for executing a sleep state detection model construction and a user sleep state detection program stored in the memory so as to realize the sleep state detection model construction method according to any one of claims 1-3 or the user sleep state detection method according to any one of claims 4-5.
9. A storage medium storing one or more programs executable by one or more processors to implement the method of sleep state detection model construction of any one of claims 1-3 or the method of user sleep state detection of any one of claims 4-5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010517041.3A CN111814830B (en) | 2020-06-08 | 2020-06-08 | Sleep state detection model construction and sleep state detection method and device |
| PCT/CN2020/140494 WO2021248882A1 (en) | 2020-06-08 | 2020-12-29 | Methods and apparatuses for constructing sleep state detection model and for detecting sleep state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010517041.3A CN111814830B (en) | 2020-06-08 | 2020-06-08 | Sleep state detection model construction and sleep state detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111814830A CN111814830A (en) | 2020-10-23 |
| CN111814830B true CN111814830B (en) | 2024-07-09 |
Family
ID=72846489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010517041.3A Active CN111814830B (en) | 2020-06-08 | 2020-06-08 | Sleep state detection model construction and sleep state detection method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111814830B (en) |
| WO (1) | WO2021248882A1 (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814830B (en) * | 2020-06-08 | 2024-07-09 | 珠海格力电器股份有限公司 | Sleep state detection model construction and sleep state detection method and device |
| CN113040710B (en) * | 2021-03-01 | 2022-05-17 | 珠海格力电器股份有限公司 | Sleep state analysis method and device |
| CN115120837A (en) * | 2022-06-27 | 2022-09-30 | 慕思健康睡眠股份有限公司 | Sleep environment adjusting method, system, device and medium based on deep learning |
| CN116030534B (en) * | 2023-02-22 | 2023-07-18 | 中国科学技术大学 | Sleep posture model training method and sleep posture recognition method |
| CN116808391B (en) * | 2023-06-29 | 2023-12-26 | 北京理工大学 | Sleep awakening method and system based on physiological signal decoding |
| CN117017233B (en) * | 2023-10-08 | 2024-01-09 | 华南师范大学 | Sleep apnea detection method, device, equipment and storage medium |
| CN117077013B (en) * | 2023-10-12 | 2024-03-26 | 之江实验室 | Sleep spindle wave detection method, electronic equipment and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111012132A (en) * | 2019-12-17 | 2020-04-17 | 珠海格力电器股份有限公司 | Sleep state adjusting method and device based on pillow and intelligent pillow |
| CN111227792A (en) * | 2020-01-10 | 2020-06-05 | 京东方科技集团股份有限公司 | Apnea detection method and system, electronic device and storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013025922A1 (en) * | 2011-08-16 | 2013-02-21 | The University Of Utah Research Foundation | Monitoring breathing via signal strength in wireless networks |
| CN106388818B (en) * | 2016-09-21 | 2019-05-07 | 广州视源电子科技股份有限公司 | Method and system for extracting characteristic information of sleep state monitoring model |
| KR20180075832A (en) * | 2016-12-27 | 2018-07-05 | 바이텔스 주식회사 | Method and Apparatus for Monitoring Sleep State |
| JP2022502153A (en) * | 2018-10-01 | 2022-01-11 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | Systems and methods for determining sleep stages |
| CN109259733A (en) * | 2018-10-25 | 2019-01-25 | 深圳和而泰智能控制股份有限公司 | Apnea detection method, apparatus and detection device in a kind of sleep |
| CN110623665A (en) * | 2019-09-26 | 2019-12-31 | 川北医学院 | An intelligent sleep phase detection and sleep quality assessment system and method |
| CN111035367B (en) * | 2019-12-31 | 2021-05-18 | 华南师范大学 | A signal detection system for judging sleep apnea |
| CN111814830B (en) * | 2020-06-08 | 2024-07-09 | 珠海格力电器股份有限公司 | Sleep state detection model construction and sleep state detection method and device |
-
2020
- 2020-06-08 CN CN202010517041.3A patent/CN111814830B/en active Active
- 2020-12-29 WO PCT/CN2020/140494 patent/WO2021248882A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111012132A (en) * | 2019-12-17 | 2020-04-17 | 珠海格力电器股份有限公司 | Sleep state adjusting method and device based on pillow and intelligent pillow |
| CN111227792A (en) * | 2020-01-10 | 2020-06-05 | 京东方科技集团股份有限公司 | Apnea detection method and system, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021248882A1 (en) | 2021-12-16 |
| CN111814830A (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814830B (en) | Sleep state detection model construction and sleep state detection method and device | |
| EP2457504B1 (en) | Sleep apnea syndrome examination device and program | |
| US8639320B2 (en) | Muscle-activity diagnosis apparatus, method, and program | |
| CN104706318B (en) | A kind of sleep analysis method and device | |
| CN109480783B (en) | Apnea detection method and device and computing equipment | |
| EP2962637A1 (en) | Human motion status monitoring method and device | |
| EP3655895A1 (en) | Discovering novel features to use in machine learning techniques, such as machine learning techniques for diagnosing medical conditions | |
| CN108697352B (en) | Physiological information measuring method, physiological information monitoring device and equipment | |
| CN106618560B (en) | Method and device for processing brain wave signals | |
| Cohen-McFarlane et al. | Comparison of silence removal methods for the identification of audio cough events | |
| Gahane et al. | An analytical review of heart failure detection based on IoT and machine learning | |
| Sharan et al. | Automated cough sound analysis for detecting childhood pneumonia | |
| Roy et al. | Recent advances in PCG signal analysis using AI: a review | |
| CN103892797B (en) | A signal processing method and device for sleep structure analysis | |
| Gong et al. | Accurate cirrhosis identification with wrist-pulse data for mobile healthcare | |
| CN112957018A (en) | Heart state detection method and device based on artificial intelligence | |
| Kwiatkowski et al. | Phonocardiogram segmentation with tiny computing | |
| CN115708677A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN113974575B (en) | Sleep staging method and device, electronic equipment and storage medium | |
| CN114983436A (en) | Electronic device for the identification of insomnia disorder based on awake resting-state EEG | |
| Chattopadhyay et al. | Sleep apnea diagnosis by DWT-based kurtosis, radar and histogram analysis of electrocardiogram | |
| CN117426755A (en) | Sleep monitoring method and device and intelligent equipment | |
| Xin et al. | Wearable Sleep Monitoring System Based on Machine Learning Using Snoring Sound Signal | |
| Mallick et al. | Resource-Constrained Device Characterization for Detecting Sleep Apnea Using Machine Learning | |
| CN113633280A (en) | In-bed and out-of-bed detection method, detection system, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |