CN113925464B - Method for detecting sleep apnea based on mobile equipment - Google Patents
Method for detecting sleep apnea based on mobile equipment Download PDFInfo
- Publication number
- CN113925464B CN113925464B CN202111217096.3A CN202111217096A CN113925464B CN 113925464 B CN113925464 B CN 113925464B CN 202111217096 A CN202111217096 A CN 202111217096A CN 113925464 B CN113925464 B CN 113925464B
- Authority
- CN
- China
- Prior art keywords
- sleep apnea
- snore
- audio
- volume
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 201000002859 sleep apnea Diseases 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 19
- 206010041235 Snoring Diseases 0.000 claims abstract description 99
- 238000001514 detection method Methods 0.000 claims abstract description 59
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 238000013135 deep learning Methods 0.000 claims abstract description 7
- 230000007958 sleep Effects 0.000 claims abstract description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 230000035772 mutation Effects 0.000 claims description 8
- 230000006399 behavior Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000005236 sound signal Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 2
- 208000024891 symptom Diseases 0.000 abstract description 7
- 208000008784 apnea Diseases 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 230000003595 spectral effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000036578 sleeping time Effects 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 208000007590 Disorders of Excessive Somnolence Diseases 0.000 description 1
- 206010019280 Heart failures Diseases 0.000 description 1
- 206010021079 Hypopnoea Diseases 0.000 description 1
- 206010041349 Somnolence Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007630 basic procedure Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4818—Sleep apnoea
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4803—Speech analysis specially adapted for diagnostic purposes
-
- 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Evolutionary Computation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Signal Processing (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method for detecting sleep apnea based on mobile equipment, which is used for detecting sleep apnea during sleep based on a deep learning and audio snore detection technology. The detection method comprises a series of steps of audio acquisition, feature processing, snore judgment, volume decibel detection, apnea detection and the like, so that the detection of sleep apnea events of a detected user is realized, and whether the user has sleep apnea symptoms or not is judged. The whole set of algorithm and flow described by the invention can be applied to mobile equipment such as mobile phones and part of embedded equipment, and the limitations of contact equipment required by the traditional sleep apnea detection method are eliminated, meanwhile, the accuracy of detection is ensured, and users with sleep apnea symptoms can find and treat early.
Description
Technical Field
The invention relates to the field of voice recognition, in particular to a method for detecting sleep apnea based on mobile equipment.
Background
Snoring is a relatively common disease in the world currently, and serious people can cause sleep apnea syndrome, thus endangering life safety.
Sleep apnea syndrome is a symptom of suspended breathing or hypopnea occurring during sleep, the duration of suspension varies from seconds to minutes, and the suspension occurs many times in one night, and meanwhile, because the symptom seriously damages normal sleep, daytime sleepiness and fatigue can be caused, if not timely treated, a series of other serious diseases such as diabetes, heart failure and the like can be caused.
Currently, the gold standard for clinically detecting sleep apnea is to use a multi-guide instrument for comprehensive detection of brain electricity, electrocardio, myoelectricity and the like, but the multi-guide instrument is expensive, hundreds of thousands of times, and the common family is difficult to bear the detection cost. Therefore, the multi-guide instrument generally has a passive effect when a user perceives the problem or sleep apnea symptoms reach an obvious ground, and is difficult to detect the active prevention effect in advance when the user checks the multi-guide instrument. In addition, the detection mode of the multi-guide instrument needs to be used for attaching a plurality of electrodes to a patient, and meanwhile, the head cover is also needed to be taken, so that the sleeping of the user can be influenced to a certain extent, and the detection is influenced. In this context, the proposed algorithm aims at realizing a low-cost and non-contact detection mode, and can achieve the effect of early discovery and early warning on potential sleep apnea users.
Disclosure of Invention
The invention provides a method for detecting sleep apnea based on mobile equipment.
The application provides a method for detecting sleep apnea based on mobile equipment, which comprises the following steps:
dividing the acquired audio into audio slices with finer granularity in a detection time period;
Using a snore detection algorithm based on a convolutional neural network to judge whether each audio slice contains snore or not and calculating the volume of a time node in each audio slice;
Storing snore judging results of all the audio slices in the detection time period and volume data of time nodes of each audio slice as logs;
Analyzing the log, if an audio slice comprising snore data exists, analyzing the audio slice and a subsequent audio slice, and judging whether a sleep apnea event exists according to the duration between the snore ending time and the time node of the next volume mutation and the difference between the volume of the snore and the volume of the time node of the volume mutation;
Further, based on the method for detecting sleep apnea by the mobile device, judging whether a sleep apnea event exists according to the duration between the snore ending time and the time node of the next volume mutation and the difference between the volume of the snore and the volume of the time node of the volume mutation:
If the time difference between the abrupt change time and the snore ending time is smaller than a preset time threshold, and the difference between the average volume in the snore duration time period and the volume of the abrupt change time is smaller than a preset volume difference threshold, recording a sleep apnea event;
Further, the method for detecting sleep apnea based on the mobile device comprises the steps of firstly detecting the snoring condition of a user in the whole night by using a snoring detection algorithm based on deep learning. The specific method comprises the following steps:
The sensor collects sound signals and slices the signals;
Judging whether sound exists in the audio slice by using a silence monitoring algorithm;
Extracting features of Mel Frequency Cepstrum Coefficient (MFCC) of the audio slices judged to contain sound, then carrying out depth feature extraction and classification by using a pre-trained deep learning model to judge whether each audio slice contains snore, and storing the judgment result into a log file or a data structure set in advance;
further, a method for detecting sleep apnea based on a mobile device, the calculation of audio volume, includes performing decibel calculation on all audio slices, whether the audio slices are mute, snore, non-snore;
Further, the sleep apnea detection algorithm firstly judges whether snoring behaviors exist in the night according to the report, and if the snoring behaviors do not exist, sleep apnea detection is not needed;
Further, after the snoring behavior of the user is determined, the sleep apnea detection algorithm uses the above-mentioned overnight snoring sound and the corresponding audio decibel log to detect the starting time and duration of the sleep apnea;
Further, after traversing the whole night sleep snore and audio decibel log, the sleep apnea detection algorithm obtains a whole night sleep apnea detection report, wherein the report comprises the starting time and the duration of each sleep apnea.
The application uses a step-by-step sleep apnea detection algorithm, which is different from the sleep apnea detection algorithm matched with the previous snore template. The sleep apnea is divided into two steps of snore detection and sleep apnea detection based on a snore detection result, so that the detection accuracy is higher. Meanwhile, the algorithm is non-contact and can be used at a mobile device such as a mobile phone end, the mobile device is required to comprise an audio acquisition module and a deep learning support module, and the mobile device can be detected only by being placed on a pillow side or a bedside table during sleeping.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:
Fig. 1 is a flow diagram of a method for detecting sleep apnea based on a mobile device according to a first embodiment of the present application;
FIG. 2 is a partial flow schematic diagram of a method for snore detection according to a first embodiment of the present application;
fig. 3 is a flow diagram of a method portion for sleep apnea detection by reporting detection of snoring detection reports according to a first embodiment of the present application.
Detailed Description
The following description of the preferred embodiments of the present invention refers to the accompanying drawings, which make the technical contents thereof more clear and easy to understand. The present invention may be embodied in many different forms of embodiments and the scope of the present invention is not limited to only the embodiments described herein.
A specific implementation of the first embodiment of the present application will be described in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for detecting sleep apnea based on a mobile device is presented, as shown, comprising the following steps.
And step S101, in which, after the user starts the detection software before sleeping, the audio signal during sleeping of the user is collected and stored, wherein the audio sampling frequency is 16KHz, and the audio collected during sleeping time is continuously segmented into audio slices with finer granularity.
And judging the audio type, namely, step S102, wherein a deep learning algorithm is used in the step, whether snore is contained in each audio slice or not is judged by a snore detection algorithm based on a convolutional neural network, and the volume of a time node in each audio slice is calculated. The calculated volume value may also be compared to a pre-stored volume threshold in this step to determine the type of audio slice. The types of audio slices include mute, non-snore, snore. And after the judgment is completed, the data are saved as a log.
And a step of storing detection information, namely, a step S103, in which the detection and calculation results in S102 are summarized and stored in a log. The stored information includes: time stamp of audio slice, snore classification, audio decibel. After the user wakes up, the detection software is turned off, the audio recording is stopped, and a snore detection report is generated.
Step S105, after analyzing the whole night snore report, obtaining a whole night sleep apnea detection result, and judging whether the user has sleep apnea phenomenon and severity according to the result. Fig. 2 shows a basic flow of determining the audio type, and referring to fig. 2, the flow includes:
An audio slice input step, i.e. step S201, in which the collected audio signal is sliced according to a duration of 6 seconds, in this embodiment, the continuous audio signal is cut into audio segments with a duration of 6 seconds, and overlapping of 3 seconds exists between two adjacent audio segments to avoid omission of snore.
A step of determining whether the audio decibel exceeds the threshold, step S202, in which it is determined whether the 6 second audio slice in S201 contains sound. And (3) calculating the maximum energy value, the minimum energy value and the standard deviation of the energy value of the sampling value in the audio slice, comparing the three values with a preset mute threshold, if the mute condition is met, considering that the current audio slice does not contain sound, and then, the audio slice does not carry out the subsequent snore monitoring steps S203, S204 and S205, and judging that the audio slice is snore-free and storing the judging result into a log file or a fixed data structure.
A MFCC feature extraction step, namely step S203, in which MFCC feature extraction is performed on the audio slice with snoring, specifically comprising the steps of: the audio digital signal is first normalized, i.e. divided by the audio energy peak to limit the signal to between plus and minus 1. Then, the audio signal is framed according to the voice recognition mode, in this embodiment, each frame is 25ms, the frame is shifted by 10ms, the 64-dimension MFCC feature is extracted for each frame, finally, the audio segment is processed into a 96×64×6 spectral image structure, and then the spectral image structure is input into a convolutional neural network for self-learning depth feature extraction.
The convolutional neural network feature extraction step, i.e. step S204, in which the convolutional neural network is a neural network structure that dominates the computer vision image processing field, and is well suited for extracting some abstract depth features in the image-like data. The extracted 96 x 64 x 6 spectral features are input into a convolutional neural network, and the convolutional neural network transforms the spectral features into 128-dimensional high-dimensional deep learning abstract features.
The full-connection layer classification step, i.e., step S205, in which 128-dimensional high-dimensional deep learning abstract features are input into the full-connection layer for classification.
A judgment result step, namely step S206, in which the classification result of the current 6 second audio piece is obtained: and storing the judging result into a log file or a fixed data structure if snoring occurs. The main information stored in the log file (or the fixed data structure) includes a timestamp of the current audio segment, a snore judging result of the current audio segment, and an average decibel of the current audio segment.
In order to acquire more accurate sleep apnea starting time and duration later, the audio segment with the duration of 6 seconds is segmented into finer granularity, the segmentation length is 1 second, namely, the audio segment with the duration of 6 seconds is segmented into 6 small segments, audio decibels are calculated respectively, and 3 seconds of overlapping exists between the adjacent audio segments with 6 seconds, so that each audio segment with 6 seconds only needs to calculate the decibels of the last three audio segments with 1 second.
Similarly, in step S103, a snore detection report is generated for storing detection information, namely, the time stamps corresponding to all audio segments throughout the night, the snore judgment result classification, 6 seconds of audio decibels, and 31 second of audio decibels with finer granularity. In addition, information such as the number of times of snoring, duration, average snoring decibels and the like in the whole night is counted and is used for subsequent sleep apnea detection.
The step S104 of analyzing the log, traversing the log to detect sleep apnea, referring to fig. 3, includes the following basic procedures:
and a snore detection report input step, namely step S301, in which when the user clicks to close the detection program to end the whole night sleep, a whole night snore detection report is generated in the above step, and then the program automatically starts the sleep apnea detection program, and the generated snore report is used as input.
A threshold judging step, namely step S302, of judging whether the snoring behavior exceeds a threshold, wherein the detection of sleep apnea will be performed, firstly judging whether the user is potential sleep apnea (the sleep apnea patient is accompanied by serious snoring behavior and snoring sounds are loud) according to the whole night snoring proportion and average snoring sound decibel information in a snoring sound log, in the embodiment, using 10% of the snoring sound and 50dB of the average snoring sound as the threshold, namely that the user is in snoring for 10% of the whole night sleeping time, and the average of the whole night snoring sound decibel exceeds 50dB, and considering that the user may have potential sleep apnea symptoms and needs further detection. Otherwise, the user is considered to have no sleep apnea symptom, and the log is not required to be traversed for detection, and step S305 is executed.
When the user may have sleep apnea phenomenon, the user starts to find the starting time of the snore, and in this step, the step of finding the starting time of the snore according to the time sequence is executed, that is, step S303 is executed, firstly, the starting time of the snore is found, and the ending time of the snore is found downwards along the log and recorded as t1, when the snore is found to end, it is required to determine whether the end of the snore is caused by sleep apnea. Firstly, calculating the average decibel of the snore from the starting time of the snore to the ending time of the current snore, then starting a time stamp, judging whether the difference between the audio decibel from the stopping time of the snore and the average decibel of the snore exceeds a threshold value or not, namely, the sleeping volume of the period of time from the ending of the snore is smaller than the sleeping volume of the snore by a certain value, for example, the threshold value is 10dB, when the average decibel of the snore from the starting time of the snore to the ending time of the snore is calculated to be 55dB, if the audio decibel after the ending of the snore is smaller than 45dB, the sleep apnea is considered to be possibly caused, otherwise, the sleep apnea is not caused. If the threshold is exceeded, the comparison is continued, and step S303 is performed until, when the threshold of the audio dB is greater than 45dB, the time t2 is recorded, when the difference between the times t2 and t1 satisfies the basic time requirement of sleep apnea (in this embodiment, the duration of sleep apnea is set to 10 seconds to one minute), if the difference between the times t2 and t1 is not within this range, it is considered not sleep apnea, otherwise it is considered as apnea, and the difference between the times is also considered as the duration of this sleep apnea.
Subsequently, a sleep apnea judging step, namely step S304, is entered, in which sleep apnea is judged, and finer granularity is cut: the sleep apnea detection is more accurate, the snore detection is carried out, the audio frequency section of 6 seconds is divided into audio frequency sections with the duration of 1 second, decibels are calculated and stored in a log file, the used audio frequency decibels are also 1 second in duration, the user looks up backwards from the snore stopping moment, if two or more of three continuous audio frequency decibels of 1 second meet the audio frequency decibel difference threshold, the user considers that the user can possibly sleep apnea, the user records the moment t1, similarly, when the user continuously looks up the moment t2 backwards, the user needs to record the time t2 after two or more audio frequency sections out of three continuous decibels of 1 second exceed the threshold, and then the duration, namely the difference between t2 and t1 is calculated as the sleep apnea duration. If the analysis of sleep apnea is still performed using audio segments of 6 seconds, the errors in start time and duration will also be at 6 seconds, which is relatively large for sleep apnea detection of only 10 seconds in the shortest time.
The starting time and the duration of one sleep apnea, after analyzing the snore report, the information related to the sleep apnea of the whole night is obtained, wherein the information comprises the number of times of the sleep apnea, the starting time and the duration of each time. And judging the severity of sleep apnea of the user according to the information, and judging whether medical treatment is needed.
And finally, generating a sleep apnea detection log, namely, step S305, wherein the result of the step S304 is displayed in detection software.
The method is realized in a computer program mode by using the mobile phone app, and a user can realize complete non-contact night snore detection and sleep apnea detection by only starting the app at the bedside when sleeping.
Finally, it should be noted that: the above embodiments are merely illustrative of the present invention, and any modifications and improvements which do not take the inventive effort of a person skilled in the art without departing from the core of the present invention fall within the scope of the present invention.
Claims (6)
1. A method for detecting sleep apnea based on a mobile device, comprising the steps of:
Dividing the audio acquired in the detection time period into audio slices with finer granularity;
judging whether each audio slice contains snore or not by using a snore detection algorithm based on a convolutional neural network and calculating the volume of a time node in each audio slice;
storing snore judging results of all the audio slices in the detection time period and volume data of time nodes of each audio slice as logs;
Analyzing the log, if an audio slice comprising snore data exists, analyzing the audio slice and a subsequent audio slice, and judging whether a sleep apnea event exists according to the duration between the snore ending time and the time node of the next volume mutation and the difference between the volume of the snore and the volume of the time node of the volume mutation;
judging whether a sleep apnea event exists according to the duration between the snore ending time and the time node of the next volume mutation and the difference between the volume of the snore and the volume of the time node of the volume mutation:
and if the time difference between the abrupt change time and the snore ending time is smaller than a preset time threshold, and the difference between the average volume in the duration time period of the snore and the volume of the abrupt change time is smaller than a preset volume difference threshold, recording a sleep apnea event.
2. A method of detecting sleep apnea based on a mobile device according to claim 1, wherein: firstly, detecting the snoring condition of a user in the whole night by using a snoring detection algorithm based on deep learning; the specific method comprises the following steps:
The sensor collects sound signals and slices the signals;
Judging whether sound exists in the audio slice by using a silence monitoring algorithm;
And carrying out Mel Frequency Cepstrum Coefficient (MFCC) feature extraction on the audio slices judged to contain sound, then carrying out depth feature extraction and classification by using a pre-trained deep learning model to judge whether each audio slice contains snore, and storing the judgment result into a log file or a data structure set in advance.
