CN106037671A - Method and system for apnea event detection based on BCG signal - Google Patents

Method and system for apnea event detection based on BCG signal Download PDF

Info

Publication number
CN106037671A
CN106037671A CN201610541244.XA CN201610541244A CN106037671A CN 106037671 A CN106037671 A CN 106037671A CN 201610541244 A CN201610541244 A CN 201610541244A CN 106037671 A CN106037671 A CN 106037671A
Authority
CN
China
Prior art keywords
section
apnea
awakening
bcg signal
signal
Prior art date
Application number
CN201610541244.XA
Other languages
Chinese (zh)
Inventor
周兴社
刘帆
王柱
倪红波
於志文
Original Assignee
西北工业大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 西北工业大学 filed Critical 西北工业大学
Priority to CN201610541244.XA priority Critical patent/CN106037671A/en
Publication of CN106037671A publication Critical patent/CN106037671A/en

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Detecting, measuring or recording for diagnostic purposes; Identification of persons
    • A61B5/22Ergometry; Measuring muscular strength or the force of a muscular blow
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Detecting, measuring or recording for diagnostic purposes; Identification of persons
    • A61B5/48Other medical applications
    • A61B5/4806Sleep evaluation
    • A61B5/4818Sleep apnoea
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Detecting, measuring or recording for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Detecting, measuring or recording for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/7253Details of waveform analysis characterised by using transforms
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Detecting, measuring or recording for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/7264Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems

Abstract

The present invention discloses a method and a system for apnea event detection based on a BCG signal for accurately detecting an apnea event during sleep. In the method, the potential event duration is located by recognizing an arousal phase, and then the potential event duration is divided into a sleep apnea phase, a respiratory effort phase and the arousal phase. Then, fine granular features which can describe a breathing pattern are respectively extracted from the three phases, and finally, with the help of a machine learning method, whether the potential event duration contains the apnea event is judged. The system mainly comprises a signal acquisition module, a data processing module and a detection result output module. The method and the system are capable of automatically and accurately locating the potential duration of the apnea event and automatically dividing the duration into three different phases so as to facilitate the fine granular characterization of the breathing pattern from multiple aspects and greatly improve the detection accuracy rate of the apnea event.

Description

A kind of apnea detection method based on BCG signal and system

Technical field

The present invention relates to biomedical sector, in particular it relates to a kind of apnea detection method and system.

Background technology

In recent years, sleep disorder has become the key factor affecting people's quality of life.Wherein, sleep apnea is comprehensive Disease has become modal sleep disorder.Showing according to the relevant data of World Health Organization (WHO), the whole world about 200,000,000 population suffers from sleep and exhales Inhale and suspend syndrome, account for the 2%-4% of total world population.Sleep apnea syndrome sickness rate high, harm is serious Can be rated as first of all kinds of sleep disorder, the detection to apnea has become the problem needing primary study.

Existing apnea detection method is broadly divided into two big classes: 1) based on PSG, pectoral girdle, blood oxygen saturation fete, gas The apnea detection of stream detection meter etc.;2) apnea based on heart rate variability detection.The former is when detection Need the some instruments of subject wears or electrode, affect comfortableness when experimenter sleeps.The latter such as generally uses at point data segment Data are divided into the section that some length is equal by strategy, this strategy ignore apnea it may happen that at any time and The fact that persistent period is not fixed, have impact on the accuracy of event detection.

Additionally, above-mentioned two class apnea detection methods all using between the potential establishment of apnea as one Individual entirety, does not consider the internal structure of apnea, and extracted feature cannot portray asphyxia to fine granularity Event, and then reduce the accuracy of event detection.

For the problems referred to above, effective solution is the most not yet proposed.

Summary of the invention

The present invention provides a kind of apnea detection method based on BCG signal, by being automatically positioned asphyxia The generation that event is possible is interval, is asphyxia section, respiratory effort section, awakening section by this interal separation;Described one based on The apnea detection method of BCG signal comprises the following steps:

S1: BCG signal is normalized;

The awakening section of S2: Primary Location apnea;

S3: merge the awakening section obtained in S2, screening etc. processes, obtains the accurately section of awakening;

S4: the segment trailer that is divided further into the BCG signal between accurately awakening section adjacent in S3 awakening, asphyxia section, Respiratory effort section;

S5: the stage each to gained in S4 carries out selectivity correcting process, the generation being finally accurately positioned apnea is interval, It is divided into asphyxia section, respiratory effort section, awakening section.

S6: extract from above-mentioned three sections respectively and fine granularity can portray the feature of breathing pattern;

Whether S7: fine granularity breathing pattern feature based on said extracted, by machine learning method, detect in this interval and comprise There is apnea.

Further, a kind of apnea detection method S2 based on BCG signal uses Z-score method pair BCG signal is normalized, and formula is:

Wherein, μ is the meansigma methods of BCG signal sequence, and σ is the standard deviation of signal sequence, XiIt it is i-th in breast impulse signal Signal value, Xnor_iIt is XiValue after normalized.

Further, Primary Location asphyxia thing in a kind of apnea detection method S3 based on BCG signal Part includes: first passes through wavelet analysis method and is decomposed by breast impact signal, and selection can either abate the noise interference again can be preferable Ground characterizes the STATIC CORRECTION USING APPROXIMATE LAYER of awakening section, then this STATIC CORRECTION USING APPROXIMATE LAYER signal is divided into isometric data segment, and by threshold method, tentatively Judge that whether each data segment is awakening section, and be marked;I-th section is designated as segi, and according to equation below, each section is entered Line flag:

Threshold=mean (std (segj))+A×std(std(segj))

Wherein, j=1,2 ..., N;N is the number of signal segment;A is weight factor.

Further, the merging treatment in a kind of apnea detection method S4 based on BCG signal refers to basis The related definition of sleep apnea event, to be unsatisfactory for event time length requirement adjacent awakening section and between data segment enter Row merges.

Further, the phase of sleep apnea event in a kind of apnea detection method based on BCG signal Close definition and refer to that apnea time of origin continues more than 10 seconds, according to equation below judge whether to need by some tentatively The awakening section of location merges:

endj-endi≤10seconds

Wherein endiWith endjIt it is the finish time of the awakening section of adjacent two Primary Location;

Further, the Screening Treatment in a kind of apnea detection method S4 based on BCG signal refers to close from each Awakening section after and extracts feature, train one grader, the section of respectively awakening of current gained is categorized as real awakening section or The false awakening section caused by noise in data, and then filter out real awakening section.

Further, screen according to equation below described in a kind of apnea detection method based on BCG signal Screen:

Wherein, condition C 1 is made up of equation below:

(Durationi≥18)∪[(Durationi> 6) ∩ (Durationi≥max{Durationj})]

Wherein, DurationiThe persistent period of the awakening section that expression i-th is potential, DurationjRepresent partially or completely the The awakening section that i is potential ± set of potential awakening section in the range of 20 seconds.

Further, the segmentation further in a kind of apnea detection method S5 based on BCG signal is: first-selected By sliding window method, the BCG signal between adjacent awakening section is processed, come by the sequence being made up of window maximum Characterize the profile information of this segment signal, then by adaptive threshold method, the profile of this segment signal finds two properly Cut-point, this segment data is divided into awakening afterbody, asphyxia stage, respiratory effort stage.

Further, in a kind of apnea detection method based on BCG signal, adaptive threshold method is: 1) pin Each maximum of points to signal profile, it is judged that whether it has the potential quality as separation, and calculates it as cut-point Time segmentation effect;2) best the putting as final cut-point of segmentation effect is selected.

Further, gained is breathed temporarily by described in a kind of apnea detection method S5 based on BCG signal It is the length by investigating asphyxia section that the section of stopping carries out selectivity correcting process, and length exceedes the breathing of a certain specific threshold Pause segment carries out truncation;Apnea is positioned at asphyxia section starting point to the end to thereafter first awakening section Interval corresponding to Dian, and it is divided into asphyxia section, respiratory effort section, awakening section three part.

Further, the described extraction in a kind of apnea detection method S6 based on BCG signal can particulate Degree is portrayed the feature of breathing pattern and is referred to extract from asphyxia section, respiratory effort section, awakening section respectively to portray breathing The feature of BCG signal fluctuation feature when suspending event occurs, such as Sample Entropy, average accumulated difference in magnitude etc..

Further, the described detection event in a kind of apnea detection method S7 based on BCG signal is potential Occur whether interval includes apnea to refer to utilize the feature extracted in S6, by engineerings such as neutral nets Learning method, trains one two classification grader, it is intended to judge whether there occurs apnea in this interval.

Based on above method, the present invention also provides for a kind of apnea detecting system based on BCG signal, including: Signal acquisition module: be used for receiving BCG signal;Data processing module: process BCG signal, detects apnea; Testing result output module;Result is exported;Described data processing module includes: preliminary treatment unit: for BCG signal It is normalized and obtains the awakening section of apnea;Accurately processing unit: each stage is further processed It is divided into asphyxia section, respiratory effort section, awakening section;Event detection unit: extract to portray respectively from three stages and exhale The feature of suction mode, and utilize machine learning method, it is judged that it is temporary whether this event potential generation interval includes real breathing Stop event.

Use a kind of based on BCG signal the apnea detection method of the present invention, can be to BCG signal the whole night In potential apnea be accurately positioned, and each potential apnea is divided into asphyxia section, exhales Inhale and make great efforts section, awakening section three part, it is simple to be many-sided, portray apnea to fine granularity, thus contribute to promoting breathing The Detection accuracy of suspending event.

Accompanying drawing explanation

Fig. 1 is a kind of apnea detection method overall procedure schematic diagram based on BCG signal of the present invention;

Fig. 2 is the structural representation of the apnea involved by present example;

Fig. 3 is to be accurately positioned the schematic flow sheet of all of awakening section in BCG signal in the embodiment of the present invention;

Fig. 4 is the schematic diagram of the linear classifier used during screening awakening section in the embodiment of the present invention;

Fig. 5 is to use method based on adaptive threshold that BCG signal intersegmental for adjacent awakening is divided into feel in present example Awake afterbody, asphyxia section, the schematic diagram of respiratory effort section three part;

Fig. 6 is the structural representation of a kind of apnea detecting system based on BCG signal of the present invention.

Detailed description of the invention

Embodiments provide a kind of apnea detection method based on BCG signal, by being automatically positioned There is interval and by this interal separation for ease of extracting the three of apnea fine granularity feature in what apnea was possible The individual stage (asphyxia section, respiratory effort section, awakening section), to improve the Detection accuracy of apnea.

Definition with hereinafter:

Awakening section: AP, Arousal Phase;

The awakening section of Primary Location: IAP, Initial Arousal Phase;

The non-awakening section of Primary Location: NAP, nonInitial Arousal Phase;

Potential awakening section: PAP, Potential Arousal Phase;

Awakening afterbody: TPA, the Tail of the Previous Arousal;

Asphyxia section: SAP, Sleep Apnea Phase;

Respiratory effort section: REP, Respiratory Effort Phase.

The potential interval that occurs of event: PED, Potential Event Duration.

A kind of apnea detection method based on BCG signal of the present invention particularly as follows:

S1: be normalized BCG signal, eliminates the impact that signal intensity is caused by individual subject's difference.

In present example, individual subject's difference refers mainly to weight differences, and different body weight can cause breast to impact (BCG) signal intensity is different, affects the accuracy of apnea detection.

Wherein, μ is the meansigma methods of BCG signal sequence, and σ is the standard deviation of signal sequence, XiIt it is i-th letter in BCG signal sequence Number value, Xnor_iIt is XiValue after normalized.

The awakening section of S2: Primary Location apnea.

According to American Academy of Sleep Medicine's correlational study, as it is shown in figure 1, apnea generally includes three phases: Respiratory effort section, respiratory effort section, awakening section.Position potential by identifying the awakening section contained in dormant data the whole night Apnea.

Decomposing BCG signal first by wavelet-decomposing method, selection can either abate the noise interference again can be preferable Ground characterizes the STATIC CORRECTION USING APPROXIMATE LAYER of awakening, and the signal of this STATIC CORRECTION USING APPROXIMATE LAYER is denoted as data1.In embodiments of the present invention, wavelet basis be sym8 (i.e. Symlet little wave system small echo, sequence number is 8), selected STATIC CORRECTION USING APPROXIMATE LAYER signal is the 7th layer.

Then data1 signal is divided into isometric data segment, and i-th section is designated as segi, and according to equation below to each Section is marked:

Threshold=mean (std (segj))+A×std(std(segj))

Wherein, j=1,2 ..., N;N is the number of signal segment;A is weight factor.In embodiments of the present invention, every segment data is long Degree is 2 seconds, and parameter A is set as 0.1.

S3: merge the IAP obtained in S2, screening etc. processes, and obtains PAP accurately.

According to medical domain correlational study, apnea time of origin has to last for more than 10 seconds, and the section of awakening generation An event by table, in order to prevent an event being blocked, needs to merge the IAP meeting certain condition, such as Fig. 3

Shown in (b).Specifically, judge whether to need to merge some IAP according to equation below:

endj-endi≤10seconds

Wherein endiWith endjIt it is the finish time of adjacent two IAP;

As shown in Fig. 3 (c), all NAP met between adjacent two IAP of above-mentioned condition are re-flagged into IAP, and will be continuously IAP merge, be labeled as PAP;

BCG signal is easily affected by equipment noise or other factors, causes the PAP of above-mentioned gained may contain false PAP, it is necessary to from In filter out real PAP, as shown in Fig. 3 (d).Specifically, carry out screening (as shown in Figure 4) according to equation below:

Wherein, condition C 1 is made up of equation below:

(Durationi≥18)∪[(Durationi> 6) ∩ (Durationi≥max{Durationj})]

Wherein, DurationiRepresent the persistent period of i-th PAP, DurationjRepresent partially or completely in i-th PAP The set of all PAP composition in the range of ± 20 seconds.

S4: the BCG signal between accurately awakening section adjacent in S3 is divided further into TPA, SAP, REP.

Specifically, first pass through sliding window method the BCG signal between adjacent awakening section to be processed, with by window The sequence of maximum composition characterizes the profile information of this segment signal, and in embodiments of the present invention, (BCG believes every 300 sampled points Number sample frequency is 100Hz) it is a window size;

Then by adaptive threshold method, the profile of this segment signal finds two suitable cut-points, by this segment data It is divided into TPA, SAP, REP, as shown in Figure 5.Specifically, algorithm main two parts content: 1) for each of signal profile Maximum of points, it is judged that whether it has the potential quality as separation, and calculates it as segmentation effect during cut-point;2) respectively For two cut-points, select best the putting as final cut-point of segmentation effect.

S5: the stage each to gained in S4 carries out selectivity correcting process, is finally accurately positioned the position of PED, and by its stroke It is divided into SAP, REP, AP.

It is the length by investigating SAP that gained SAP carries out selectivity correcting process, and length exceedes a certain specific threshold SAP carry out truncation, in the present invention, the apnea persistent period is 10~80 seconds, sets a threshold to the most here 100 seconds, if gained SAP was more than 100 seconds, the most only retain the data of last 100 seconds of this SAP.Potential by apnea Occur interval to be positioned at the starting point terminal to thereafter first AP of SAP, and be divided into SAP, REP, AP tri-part.

As shown in Figure 6, a kind of apnea detecting system based on BCG signal, including: signal acquisition module: use In receiving BCG signal;Data processing module: process BCG signal, detects apnea;Testing result output mould Block;Result is exported.Described data processing module includes: preliminary treatment unit: for being normalized BCG signal And obtain the awakening section of apnea;Accurately processing unit: each stage is further processed and is divided into asphyxia Section, respiratory effort section, awakening section;Event detection unit: extract the feature that can portray breathing pattern respectively from three stages, and Utilize machine learning method, it is judged that this event is potential occurs whether interval includes real apnea.

Claims (10)

1. an apnea detection method based on BCG signal and system, it is characterised in that: it is automatically positioned asphyxia The potential generation interval of event, is divided into potential for event generation interval asphyxia section, respiratory effort section, awakening section, utilizes The feature relevant with breathing pattern contained in three sections, by machine learning method, the final detection potential generating region of this event Between whether comprise apnea;Described apnea detection method of exhaling comprises the following steps:
S1: BCG signal is normalized;
The awakening section of S2: Primary Location apnea;
S3: merge the awakening section obtained in S2, screening etc. processes, obtains the accurately section of awakening;
S4: the segment trailer that is divided further into the BCG signal between accurately awakening section adjacent in S3 awakening, asphyxia section, Respiratory effort section;
S5: the stage each to gained in S4 carries out selectivity correcting process, is finally accurately positioned the potential generation of apnea Interval, is divided into asphyxia section, respiratory effort section, awakening section;
S6: extract from above-mentioned three sections respectively and fine granularity can portray the feature of breathing pattern;
Whether S7: fine granularity breathing pattern feature based on said extracted, by machine learning method, detect in this interval and comprise There is apnea.
A kind of apnea detection method based on BCG signal the most according to claim 1, it is characterised in that: institute The S1 stated use Z-score method BCG signal is normalized.
A kind of apnea detection method based on BCG signal the most according to claim 1, it is characterised in that: institute In the S2 stated, Primary Location apnea includes: first passes through wavelet analysis method and is decomposed by breast impact signal, selects The interference that can either abate the noise can preferably characterize again the STATIC CORRECTION USING APPROXIMATE LAYER of awakening section, is then divided into isometric by this STATIC CORRECTION USING APPROXIMATE LAYER signal Data segment, and by threshold method, tentatively judge that whether each data segment is awakening section, and be marked.
A kind of apnea detection method based on BCG signal the most according to claim 1, it is characterised in that: institute Merging treatment in the S3 stated refer to be unsatisfactory for event time length requirement adjacent awakening section and between data segment carry out Merge;Described event time length requirement refers to that the apnea persistent period should be sentenced according to equation below more than 10 seconds Break and merge the need of by the awakening section of Primary Location:
endj-endi≤10seconds
Wherein endiWith endjIt it is the finish time of the awakening section of adjacent two Primary Location.
A kind of apnea detection method based on BCG signal the most according to claim 1, it is characterised in that: institute Screening Treatment in the S3 stated refers to that the awakening section after each merges extracts feature, trains a grader, by current gained Each awakening section be categorized as real awakening section or the false section of awakening caused by noise in data, and then filter out real awakening Section;Described screening is screened according to equation below:
PoArousalPha i = t r u e A r o u s a l P h a s e , i f Duration i m e e t c o n d i t i o n C 1 f a k e A r o u s a l P h a s e , o t h e r w i s e
Wherein, condition C 1 is made up of equation below:
(Durationi≥18)∪[(DuratiOni > 6) ∩ (Durationi≥max{Durationj})]
Wherein, DurationiThe persistent period of the awakening section that expression i-th is potential, DurationjRepresent partially or completely i-th Individual potential awakening section ± set of potential awakening section in the range of 20 seconds.
A kind of apnea detection method based on BCG signal the most according to claim 1, it is characterised in that: institute Segmentation further in the S4 stated is: first passes through sliding window method and processes the BCG signal between adjacent awakening section, The profile information of this segment signal is characterized, then by adaptive threshold method, at this by the sequence being made up of window maximum The profile of segment signal finds two suitable cut-points, this segment data is divided into awakening afterbody, asphyxia stage, breathing The effort stage.
A kind of apnea detection method based on BCG signal the most according to claim 1, it is characterised in that: institute The selectivity correcting process that carries out gained asphyxia section in the S5 stated is the length by investigating asphyxia section, to length The asphyxia section exceeding a certain specific threshold carries out truncation;The potential generation interval of apnea is positioned at and exhales Inhale the starting point terminal to the most nearest awakening section of pause stage, and be divided into asphyxia section, respiratory effort section, feel Awake section three part.
A kind of apnea detection method based on BCG signal the most according to claim 1, it is characterised in that: institute State the extraction in S6 fine granularity to portray the feature of breathing pattern and refer to respectively from asphyxia section, respiratory effort section, awakening Extract in Duan and can portray the feature of BCG signal fluctuation feature when apnea occurs.
A kind of apnea detection method based on BCG signal the most according to claim 1, it is characterised in that: institute State and whether the detection event potential generation interval in S7 includes apnea refer to utilize the feature extracted in S6, By neural-network classification method, it is judged that whether this interval there occurs apnea.
10. an apnea detecting system based on BCG signal, it is characterised in that: described detecting system includes:
Signal acquisition module: be used for receiving BCG signal;
Data processing module: process BCG signal, detects apnea;
Testing result output module;Result is exported;
Described data processing module includes:
Preliminary treatment unit: for BCG signal being normalized and obtained the awakening section of apnea;
Accurately processing unit: potential for each event generation interval is further processed and is divided into asphyxia section, breathe and exert Power section, awakening section;
Event detection unit: extract the feature that can portray breathing pattern respectively from three stages, and utilize machine learning method, Judge that this event is potential and occur whether interval includes real apnea.
CN201610541244.XA 2016-07-11 2016-07-11 Method and system for apnea event detection based on BCG signal CN106037671A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610541244.XA CN106037671A (en) 2016-07-11 2016-07-11 Method and system for apnea event detection based on BCG signal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610541244.XA CN106037671A (en) 2016-07-11 2016-07-11 Method and system for apnea event detection based on BCG signal

Publications (1)

Publication Number Publication Date
CN106037671A true CN106037671A (en) 2016-10-26

Family

ID=57185934

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610541244.XA CN106037671A (en) 2016-07-11 2016-07-11 Method and system for apnea event detection based on BCG signal

Country Status (1)

Country Link
CN (1) CN106037671A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002013677A2 (en) * 2000-08-17 2002-02-21 Ilife Systems, Inc. System and method for treating obstructive sleep apnea
CN1923132A (en) * 2006-09-04 2007-03-07 北京新兴阳升科技有限公司 Process and apparatus for detecting sleeping respiration force and use thereof
CN102355852A (en) * 2009-02-06 2012-02-15 必安康医疗有限公司 Apparatus, system and method for chronic disease monitoring
CN102469958A (en) * 2009-07-31 2012-05-23 皇家飞利浦电子股份有限公司 Method and apparatus for the analysis of a ballistocardiogram signal

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002013677A2 (en) * 2000-08-17 2002-02-21 Ilife Systems, Inc. System and method for treating obstructive sleep apnea
CN1923132A (en) * 2006-09-04 2007-03-07 北京新兴阳升科技有限公司 Process and apparatus for detecting sleeping respiration force and use thereof
CN102355852A (en) * 2009-02-06 2012-02-15 必安康医疗有限公司 Apparatus, system and method for chronic disease monitoring
CN102469958A (en) * 2009-07-31 2012-05-23 皇家飞利浦电子股份有限公司 Method and apparatus for the analysis of a ballistocardiogram signal

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
蒋芳芳等: "《基于心冲击信号的呼吸率检测方法研究》", 《系统仿真学报》 *
陈超: "《微动敏感床垫睡眠检测系统对儿童阻塞性睡眠呼吸暂综合征诊断的临床研究》", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 *

Similar Documents

Publication Publication Date Title
Zraick et al. Adult normative data for the KayPENTAX phonatory aerodynamic system model 6600
Lázaro et al. Pulse rate variability analysis for discrimination of sleep-apnea-related decreases in the amplitude fluctuations of pulse photoplethysmographic signal in children
US7640055B2 (en) Self-adaptive system for the analysis of biomedical signals of a patient
Taplidou et al. Wheeze detection based on time-frequency analysis of breath sounds
Paalasmaa et al. Adaptive heartbeat modeling for beat-to-beat heart rate measurement in ballistocardiograms
US7267652B2 (en) Systems and methods for respiratory event detection
Huupponen et al. Development and comparison of four sleep spindle detection methods
Gierałtowski et al. Multiscale multifractal analysis of heart rate variability recordings with a large number of occurrences of arrhythmia
CN103083013B (en) Electrocardio signal QRS complex wave detection method based on morphology and wavelet transform
Quiceno-Manrique et al. Detection of obstructive sleep apnea in ECG recordings using time-frequency distributions and dynamic features
JP5090155B2 (en) Non-invasive monitoring of respiratory rate, heart rate, and apnea
Ghazanfar et al. Dynamic, rhythmic facial expressions and the superior temporal sulcus of macaque monkeys: Implications for the evolution of audiovisual speech
Moussavi Fundamentals of respiratory sounds and analysis
Muthuswamy et al. Higher-order spectral analysis of burst patterns in EEG
Cuppens et al. Detection of nocturnal frontal lobe seizures in pediatric patients by means of accelerometers: a first study
Yuen et al. Classification of human emotions from EEG signals using statistical features and neural network
US20090292215A1 (en) Sleep quality indicators
Widdicombe et al. Voluntary and reflex cough and the expiration reflex; implications for aspiration after stroke
Taplidou et al. Analysis of wheezes using wavelet higher order spectral features
CN102843966B (en) For the treatment of the method and apparatus of cyclic physiological signal
Hegland et al. Sequential voluntary cough and aspiration or aspiration risk in Parkinson’s disease
US20140025311A1 (en) Physiological Signal Quality Classification for Ambulatory Monitoring
Almazaydeh et al. Obstructive sleep apnea detection using SVM-based classification of ECG signal features
WO2010066008A1 (en) Multi-parametric analysis of snore sounds for the community screening of sleep apnea with non-gaussianity index
CN105147248A (en) Physiological information-based depressive disorder evaluation system and evaluation method thereof

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20161026