CN102138795A - Method for determining severity of obstructive sleep apnea hypopnea syndrome (OSAHS) according to snore acoustic characteristics - Google Patents
Method for determining severity of obstructive sleep apnea hypopnea syndrome (OSAHS) according to snore acoustic characteristics Download PDFInfo
- Publication number
- CN102138795A CN102138795A CN2011100413782A CN201110041378A CN102138795A CN 102138795 A CN102138795 A CN 102138795A CN 2011100413782 A CN2011100413782 A CN 2011100413782A CN 201110041378 A CN201110041378 A CN 201110041378A CN 102138795 A CN102138795 A CN 102138795A
- Authority
- CN
- China
- Prior art keywords
- sound
- snoring
- osahs
- severity
- sbfp
- 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
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to a method for determining severity of an obstructive sleep apnea hypopnea syndrome (OSAHS) according to snore acoustic characteristics. The method comprises the following steps of: performing cluster analysis on format probability in sub-band (SBFP) parameters of a large number of experimental samples with the same OSAHS severity to obtain models representing four OSAHS severities: a simple snore mode, a mild OSAHS model, a moderate OSAHS model and a severe OSAHS model; and when a subject needs to be judged to which OSAHS severity the subject belongs, recording sound data of the subject all night long only, calculating an SBFP characteristic parameter, and matching the SBFP with the four models, so that which OSAHS severity the subject belongs to can be judged according to the model corresponding to the maximum matching probability. The snore when the subject sleeps is needed to be recorded only, so the method is simple and convenient without influencing the sleep quality of the patient.
Description
Technical field
The present invention relates to the method for a kind of definite obstructive sleep apnea low-ventilatory syndrome (Obstructive sleep apnea hypopnea syndrome is called for short OSAHS) order of severity.Be different from traditional sleep analysis monitor system (PSG), the present invention determines the order of severity of OSAHS by " formant is at the distribution probability (formant probability in sub-band; be called for short SBFP) of each frequency sub-band " this acoustic features of analyzing the sound of snoring, for the patient provides preliminary diagnostic result, for next step operation need provide reference.
Background technology
Medically, PSG is as the golden standard of judging the OSAHS order of severity, mainly by the professional according to multichannel transducing signal (electro-oculogram, electroencephalogram, electrocardiogram, electromyogram, nose air-flow, chest exercise, abdominal exercise, blood oxygen variation etc.) comprehensively judge the type (the maincenter type is blocked type or mixed type) that patient respiratory suspends, and the OSAHS order of severity.Medically asphyxia and low ventilation index (Apnea Hypopnea Index, AHI) the expression OSAHS order of severity, the sound of snoring can be divided into four classes: 0＜AHI≤5 by AHI and belong to the simple sound of snoring (or simple sound of snoring), 5＜AHI≤20 belong to slight OSAHS, 20＜AHI≤40 belong to moderate OSAHS, AHI〉40 belong to moderate or severe OSAHS.PSG monitoring sketch map as shown in Figure 1, all post different pick offs on patient face, breast abdominal part and the finger, pick off is wired on the bedside " flight data recorder ", and " flight data recorder " is connected to the PC at nurse center by cable, can see the live signal of each road pick off as shown in Figure 2 from PC.As shown in Figure 1, when PSG provides accurate diagnosis, the comfort level of also having cut down the patient, the worse situation is, the change of (sleep at ordinary times do not have pick off be attached on one's body) because sleep environment, the PSG monitoring result can not correctly reflect patient's state at ordinary times sometimes.In addition, PSG monitoring expense costliness, the inconvenience of PSG equipment is carried, and needs the professional to connect loaded down with trivial details circuit and the data etc. of analyzing multiple signals are the whole night had a greatly reduced quality the practicality of PSG equipment and universality.
The sound of snoring is one of the most outstanding characteristics of OSAHS, although PSG has one road paster microphone signal to be used to monitor the laryngeal vibration situation, only can judge according to this signal to have or not the sound of snoring.And obtaining of sound of snoring signal is different from other transducing signals, and microphone apparatus does not need body contact.
Summary of the invention
The objective of the invention is to the deficiency that exists at PSG monitoring, provide a kind of and determine the method for the obstructive sleep apnea and the hypoventilation syndrome order of severity, and diagnostic result is shown according to sound of snoring acoustic features.
Ultimate principle: well-known, sound causes by vibration, and the generation of voice to be air-flows strike a chord via sound channels such as oral cavity nasal cavities, the resonant frequency of sound channel is called formant frequency, is called for short formant.Similar to voice, the sound of snoring is to be subsided or blocked by respiratory tract a part (organ), causes obstructed the striking a chord of respiratory air flow and the sound that sends.That is to say, the sound of snoring and closed position are closely related, OSAHS order of severity difference, formant frequency distribution (the formant probability in sub-band of the corresponding sound of snoring, be called for short SBFP) also different, and for the patient of the same OSAHS order of severity, its sound of snoring has consistent rule in a certain frequency range.In other words, the sound of snoring of moderate or severe OSAHS is at the easier formant that occurs of some frequency band, and the sound of snoring is easier formant occurs at another frequency band simple.The patient's of the different orders of severity of four kinds of OSAHS SBFP characteristic parameter rule as shown in Figure 3, corresponding 8 frequency sub-band of transverse axis wherein, bandwidth is 500Hz, and the longitudinal axis is represented the distribution probability of formant at each frequency sub-band.
Design of the present invention is: the OSAHS order of severity of determining the patient by this acoustic features of formant distribution probability (SBFP) of air-breathing section of the statistics sound of snoring.The sound of snoring is made up of air-breathing section, changeover portion and breathing section, because the formant of air-breathing section of the sound of snoring is stable and obviously, the analytic target of this feature is air-breathing section of the sound of snoring, the following sound of snoring all refers to its air-breathing section.
A kind ofly determine to it is characterized in that the method for the obstructive sleep apnea and the hypoventilation syndrome order of severity according to sound of snoring acoustic features:
(1) sets up the reference model of four different OSAHS orders of severity: the formant regularity of distribution of adding up the different OSAHS orders of severity, set up the reference model of four different OSAHS orders of severity according to the SBFP characteristic parameter, be respectively: simple sound of snoring model, slight OSAHS model, moderate OSAHS model and moderate or severe OSAHS model;
(2) detect the sound of snoring and calculate its SBFP characteristic parameter: record subjects's the sound of snoring, calculate the SBFP characteristic parameter of its sound of snoring;
(3) with four reference models of SBFP characteristic parameter coupling: according to four reference models in subjects's the SBFP acoustical characteristic parameters coupling step (1), the corresponding subjects's of the model of matching probability maximum OSAHS order of severity type;
(4) demonstration is based on the OSAHS diagnostic result of acoustic features.
The present invention has following conspicuous outstanding substantive distinguishing features and remarkable advantage compared with prior art: by the sound of snoring signal of gathering the patient, the acoustic features of analyzing the sound of snoring and the diagnostic result of match PSG, determine the order of severity of OSAHS.Do not influencing under the comfort level of patient sleep, less demanding to test environment, easy to detect, the condition that expense is cheap, determining patient's the OSAHS order of severity.
Description of drawings
The connection layout of Fig. 1 PSG sleep analysis monitor.
The synchronous display interface of many derivative sensors of Fig. 2 PSG signal.
The patient's of four different OSAHS orders of severity of Fig. 3 SBFP characteristic parameter rule figure.
Fig. 4 determines sound of snoring patient's OSAHS order of severity flow chart according to the SBFP acoustic features of the sound of snoring.
The flow chart of the acoustics rule of the different OSAHS orders of severity of Fig. 5 " off-line analysis ".
Fig. 6 " on-line analysis " calculates the flow chart of subjects SBFP characteristic parameter.
Fig. 7 analyzes the man machine interface of OSAHS according to sound of snoring acoustic features.
The specific embodiment
Details are as follows in conjunction with the accompanying drawings for the preferred embodiments of the present invention:
Embodiment one: referring to Fig. 4, Fig. 5 and Fig. 6, determine the obstructive sleep apnea and low ventilation syndrome (OSAHS) order of severity according to sound of snoring acoustic features, it is characterized in that:
(1) sets up the reference model of four different OSAHS orders of severity: the formant regularity of distribution of adding up the different OSAHS orders of severity, set up the reference model of four different OSAHS orders of severity according to the SBFP characteristic parameter, be respectively: simple sound of snoring model, slight OSAHS model, moderate OSAHS model and moderate or severe OSAHS model;
(2) detect the sound of snoring and calculate its SBFP characteristic parameter: record subjects's the sound of snoring, calculate the SBFP characteristic parameter of its sound of snoring;
(3) with four reference models of SBFP characteristic parameter coupling: according to four reference models in subjects's the SBFP acoustical characteristic parameters coupling step (1), the corresponding subjects's of the model of matching probability maximum OSAHS order of severity type;
(4) demonstration is based on the OSAHS diagnostic result of acoustic features.
Embodiment two: present embodiment and embodiment two are basic identical, and special feature is as follows:
Needs when described step (1) is set up the reference model of four different OSAHS orders of severity:
1) obtain the sound of snoring of a large amount of different OSAHS orders of severity, the wherein different OSAHS orders of severity are obtained by the PSG of hospital monitoring result, and described PSG monitoring result must be correct; The experiment of each class OSAHS need surpass 500, i.e. the patient of four kinds of OSAHS degree each 500 people at least; For OSAHS patient, need make the Alice signal and the sound of snoring synchronous in conjunction with the MicL signal among the Alice, according to the apnea low position that medical diagnosis is demarcated, air-breathing section of the sound of snoring of intercepting correspondence is as the experimental data of statistical acoustics rule; For simple sound of snoring patient, air-breathing section rule that all can be used as statistics SBFP characteristic parameter of all sounds of snoring; Because SBFP is the statistics to the formant regularity of distribution of air-breathing section of all sounds of snoring of subjects, so air-breathing section necessary complete and apnea low time correspondence of the sound of snoring needs the hand cut sound of snoring.
2) according to the SBFP features training model of the same class OSAHS sound of snoring, adopt gauss hybrid models, guarantee that wherein the Gaussian Mixture number equates with the frequency sub-band number, causes the possible closed position of OSAHS with further analysis.
Needs when described step (2) detects the sound of snoring and calculates the SBFP characteristic parameter:
1. guarantee that the subjects is in good playback environ-ment: reduce noise, except possible air-conditioning and host computer, the experimenter is separately in the bedroom during monitoring as far as possible, and door is closed, and keeps quite in the outside, bedroom; The position of mike need constantly be adjusted by the method for playing test tone, must guarantee that the sensitivity of recording when setting up the reference model is consistent;
2. effectively the sound of snoring detects: the sound relevant with the sound of snoring comprises air-breathing section of quiet, the sound of snoring, sound of snoring expiration section and voice, the sound of snoring detects and refer to detect air-breathing section of the sound of snoring from the sound relevant with the sound of snoring, must guarantee that air-breathing section detection of the sound of snoring is errorless, it is just meaningful to add up the SBFP characteristic parameter like this;
3. ask the distribution probability SBFP of formant at sound of snoring air-suction-noise at different frequency sub-band, 8 frequency sub-band are divided into: 0-500Hz, 500-1000Hz, 1000-1500Hz, 1500-2000Hz, 2000-2500Hz, 2500-3000Hz, 3000-3500Hz and 3500-4000Hz need merge the situation that occurs an above formant in the 500Hz when estimating formant and handle, and the accuracy that requires to calculate formant is higher than 90%.
Described step (4) shows that diagnostic result is: judge process and result in the middle of needing to keep, time and sound that the sound of snoring is detected are saved in PC automatically, waveform shows and show different respiration cases with contrast color simultaneously---mainly refer to sound of snoring incident, eupnea incident and asphyxia and low ventilation incident, so that examine and calibrate.
Embodiment three:
As shown in Figure 4, determine that according to the sound of snoring SBFP acoustic features OSAHS order of severity can divide for four steps:
(1) the acoustics rule of " off-line analysis " different OSAHS orders of severity is set up the model of four different OSAHS orders of severity; (here according to existing data analysis rule, rather than to the real-time recording data analysis, so be called off-line analysis)
(2) " on-line analysis " calculating subjects's SBFP characteristic parameter; (on-line analysis refers to the real-time recording date processing)
(3) with four models of the off-line analysis in the SBFP coupling of calculating in the step (2) (1), determine the model that the subjects is mated according to maximum of probability;
(4) result shows: determine the OSAHS order of severity according to Matching Model, and show the OSAHS order of severity and sound of snoring number of times and corresponding time.
In the above-mentioned steps (1) implementation process as shown in Figure 5, concrete steps are as follows:
1) sound of snoring of obtaining the different OSAHS orders of severity and the simple sound of snoring, and manually cut the sound of snoring after asphyxia and the low ventilation in conjunction with the Alice monitoring waveform of PSG, as the experiment sample of statistics formant rule;
2) according to concrete playback environ-ment,, comprise that denoising, the sound of snoring are divided into short time frame etc. to the experiment sample pretreatment;
3) adopt the method for linear prediction analysis (LPC) to calculate formant;
4) according to the subband of dividing, statistic procedure 3) in the formant that calculates drop on the rule of each subband, finally obtain the SBFP characteristic parameter of this experiment sample;
5) adopt clustering algorithm, the SBFP characteristic parameter of same class OSAHS experiment sample is analyzed, finally each class OSAHS is with a GMM model representation, and wherein model parameter is represented by the weight coefficient of average, variance and the Gaussian Mixture of SBFP characteristic parameter.
Realization flow in the above-mentioned steps (2) as shown in Figure 6, concrete steps are as follows:
＜1〉analyze to as if subjects's voice data the whole night, this voice data is to obtain by mike collection subjects sleep procedure the whole night;
＜2〉sound of snoring detects: voice data may comprise sound such as the sound of snoring, voice, eupnea sound, air-conditioning noise the whole night, and the sound of snoring detects and refers to according to certain judgment criterion from detecting air-breathing section of the sound of snoring automatically the voice data the whole night, to treat next step analysis;
＜3〉pretreatment: be divided into short time frame to calculate formant according to playback environ-ment suitable " denoising " and with each sound of snoring;
＜4〉adopt the method for linear prediction analysis to calculate formant;
＜5 〉, statistics＜4 according to the subband of dividing〉in the formant that calculates drop on the rule of each subband, finally obtain subjects's SBFP characteristic parameter.
GMM model in the above-mentioned steps (3) is by the weight coefficient of Gaussian Mixture
, the characteristic parameter average
And variance
Expression,
,
It is the Gaussian Mixture number.If known subjects's SBFP characteristic parameter
(
Be
The vector of dimension), the probability calculation of Matching Model can be expressed as shown in the formula (1):
(1)
Technique effect:
Determine the method for the OSAHS order of severity based on sound of snoring acoustic features, can realize in conjunction with software interface shown in Figure 7.This software interface can be realized that collection, acoustic features analysis, the analytical data of the sound of snoring are preserved automatically and determine that by the SBFP acoustic features of the sound of snoring result of its OSAHS order of severity shows.Both monitoring analysis in real time can be judged the OSAHS order of severity according to certain audio files off-line again, introduce software interface shown in Figure 7 below simply:
1. begin recording (on-line analysis): comprise the startup recording, real-time voice data carried out sound of snoring detection and preserves the automatic each time sound of snoring that detects (comprises time and audio files), preserves each frame of air-breathing section of each sound of snoring to PC formant result of calculation automatically, for examining; The sound the whole night that preservation is recorded is to PC, so that off-line analysis; Show the OSAHS order of severity; Add up respiration case simply, judge whether the method (continue noiseless time surpass be considered as asphyxia and low ventilation more than the 10s) of asphyxia and low ventilation, the number of times of statistics asphyxia and low ventilation by the time of detecting unvoiced segments;
When 2. " suspending recording ", the time of statistics sleep procedure also can be suspended, and does not influence the value of being calculated AHI by asphyxia and low ventilation number of times like this;
3. when " on-line analysis ", will show as shown in Figure 7 result, comprise sound of snoring number of times, asphyxia and low ventilation number of times and AHI value and subjects's the OSAHS order of severity in results display area;
4. " the importing sound of snoring " (off-line analysis): can be by importing the whole night sound in software, determine this patient's the serious situation of OSAHS by the sound of snoring, off-line analysis is very effective to checking and the algorithm that improves in the software;
5. off-line analysis and on-line analysis are similar, are imported the OSAHS order of severity and sound of snoring number of times, apnea low number of times and the AHI value of the sound of snoring as can be known by off-line analysis.
Along with the continuous research of sound of snoring acoustic features, also can in software, add algorithm and function, such as analyzing the possible closed position of OSAHS patient, the not reciprocity reason that causes OSAHS of sleeping position whether, these all await the more deep research of sound of snoring acoustic features.
Claims (4)
1. determine to it is characterized in that the method for obstructive sleep apnea and low ventilation syndrome (OSAHS) order of severity according to sound of snoring acoustic features for one kind:
(1) sets up the reference model of four different OSAHS orders of severity: the formant regularity of distribution of adding up different OSAHS sound of snoring types, set up the reference model of four different OSAHS orders of severity according to the SBFP characteristic parameter, be respectively: simple sound of snoring model, slight OSAHS model, moderate OSAHS model and moderate or severe OSAHS model;
(2) detect the sound of snoring and calculate its SBFP characteristic parameter: record subjects's the sound of snoring, calculate the SBFP characteristic parameter of its sound of snoring;
(3) with four reference models of SBFP characteristic parameter coupling: according to four reference models in subjects's the SBFP acoustical characteristic parameters coupling step (1), the corresponding subjects's of the model of matching probability maximum OSAHS order of severity type;
(4) demonstration is based on the OSAHS diagnostic result of acoustic features.
2. according to claim 1ly determine the method for the obstructive sleep apnea and the hypoventilation syndrome order of severity, needs when it is characterized in that described step (1) is set up the reference model of four different OSAHS orders of severity according to sound of snoring acoustic features:
1) obtain the sound of snoring of a large amount of different OSAHS orders of severity, the wherein different OSAHS orders of severity are obtained by the PSG monitoring result of hospital, and described PSG monitoring result must be correct; The experiment needs of patients of each class OSAHS surpasses 500, i.e. the patient of four kinds of OSAHS degree each 500 people at least; For OSAHS patient, need make the Alice signal and the sound of snoring synchronous in conjunction with the MicL signal among the Alice, according to the apnea low position that medical diagnosis is demarcated, air-breathing section of the sound of snoring of intercepting correspondence is as the experimental data of statistical acoustics rule; For simple sound of snoring patient, air-breathing section rule that all can be used as statistics SBFP characteristic parameter of all sounds of snoring; Because SBFP is the statistics to the formant regularity of distribution of air-breathing section of all sounds of snoring of subjects,, need the hand cut sound of snoring so air-breathing section of the sound of snoring must be complete and corresponding with the apnea low time;
2) according to same type OSAHS patient's SBFP features training model, adopt gauss hybrid models, guarantee that wherein the Gaussian Mixture number equates with the frequency sub-band number, causes the possible closed position of OSAHS with further analysis.
3. according to claim 1ly determine the method for the obstructive sleep apnea and the hypoventilation syndrome order of severity, needs when it is characterized in that described step (2) detects the sound of snoring and calculates the SBFP characteristic parameter according to sound of snoring acoustic features:
1. guarantee that the experimenter is in good playback environ-ment: reduce noise, except possible air-conditioning and host computer, the experimenter is separately in the bedroom during monitoring as far as possible, and door is closed, and keeps quite in the outside, bedroom; The position of mike need constantly be adjusted by the method for playing test tone, must guarantee that the sensitivity of recording when setting up the reference model is consistent;
2. effectively the sound of snoring detects: the sound relevant with the sound of snoring comprises air-breathing section of quiet, the sound of snoring, sound of snoring expiration section and voice, the sound of snoring detects and refer to detect air-breathing section of the sound of snoring from the sound relevant with the sound of snoring, must guarantee that air-breathing section detection of the sound of snoring is errorless, it is just meaningful to add up the SBFP characteristic parameter like this;
3. ask the distribution probability SBFP of formant at sound of snoring air-suction-noise at different frequency sub-band, 8 frequency sub-band are divided into: 0-500Hz, 500-1000Hz, 1000-1500Hz, 1500-2000Hz, 2000-2500Hz, 2500-3000Hz, 3000-3500Hz and 3500-4000Hz need merge the situation that occurs an above formant in the 500Hz when estimating formant and handle, and the accuracy that requires to calculate formant is higher than 90%.
4. the method for determining the obstructive sleep apnea and the hypoventilation syndrome order of severity according to sound of snoring acoustic features according to claim 1, the demonstration diagnostic result that it is characterized in that described step (4) is: judge process and result in the middle of needs keep, time and sound that the sound of snoring is detected are saved in PC automatically, waveform shows and show different respiration cases with contrast color simultaneously---mainly refer to sound of snoring incident, eupnea incident and asphyxia and low ventilation incident, so that examine and calibrate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100413782A CN102138795A (en) | 2011-02-21 | 2011-02-21 | Method for determining severity of obstructive sleep apnea hypopnea syndrome (OSAHS) according to snore acoustic characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100413782A CN102138795A (en) | 2011-02-21 | 2011-02-21 | Method for determining severity of obstructive sleep apnea hypopnea syndrome (OSAHS) according to snore acoustic characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102138795A true CN102138795A (en) | 2011-08-03 |
Family
ID=44406761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100413782A Pending CN102138795A (en) | 2011-02-21 | 2011-02-21 | Method for determining severity of obstructive sleep apnea hypopnea syndrome (OSAHS) according to snore acoustic characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102138795A (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102429662A (en) * | 2011-11-10 | 2012-05-02 | 大连理工大学 | Screening system for sleep apnea syndrome in family environment |
| CN102499637A (en) * | 2011-09-26 | 2012-06-20 | 大连理工大学 | Obstructive sleep apnea-hypopnea syndrome screening method and device thereof |
| CN103190911A (en) * | 2013-04-16 | 2013-07-10 | 南京理工大学 | Upper airway change monitoring method based on snore formants and power ratio tracks |
| CN103251388A (en) * | 2013-04-25 | 2013-08-21 | 北京大学深圳研究生院 | Method and system of snoring monitoring and prevention and treatment based on smart phone platform |
| CN103385707A (en) * | 2013-07-31 | 2013-11-13 | 太仓市同维电子有限公司 | Intelligent router capable of distinguishing snore types and distinguishing method thereof |
| CN103462597A (en) * | 2013-09-18 | 2013-12-25 | 温州医科大学 | Method and device for preventing obstructive sleep sudden death based on intelligent mobile phone control |
| CN103735267A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Device for screening OSAHS (Obstructive Sleep Apnea-Hypopnea Syndrome) based on snore |
| WO2015078082A1 (en) * | 2013-11-27 | 2015-06-04 | 张孝文 | Sleep breathing pathological typing method |
| CN104739412A (en) * | 2013-12-29 | 2015-07-01 | 中国移动通信集团公司 | Method and equipment for monitoring sleep apnea |
| WO2015096217A1 (en) * | 2013-12-23 | 2015-07-02 | 张孝文 | Computer-assisted method for classifying snores |
| WO2015196695A1 (en) * | 2014-06-24 | 2015-12-30 | 中兴通讯股份有限公司 | Method and device for collecting sound information |
| CN106328152A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | Automatic identification and monitoring system for indoor noise pollution |
| TWI593390B (en) * | 2016-05-05 | 2017-08-01 | 國立中央大學 | Bed set for inhibition of obstructive sleep apnea |
| CN109717835A (en) * | 2018-12-21 | 2019-05-07 | 南京理工大学 | A kind of sound of snoring position detection method based on microphone array |
| CN109745011A (en) * | 2019-02-20 | 2019-05-14 | 华为终端有限公司 | User's sleep-respiratory risk monitoring and control method, terminal and computer-readable medium |
| CN110570880A (en) * | 2019-09-04 | 2019-12-13 | 杭州深蓝睡眠科技有限公司 | Snore signal identification method |
| CN110584626A (en) * | 2019-09-04 | 2019-12-20 | 冯学艺 | Head-mounted snore monitoring device and snore stopping method |
| CN110634504A (en) * | 2019-09-16 | 2019-12-31 | 北京理工大学 | Snore detection method and device |
| CN110942784A (en) * | 2019-11-21 | 2020-03-31 | 杭州电子科技大学 | Snore classification system based on support vector machine |
| CN111938650A (en) * | 2020-07-03 | 2020-11-17 | 上海诺斯清生物科技有限公司 | Method and device for monitoring sleep apnea |
| CN113180691A (en) * | 2020-12-28 | 2021-07-30 | 天津大学 | Three-channel sleep apnea and hypopnea syndrome recognition device |
| TWI735879B (en) * | 2019-05-16 | 2021-08-11 | 醫療財團法人徐元智先生醫藥基金會亞東紀念醫院 | Method of predicting sleep apnea from snoring using neural network |
| CN113273992A (en) * | 2021-05-11 | 2021-08-20 | 清华大学深圳国际研究生院 | Signal processing method and device |
| CN113288056A (en) * | 2021-05-21 | 2021-08-24 | 张安斌 | Method and device for intervening snoring by rapid detection |
| WO2021253125A1 (en) * | 2020-06-18 | 2021-12-23 | University Of Manitoba | Systems and methods for screening obstructive sleep apnea during wakefulness using anthropometric information and tracheal breathing sounds |
| CN114668497A (en) * | 2022-03-29 | 2022-06-28 | 四川大学华西医院 | Computer-aided liver surgery planning three-dimensional modeling system |
| CN115206291A (en) * | 2022-05-30 | 2022-10-18 | 华南理工大学 | OSAHS detection system and method based on sleep snore characteristics |
-
2011
- 2011-02-21 CN CN2011100413782A patent/CN102138795A/en active Pending
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102499637A (en) * | 2011-09-26 | 2012-06-20 | 大连理工大学 | Obstructive sleep apnea-hypopnea syndrome screening method and device thereof |
| CN102499637B (en) * | 2011-09-26 | 2013-11-06 | 大连理工大学 | Obstructive sleep apnea-hypopnea syndrome screening method and device thereof |
| CN102429662B (en) * | 2011-11-10 | 2014-04-09 | 大连理工大学 | Screening system for sleep apnea syndrome in family environment |
| CN102429662A (en) * | 2011-11-10 | 2012-05-02 | 大连理工大学 | Screening system for sleep apnea syndrome in family environment |
| CN103190911A (en) * | 2013-04-16 | 2013-07-10 | 南京理工大学 | Upper airway change monitoring method based on snore formants and power ratio tracks |
| CN103251388A (en) * | 2013-04-25 | 2013-08-21 | 北京大学深圳研究生院 | Method and system of snoring monitoring and prevention and treatment based on smart phone platform |
| CN103385707A (en) * | 2013-07-31 | 2013-11-13 | 太仓市同维电子有限公司 | Intelligent router capable of distinguishing snore types and distinguishing method thereof |
| CN103462597A (en) * | 2013-09-18 | 2013-12-25 | 温州医科大学 | Method and device for preventing obstructive sleep sudden death based on intelligent mobile phone control |
| CN103462597B (en) * | 2013-09-18 | 2015-04-29 | 温州医科大学 | Device for preventing obstructive sleep sudden death based on intelligent mobile phone control |
| WO2015078082A1 (en) * | 2013-11-27 | 2015-06-04 | 张孝文 | Sleep breathing pathological typing method |
| WO2015096217A1 (en) * | 2013-12-23 | 2015-07-02 | 张孝文 | Computer-assisted method for classifying snores |
| CN104739412A (en) * | 2013-12-29 | 2015-07-01 | 中国移动通信集团公司 | Method and equipment for monitoring sleep apnea |
| CN104739412B (en) * | 2013-12-29 | 2017-11-03 | 中国移动通信集团公司 | A kind of method and apparatus being monitored to sleep apnea |
| CN103735267A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Device for screening OSAHS (Obstructive Sleep Apnea-Hypopnea Syndrome) based on snore |
| WO2015196695A1 (en) * | 2014-06-24 | 2015-12-30 | 中兴通讯股份有限公司 | Method and device for collecting sound information |
| CN106328152B (en) * | 2015-06-30 | 2020-01-31 | 芋头科技（杭州）有限公司 | automatic indoor noise pollution identification and monitoring system |
| CN106328152A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | Automatic identification and monitoring system for indoor noise pollution |
| TWI593390B (en) * | 2016-05-05 | 2017-08-01 | 國立中央大學 | Bed set for inhibition of obstructive sleep apnea |
| CN109717835A (en) * | 2018-12-21 | 2019-05-07 | 南京理工大学 | A kind of sound of snoring position detection method based on microphone array |
| CN109745011A (en) * | 2019-02-20 | 2019-05-14 | 华为终端有限公司 | User's sleep-respiratory risk monitoring and control method, terminal and computer-readable medium |
| CN109745011B (en) * | 2019-02-20 | 2021-12-03 | 华为终端有限公司 | User sleep respiration risk monitoring method, terminal and computer readable medium |
| TWI735879B (en) * | 2019-05-16 | 2021-08-11 | 醫療財團法人徐元智先生醫藥基金會亞東紀念醫院 | Method of predicting sleep apnea from snoring using neural network |
| CN110570880A (en) * | 2019-09-04 | 2019-12-13 | 杭州深蓝睡眠科技有限公司 | Snore signal identification method |
| CN110584626A (en) * | 2019-09-04 | 2019-12-20 | 冯学艺 | Head-mounted snore monitoring device and snore stopping method |
| CN110634504B (en) * | 2019-09-16 | 2021-09-21 | 北京理工大学 | Snore detection method and device |
| CN110634504A (en) * | 2019-09-16 | 2019-12-31 | 北京理工大学 | Snore detection method and device |
| CN110942784A (en) * | 2019-11-21 | 2020-03-31 | 杭州电子科技大学 | Snore classification system based on support vector machine |
| WO2021253125A1 (en) * | 2020-06-18 | 2021-12-23 | University Of Manitoba | Systems and methods for screening obstructive sleep apnea during wakefulness using anthropometric information and tracheal breathing sounds |
| CN111938650A (en) * | 2020-07-03 | 2020-11-17 | 上海诺斯清生物科技有限公司 | Method and device for monitoring sleep apnea |
| CN111938650B (en) * | 2020-07-03 | 2024-06-11 | 上海诺斯清生物科技有限公司 | Method and device for monitoring sleep apnea |
| CN113180691A (en) * | 2020-12-28 | 2021-07-30 | 天津大学 | Three-channel sleep apnea and hypopnea syndrome recognition device |
| CN113180691B (en) * | 2020-12-28 | 2022-10-21 | 天津大学 | Three-channel sleep apnea and hypopnea syndrome recognition device |
| CN113273992A (en) * | 2021-05-11 | 2021-08-20 | 清华大学深圳国际研究生院 | Signal processing method and device |
| CN113273992B (en) * | 2021-05-11 | 2023-04-18 | 清华大学深圳国际研究生院 | Signal processing method and device |
| CN113288056A (en) * | 2021-05-21 | 2021-08-24 | 张安斌 | Method and device for intervening snoring by rapid detection |
| CN114668497B (en) * | 2022-03-29 | 2023-06-06 | 四川大学华西医院 | Three-dimensional modeling system for planning liver surgery assisted by computer |
| CN114668497A (en) * | 2022-03-29 | 2022-06-28 | 四川大学华西医院 | Computer-aided liver surgery planning three-dimensional modeling system |
| CN115206291A (en) * | 2022-05-30 | 2022-10-18 | 华南理工大学 | OSAHS detection system and method based on sleep snore characteristics |
| CN115206291B (en) * | 2022-05-30 | 2024-03-19 | 华南理工大学 | OSAHS detection system and method based on sleep snore characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102138795A (en) | Method for determining severity of obstructive sleep apnea hypopnea syndrome (OSAHS) according to snore acoustic characteristics | |
| US7559903B2 (en) | Breathing sound analysis for detection of sleep apnea/popnea events | |
| Duckitt et al. | Automatic detection, segmentation and assessment of snoring from ambient acoustic data | |
| Abeyratne et al. | Pitch jump probability measures for the analysis of snoring sounds in apnea | |
| CN103687540B (en) | Use respiratory murmur amplitude spectrogram and the pitch contour diagnosis OSA/CSA of record | |
| US20120071741A1 (en) | Sleep apnea monitoring and diagnosis based on pulse oximetery and tracheal sound signals | |
| Penzel et al. | The use of tracheal sounds for the diagnosis of sleep apnoea | |
| EP0956820A1 (en) | Apnea determination | |
| US20130144190A1 (en) | Sleep apnea detection system | |
| JP2013518607A (en) | Method and system for classifying physiological signal quality for portable monitoring | |
| US10004452B2 (en) | System and methods for estimating respiratory airflow | |
| WO2020238954A1 (en) | Apnea monitoring method and device | |
| CN103841888A (en) | Apnea and hypopnea detection using breath pattern recognition | |
| CA2897883A1 (en) | Mask and method for breathing disorder identification, characterization and/or diagnosis | |
| CN105962897B (en) | A kind of adaptive sound of snoring signal detecting method | |
| Romero et al. | Deep learning features for robust detection of acoustic events in sleep-disordered breathing | |
| CN104622432B (en) | Based on bass than sleep sound of snoring monitoring method and system | |
| CA2585824A1 (en) | Breathing sound analysis for detection of sleep apnea/hypopnea events | |
| KR20230026349A (en) | System and method for screening for obstructive sleep apnea during wakefulness using anthropometric information and tracheal breathing sounds | |
| Kim et al. | Breathing sounds analysis system for early detection of airway problems in patients with a tracheostomy tube | |
| CA2584258A1 (en) | Breathing sound analysis for estimation of airflow rate | |
| Andres et al. | Respiratory sounds analysis in the world of health 2.0 and medicine 2.0 | |
| Wei et al. | Portable Obstructive Sleep Apnea Detection Device Based on Bone Conduction Microphone | |
| Muñoz Rojo et al. | Validation of Tracheal Sound-Based Respiratory Effort Monitoring for Obstructive Sleep Apnoea Diagnosis | |
| Lima Junior et al. | Determining airflow obstruction from tracheal sound analysis: simulated tests and evaluations in patients with acromegaly |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110803 |