CN109480783A - A kind of apnea detection method, apparatus and calculate equipment - Google Patents
A kind of apnea detection method, apparatus and calculate equipment Download PDFInfo
- Publication number
- CN109480783A CN109480783A CN201811564593.9A CN201811564593A CN109480783A CN 109480783 A CN109480783 A CN 109480783A CN 201811564593 A CN201811564593 A CN 201811564593A CN 109480783 A CN109480783 A CN 109480783A
- Authority
- CN
- China
- Prior art keywords
- apnea
- characteristic
- respiratory
- human body
- envelope
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—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
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7282—Event detection, e.g. detecting unique waveforms indicative of a medical condition
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention relates to breathing detection technical fields, it in particular discloses a kind of apnea detection method, apparatus and calculates equipment and computer storage medium, wherein, method includes: to extract the respiratory characteristic of the human body respiration signal, wherein, the respiratory characteristic of the human body respiration signal includes envelope characteristic, statistical nature and trend feature；The respiratory characteristic is input in default neural network model, is handled by default neural network model, obtains processing result；According to the processing result, it is determined whether there are apneas.It can be seen that, the distinguishing characteristics that the present invention program uses envelope characteristic, statistical nature and the trend feature of piezoelectric membrane acquisition human body respiration signal to identify as apnea, and neural network recognition apnea is used, it facilitates user and carries out domestic sleeping monitoring.
Description
Technical field
Embodiment of the present invention is related to breathing detection technical field, more particularly to a kind of apnea detection method, dress
It sets, calculate equipment and computer storage medium.
Background technique
Apnea is a kind of obstructive sleep apnea disease or central sleep asphyxia disease with sleep mutually respectively, Huan Zhe
Occurs respiratory air flow stopping in sleep procedure repeatedly, the duration is more than 10 seconds or throughput is sleep lower than normal 20%
Pause, it is not noticeable since apnea occurs in sleep procedure, if long-term apnea phenomenon is undiscovered, obtain
Less than effective treatment, it just will appear a series of disease, therefore, detection apnea is most important to human health.
Have portable apnea detection equipment at present, according to the difference of measurement method, is broadly divided into electrocardiosignal class
Detection device and mouth and nose class of traffic detection device.
In the implementation of the present invention, discovery: electrocardiosignal class detection device is needed electrocardio the present inventor
With electrode is attached to the whole night, discomfort can be caused to patient；Mouth and nose class of traffic detection device needs to pass when monitoring mouth and nose air-flow
Sensor is affixed below nasal cavity, can also be impacted to the sleep of patient.
Summary of the invention
In view of the above problems, it proposes on the present invention overcomes the above problem or at least be partially solved in order to provide one kind
It states a kind of apnea detection method, apparatus of problem, calculate equipment and computer storage medium.
In order to solve the above technical problems, the technical solution that embodiment of the present invention uses is: it is temporary to provide a kind of breathing
Stop detection method, comprising: receive the human body respiration signal that piezoelectric membrane collects user；Extract exhaling for the human body respiration signal
Inhale feature, wherein the respiratory characteristic of the human body respiration signal includes envelope characteristic, statistical nature and trend feature；By institute
It states respiratory characteristic to be input in default neural network model, is handled by default neural network model, obtain processing result；Root
According to the processing result, it is determined whether there are apneas.
Wherein, the method also includes: when the processing result be have apnea when, obtain the number of apnea with
And sleeping time；Apnea hypopnea indexes are calculated according to the apnea number and sleeping time.
Wherein, the extraction of the envelope characteristic includes:
Respiratory waveform search peak corresponding to the breath signal；
It connects the peak value to form envelope；
Interpolation is done to the envelope, obtains envelope characteristic.
Wherein, the statistical nature includes: that the peak-to-average of peak value, peak value be very poor and peak value standard deviation, the respiratory cycle
It breathes mean value, breathe very poor and breathing standard deviation, the slope mean value of slope, slope are very poor and slope standard deviation, the statistics are special
The extraction of sign includes:
Respiratory waveform search peak corresponding to the breath signal；
Calculate the peak value peak-to-average, peak value be very poor and peak value standard deviation；
According to the peak value corresponding time, the respiratory cycle is obtained；
It calculates the breathing mean value of the respiratory cycle, breathe very poor and breathing standard deviation；
According to the peak value and respiratory cycle, slope is obtained；
Calculate that the slope mean value of the slope, slope be very poor and slope standard deviation.
Wherein, the extraction of the trend feature includes:
It calculates in preset time, the duration of each trough of sampling curve, the sampling curve is by envelope characteristic
The curve being formed by connecting as sampled point；
Judge whether the duration is greater than preset threshold；
If so, frequency is added one, the frequency is the number for the duration being greater than that preset threshold occurs；
Using the maximum value of the duration and the frequency as the characteristic value of the trend feature.
In order to solve the above technical problems, another technical solution that embodiment of the present invention uses is: providing a kind of breathing
Suspend detection device, comprising: the human body respiration signal of user receiving module: is collected for receiving piezoelectric membrane；Feature extraction
Module: for extracting the respiratory characteristic of the human body respiration signal, wherein the respiratory characteristic of the human body respiration signal includes packet
Network feature, statistical nature and trend feature；Processing module: for the respiratory characteristic to be input to default neural network model
In, it is handled by default neural network model, obtains processing result；Determining module module: being used for according to the processing result,
Determine whether there is apnea.
Wherein, described device further include: obtain module: being to have apnea for the processing result when the processing module
When, obtain number and the sleeping time of apnea；Computing module: when for according to the apnea number and sleep
Between calculate apnea hypopnea indexes.
Wherein, the characteristic extracting module envelope:
Envelop feature extraction unit: for extracting the envelope characteristic；
Statistical nature extraction unit: for extracting the statistical nature；
Trend character extraction unit: for extracting the trend feature.
In order to solve the above technical problems, another technical solution that embodiment of the present invention uses is: providing a kind of calculating
Equipment, comprising: processor, memory, communication interface and communication bus, the processor, the memory and the communication connect
Mouth completes mutual communication by the communication bus；
The memory makes described in the processor execution for storing an at least executable instruction, the executable instruction
A kind of corresponding operation of apnea detection method.
In order to solve the above technical problems, another technical solution that embodiment of the present invention uses is: providing a kind of calculating
Machine storage medium, an at least executable instruction is stored in the storage medium, and the executable instruction makes processor execute institute
The corresponding operation of a kind of apnea detection method stated.
The beneficial effect of embodiment of the present invention is: being in contrast to the prior art, embodiment of the present invention passes through pressure
Conductive film collects the human body respiration signal of user, will not impact to the sleep of user；In addition, by extracting human body respiration
Feature, and default neural network model is combined to be handled, apnea can be whether there is with automatic discrimination.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is a kind of apnea detection method flow diagram of embodiment of the present invention；
Fig. 2 is respiratory waveform contrast schematic diagram in a kind of apnea detection method of embodiment of the present invention；
Fig. 3 A is envelop feature extraction flow chart in a kind of apnea detection method of embodiment of the present invention；
Fig. 3 B is that statistical nature extracts flow chart in a kind of apnea detection method of embodiment of the present invention；
Fig. 3 C is trend character extraction flow chart in a kind of apnea detection method of embodiment of the present invention；
Fig. 4 is another apnea detection method flow diagram of embodiment of the present invention；
Fig. 5 is a kind of apnea detection apparatus function block diagram of embodiment of the present invention；
Fig. 6 is a kind of calculating device structure schematic diagram of embodiment of the present invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Fig. 1 is a kind of apnea detection method flow diagram of the embodiment of the present invention.As shown in Figure 1, this method include with
Lower step:
Step S101: the human body respiration signal that piezoelectric membrane collects user is received.
In this step, using the human body respiration signal of piezoelectric membrane acquisition user, piezoelectric membrane is to presser sensor, vertical
When to the power for applying a very little, very big pressure can be generated in transverse direction, the piezoelectric membrane is placed under the thoracic cavity of user,
When user's breathing, as the contraction in thoracic cavity can apply different power to piezoelectric membrane, by the collected signal of piezoelectric membrane,
It can reflect the breath state of user.
Step S102: the respiratory characteristic of the human body respiration signal is extracted, wherein the breathing of the human body respiration signal is special
Sign includes envelope characteristic, statistical nature and trend feature.
In this step, the human body respiration signal is telecommunications of the piezoelectric membrane by the pressure output of collected human body
Number.
Fig. 2 is respiratory waveform contrast schematic diagram in a kind of apnea detection method of the embodiment of the present invention, such as Fig. 2 institute
Show, normal person's respiratory waveform can follow the contraction in thoracic cavity to generate regular peaks and troughs, and have the respiratory wave of apnea
Shape will not generate regular peaks and troughs, therefore, by human normal respiratory waveform and have apnea respiratory waveform pair
Than distinguishing characteristics can be extracted, the respiratory characteristic as human body respiration signal.
It is worth noting that the corresponding respiratory waveform of more effective human body respiration signal in order to obtain, mentions carrying out feature
Before taking, the respiratory waveform is filtered, comprising: removed in the human body respiration signal using power frequency notch filter
Hz noise；The respiratory waveform in the breath signal after removal interference is extracted using bandpass filter；It is described to extract the human body
The respiratory characteristic of breath signal specifically: the respiratory characteristic is extracted from the respiratory waveform.
As shown in Fig. 2, the peak value of eupnea waveform is much larger than the peak value of apnea waveform, in order to distinguish on the whole
Eupnea waveform and apnea waveform, using envelope characteristic as differentiation one of eupnea and the feature of apnea.
Fig. 3 A is envelop feature extraction flow chart in a kind of apnea detection method of the embodiment of the present invention.Such as Fig. 3 A institute
Show, the extraction of the envelope characteristic the following steps are included:
Step A1: respiratory waveform search peak corresponding to the breath signal.
In this step, each peak value of respiratory waveform is connected into the envelope to be formed, it is right when extracting envelope characteristic
The corresponding respiratory waveform search peak of collected human body respiration signal, and the time gap between peak value is removed less than preset time
The peak value of threshold value.Wherein, the preset time threshold is set according to respiratory rate, it is therefore an objective to reduce sampling error；Such as, generally
Human body respiration rate is no more than 30 times per minute, and the time of corresponding respiration is 2s, so, in the present embodiment, preset time
Threshold value is 2s.
Step A2: it connects the peak value to form envelope.
In this step, the time gap removed between peak value is connected less than the peak value of preset time threshold, is formed
Envelope.
Step A3: interpolation is done to the envelope, obtains the envelope characteristic.
In this step, consistent in order to make the envelope characteristic exported per minute count, interpolation is done to the envelope, it is described
Interpolation point is the characteristic point of envelope characteristic.
It is worth noting that the interpolation can be various interpolation in the prior art, as linear interpolation, Lagrange are inserted
Value uses cubic spline interpolation to the envelope, obtains the envelope characteristic in embodiments of the present invention.
Peak value is eupnea and apnea most obvious characteristic, therefore, in order to more accurately identify apnea,
Using the corresponding statistical nature of peak value as one of eupnea and the feature of apnea is distinguished, specifically, the statistical nature
Peak-to-average, peak value including peak value are very poor and peak value standard deviation, the breathing mean value of respiratory cycle breathe very poor and breathing standard
Difference, the slope mean value of slope, slope be very poor and slope standard deviation.
Fig. 3 B is that statistical nature extracts flow chart in a kind of apnea detection method of the embodiment of the present invention.Such as Fig. 3 B institute
Show, the extraction of the statistical nature the following steps are included:
Step B1: respiratory waveform search peak corresponding to the breath signal.
In this step, it to the corresponding respiratory waveform search peak of collected human body respiration signal, and removes between peak value
Time gap be less than preset time threshold peak value.Wherein, the preset time threshold is set according to respiratory rate, purpose
It is to reduce sampling error；Such as, general human body respiratory rate is no more than 30 times per minute, and the time of corresponding respiration is 2s, so,
In the present embodiment, preset time threshold 2s.
Step B2: calculate the peak value peak-to-average, peak value be very poor and peak value standard deviation.
In this step, will remove peak value between time gap be less than preset time threshold peak computational peak-to-average,
Peak value is very poor and peak value standard deviation, circular are the prior art, and this will not be repeated here.
Step B3: the peak value corresponding time is used, the respiratory cycle is obtained.
In this step, since apnea occurs in eupnea, in order to distinguish the apnea time, to adjacent peak
Being worth the corresponding time seeks difference, and divided by sample frequency, obtains the respiratory cycle.
Step B4: it calculates the breathing mean value of the respiratory cycle, breathe very poor and breathing standard deviation.
Step B5: peak value and respiratory cycle are used, slope is obtained.
In this step, it is small that floating difference is fluctuated between eupnea adjacent peak, the peak of apnea and eupnea
Value fluctuation difference is big, to distinguish this feature, obtains slope divided by the respiratory cycle with two neighboring peak difference values.
Step B6: calculate that the slope mean value of the slope, slope be very poor and slope standard deviation.
Eupnea and respiratory waveform trend corresponding to apnea are significantly different, therefore, using trend feature as area
Divide one of eupnea and the feature of apnea.
Fig. 3 C is trend character extraction flow chart in a kind of apnea detection method of the embodiment of the present invention.Such as Fig. 3 C institute
Show, the extraction of the trend feature the following steps are included:
Step C1: it calculates in preset time, the duration of each trough of sampling curve, the sampling curve is will to wrap
The curve that network feature is formed by connecting as sampled point.
In this step, using the characteristic point in envelope characteristic as sampled point, and sample frequency is set as 1Hz, it will be described
First sampled point be as starting sample point in sampled point, and the preset time is according to judging that the period is arranged, in the present invention
In embodiment, set the preset time to 1 minute, i.e., whether judgement in one minute once occurs apnea, it is possible to understand that
, when apnea occurs, the value of the corresponding sampled point of the apnea is significantly lower than the corresponding sampling of eupnea
Point, therefore, when the sampled point is connected into curve, the corresponding sampled point of the apnea forms trough.
It should be noted that the duration of the trough is calculated by fall, it specifically include: to calculate
Beginning sampled point is to the fall that each is put between the n-th sampled point, and it is pre- to judge whether the fall is greater than
If amplitude, if so, stopping calculating, n-th point is arrived if calculating, the point that the fall is greater than default amplitude does not occur,
The starting sample point is then repeated into above step, directly sequentially in time to the latter point as new starting sample point
It is greater than default amplitude to the fall, and the fall is greater than to the sampled point corresponding time of the default amplitude
It is denoted as T1.The fall between the sampled point after the starting sample point to the corresponding sampled point of the T1 is calculated one by one,
Until the fall is less than the default amplitude, the time T1 is the starting detected when apnea occurs for high probability
At time point, the corresponding time T2 of sampled point that the fall is less than the default amplitude is to return to normally to exhale from apnea
The difference of start time point when suction state, T2 and T1 are the trough duration.In embodiments of the present invention, because adopting
It is 1Hz with frequency, i.e., 1s clock can acquire 1 point, when the apnea time reaching 10s, be defined as apnea, preferably
, for the pause of effective identification of breathing, in embodiments of the present invention, natural number N is set as 10, that is, to the initial calculation
Point searches for 10 points backward sequentially in time, calculates separately the decline between each point between the starting point and 10 points
Amplitude.
It is understood that the breathing amplitude of different people is different, the breathing amplitude of same people also can difference, therefore,
In the present embodiment, 30%, 50% and 90% is set by the default amplitude respectively, corresponding trough in the case of three kinds of acquisition
Duration；Wherein, the default amplitude is can be adjusted according to the breathing situation of actual use person.
It is understood that within a preset period of time, the number that the trough occurs may more than once, therefore, when complete
After judging at first time, using the corresponding sampled point of the T2 as new starting sample point, the operation continued the above is found new
Duration.
Step C2: judging whether the duration is greater than preset threshold, if so, executing step C3.
In this step, the difference of the T2 calculated each time and T1 is judged with preset threshold, if the difference is big
In preset threshold, C3 is thened follow the steps.Preferably, in embodiments of the present invention, in order to more accurately identify whether to breathe
Pause, sets 10 for the preset threshold.
Step C3: by frequency plus one, the frequency is time for being greater than preset threshold the duration and occurring
Number.
In this step, the number of apnea occurs for the frequency reflection maximum probability.
Step C4: using the maximum value of the duration and the frequency as the characteristic value of the trend feature.
In this step, the difference of the T2 and T1 that are calculated in the preset time are compared, selects maximum value, made
For one of the characteristic value of trend feature；At the end of the preset time, using the value of the frequency as trend feature
One of characteristic value.Such as, within 1 minute, the difference of T2 twice and T1 is calculated, wherein a difference is 8 seconds, Ling Yici
Difference is 10 seconds, then by 10 seconds characteristic values with frequency 2 as trend feature.
Step S103: the respiratory characteristic is input in default neural network model, by default neural network model into
Row processing, obtains processing result.
In this step, the default neural network model is by acquiring exhaling for a large amount of normal persons and apnea patient
Waveform is inhaled, and characteristic point described in extraction step S102 trains the model come as input.For presetting neural network mould
The training process of type belongs to the prior art, and details are not described herein again for detailed process.
Step S104: according to the processing result, it is determined whether there are apneas.
In this step, by characteristic point described in unknown respiratory waveform extraction step S102, and as step S103
Described in neural network model input, output result is to have apnea or apnea to suspend corresponding label, root
According to label it is known that the corresponding user of the respiratory waveform of the position whether there is apnea.
The respiratory waveform of human body there are apnea and there is no when apnea envelope characteristic, statistical nature and
Trend feature all has the different forms of expression, and therefore, envelope characteristic, statistical nature and trend feature are as default nerve net
The input factor of network model is conducive to improve default neural network model in the accuracy for determining whether there is apnea.
In the present embodiment, the human body respiration signal of user is acquired by piezoelectric membrane, and passes through human body respiration signal
The respiratory characteristic of the human body respiration signal is extracted in comparison of wave shape analysis, and the respiratory characteristic is input to default neural network mould
In type, carry out recognizing whether apnea by default neural network model.It can be seen that the present invention program will not be to user
Sleep interferes；In addition, facilitating user using neural network recognition apnea and carrying out domestic sleeping monitoring.
Referring to Fig. 4, Fig. 4 is a kind of apnea detection method flow diagram for another embodiment of the present invention, the implementation
Example with above-described embodiment in the difference is that, method further include:
Step S105: apnea if it exists then records the number of user's apnea.
Step S106: apnea hypopnea indexes are calculated according to the apnea number and sleeping time.
Wherein, the apnea hypopnea indexes (AHI) refer to the number of apnea per hour, can be used as
The standard of user's apnea severity.
In the present embodiment, the processing result and the apnea hypopnea indexes are uploaded into service
Device, and it is sent to the mobile terminal of the user, so that user can obtain user by mobile terminal or login service device
The sleep quality of itself.
In some embodiments, before step S102, the human body respiration signal is handled, specifically includes: making
The Hz noise in the human body respiration signal is removed with power frequency notch filter；Exhaling after removal is interfered is extracted using bandpass filter
Inhale the respiratory waveform in signal.The respiratory characteristic for extracting the human body respiration signal specifically: from the respiratory waveform
Extract the respiratory characteristic.
In the present embodiment, when detecting apnea, the low pass index of sleep apnea is calculated, is exhaled as user
The standard for inhaling pause severity facilitates user to understand self health status；In addition, by Processing with Neural Network result and will sleep
Dormancy apnea test is sent to users' mobile end, and user is facilitated to know testing result.
Fig. 5 is a kind of apnea detection apparatus function block diagram of the embodiment of the present invention.As shown in figure 4, the device includes:
Receiving module 501, characteristic extracting module 502, processing module 503 and determining module 504, wherein the receiving module 501 is used
The human body respiration signal of user is collected in reception piezoelectric membrane；Characteristic extracting module 502, for extracting the human body respiration letter
Number respiratory characteristic, wherein the respiratory characteristic of the human body respiration signal includes that envelope characteristic, statistical nature and trend are special
Sign；Processing module 503, for the respiratory characteristic to be input in default neural network model, by presetting neural network model
It is handled, obtains processing result；Determining module 504, for according to the processing result, it is determined whether there are apneas.
In the present embodiment, described device further include: obtain module 505 and computing module 506, wherein obtain module
505, for when the processing result of the processing module be have apnea when, when obtaining number and the sleep of apnea
Between；Computing module 506 refers to for calculating sleep apnea low according to the apnea number and sleeping time
Number.
In the present embodiment, piezoelectric membrane is received by receiving module and acquires the human body respiration signal of user, and pass through spy
Sign extraction module extracts the respiratory characteristic of the human body respiration signal, the respiratory characteristic is input in processing module, by pre-
If neural network model carries out recognizing whether apnea.It is caused it can be seen that the present invention program will not sleep to user
Interference；In addition, facilitating user using neural network recognition apnea and carrying out domestic sleeping monitoring.
The embodiment of the present application provides a kind of nonvolatile computer storage media, and the computer storage medium is stored with
The inspection of one of above-mentioned any means embodiment apnea can be performed in an at least executable instruction, the computer executable instructions
The method of survey.
Fig. 6 is the structural schematic diagram that the present invention calculates apparatus embodiments, and the specific embodiment of the invention is not to calculating equipment
Specific implementation limit.
As shown in fig. 6, the calculating equipment may include: processor (processor) 602, communication interface
(Communications Interface) 604, memory (memory) 606 and communication bus 608.
Wherein:
Processor 602, communication interface 604 and memory 606 complete mutual communication by communication bus 608.
Communication interface 604, for being communicated with the network element of other equipment such as client or other servers etc..
Processor 602, for executing program 610, in a kind of can specifically execute apnea detection embodiment of the method
Correlation step.
Specifically, program 610 may include program code, which includes computer operation instruction.
Processor 602 may be central processor CPU or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road.The one or more processors that equipment includes are calculated, can be same type of processor, such as one or more CPU；It can also
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 606, for storing program 610.Memory 606 may include high speed RAM memory, it is also possible to further include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 610 specifically can be used for so that processor 602 executes following operation:
Receive the human body respiration signal that piezoelectric membrane collects user；
Extract the respiratory characteristic of the human body respiration signal, wherein the respiratory characteristic of the human body respiration signal includes packet
Network feature, statistical nature and trend feature；
The respiratory characteristic is input in default neural network model, is handled, is obtained by default neural network model
To processing result；
According to the processing result, it is determined whether there are apneas.
In a kind of optional mode, program 610 can specifically be further used for so that processor 602 executes following behaviour
Make:
When the processing result, which is, apnea, number and the sleeping time of apnea are obtained；
Apnea hypopnea indexes are calculated according to the apnea number and sleeping time.
In a kind of optional mode, program 610 can specifically be further used for so that processor 602 executes following behaviour
Make:
Respiratory waveform search peak corresponding to the breath signal；
It connects the peak value to form envelope；
Interpolation is done to the envelope, obtains envelope characteristic.
In a kind of optional mode, program 610 can specifically be further used for so that processor 602 executes following behaviour
Make:
Respiratory waveform search peak corresponding to the breath signal；
Calculate the peak value peak-to-average, peak value be very poor and peak value standard deviation；
Using the peak value corresponding time, the respiratory cycle is obtained；
It calculates the breathing mean value of the respiratory cycle, breathe very poor and breathing standard deviation；
Using peak value and respiratory cycle, slope is obtained；
Calculate that the slope mean value of the slope, slope be very poor and slope standard deviation.
In a kind of optional mode, program 610 can specifically be further used for so that processor 602 executes following behaviour
Make:
It calculates in preset time, the duration of each trough of sampling curve, the sampling curve is by envelope characteristic
The curve being formed by connecting as sampled point；
Judge whether the duration is greater than preset threshold；
If so, frequency is added one, the frequency is the number for the duration being greater than that preset threshold occurs；
Using the maximum value of the duration and the frequency as the characteristic value of the trend feature.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various
Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, such as right
As claim reflects, inventive aspect is all features less than single embodiment disclosed above.Therefore, it then follows tool
Thus claims of body embodiment are expressly incorporated in the specific embodiment, wherein each claim conduct itself
Separate embodiments of the invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) are realized in a kind of apnea detection device according to an embodiment of the present invention
Some or all components some or all functions.The present invention is also implemented as executing side as described herein
Some or all device or device programs (for example, computer program and computer program product) of method.It is such
It realizes that program of the invention can store on a computer-readable medium, or can have the shape of one or more signal
Formula.Such signal can be downloaded from an internet website to obtain, and perhaps be provided on the carrier signal or with any other shape
Formula provides.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
Claims (10)
1. a kind of apnea detection method, which is characterized in that the described method includes:
Receive the human body respiration signal that piezoelectric membrane collects user；
Extract the respiratory characteristic of the human body respiration signal, wherein the respiratory characteristic of the human body respiration signal includes envelope spy
Sign, statistical nature and trend feature；
The respiratory characteristic is input in default neural network model, is handled, is obtained everywhere by default neural network model
Manage result；
According to the processing result, it is determined whether there are apneas.
2. the method according to claim 1, wherein the method also includes:
When the processing result, which is, apnea, number and the sleeping time of apnea are obtained；
Apnea hypopnea indexes are calculated according to the apnea number and sleeping time.
3. the method according to claim 1, wherein the extraction of the envelope characteristic includes:
Respiratory waveform search peak corresponding to the breath signal；
It connects the peak value to form envelope；
Interpolation is done to the envelope, obtains the envelope characteristic.
4. the method according to claim 1, wherein the statistical nature includes: the peak-to-average of peak value, peak value
Very poor and peak value standard deviation, the breathing mean value of respiratory cycle, breathing is very poor and breathes standard deviation, the slope mean value of slope, slope
Very poor and slope standard deviation, the extraction of the statistical nature include:
Respiratory waveform search peak corresponding to the breath signal；
Calculate the peak value peak-to-average, peak value be very poor and peak value standard deviation；
According to the peak value corresponding time, the respiratory cycle is obtained；
It calculates the breathing mean value of the respiratory cycle, breathe very poor and breathing standard deviation；
According to the peak value and respiratory cycle, slope is obtained；
Calculate that the slope mean value of the slope, slope be very poor and slope standard deviation.
5. the method according to claim 1, wherein the extraction of the trend feature includes:
Calculate preset time in, the duration of each trough of sampling curve, the sampling curve be using envelope characteristic as
The curve that sampled point is formed by connecting；
Judge whether the duration is greater than preset threshold；
If so, frequency is added one, the frequency is the number for the duration being greater than that preset threshold occurs；
Using the maximum value of the duration and the frequency as the characteristic value of the trend feature.
6. a kind of apnea detection device, which is characterized in that described device includes:
Receiving module: the human body respiration signal of user is collected for receiving piezoelectric membrane；
Characteristic extracting module: for extracting the respiratory characteristic of the human body respiration signal, wherein the human body respiration signal is exhaled
Inhaling feature includes envelope characteristic, statistical nature and trend feature；
Processing module: for the respiratory characteristic to be input in default neural network model, by default neural network model into
Row processing, obtains processing result；
Determining module: for according to the processing result, it is determined whether there are apneas.
7. device according to claim 6, which is characterized in that described device further include:
Obtain module: for when the processing result of the processing module be have apnea when, obtain the number of apnea with
And sleeping time；
Computing module: for calculating apnea hypopnea indexes according to the apnea number and sleeping time.
8. device according to claim 6, which is characterized in that the characteristic extracting module envelope:
Envelop feature extraction unit: for extracting the envelope characteristic；
Statistical nature extraction unit: for extracting the statistical nature；
Trend character extraction unit: for extracting the trend feature.
9. a kind of calculating equipment, comprising: processor, memory, communication interface and communication bus, the processor, the storage
Device and the communication interface complete mutual communication by the communication bus；
The memory executes the processor as right is wanted for storing an at least executable instruction, the executable instruction
Ask a kind of corresponding operation of apnea detection method described in any one of 1-5.
10. a kind of computer storage medium, an at least executable instruction, the executable instruction are stored in the storage medium
Processor is set to execute a kind of corresponding operation of apnea detection method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811564593.9A CN109480783B (en) | 2018-12-20 | 2018-12-20 | Apnea detection method and device and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811564593.9A CN109480783B (en) | 2018-12-20 | 2018-12-20 | Apnea detection method and device and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109480783A true CN109480783A (en) | 2019-03-19 |
| CN109480783B CN109480783B (en) | 2022-02-18 |
Family
ID=65711172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811564593.9A Active CN109480783B (en) | 2018-12-20 | 2018-12-20 | Apnea detection method and device and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109480783B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110151182A (en) * | 2019-04-04 | 2019-08-23 | 深圳创达云睿智能科技有限公司 | A kind of apnea kind identification method and equipment |
| 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 |
| CN112914506A (en) * | 2021-01-19 | 2021-06-08 | 青岛歌尔智能传感器有限公司 | Sleep quality detection method, device and computer readable storage medium |
| CN113080857A (en) * | 2021-03-30 | 2021-07-09 | 安徽华米健康医疗有限公司 | Respiration monitoring method and device and terminal equipment |
| CN113243890A (en) * | 2021-05-10 | 2021-08-13 | 清华大学深圳国际研究生院 | Sleep apnea syndrome recognition device |
| WO2022242123A1 (en) * | 2021-05-20 | 2022-11-24 | 深圳先进技术研究院 | Mechanical ventilation man-machine asynchronous detection method and apparatus, and computer-readable storage medium |
| CN116211256A (en) * | 2023-03-16 | 2023-06-06 | 武汉理工大学 | Non-contact sleep breathing signal acquisition method and device |
| CN116919347A (en) * | 2023-07-19 | 2023-10-24 | 中国人民解放军空军军医大学 | Apnea monitoring system, method and emergency awakening device |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070093724A1 (en) * | 2005-10-11 | 2007-04-26 | Takeshi Tanigawa | Automatic apnea/hypopnea detection device, detection method, program and recording medium |
| CN101087559A (en) * | 2004-12-23 | 2007-12-12 | 雷斯梅德有限公司 | Method for detecting and disciminatng breathing patterns from respiratory signals |
| CN102274009A (en) * | 2010-06-13 | 2011-12-14 | 深圳市迈迪加科技发展有限公司 | Respiratory and heartbeat signal processing circuit based on piezoelectric sensor |
| CN104107034A (en) * | 2013-04-16 | 2014-10-22 | 海思康利(北京)新技术有限公司 | Spontaneous breathing apparatus |
| CN104706355A (en) * | 2015-03-26 | 2015-06-17 | 北京怡和嘉业医疗科技有限公司 | Method and system for determining type of apnea event |
| CN106037671A (en) * | 2016-07-11 | 2016-10-26 | 西北工业大学 | Method and system for apnea event detection based on BCG signal |
| CN106175770A (en) * | 2016-08-01 | 2016-12-07 | 华南师范大学 | Apneic determination methods and system during a kind of sleep |
| CN107072594A (en) * | 2014-07-28 | 2017-08-18 | S V Siu联合有限责任公司 | Method and apparatus for assessing respiratory distress |
| CN107205721A (en) * | 2014-12-08 | 2017-09-26 | 华盛顿大学 | The system and method for recognizing the motion of subject |
| CN107981844A (en) * | 2017-12-08 | 2018-05-04 | 绵眠（上海）智能科技有限公司 | A kind of sound of snoring recognition methods and system based on piezoelectric membrane |
| CN108392203A (en) * | 2018-05-16 | 2018-08-14 | 山西工程职业技术学院 | A kind of portable breath signal detection device |
| CN108420408A (en) * | 2018-03-31 | 2018-08-21 | 湖南明康中锦医疗科技发展有限公司 | Sleep breath monitoring method |
-
2018
- 2018-12-20 CN CN201811564593.9A patent/CN109480783B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101087559A (en) * | 2004-12-23 | 2007-12-12 | 雷斯梅德有限公司 | Method for detecting and disciminatng breathing patterns from respiratory signals |
| US20070093724A1 (en) * | 2005-10-11 | 2007-04-26 | Takeshi Tanigawa | Automatic apnea/hypopnea detection device, detection method, program and recording medium |
| CN102274009A (en) * | 2010-06-13 | 2011-12-14 | 深圳市迈迪加科技发展有限公司 | Respiratory and heartbeat signal processing circuit based on piezoelectric sensor |
| CN104107034A (en) * | 2013-04-16 | 2014-10-22 | 海思康利(北京)新技术有限公司 | Spontaneous breathing apparatus |
| CN107072594A (en) * | 2014-07-28 | 2017-08-18 | S V Siu联合有限责任公司 | Method and apparatus for assessing respiratory distress |
| CN107205721A (en) * | 2014-12-08 | 2017-09-26 | 华盛顿大学 | The system and method for recognizing the motion of subject |
| CN104706355A (en) * | 2015-03-26 | 2015-06-17 | 北京怡和嘉业医疗科技有限公司 | Method and system for determining type of apnea event |
| CN106037671A (en) * | 2016-07-11 | 2016-10-26 | 西北工业大学 | Method and system for apnea event detection based on BCG signal |
| CN106175770A (en) * | 2016-08-01 | 2016-12-07 | 华南师范大学 | Apneic determination methods and system during a kind of sleep |
| CN107981844A (en) * | 2017-12-08 | 2018-05-04 | 绵眠（上海）智能科技有限公司 | A kind of sound of snoring recognition methods and system based on piezoelectric membrane |
| CN108420408A (en) * | 2018-03-31 | 2018-08-21 | 湖南明康中锦医疗科技发展有限公司 | Sleep breath monitoring method |
| CN108392203A (en) * | 2018-05-16 | 2018-08-14 | 山西工程职业技术学院 | A kind of portable breath signal detection device |
Non-Patent Citations (3)
| Title |
|---|
| 徐现通: "睡眠状态下人体生理信号的监测", 《医学信息》 * |
| 潘俊君等: "基于BP神经网络的睡眠呼吸综合症智能检测系统", 《计算机应用与软件》 * |
| 荆斌等: "基于智能算法睡眠呼吸暂停监测系统设计", 《中国医学装备》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110151182A (en) * | 2019-04-04 | 2019-08-23 | 深圳创达云睿智能科技有限公司 | A kind of apnea kind identification method and equipment |
| CN110151182B (en) * | 2019-04-04 | 2022-04-19 | 深圳创达云睿智能科技有限公司 | Apnea type identification method and device |
| 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 |
| CN112914506A (en) * | 2021-01-19 | 2021-06-08 | 青岛歌尔智能传感器有限公司 | Sleep quality detection method, device and computer readable storage medium |
| CN113080857A (en) * | 2021-03-30 | 2021-07-09 | 安徽华米健康医疗有限公司 | Respiration monitoring method and device and terminal equipment |
| CN113243890A (en) * | 2021-05-10 | 2021-08-13 | 清华大学深圳国际研究生院 | Sleep apnea syndrome recognition device |
| WO2022242123A1 (en) * | 2021-05-20 | 2022-11-24 | 深圳先进技术研究院 | Mechanical ventilation man-machine asynchronous detection method and apparatus, and computer-readable storage medium |
| CN116211256A (en) * | 2023-03-16 | 2023-06-06 | 武汉理工大学 | Non-contact sleep breathing signal acquisition method and device |
| CN116211256B (en) * | 2023-03-16 | 2023-12-22 | 武汉理工大学 | Non-contact sleep breathing signal acquisition method and device |
| CN116919347A (en) * | 2023-07-19 | 2023-10-24 | 中国人民解放军空军军医大学 | Apnea monitoring system, method and emergency awakening device |
| CN116919347B (en) * | 2023-07-19 | 2024-06-07 | 中国人民解放军空军军医大学 | Apnea monitoring system, method and emergency awakening device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109480783B (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109480783A (en) | A kind of apnea detection method, apparatus and calculate equipment | |
| CN108056769A (en) | A kind of vital sign parameter signals analysis and processing method, device and vital sign monitoring device | |
| CN108135535A (en) | For handling the device and method of the electromyogram signal related with respiratory activity | |
| US20140155773A1 (en) | Methods and apparatus for performing dynamic respiratory classification and tracking | |
| JP2014505566A (en) | Respiration monitoring method and system | |
| JP2008520384A (en) | Method and system for real time determination of respiratory rate with limited processor resources | |
| US10602944B2 (en) | Detecting artifacts in a signal | |
| US20200107775A1 (en) | Methods and Systems for Monitoring Sleep Apnea | |
| CN109106350A (en) | The preliminary screening method of the Sleep Apnea-hypopnea Syndrome of low physiological stress | |
| CN109328034A (en) | For determining the determination system and method for the sleep stage of object | |
| CN103405225B (en) | A kind of pain that obtains feels the method for evaluation metrics, device and equipment | |
| CN107530015B (en) | Vital sign analysis method and system | |
| WO2012163738A1 (en) | Monitoring stenosis formation in an arteriovenous access | |
| CN111035395A (en) | Blood oxygen saturation signal analysis method and device, computer equipment and storage medium | |
| CN110115583A (en) | The method and apparatus of monitoring of respiration | |
| CN109674474B (en) | Sleep apnea recognition method, device and computer readable medium | |
| CN108186018A (en) | A kind of breath data processing method and processing device | |
| CN102622039A (en) | Intelligent control handle based on natural contact sensors and applications thereof | |
| WO2019245451A1 (en) | Sensing olfactory response to one or more scents | |
| CN200994790Y (en) | System for measuring mental state parameter | |
| CN104424488B (en) | A kind of method and system for extracting BCG signal characteristics | |
| CN105796118A (en) | A non-invasive emotion analysis method | |
| CN115944275A (en) | Method for judging sleep stage through respiratory rate variability | |
| JP2020048622A (en) | Biological state estimation apparatus | |
| US11723588B2 (en) | Device for apnea detection, system and method for expediting detection of apnea events of a user |
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 |