CN104905791A - Method and system for extracting respiration signals based on a clustering algorithm - Google Patents
Method and system for extracting respiration signals based on a clustering algorithm Download PDFInfo
- Publication number
- CN104905791A CN104905791A CN201410088719.5A CN201410088719A CN104905791A CN 104905791 A CN104905791 A CN 104905791A CN 201410088719 A CN201410088719 A CN 201410088719A CN 104905791 A CN104905791 A CN 104905791A
- Authority
- CN
- China
- Prior art keywords
- clustering
- clustering algorithm
- cluster
- breath signal
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention provides a method and a system for extracting respiration signals based on a clustering algorithm. The method comprises: firstly, performing frequency band division and dimension reduction processing for each in a plurality of obtained coherent signals to obtain a plurality of frequency band signals; then, clustering the plurality of frequency band signals based on the clustering algorithm to obtain a plurality of clustering clusters; therewith, performing characteristic analysis for each clustering cluster to obtain respiration signals. The respiration of a monitored person is monitored during sleep without any influence on the monitored person because the relevant information comes from signals collected by a mattress type life monitor, and thereby screening out sleep apnea syndrome patients.
Description
Technical field
The present invention relates to respiratory characteristic analysis field, particularly relate to a kind of method and system extracting breath signal based on clustering algorithm.
Background technology
Along with the raising of people's living standard, start to rise to the attention rate of health problem, especially sleep quality problem.Common unsound sleep quality comprises: repeatedly suppress awake in sleep snoring, mouth breathing, even appearance breathing temporarily stopping, sleep, insomnia, frequent generation Nocturnal angina patients and arrhythmia etc.
And sleep apnea syndrome is a kind of disease that sickness rate is higher in mid-aged population.Namely snoring snores, and is the main manifestations of this disease.The even rule of snore of the common person of snoring, generally in horizontal position sleep, tired or appearance after drinking.If snore is loud and irregular, off and on, sound is fluctuated, just indicates that airway constriction increases the weight of, and has airway obstruction to occur, and just can cause asphyxia.If asphyxia occurs more than 30 times in the night, or average generation per hour more than 5 times, patient will suppress awake repeatedly from sleep, is medically referred to as sleep apnea syndrome.Awake owing to repeatedly suppressing in patient sleeps, headache after causing wakeing up, blood pressure rising, Nocturnal angina patients, cardiac arrhythmia, sleep are not recovered from fatigue, daytime sleepiness, drowsiness, hypomnesis, bradykinesia, ability to work reduction etc.
At present, sleep apnea syndrome must be detected and can be made a definite diagnosis by polysomnogram, and sleep-respiratory detection whole night often needs in human body nasal cavity or head-mount pertinent instruments, some special instrument then needs to monitor in the environment that medical space is specified, and often can not reach the object of long term monitoring.
Such as, be in the Chinese patent literature of 201010120237.5 at application number, disclose the apneic device of a kind of monitoring sleep, this device is made up of respiration pickup, voltage signal amplifier, shaping circuit, time-discriminating circuit and pulse generator.Wherein, this respiration pickup needs the nasal cavity being placed on monitored personnel.
Again such as, be in the Chinese patent literature of 201110355375.6 at application number, disclose the screening system of sleep apnea syndrome in a kind of home environment.This screening system comprises sound of snoring data acquisition module, sound of snoring processing module and discrimination module.Wherein, this sound of snoring data acquisition module needs noncontact omnidirectional microphone worn and be placed in above the mouth and nose of monitored personnel.
Because existing monitoring mode all needs monitored personnel to wear relevant apparatus, monitoring is inconvenience very, therefore needs a kind of breath signal acquisition methods without the need to wearing to realize the accurate extraction of the breath signal to crowd in need.
Summary of the invention
The shortcoming of prior art in view of the above, the object of the present invention is to provide a kind of method and system extracting breath signal based on clustering algorithm, monitors with the breathing realized when sleeping to crowd in need.
For achieving the above object and other relevant objects, the invention provides a kind of method extracting breath signal based on clustering algorithm, it at least comprises:
Frequency range division and dimension-reduction treatment are carried out to obtain multiple frequency band signals to each in the multiple coherent signals obtained;
Based on clustering algorithm, cluster is carried out to obtain multiple clustering cluster to described multiple frequency band signals;
Feature analysis is carried out to obtain breath signal to each clustering cluster.
The present invention also provides a kind of extraction system extracting breath signal based on clustering algorithm, and it at least comprises:
Divide module, for carrying out frequency range division and dimension-reduction treatment to obtain multiple frequency band signals to each in the multiple coherent signals obtained;
Cluster module, for carrying out cluster to obtain multiple clustering cluster based on clustering algorithm to described multiple frequency band signals;
Analysis module, for carrying out feature analysis to obtain breath signal to each clustering cluster.
Preferably, described clustering algorithm comprises k-means algorithm.
Preferably, based on sorting algorithm, feature analysis is carried out to determine frequency range to be extracted to each clustering cluster.
Preferably, described coherent signal comprises the signal that mattress formula life monitoring instrument gathers.
As mentioned above, the method and system extracting breath signal based on clustering algorithm of the present invention, there is following beneficial effect: can under the prerequisite that monitored personnel are had no effect, the breathing realized when sleeping to monitored personnel is monitored, thus examination goes out patients with sleep apnea.
Accompanying drawing explanation
Fig. 1 is shown as the flow chart extracting the method for breath signal based on clustering algorithm of the present invention.
Fig. 2 is shown as the extraction system schematic diagram extracting breath signal based on clustering algorithm of the present invention.
Element numbers explanation
1 extraction system
11 divide module
12 cluster module
13 analysis modules
S1 ~ S3 step
Detailed description of the invention
Below by way of specific instantiation, embodiments of the present invention are described, those skilled in the art the content disclosed by this description can understand other advantages of the present invention and effect easily.The present invention can also be implemented or be applied by detailed description of the invention different in addition, and the every details in this description also can based on different viewpoints and application, carries out various modification or change not deviating under spirit of the present invention.
Refer to Fig. 1 to Fig. 2.It should be noted that, the diagram provided in the present embodiment only illustrates basic conception of the present invention in a schematic way, then only the assembly relevant with the present invention is shown in graphic but not component count, shape and size when implementing according to reality is drawn, it is actual when implementing, and the kenel of each assembly, quantity and ratio can be a kind of change arbitrarily, and its assembly layout kenel also may be more complicated.
As shown in Figure 1, the invention provides a kind of method extracting breath signal based on clustering algorithm.Wherein, method according to the present invention has been come mainly through extraction system, and this extraction system to include but not limited to be arranged in computer equipment and can realize the such as application module of the present invention program.
In step sl, described extraction system carries out frequency range division and dimension-reduction treatment to obtain multiple frequency band signals to each in the multiple coherent signals obtained.
Wherein, described relevant information is the information relevant to breath signal, preferably, includes but not limited to: the signal etc. gathered by mattress formula life monitoring instrument.
Particularly, described extraction system, in advance by analyzing the frequency spectrum of known breath signal, obtains the frequency range at breath signal place; Subsequently each coherent signal is divided into three frequency ranges, then based on the frequency range at breath signal place, each frequency range not comprising breath signal is removed.
Then, in step s 2, described extraction system carries out cluster to obtain multiple clustering cluster based on clustering algorithm to described multiple frequency band signals.
Preferably, described extraction system adopts k-means algorithm to carry out cluster operation.
Wherein, k-means algorithm accepts input quantity k; Then n data object is divided into k cluster to make obtained cluster meet: the object similarity in same clustering cluster is higher; And object similarity in different clustering cluster is less.Cluster similarity be utilize the average of object in each clustering cluster obtain " center object " (center of attraction) and carry out calculating.
The work process of k-means algorithm is as follows:
First select arbitrarily k object as initial cluster center from n data object; And for other object remaining, then according to the similarity (distance) of they and these cluster centres, respectively they are distributed to the most similar to it (representated by cluster centre) clustering cluster;
And then calculate the cluster centre average of all objects (in this cluster) of each obtained new cluster; Constantly repeat this process until canonical measure function starts convergence.
Generally all adopt mean square deviation as canonical measure function, k clustering cluster has following characteristics: each clustering cluster itself is compact as much as possible, and separates as much as possible between each clustering cluster.
K-means algorithm application is extensive, fast convergence rate, and energy expanded application is in large-scale data set.
Then, in step s3, described extraction system carries out feature analysis to obtain breath signal to each clustering cluster.
Wherein, described extraction system can carry out feature analysis to determine frequency range to be extracted based on sorting algorithm to each clustering cluster; Wherein, sorting algorithm preferably adopts the algorithm of support vector machine theory.
Particularly, described extraction system first utilizes known respiratory wave to train, and then each the clustering cluster data separate support vector machine after K-means algorithm is calculated, constantly improves accuracy, obtain breath signal thus
As shown in Figure 2, the invention provides a kind of extraction system extracting breath signal based on clustering algorithm.This extraction system 1 at least comprises: divide module 11, cluster module 12 and analysis module 13.
Described division module 11 carries out frequency range division and dimension-reduction treatment to obtain multiple frequency band signals to each in the multiple coherent signals obtained.
Wherein, described relevant information is the information relevant to breath signal, preferably, includes but not limited to: the signal etc. gathered by mattress formula life monitoring instrument.
Particularly, described division module 11, in advance by analyzing the frequency spectrum of known breath signal, obtains the frequency range at breath signal place; Subsequently each coherent signal is divided into three frequency ranges, then based on the frequency range at breath signal place, each frequency range not comprising breath signal is removed.
Then, described cluster module 12 carries out cluster to obtain multiple clustering cluster based on clustering algorithm to each frequency band signals.
Preferably, described extraction system adopts k-means algorithm to carry out cluster operation.
Wherein, k-means algorithm describes in detail in the embodiment shown in fig. 1, and is contained in this by reference, no longer repeats.
Then, described analysis module 13 carries out feature analysis to obtain breath signal to described multiple clustering cluster.
Wherein, described analysis module 13 can carry out feature analysis to determine frequency range to be extracted based on sorting algorithm to each clustering cluster; Wherein, sorting algorithm preferably adopts the algorithm of support vector machine theory.
Particularly, described analysis module 13 first utilizes known respiratory wave to train, and then each the clustering cluster data separate support vector machine after K-means algorithm is calculated, constantly improves accuracy, obtain breath signal thus.
In sum, of the present invention based on clustering algorithm extract breath signal method and system adopt clustering algorithm cluster is carried out to the relevant information that mattress formula life monitoring instrument gathers after analyze again, can realize thus extracting accurately the carrying out of monitored personnel's respiratory waveform, and then the examination to sleep apnea syndrome can be realized; Due to employing is the information that mattress formula life monitoring instrument provides, therefore has no effect to monitored personnel, effectively can realize long term monitoring.So the present invention effectively overcomes various shortcoming of the prior art and tool high industrial utilization.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not for limiting the present invention.Any person skilled in the art scholar all without prejudice under spirit of the present invention and category, can modify above-described embodiment or changes.Therefore, such as have in art usually know the knowledgeable do not depart from complete under disclosed spirit and technological thought all equivalence modify or change, must be contained by claim of the present invention.
Claims (8)
1. extract a method for breath signal based on clustering algorithm, it is characterized in that, the described method extracting breath signal based on clustering algorithm at least comprises:
Frequency range division and dimension-reduction treatment are carried out to obtain multiple frequency band signals to each in the multiple coherent signals obtained;
Based on clustering algorithm, cluster is carried out to obtain multiple clustering cluster to described multiple frequency band signals;
Feature analysis is carried out to obtain breath signal to each clustering cluster.
2. the method extracting breath signal based on clustering algorithm according to claim 1, is characterized in that: described clustering algorithm comprises k-means algorithm.
3. the method extracting breath signal based on clustering algorithm according to claim 1, is characterized in that: carry out feature analysis to determine frequency range to be extracted based on sorting algorithm to each clustering cluster.
4. the method extracting breath signal based on clustering algorithm according to claim 1, is characterized in that: described coherent signal comprises the signal that mattress formula life monitoring instrument gathers.
5. extract an extraction system for breath signal based on clustering algorithm, it is characterized in that, the described extraction system extracting breath signal based on clustering algorithm at least comprises:
Divide module, for carrying out frequency range division and dimension-reduction treatment to obtain multiple frequency band signals to each in the multiple coherent signals obtained;
Cluster module, for carrying out cluster to obtain multiple clustering cluster based on clustering algorithm to described multiple frequency band signals;
Analysis module, for carrying out feature analysis to obtain breath signal to each clustering cluster.
6. the extraction system extracting breath signal based on clustering algorithm according to claim 5, is characterized in that: described clustering algorithm comprises k-means algorithm.
7. the extraction system extracting breath signal based on clustering algorithm according to claim 5, is characterized in that: described analysis module carries out feature analysis to determine frequency range to be extracted based on sorting algorithm to each clustering cluster.
8. the extraction system extracting breath signal based on clustering algorithm according to claim 5, is characterized in that: described coherent signal comprises the signal that mattress formula life monitoring instrument gathers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410088719.5A CN104905791B (en) | 2014-03-11 | 2014-03-11 | The method and system of breath signal are extracted based on clustering algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410088719.5A CN104905791B (en) | 2014-03-11 | 2014-03-11 | The method and system of breath signal are extracted based on clustering algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104905791A true CN104905791A (en) | 2015-09-16 |
| CN104905791B CN104905791B (en) | 2017-07-28 |
Family
ID=54075551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410088719.5A Active CN104905791B (en) | 2014-03-11 | 2014-03-11 | The method and system of breath signal are extracted based on clustering algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104905791B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919775A (en) * | 2015-12-24 | 2017-07-04 | 中国移动通信集团公司 | A kind of processing method and processing device of sleep info |
| CN110113998A (en) * | 2016-12-28 | 2019-08-09 | 皇家飞利浦有限公司 | The method for characterizing sleep disordered breathing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003057025A2 (en) * | 2002-01-07 | 2003-07-17 | Widemed Ltd. | Self-adaptive system for the analysis of biomedical signals of a patient |
| US7413549B1 (en) * | 2004-03-17 | 2008-08-19 | Pacesetter, Inc. | Detecting and quantifying apnea using ventilatory cycle histograms |
| 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 |
| CN102512158A (en) * | 2011-12-31 | 2012-06-27 | 济南汇医融工科技有限公司 | Electrocardiosignal quality evaluation method and device based on high-dimensional fuzzy recognition |
| CN103006223A (en) * | 2012-12-13 | 2013-04-03 | 中国人民解放军第四军医大学 | Household non-contact sleeping monitoring device and method |
-
2014
- 2014-03-11 CN CN201410088719.5A patent/CN104905791B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003057025A2 (en) * | 2002-01-07 | 2003-07-17 | Widemed Ltd. | Self-adaptive system for the analysis of biomedical signals of a patient |
| US7413549B1 (en) * | 2004-03-17 | 2008-08-19 | Pacesetter, Inc. | Detecting and quantifying apnea using ventilatory cycle histograms |
| CN102499637A (en) * | 2011-09-26 | 2012-06-20 | 大连理工大学 | Obstructive sleep apnea-hypopnea syndrome screening method and device thereof |
| CN102429662A (en) * | 2011-11-10 | 2012-05-02 | 大连理工大学 | Screening system for sleep apnea syndrome in family environment |
| CN102512158A (en) * | 2011-12-31 | 2012-06-27 | 济南汇医融工科技有限公司 | Electrocardiosignal quality evaluation method and device based on high-dimensional fuzzy recognition |
| CN103006223A (en) * | 2012-12-13 | 2013-04-03 | 中国人民解放军第四军医大学 | Household non-contact sleeping monitoring device and method |
Non-Patent Citations (1)
| Title |
|---|
| MEGAN HOWELL JONES等: "Reliable Respiratory Rate Estimation from a Bed Pressure Array", 《PROCEEDINGS OF THE 28TH IEEE》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919775A (en) * | 2015-12-24 | 2017-07-04 | 中国移动通信集团公司 | A kind of processing method and processing device of sleep info |
| CN106919775B (en) * | 2015-12-24 | 2019-11-01 | 中国移动通信集团公司 | A kind of processing method and processing device of sleep info |
| CN110113998A (en) * | 2016-12-28 | 2019-08-09 | 皇家飞利浦有限公司 | The method for characterizing sleep disordered breathing |
| CN110113998B (en) * | 2016-12-28 | 2022-05-13 | 皇家飞利浦有限公司 | Method for characterizing sleep disordered breathing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104905791B (en) | 2017-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6594399B2 (en) | Biological information monitoring system | |
| JP5155856B2 (en) | Clinical symptom prediction and monitoring technology | |
| JP5961235B2 (en) | Sleep / wake state evaluation method and system | |
| CN108388912A (en) | Sleep stage method based on multisensor feature optimization algorithm | |
| US11540769B2 (en) | System and method for tracking sleep dynamics using behavioral and physiological information | |
| US20140180036A1 (en) | Device and method for predicting and preventing obstructive sleep apnea (osa) episodes | |
| US11534104B2 (en) | Systems and methods for contraction monitoring and labor detection | |
| CN105792733A (en) | Sleep monitoring device | |
| KR102100120B1 (en) | Method, apparatus and computer program for monitoring of bio signals | |
| WO2014066666A2 (en) | Systems and methods for detecting brain-based bio-signals | |
| US20140128753A1 (en) | Piezoelectric heart rate sensing for wearable devices or mobile devices | |
| CN104545818A (en) | Sleep apnea syndrome detection method based on pulse and blood oxygen signals | |
| US8708920B2 (en) | Method and system for detecting apnea | |
| Movahedi et al. | A comparison between swallowing sounds and vibrations in patients with dysphagia | |
| JP2008068019A (en) | Method and apparatus for outputting exhalation time | |
| CN110477887A (en) | A kind of monitoring device of non-invasive long-range apnea syndrome | |
| Le et al. | Prediction of sleep apnea episodes from a wireless wearable multisensor suite | |
| US11291406B2 (en) | System for determining a set of at least one cardio-respiratory descriptor of an individual during sleep | |
| CN104905791A (en) | Method and system for extracting respiration signals based on a clustering algorithm | |
| EP3918997A3 (en) | Methods, systems, and devices for detecting apnea events and sleep | |
| Patil et al. | Understanding smoking behavior using wearable sensors: Relative importance of various sensor modalities | |
| EP3970127A1 (en) | Non-contact identification of sleep and wake periods for elderly care | |
| CN209347880U (en) | A kind of sleeping and anti-apnea device | |
| CN104274181A (en) | Furniture type physical sign detection method, system and monitoring system | |
| Sampson et al. | A Polymer Sensor Integrated T-Shirt for Long-Term Monitoring Of Sleep Disordered Breathing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |