CN112472066A - Breathing disorder monitoring terminal, monitor and system - Google Patents
Breathing disorder monitoring terminal, monitor and system Download PDFInfo
- Publication number
- CN112472066A CN112472066A CN202011336898.1A CN202011336898A CN112472066A CN 112472066 A CN112472066 A CN 112472066A CN 202011336898 A CN202011336898 A CN 202011336898A CN 112472066 A CN112472066 A CN 112472066A
- Authority
- CN
- China
- Prior art keywords
- sound signal
- frequency spectrum
- respiratory
- module
- breathing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 136
- 230000029058 respiratory gaseous exchange Effects 0.000 title claims abstract description 58
- 230000005236 sound signal Effects 0.000 claims abstract description 161
- 238000001228 spectrum Methods 0.000 claims abstract description 138
- 208000023504 respiratory system disease Diseases 0.000 claims abstract description 97
- 210000000056 organ Anatomy 0.000 claims abstract description 92
- 208000037656 Respiratory Sounds Diseases 0.000 claims abstract description 38
- 238000000926 separation method Methods 0.000 claims abstract description 27
- 238000006243 chemical reaction Methods 0.000 claims abstract description 13
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 42
- 229910052760 oxygen Inorganic materials 0.000 claims description 42
- 239000001301 oxygen Substances 0.000 claims description 42
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 30
- 208000008784 apnea Diseases 0.000 claims description 27
- 230000000241 respiratory effect Effects 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 20
- 230000005540 biological transmission Effects 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 5
- 238000012795 verification Methods 0.000 description 16
- 238000000034 method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000000338 in vitro Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 1
- 206010035664 Pneumonia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 210000000867 larynx Anatomy 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008667 sleep stage Effects 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording 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
- 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
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B7/00—Instruments for auscultation
- A61B7/02—Stethoscopes
- A61B7/04—Electric stethoscopes
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L21/0232—Processing in the frequency domain
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0272—Voice signal separating
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
Abstract
The application relates to a respiratory disorder monitoring terminal, a monitor and a system. Breathing obstacle monitor terminal includes: the frequency spectrum conversion module is used for converting the acquired organ sound signals into audio frequency spectrums; the organ sound signal comprises a breath sound signal; the signal separation module is used for confirming the breathing characteristic information of the organ sound signal and separating a target frequency spectrum corresponding to the breathing sound signal from the audio frequency spectrum according to the breathing characteristic information; and the monitoring result confirming module is used for classifying the target frequency spectrum by adopting a naive Bayesian classifier to obtain a monitoring result. The monitoring result can be generated through the characteristic signals with less quantity, so that the quantity of connected sensors can be reduced, the influence of the respiratory disorder monitoring terminal on a testee is reduced, the advantage of no constraint is achieved, and the monitoring accuracy is improved.
Description
Technical Field
The application relates to the technical field of biological measurement, in particular to a breathing disorder monitoring terminal, a monitor and a system.
Background
When the traditional equipment monitors the sleep breathing disorder, the traditional equipment needs to be connected with various sensors arranged at a person to be detected, and the sensors are used for collecting characteristic signals of the person to be detected in different sleep stages and the like.
However, in the implementation process, the inventor finds that at least the following problems exist in the conventional technology: the problem that the monitoring accuracy is low exists in the conventional respiratory disorder monitoring terminal.
Disclosure of Invention
Based on this, it is necessary to provide a respiratory disorder monitoring terminal, a monitor and a system capable of improving the monitoring accuracy of the device, aiming at the problem of low monitoring accuracy existing in the conventional device.
A breathing disorder monitoring terminal, comprising:
the frequency spectrum conversion module is used for converting the acquired organ sound signals into audio frequency spectrums; the organ sound signal comprises a breath sound signal;
the signal separation module is used for confirming the breathing characteristic information of the organ sound signal and separating a target frequency spectrum corresponding to the breathing sound signal from the audio frequency spectrum according to the breathing characteristic information;
and the monitoring result confirming module is used for classifying the target frequency spectrum by adopting a naive Bayesian classifier to obtain a monitoring result.
In one embodiment, the monitoring result confirming module is further configured to train a model according to the acquired training set and generate a naive bayesian classifier according to the trained model; the training set includes training data; the training data includes an initial spectrum and corresponding monitoring results.
In one embodiment, the signal separation module comprises a frequency range determination unit and a breath sound signal separation unit;
the frequency range determining unit is used for determining a target frequency range of the breathing sound signal according to the breathing characteristic information; and the respiratory sound signal separation unit is used for filtering frequencies in the audio frequency spectrum except the target frequency range and obtaining a target frequency spectrum.
A respiratory disorder monitor comprising:
the sound signal acquisition module is used for acquiring organ sound signals; the organ sound signal is used for indicating the breathing disorder monitoring terminal to convert into an audio frequency spectrum and confirming the breathing characteristic information of the organ sound signal; the respiratory characteristic information is used for indicating the respiratory disorder monitoring terminal to separate a target frequency spectrum corresponding to the respiratory sound signal from the audio frequency spectrum, and classifying the target frequency spectrum by adopting a naive Bayes classifier to obtain a monitoring result; the organ sound signal comprises a breath sound signal.
In one embodiment, the method further comprises the following steps:
the amplitude alarm threshold determination module is used for converting the organ sound signal into a corresponding audio frequency spectrum, separating an initial frequency spectrum of the respiratory sound signal from the audio frequency spectrum, updating an initial frequency spectrum amplitude maximum value of the respiratory sound signal in real time according to the initial frequency spectrum, obtaining an amplitude alarm threshold based on the initial frequency spectrum amplitude maximum value, and comparing the frequency spectrum amplitude of the initial frequency spectrum with the amplitude alarm threshold to obtain initial apnea duration;
and the monitor transmission module is used for transmitting organ sound signals to the respiratory disorder monitoring terminal according to the initial apnea duration.
In one embodiment, the method further comprises the following steps:
the oxygen content acquisition module is used for acquiring oxygen content information;
the amplitude threshold value determining module is further used for comparing the oxygen content information with an oxygen content alarm threshold value to obtain an oxygen content comparison result, comparing the initial apnea duration with a duration alarm threshold value to obtain a duration comparison result, and generating a monitoring result based on the oxygen content comparison result and the duration comparison result;
and the monitor transmission module is also used for transmitting organ sound signals to the breathing disorder monitoring terminal according to the oxygen content comparison result and the duration comparison result.
In one embodiment, the amplitude threshold determination module is further configured to determine a product of the initial spectrum amplitude maximum value and a preset ratio as the amplitude alarm threshold.
In one embodiment, the amplitude threshold determination module is further configured to pair and authenticate with the respiratory disorder monitoring terminal.
A respiratory disorder monitoring system comprises the respiratory disorder monitoring terminal and the respiratory disorder monitor.
In one embodiment, the system further comprises a cloud server; the cloud server is in communication connection with the respiratory disorder monitoring terminal.
One of the above technical solutions has the following advantages and beneficial effects:
breathing obstacle monitoring terminal in each embodiment of this application includes: the frequency spectrum conversion module is used for converting the acquired organ sound signals into audio frequency spectrums; the organ sound signal comprises a breath sound signal; the signal separation module is used for confirming the breathing characteristic information of the organ sound signal and separating a target frequency spectrum corresponding to the breathing sound signal from the audio frequency spectrum according to the breathing characteristic information; and the monitoring result confirming module is used for classifying the target frequency spectrum by adopting a naive Bayesian classifier to obtain a monitoring result. The monitoring result can be generated through the characteristic signals with less quantity, so that the quantity of connected sensors can be reduced, the influence of the respiratory disorder monitoring terminal on a testee is reduced, the advantage of no constraint is achieved, and the monitoring accuracy is improved.
Drawings
FIG. 1 is a first schematic block diagram of a respiratory disorder monitoring terminal according to an embodiment;
FIG. 2 is a second schematic block diagram of a respiratory disorder monitoring terminal according to an embodiment;
FIG. 3 is a first schematic block diagram of a respiratory disorder monitor in one embodiment;
FIG. 4 is a second schematic block diagram of a respiratory disorder monitor in one embodiment;
fig. 5 is a schematic block diagram of a respiratory disorder monitoring system in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
In one embodiment, as shown in fig. 1, there is provided a respiratory disorder monitoring terminal, including:
a breathing disorder monitoring terminal, comprising:
the frequency spectrum conversion module is used for converting the acquired organ sound signals into audio frequency spectrums; the organ sound signal comprises a breath sound signal;
the signal separation module is used for confirming the breathing characteristic information of the organ sound signal and separating a target frequency spectrum corresponding to the breathing sound signal from the audio frequency spectrum according to the breathing characteristic information;
and the monitoring result confirming module is used for classifying the target frequency spectrum by adopting a naive Bayesian classifier to obtain a monitoring result.
The organ sound signal may be a sound signal of an internal organ, including but not limited to a heart sound signal, a lung sound signal, a larynx sound signal, and the like. The respiratory characteristic information may be used to indicate a respiratory state, for example, the respiratory state may be a cough respiratory state, a cold respiratory state, a pneumonia respiratory state, and the like. Further, the breathing state may be used to indicate a frequency range of the breathing sound signal. The target spectrum of the respiratory sound signal is a spectrum containing part or all of the respiratory sound signal.
The organ sound signal acquisition is realized by receiving the organ sound signal transmitted by the external equipment, wherein the external equipment comprises but is not limited to equipment in communication connection with a respiratory disorder monitoring terminal and equipment in electric connection with the respiratory disorder monitoring terminal, such as a server, a respiratory disorder monitor arranged on a person to be detected and the like. The frequency spectrum conversion module can also receive organ sound signals transmitted by other modules in the respiratory disorder monitoring terminal, for example, the respiratory disorder monitoring terminal can also comprise a communication module, the communication module is used for communicating with external equipment, receiving the organ sound signals transmitted by the external equipment, and transmitting the organ sound signals to the frequency spectrum conversion module; or the breathing disorder monitoring terminal can also comprise an acquisition module, and the acquisition module transmits the acquired organ sound signals to the frequency spectrum conversion module. The frequency spectrum conversion module can acquire organ sound signals through the frequency spectrum conversion module so as to acquire the signals.
The frequency spectrum conversion module is configured to obtain an organ sound signal, and then convert the organ sound signal into a time domain signal, and convert the time domain signal (i.e., the organ sound signal) into a frequency spectrum (i.e., an audio frequency spectrum) corresponding to the organ sound signal, for example, by Fast Fourier Transform (FFT).
When the spectrum conversion module converts the organ sound signal into the audio spectrum, the signal separation module may determine the respiratory characteristic information of the organ sound signal, for example, a plurality of organ sound signals may be used to train the model in advance, and the organ sound signal is processed by the trained model, so as to obtain the corresponding respiratory characteristic information. For another example, the signal separation module may compare the organ sound signal with a plurality of preset sound signals one by one, and determine the respiratory characteristic information according to the comparison result. It should be noted that, in addition to the above examples, the signal separation module may also select corresponding module devices in the prior art according to actual situations and design requirements, and obtain the respiratory characteristic information corresponding to the organ sound signal by using the existing algorithm or method, which is not limited in this application.
After the signal separation module obtains the breathing characteristic information, a target frequency spectrum corresponding to the breathing sound signal can be separated from the audio frequency spectrum according to the breathing characteristic information, so that the target frequency spectrum obtained through separation can accurately reflect the breathing sound signal, and the monitoring accuracy of the breathing disorder monitoring terminal is improved. Specifically, the signal separation module may achieve separation of the target spectrum by any one or any number of any combination of the following: mel Spectrogram (Mel Spectrum), MFCC (Mel-scale Frequency Cepstral coeffients, Mel Cepstral coefficient), CQT (constant Q transform), Chroma, and the like. It should be noted that, besides the examples listed above, the signal separation module may also implement spectrum separation in other manners disclosed in the prior art, and the present application is not limited thereto. In one example, the signal splitting module may be implemented using Librosa.
The monitoring result confirmation module can be used for classifying the target frequency spectrum by adopting a naive Bayesian classifier and obtaining a monitoring result. Wherein, the monitoring result can be used for feeding back the sleep health condition and the sleep breathing disorder degree.
Among the above-mentioned respiratory disorder monitor terminal, the less characteristic signal of accessible quantity generates the monitoring result to reducible sensor quantity of plugging into, and reduce respiratory disorder monitor terminal and treat the person's that awaits measuring influence, thereby possess the advantage of unrestrained, and then improved the monitoring accuracy.
In one embodiment, the monitoring result confirmation module is further configured to train a model according to the acquired training set and generate a naive bayesian classifier according to the trained model; the training set includes training data; the training data includes an initial spectrum and corresponding monitoring results.
Specifically, the training set may include 16 types of training data, where each type may include a plurality of data, each training data including an initial spectrum and a corresponding monitoring result. According to the method and the device, the initial model is trained by adopting a training set to obtain the trained target model, so that a naive Bayes classifier can be obtained based on the target model, the target frequency spectrum is classified by adopting the naive Bayes classifier, and the classified class is confirmed as the monitoring result.
In one embodiment, the signal separation module comprises a frequency range determination unit and a breath sound signal separation unit; the frequency range determining unit is used for determining a target frequency range of the breathing sound signal according to the breathing characteristic information; and the respiratory sound signal separation unit is used for filtering frequencies in the audio frequency spectrum except the target frequency range and obtaining a target frequency spectrum.
Specifically, the frequency range determining unit may collect a training set in advance, where the training set may include a plurality of samples corresponding to each piece of respiratory characteristic information, train the model using the sample set, and process the respiratory characteristic information through the trained model, thereby obtaining a corresponding target frequency range. Alternatively, the frequency range determination unit may determine the breathing state from the breathing sound signal and determine a target frequency range corresponding to the breathing state. For example, if it can be determined from the breathing characteristic information that the breathing state is a cold breathing state, the frequency range determination unit may determine the target frequency range as a frequency range corresponding to the cold breathing state.
The respiratory sound signal separation unit filters the audio frequency spectrum according to the target frequency range determined by the frequency range determination unit, reserves signals in the target frequency range in the audio frequency spectrum, and filters signals in the audio frequency spectrum except the target frequency range to obtain the target frequency spectrum. Further, the target spectrum may retain signals corresponding to the boundary frequency of the target frequency range, or may filter signals corresponding to the boundary frequency. For example, when the target frequency is 1000Hz (hertz), the target spectrum may retain signals having a frequency of 1000Hz, and may also filter out signals having a frequency of 1000 Hz. Therefore, the interference in the target frequency spectrum can be reduced, and the monitoring accuracy is improved.
In one embodiment, the breathing disorder monitoring terminal further comprises: and the data uploading module is used for uploading the monitoring result, the organ sound signal and/or the breathing sound signal to the cloud server.
Specifically, the respiratory disorder monitoring terminal may further include a data uploading module, and the data uploading module is configured to upload any one or any combination of the monitoring result, the organ sound signal, and the respiratory sound signal to the cloud server through the wireless network. Furthermore, when a plurality of data are uploaded, the data can be uploaded to the same cloud server, the data can be uploaded to different cloud servers, or part of the data is uploaded to the same cloud server, and the rest of the data is uploaded to different cloud servers respectively, so that the uploaded data can be analyzed and recorded, and the data reliability is improved.
In one embodiment, the terminal further comprises: and the terminal verification module is used for pairing and identity verification with the respiratory disorder monitor. Specifically, the respiratory disorder monitoring terminal may further include a terminal verification module, where the terminal verification module is configured to pair with the respiratory disorder monitor and perform identity verification, and when the pairing is successful, the respiratory disorder monitoring terminal may receive an organ sound signal transmitted by the respiratory disorder monitor, and the like. In one example, the terminal verification module may be used for bluetooth pairing with a respiratory disorder monitor.
In one embodiment, the terminal further comprises: and the terminal transmission module is used for carrying out information interaction with the respiratory disorder monitor. Specifically, the terminal transmission module sends a control instruction to the respiratory disorder monitor, and can also receive information such as organ sound signals transmitted by the respiratory disorder monitor. Further, before pairing and identity verification, the terminal transmission module may receive pairing and verification information transmitted by the respiratory disorder monitor, or transmit corresponding pairing and verification information to the respiratory disorder monitor for verification.
In one embodiment, the terminal further comprises: and the display module is used for displaying the monitoring result, the organ sound signal and/or the breathing sound signal.
To facilitate understanding of the respiratory disorder monitoring terminal of the present application, a specific example is described below. As shown in fig. 2, there is provided a respiratory disorder monitoring terminal, including:
and the terminal transmission module is used for carrying out information interaction with the respiratory disorder monitor.
And the terminal verification module is used for carrying out Bluetooth pairing with the respiratory disorder monitor.
The frequency spectrum conversion module is used for converting the acquired organ sound signals into audio frequency spectrums; the organ sound signal comprises a breath sound signal.
The signal separation module comprises a frequency range determination unit and a respiratory sound signal separation unit, wherein the frequency range determination unit is used for determining a target frequency range of the respiratory sound signal according to the respiratory characteristic information; and the respiratory sound signal separation unit is used for filtering frequencies in the audio frequency spectrum except the target frequency range and obtaining a target frequency spectrum.
And the monitoring result confirming module is used for training the model according to the obtained training set, generating a naive Bayes classifier according to the trained model, and classifying the target frequency spectrum by adopting the naive Bayes classifier to obtain the monitoring result.
And the data uploading module is used for uploading any one or any combination of the monitoring result, the organ sound signal and the breath sound signal to the cloud server through a wireless network.
And the display module is used for displaying the monitoring result, the organ sound signal and/or the breathing sound signal.
The breathing disorder monitoring terminal can carry out data classification, display graph and characters to organ sound signals at the smart machine to possess and remind and see through mobile communication technology transmission data to cloud server and do data analysis or record to electronic medical record platform.
In one embodiment, there is provided a respiratory disorder monitor comprising:
the sound signal acquisition module is used for acquiring organ sound signals; the organ sound signal is used for indicating the breathing disorder monitoring terminal to convert into an audio frequency spectrum and confirming the breathing characteristic information of the organ sound signal; the respiratory characteristic information is used for indicating the respiratory disorder monitoring terminal to separate a target frequency spectrum corresponding to the respiratory sound signal from the audio frequency spectrum, and classifying the target frequency spectrum by adopting a naive Bayes classifier to obtain a monitoring result; the organ sound signal comprises a breath sound signal.
In particular, the sound signal collection module may be used to continuously collect organ sound signals. The sound signal collecting module may include a sound collecting device, and collects the organ sound signal through the sound collecting device. Further, the sound signal collection module may further include a signal processing circuit electrically connected to the sound collection device. In one embodiment, as shown in fig. 3, the respiratory disorder monitor further comprises:
the amplitude threshold value determining module is used for converting the organ sound signal into a corresponding audio frequency spectrum, separating an initial frequency spectrum of the respiratory sound signal from the audio frequency spectrum, updating an initial frequency spectrum amplitude maximum value of the respiratory sound signal in real time according to the initial frequency spectrum, obtaining an amplitude alarm threshold value based on the initial frequency spectrum amplitude maximum value, and comparing the frequency spectrum amplitude of the initial frequency spectrum with the amplitude alarm threshold value to obtain initial apnea duration;
and the monitor transmission module is used for transmitting organ sound signals to the respiratory disorder monitoring terminal according to the initial apnea duration.
Wherein the initial spectrum is a spectrum containing all or part of the breathing sound signal, and further, the frequency of the initial spectrum may include all the frequencies of the target spectrum, or may not partially coincide with the frequencies of the target spectrum. The initial apnea field of view is the duration of the apnea derived based on the initial spectrum.
Specifically, the amplitude threshold determination module may convert the organ sound signal into a corresponding audio frequency spectrum through a processing manner such as FFT, and preliminarily separate an initial frequency spectrum of the breath sound signal from the audio frequency spectrum. For example, the amplitude threshold determination module may determine an initial frequency range in advance, and different organ sound signals may all correspond to the initial frequency range, and filter frequencies in the audio frequency spectrum except the initial frequency range, and retain frequency signals within the initial frequency range, thereby obtaining an initial frequency spectrum, and then may perform preliminary extraction on the respiratory sound signals according to the initial frequency spectrum, thereby improving the monitoring efficiency of the respiratory disorder monitor.
The amplitude threshold value determining module monitors the amplitude value of the breath sound signal in the initial frequency spectrum in real time, updates the maximum value of the amplitude of the initial frequency spectrum in real time, and determines an amplitude alarm threshold value according to the maximum value of the amplitude of the initial frequency spectrum. The maximum value of the amplitude of the initial spectrum can be the maximum amplitude value of the initial spectrum in one continuous monitoring process, or the maximum amplitude value of the initial spectrum in the past monitoring process; the amplitude alarm threshold is a threshold for indicating whether apnea occurs, and if the amplitude of the breath sound signal is smaller than or equal to the amplitude alarm threshold, the apnea can be judged to occur.
The amplitude threshold value determining module compares the frequency spectrum amplitude of each frequency in the initial frequency spectrum with the amplitude alarm threshold value respectively, so that whether apnea occurs or not can be preliminarily determined with high monitoring efficiency. If the spectrum amplitude less than or equal to the amplitude alarm threshold exists in the initial spectrum, the occurrence of apnea can be judged, and the duration of the occurrence of apnea, namely the duration of the initial apnea, is obtained through the initial spectrum.
The monitor transmission module can transmit organ sound signals to the respiratory disturbance monitoring terminal according to the initial apnea duration. Further, the monitor transmission module can transmit organ sound signals to the respiratory disturbance monitoring terminal when the initial apnea duration is greater than or equal to the duration alarm threshold.
The amplitude threshold determination module of the respiratory disorder monitor can be used for analyzing the acquired organ sound signals and separating the respiratory sound signals from the organ sound signals. Further, if the amplitude threshold determination module cannot effectively separate the breathing sound signal within the preset period, or the spectrum amplitude of the initial spectrum is weak, the monitor transmission module may transmit the organ sound signal to the breathing disorder monitoring terminal.
In the respiratory disorder monitor, the sleep respiratory disorder condition can be monitored through a small number of characteristic signals, so that the number of connected sensors can be reduced, the influence of the respiratory disorder monitor on a testee is reduced, information can be transmitted to the respiratory disorder monitoring terminal in a wireless mode in real time, and the monitoring accuracy is improved.
In one embodiment, as shown in fig. 3, the respiratory disorder monitor further comprises:
the oxygen content acquisition module is used for acquiring oxygen content information;
the amplitude threshold value determining module is further used for comparing the oxygen content information with an oxygen content alarm threshold value to obtain an oxygen content comparison result, comparing the initial apnea duration with a duration alarm threshold value to obtain a duration comparison result, and generating a monitoring result based on the oxygen content comparison result and the duration comparison result;
and the monitor transmission module is also used for transmitting organ sound signals to the breathing disorder monitoring terminal according to the oxygen content comparison result and the duration comparison result. Specifically, the oxygen content collection module can be used for collecting oxygen content information in real time, and the oxygen content information can be used for indicating whether the breathing disorder monitor is attached to the setting of the person to be tested, judging whether the organ sound signal collected currently is the organ sound signal of the person to be tested, and reducing the error influence caused by the in-vitro setting of the breathing disorder monitor.
Specifically, the amplitude threshold determination module may determine whether the oxygen content information is greater than, equal to, or less than the oxygen content alarm threshold, and obtain an oxygen content comparison result, where the oxygen content comparison result is used to indicate a magnitude relationship between the oxygen content information and the oxygen content alarm threshold. Meanwhile, the amplitude threshold value determining module can compare whether the initial apnea duration is greater than, equal to or less than the duration alarm threshold value, and obtain a duration comparison result, wherein the duration comparison result can be used for indicating the size relation between the initial apnea duration and the duration alarm threshold value. And the amplitude threshold value determining module generates a monitoring result according to the oxygen content comparison result and the duration comparison result.
In one example, the amplitude threshold determination module may determine whether the respiratory disorder monitor is attached to the subject by the oxygen content comparison result, thereby determining whether the organ sound signal collected currently accurately reflects the respiratory state of the subject. And when the breathing disorder monitor is confirmed to be attached to the person to be detected and the initial apnea duration is greater than or equal to the duration alarm threshold, generating a monitoring result of the sleep breathing disorder. Further, the amplitude threshold determination module may further generate a monitoring result that sleep disordered breathing does not occur when the target apnea duration is less than the duration alarm threshold, and/or generate an in-vitro alarm of the disordered breathing monitor when the oxygen content information is less than or equal to the oxygen content alarm threshold.
When the amplitude threshold value determining module confirms that the respiratory disorder monitor is attached to a person to be tested and the initial apnea duration is greater than or equal to the duration alarm threshold value, organ sound signals are transmitted to the respiratory disorder monitoring terminal through the monitor transmission module.
Among the above-mentioned respiratory disorder monitor, can avoid the organ sound signal to acquire the bad influence that the inaccuracy caused the monitoring result, improved the monitoring accuracy.
In one embodiment, the amplitude threshold determination module is further configured to determine a product of the initial spectrum amplitude maximum value and the preset ratio as the amplitude alarm threshold, so that a processing procedure of the amplitude threshold determination module can be simplified, and monitoring efficiency can be improved. The preset proportion can be set according to actual conditions and identification requirements, and the application does not specifically limit the preset proportion. In one embodiment, the amplitude threshold determination module is further configured to pair and authenticate with the respiratory disorder monitoring terminal. Specifically, the amplitude threshold determination module may include a monitor verification unit configured to perform pairing and identity verification with the respiratory disorder monitoring terminal, and when the pairing is successful, the respiratory disorder monitor may transmit data such as an organ sound signal to the respiratory disorder monitoring terminal. In one example, the monitor verification unit may be used for bluetooth pairing with a respiratory disorder monitoring terminal.
In one embodiment, as shown in fig. 3, the respiratory disorder monitor further comprises: and the storage module is used for storing the collected organ sound signals.
To facilitate an understanding of the respiratory disorder monitor of the present application, a specific example is described below. As shown in fig. 4, there is provided a respiratory disorder monitor comprising:
and the sound signal acquisition module is used for acquiring organ sound signals.
And the oxygen content acquisition module is used for acquiring oxygen content information.
The amplitude threshold value determining module comprises a band-pass filtering unit, a frequency detecting unit, an initial spectrum amplitude maximum value confirming unit, a threshold value confirming unit, a duration comparing unit, an oxygen content comparing unit, a monitoring result confirming unit and a monitor verifying unit.
The system comprises a band-pass filtering unit, a signal acquisition unit and a signal processing unit, wherein the band-pass filtering unit is used for performing band-pass filtering on collected organ sound signals; the frequency detection unit is used for converting the filtered organ sound signals into corresponding audio frequency spectrums and separating the initial frequency spectrums of the breathing sound signals from the audio frequency spectrums; the initial spectrum amplitude maximum value confirming unit is used for updating the initial spectrum amplitude maximum value of the breath sound signal in real time according to the initial spectrum; the threshold confirming unit is used for obtaining an amplitude alarm threshold based on the maximum value of the initial spectrum amplitude; the duration comparison unit is used for comparing the oxygen content information with an oxygen content alarm threshold value to obtain an oxygen content comparison result; the oxygen content comparison unit is used for comparing the initial apnea duration with a duration alarm threshold to obtain a duration comparison result; a monitoring result confirmation unit for generating a monitoring result based on the oxygen content comparison result and the duration comparison result; and the monitor verification unit is used for carrying out Bluetooth pairing with the respiratory disorder monitoring terminal supporting the Bluetooth protocol and carrying out identity verification.
And the monitor transmission module is used for transmitting organ sound signals to the respiratory disorder monitoring terminal when the respiratory disorder monitor is attached to the person to be detected and the initial apnea duration is greater than or equal to the duration alarm threshold.
And the storage module is used for storing the historical organ sound signals.
In one embodiment, as shown in fig. 5, there is provided a respiratory disorder monitoring system comprising a respiratory disorder monitoring terminal in any of the above embodiments, and a respiratory disorder monitor in any of the above embodiments.
In particular, the respiratory disorder monitoring terminal may be the respiratory disorder monitoring terminal of any of the above embodiments, and the respiratory disorder monitor may be the respiratory disorder monitor of any of the above embodiments. The respiratory disorder monitor can be used for collecting organ sound signals and carrying out preliminary judgment on the organ sound signals. If the breathing disorder monitor confirms that the sleep breathing disorder occurs, organ sound signals can be transmitted to the breathing disorder monitoring terminal in real time in a wireless mode. The breathing disorder monitoring terminal further analyzes the organ sound signals in depth and obtains an accurate monitoring result.
In particular, the breathing disorder monitor may be used to acquire, preliminarily analyze, transmit, record, display, generate sound data, and analyze data characteristics of organ sound signals. The sleep respiratory disorder monitor can monitor high-frequency or low-frequency organ sound signals through the sound signal acquisition module.
Above-mentioned respiratory disorder monitoring system, including respiratory disorder monitor and respiratory disorder monitor terminal, can monitor the sleep respiratory disorder condition through the less characteristic signal of quantity to reducible sensor quantity of plugging into, and reduce the influence that the person is treated to the sensor, improve monitoring accuracy and easy operation.
In one embodiment, as shown in fig. 5, the respiratory disorder monitoring system further comprises a cloud server; the cloud server is connected with the respiratory disorder monitoring terminal.
Specifically, the respiratory disorder monitoring terminal can upload data such as historical organ sound signals and historical monitoring results to the cloud server, and the cloud server can generate records according to the received historical data, so that the historical data can be conveniently consulted. When the breathing disorder monitoring terminal confirms that the target apnea duration exceeds the duration alarm threshold, the cloud server can give an alarm to the designated terminal.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A breathing disorder monitoring terminal, comprising:
the frequency spectrum conversion module is used for converting the acquired organ sound signals into audio frequency spectrums; the organ sound signal comprises a breath sound signal;
the signal separation module is used for confirming the respiratory characteristic information of the organ sound signal and separating a target frequency spectrum corresponding to the respiratory sound signal from the audio frequency spectrum according to the respiratory characteristic information;
and the monitoring result confirmation module is used for classifying the target frequency spectrum by adopting a naive Bayesian classifier to obtain a monitoring result.
2. The respiratory disorder monitoring terminal of claim 1, wherein the monitoring result confirmation module is further configured to train a model according to the acquired training set and generate the naive bayes classifier according to the trained model; the training set comprises training data; the training data includes an initial spectrum and corresponding monitoring results.
3. The respiratory disorder monitoring terminal of claim 1, wherein the signal separation module comprises a frequency range determination unit and a respiratory sound signal separation unit;
the frequency range determining unit is used for determining a target frequency range of the breathing sound signal according to the breathing characteristic information; the breath sound signal separation unit is used for filtering out frequencies in the audio frequency spectrum except the target frequency range and obtaining the target frequency spectrum.
4. A respiratory disorder monitor, comprising:
the sound signal acquisition module is used for acquiring organ sound signals; the organ sound signal is used for indicating the breathing disorder monitoring terminal to convert into an audio frequency spectrum and confirming the breathing characteristic information of the organ sound signal; the respiratory characteristic information is used for indicating the respiratory disorder monitoring terminal to separate a target frequency spectrum corresponding to a respiratory sound signal from the audio frequency spectrum, and classifying the target frequency spectrum by adopting a naive Bayes classifier to obtain a monitoring result; the organ sound signal comprises the breath sound signal.
5. The respiratory disorder monitor of claim 4, further comprising:
the amplitude alarm threshold determination module is used for converting the organ sound signal into a corresponding audio frequency spectrum, separating an initial frequency spectrum of the breath sound signal from the audio frequency spectrum, updating an initial frequency spectrum amplitude maximum value of the breath sound signal in real time according to the initial frequency spectrum, obtaining an amplitude alarm threshold based on the initial frequency spectrum amplitude maximum value, and comparing the frequency spectrum amplitude of the initial frequency spectrum with the amplitude alarm threshold to obtain an initial apnea duration;
and the monitor transmission module is used for transmitting the organ sound signal to the respiratory disorder monitoring terminal according to the initial apnea duration.
6. The respiratory disorder monitor of claim 5, further comprising:
the oxygen content acquisition module is used for acquiring oxygen content information;
the amplitude threshold value determining module is further configured to compare the oxygen content information with an oxygen content alarm threshold value to obtain an oxygen content comparison result, compare the initial apnea duration with a duration alarm threshold value to obtain a duration comparison result, and generate the monitoring result based on the oxygen content comparison result and the duration comparison result;
the monitor transmission module is further configured to transmit the organ sound signal to the respiratory disorder monitoring terminal according to the oxygen content comparison result and the duration comparison result.
7. The respiratory disorder monitor of claim 5, wherein the amplitude threshold determination module is further configured to determine the amplitude alarm threshold as a product of the initial spectral amplitude maximum and a preset ratio.
8. The respiratory disorder monitor of claim 5, wherein the amplitude threshold determination module is further configured to pair and authenticate with the respiratory disorder monitoring terminal.
9. A breathing disorder monitoring system comprising a breathing disorder monitoring terminal according to claims 1 to 3 and a breathing disorder monitor according to claims 4 to 8.
10. The respiratory disorder monitoring system of claim 9, further comprising a cloud server; the cloud server is in communication connection with the respiratory disorder monitoring terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011336898.1A CN112472066A (en) | 2020-11-25 | 2020-11-25 | Breathing disorder monitoring terminal, monitor and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011336898.1A CN112472066A (en) | 2020-11-25 | 2020-11-25 | Breathing disorder monitoring terminal, monitor and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112472066A true CN112472066A (en) | 2021-03-12 |
Family
ID=74934257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011336898.1A Pending CN112472066A (en) | 2020-11-25 | 2020-11-25 | Breathing disorder monitoring terminal, monitor and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112472066A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113314143A (en) * | 2021-06-07 | 2021-08-27 | 南京优博一创智能科技有限公司 | Apnea judgment method and device and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102641125A (en) * | 2011-02-18 | 2012-08-22 | 西铁城控股株式会社 | Sleep breath pause judging device |
| WO2014045257A1 (en) * | 2012-09-24 | 2014-03-27 | Koninklijke Philips N.V. | System and method for determining a person's breathing |
| CN104107036A (en) * | 2014-07-09 | 2014-10-22 | 中南民族大学 | Household portable monitoring device for sleep apnea |
| CN105816176A (en) * | 2016-03-09 | 2016-08-03 | 清华大学 | Flexible respiratory monitoring devices |
| KR20170083483A (en) * | 2016-01-08 | 2017-07-18 | 전남대학교산학협력단 | Realtime monitoring apparatus for sleep disorders |
| CN107280674A (en) * | 2017-06-02 | 2017-10-24 | 南京理工大学 | The breathing pattern decision method of equipment is enrolled based on audio |
| US20190374167A1 (en) * | 2018-06-12 | 2019-12-12 | Industry Foundation Of Chonnam National University | Method of generating respiratory status classifier and method of determining respiratory status |
-
2020
- 2020-11-25 CN CN202011336898.1A patent/CN112472066A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102641125A (en) * | 2011-02-18 | 2012-08-22 | 西铁城控股株式会社 | Sleep breath pause judging device |
| WO2014045257A1 (en) * | 2012-09-24 | 2014-03-27 | Koninklijke Philips N.V. | System and method for determining a person's breathing |
| CN104107036A (en) * | 2014-07-09 | 2014-10-22 | 中南民族大学 | Household portable monitoring device for sleep apnea |
| KR20170083483A (en) * | 2016-01-08 | 2017-07-18 | 전남대학교산학협력단 | Realtime monitoring apparatus for sleep disorders |
| CN105816176A (en) * | 2016-03-09 | 2016-08-03 | 清华大学 | Flexible respiratory monitoring devices |
| CN107280674A (en) * | 2017-06-02 | 2017-10-24 | 南京理工大学 | The breathing pattern decision method of equipment is enrolled based on audio |
| US20190374167A1 (en) * | 2018-06-12 | 2019-12-12 | Industry Foundation Of Chonnam National University | Method of generating respiratory status classifier and method of determining respiratory status |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113314143A (en) * | 2021-06-07 | 2021-08-27 | 南京优博一创智能科技有限公司 | Apnea judgment method and device and electronic equipment |
| CN113314143B (en) * | 2021-06-07 | 2024-01-30 | 南京优博一创智能科技有限公司 | Method and device for judging apnea and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240023886A1 (en) | Noninvasive method and system for sleep apnea detection | |
| CN109273085B (en) | Pathological respiratory sound library establishing method, respiratory disease detection system and respiratory sound processing method | |
| US9814438B2 (en) | Methods and apparatus for performing dynamic respiratory classification and tracking | |
| CN107822617B (en) | Heartbeat anomaly detection method based on WiFi signals | |
| CN112716474A (en) | Non-contact sleep state monitoring method and system based on biological microwave radar | |
| CN110811647B (en) | Multi-channel hidden lie detection method based on ballistocardiogram signal | |
| CN112486316B (en) | Continuous attention regulation and control system with combined feedback of electroencephalogram and finger pressure | |
| US20220007964A1 (en) | Apparatus and method for detection of breathing abnormalities | |
| DK177536B1 (en) | Method for detecting seizures | |
| JP2013518607A (en) | Method and system for classifying physiological signal quality for portable monitoring | |
| WO2013185775A1 (en) | Method and system of detecting seizures | |
| CN104173064A (en) | Heart rate variability analysis based lie detection method and lie detection device | |
| CN112754444A (en) | Radar-based non-contact pig respiration detection method | |
| CN111248928A (en) | Pressure identification method and device | |
| CN111370124A (en) | Health analysis system and method based on facial recognition and big data | |
| WO2016072940A1 (en) | Multi-channel ballistocardiography with cepstrum smoothing and quality-based dynamic channel selection | |
| AU2019360358A1 (en) | A method and apparatus for diagnosis of maladies from patient sounds | |
| CN112472066A (en) | Breathing disorder monitoring terminal, monitor and system | |
| CN107865638A (en) | Computer-readable recording medium, built-in earplug detection means | |
| KR102281420B1 (en) | Smart toilet system for bio signal measurement capable of user authentication and monitoring of fall | |
| CN113069091A (en) | Pulse condition classification device and method for PPG (photoplethysmography) signals | |
| CN113627340A (en) | Method and equipment capable of identifying rope skipping mode | |
| CN106326672A (en) | Falling into sleep detecting method and system | |
| KR101295072B1 (en) | An apparatus of heart sound analysis base on simplicity and the method | |
| JP7089650B2 (en) | Processing equipment, systems, processing methods, and programs |
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 |