3. A method of detecting sleep apnea based on a mobile device according to claim 1, wherein: the calculation of the audio volume includes a decibel calculation for all audio slices, whether the audio slices are mute, snore, non-snore.
4. A sleep apnea detection algorithm as claimed in claim 3, wherein: firstly, judging whether the user has snoring behaviors at night according to the report, and if the user does not have the snoring behaviors, not needing to detect sleep apnea.
5. The sleep apnea detection algorithm of claim 4, wherein: after determining that the user has snoring, the detection of the start and duration of sleep apnea is performed using the overnight snoring and the corresponding audio decibel log.
6. The sleep apnea detection algorithm of claim 5, wherein: after traversing the whole night sleep snore and audio decibel logs, obtaining a whole night sleep apnea detection report, wherein the report comprises the starting time and the duration of each sleep apnea.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111217096.3A CN113925464B (en) | 2021-10-19 | 2021-10-19 | Method for detecting sleep apnea based on mobile equipment |
| PCT/CN2022/125138 WO2023066135A1 (en) | 2021-10-19 | 2022-10-13 | Sleep apnea detection method based on mobile device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111217096.3A CN113925464B (en) | 2021-10-19 | 2021-10-19 | Method for detecting sleep apnea based on mobile equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113925464A CN113925464A (en) | 2022-01-14 |
| CN113925464B true CN113925464B (en) | 2024-06-04 |
Family
ID=79280636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111217096.3A Active CN113925464B (en) | 2021-10-19 | 2021-10-19 | Method for detecting sleep apnea based on mobile equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113925464B (en) |
| WO (1) | WO2023066135A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113571091B (en) * | 2021-06-30 | 2024-04-19 | 青岛海尔科技有限公司 | Audio mutation detection method and device for monitoring and household appliance |
| CN113599052B (en) * | 2021-07-15 | 2024-09-03 | 麒盛科技股份有限公司 | Snore monitoring method and system based on deep learning algorithm and corresponding electric bed control method and system |
| CN113925464B (en) * | 2021-10-19 | 2024-06-04 | 麒盛科技股份有限公司 | Method for detecting sleep apnea based on mobile equipment |
| CN114916912B (en) * | 2022-05-09 | 2024-06-21 | 大连理工大学 | Non-contact sleep apnea detection method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1410759A1 (en) * | 2002-10-17 | 2004-04-21 | Sibel, S.A. | Procedure for analysis of snoring and apnea and apparatus to carry out this analysis |
| JP2016047156A (en) * | 2014-08-27 | 2016-04-07 | 株式会社ミツバ | Snoring stability evaluation device |
| KR20180096176A (en) * | 2017-02-20 | 2018-08-29 | 가천대학교 산학협력단 | Apparatus for analyzing sleeping state and method of analyzing for sleeping state |
| CN109044279A (en) * | 2018-08-20 | 2018-12-21 | 深圳和而泰数据资源与云技术有限公司 | A kind of sound of snoring detection method and relevant device |
| CN113040714A (en) * | 2021-03-09 | 2021-06-29 | 深圳市科瑞康实业有限公司 | Apnea monitoring and percutaneous electrical stimulation method and device |
| CN113397492A (en) * | 2021-08-20 | 2021-09-17 | 广东德泷智能科技有限公司 | Intelligent voice recognition wrist type sleep apnea monitoring system |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100418468C (en) * | 2006-01-20 | 2008-09-17 | 浙江工业大学 | Constrain-free, imperceptible sleep disorder measuring device and its method |
| WO2010066008A1 (en) * | 2008-12-10 | 2010-06-17 | The University Of Queensland | Multi-parametric analysis of snore sounds for the community screening of sleep apnea with non-gaussianity index |
| US20130144190A1 (en) * | 2010-05-28 | 2013-06-06 | Mayo Foundation For Medical Education And Research | Sleep apnea detection system |
| WO2012025892A2 (en) * | 2010-08-26 | 2012-03-01 | Ben Gurion University Of The Negev Research And Development Authority | Apparatus and method for diagnosing obstructive sleep apnea |
| CA2888394A1 (en) * | 2014-05-02 | 2015-11-02 | University Health Network | Method and system for sleep detection |
| CN106419865A (en) * | 2015-08-07 | 2017-02-22 | 上海宽带技术及应用工程研究中心 | Sleep apnea syndrome determining method based on vibration sensor |
| 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 |
| WO2021067860A1 (en) * | 2019-10-03 | 2021-04-08 | DawnLight Technologies Inc. | Systems and methods for contactless sleep monitoring |
| CN117357070A (en) * | 2019-10-11 | 2024-01-09 | 京东方科技集团股份有限公司 | Sleep monitoring method, device, equipment and storage medium |
| CN111613210A (en) * | 2020-07-06 | 2020-09-01 | 杭州电子科技大学 | Categorised detecting system of all kinds of apnea syndromes |
| CN113288065A (en) * | 2021-06-03 | 2021-08-24 | 北京好医生云医院管理技术有限公司 | Real-time apnea and hypopnea prediction method based on snore |
| CN113925464B (en) * | 2021-10-19 | 2024-06-04 | 麒盛科技股份有限公司 | Method for detecting sleep apnea based on mobile equipment |
-
2021
- 2021-10-19 CN CN202111217096.3A patent/CN113925464B/en active Active
-
2022
- 2022-10-13 WO PCT/CN2022/125138 patent/WO2023066135A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1410759A1 (en) * | 2002-10-17 | 2004-04-21 | Sibel, S.A. | Procedure for analysis of snoring and apnea and apparatus to carry out this analysis |
| JP2016047156A (en) * | 2014-08-27 | 2016-04-07 | 株式会社ミツバ | Snoring stability evaluation device |
| KR20180096176A (en) * | 2017-02-20 | 2018-08-29 | 가천대학교 산학협력단 | Apparatus for analyzing sleeping state and method of analyzing for sleeping state |
| CN109044279A (en) * | 2018-08-20 | 2018-12-21 | 深圳和而泰数据资源与云技术有限公司 | A kind of sound of snoring detection method and relevant device |
| CN113040714A (en) * | 2021-03-09 | 2021-06-29 | 深圳市科瑞康实业有限公司 | Apnea monitoring and percutaneous electrical stimulation method and device |
| CN113397492A (en) * | 2021-08-20 | 2021-09-17 | 广东德泷智能科技有限公司 | Intelligent voice recognition wrist type sleep apnea monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113925464A (en) | 2022-01-14 |
| WO2023066135A1 (en) | 2023-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113925464B (en) | Method for detecting sleep apnea based on mobile equipment | |
| CN108670200B (en) | Sleep snore classification detection method and system based on deep learning | |
| CN109431470B (en) | Sleep respiration monitoring method and device | |
| EP2593007B1 (en) | Feature characterization for breathing monitor | |
| US9357953B2 (en) | System and method for diagnosing sleep apnea | |
| US20150342519A1 (en) | System and method for diagnosing medical condition | |
| US20130331723A1 (en) | Respiration monitoring method and system | |
| KR102004219B1 (en) | A system of detecting sleep disturbance using a microvibration sensor and a sound sensor | |
| EP3954278A1 (en) | Apnea monitoring method and device | |
| CN110558946B (en) | Method for recording abnormal sleep state of user and sleep instrument | |
| CN111938650B (en) | Method and device for monitoring sleep apnea | |
| CN113599052B (en) | Snore monitoring method and system based on deep learning algorithm and corresponding electric bed control method and system | |
| CN109767784B (en) | Snore identification method and device, storage medium and processor | |
| WO2024188177A1 (en) | Snore detection method and apparatus based on multi-model superimposition | |
| CN113273992B (en) | Signal processing method and device | |
| CN116115198A (en) | Low-power consumption snore automatic recording method and device based on physiological sign | |
| CN110660411A (en) | Body-building safety prompting method, device, equipment and medium based on voice recognition | |
| CN113247730B (en) | Elevator passenger screaming detection method and system based on multi-dimensional features | |
| CN211827514U (en) | Fall alarm device and system | |
| US20180279962A1 (en) | Methods and apparatus for determining biological effects of environmental sounds | |
| CN112349418A (en) | Auditory function abnormity monitoring method, device, equipment and storage medium | |
| CN114287888A (en) | Method for detecting sleeping quality of multiple persons through sound collection | |
| EP3821793A1 (en) | A method for determining the risk of a user waking up in an undesirable state | |
| US11937938B1 (en) | Methods for assessing sleep conditions | |
| WO2023246545A1 (en) | Cough monitoring method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |