CN113925496B - Fatigue sleep analysis method and device - Google Patents
Fatigue sleep analysis method and device Download PDFInfo
- Publication number
- CN113925496B CN113925496B CN202111221674.0A CN202111221674A CN113925496B CN 113925496 B CN113925496 B CN 113925496B CN 202111221674 A CN202111221674 A CN 202111221674A CN 113925496 B CN113925496 B CN 113925496B
- Authority
- CN
- China
- Prior art keywords
- signal
- heart rate
- rate variability
- filtering
- bcg
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 24
- 230000008878 coupling Effects 0.000 claims abstract description 63
- 238000010168 coupling process Methods 0.000 claims abstract description 63
- 238000005859 coupling reaction Methods 0.000 claims abstract description 63
- 238000001228 spectrum Methods 0.000 claims abstract description 46
- 238000001914 filtration Methods 0.000 claims abstract description 32
- 230000000241 respiratory effect Effects 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 21
- 238000010801 machine learning Methods 0.000 claims abstract description 14
- 230000002612 cardiopulmonary effect Effects 0.000 claims description 30
- 238000000034 method Methods 0.000 claims description 25
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims description 5
- 230000000737 periodic effect Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000005070 sampling Methods 0.000 abstract description 3
- 238000009610 ballistocardiography Methods 0.000 description 37
- 206010016256 fatigue Diseases 0.000 description 22
- 208000019914 Mental Fatigue Diseases 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 3
- 208000019116 sleep disease Diseases 0.000 description 3
- 230000008667 sleep stage Effects 0.000 description 3
- 206010021079 Hypopnoea Diseases 0.000 description 2
- 208000008784 apnea Diseases 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 210000000748 cardiovascular system Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 210000002345 respiratory system Anatomy 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010041349 Somnolence Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000001217 buttock Anatomy 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 230000005800 cardiovascular problem Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000009982 effect on human Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003860 sleep quality Effects 0.000 description 1
- 208000020685 sleep-wake disease Diseases 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 230000002618 waking effect 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
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1102—Ballistocardiography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02405—Determining heart rate variability
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Physiology (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Pulmonology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a fatigue sleep analysis method, which comprises the following steps: step 1, acquiring BCG signals of a user; step 2, performing first filtering on the original BCG signal; step 3, performing second filtering on the original BCG signal; step 4, eliminating abnormal values of the characteristic peaks; step 4, performing power spectrum calculation on the respiratory signal and the heart rate variability signal by using a Lomb-Scargle algorithm; step 5, carrying out heart-lung coupling analysis on the respiratory signal and the heart rate variability signal; and 6, classifying the heart-lung coupling strength by using a classifier model in machine learning, so as to analyze the fatigue and sleep state. The non-equidistant sampling signal can be processed, the signal is insensitive to the interference of the abnormal point, and the higher frequency precision can be obtained. The algorithm improves the detection precision of the algorithm, reduces the complexity of the algorithm and has wide application range.
Description
Technical Field
The application relates to the field of fatigue, namely sleep monitoring, in particular to a fatigue sleep analysis method and device.
Background
Ballistocardiography (BCG) is a non-contact vital sign monitoring method, and the BCG signal has periodicity similar to an electrocardiogram, and reflects weak acting force changes generated on a support during periodic ejection of a heart of a human body, including chest cavity fluctuation, heartbeat, body movement and other human body activities during respiration. The acquisition modes of the BCG signals comprise a vertical mode, a sitting mode, a lying mode and a wearable mode. For a flat-bed BCG acquisition device, respiration and cardiac ejection can generate reaction forces on the mattress below the body of a person when the person is lying flat on the mattress. Thus, contactless sleep monitoring based on BCG signals may be possible. When a person sits on the seat cushion, respiration and heartbeat activities also generate reaction forces to the seat cushion below the buttocks, so that non-contact mental fatigue monitoring based on the BCG signals can be performed.
With the acceleration of the pace of life and the increase of the pressures of work and life, more and more people have problems in terms of sleep disorders. Research shows that the quality of sleep has an important effect on human health, and people are increasingly concerned about the quality of sleep. At the same time, a number of underlying diseases may be present in different sleep stages. Therefore, some basic researches on sleep stage can provide theoretical basis for judging sleep quality, and further provide necessary help for treating patients such as sleep disorder.
The inventors have found that sleep staging of current Polysomnography (PSG) monitoring systems remains the most important standard method of studying sleep staging. However, the system has the defects of complex electrode connection, poor user experience and unsuitability for long-term sleep monitoring of people.
At the same time, mental fatigue is also a non-trivial problem in modern society, and when people are in mental fatigue state, drowsiness, slow reaction and reduced efficiency can be caused, even accidents occur. The consequences of accidents caused by fatigue of special people such as drivers, doctors, dangerous instrument operators, etc. are often extraordinarily serious. Mental fatigue monitoring has been studied for a long time, but it is mostly necessary to equip complicated detecting devices, so that it is necessary to provide a undisturbed, portable, non-contact, high-accuracy mental fatigue monitoring method.
How to invent a fatigue sleep analysis method and device to improve the problems becomes a problem to be solved urgently by the person skilled in the art.
Disclosure of Invention
In order to make up for the above shortcomings, the present application provides a method and a device for analyzing fatigue sleep, which are used for analyzing mental fatigue and sleep state, and aim to improve the problems existing in the above background technology.
In a first aspect, an embodiment of the present application provides a method for analyzing fatigue sleep, including the steps of:
step 1: collecting BCG signals of a user;
step 2: performing first filtering on the original BCG signal to obtain a respiration signal waveform;
step 3: performing second filtering on the original BCG signal, and extracting characteristic peaks;
step 4: removing abnormal values of the characteristic peaks to obtain heart rate variability signals;
step 5: carrying out power spectrum calculation on the respiratory signal and the heart rate variability signal by using a Lomb-Scargle algorithm to obtain power spectrum densities of the respiratory signal and the heart rate variability signal;
step 6: carrying out cardiopulmonary coupling analysis on the respiratory signal and the heart rate variability signal to obtain a cardiopulmonary coupling intensity spectrum of the user;
step 7: and classifying the heart-lung coupling strength by using a classifier model in machine learning, and analyzing the fatigue and sleep state.
In a specific embodiment, the acquisition of BCG signals in step 1 is obtained by one of the following means: mach-Zehnder interferometers, michelson interferometers, or intermode interferometers.
In a specific embodiment, the acquisition of BCG signals in step 1 is obtained by a smart cushion or a smart mattress.
In a specific embodiment, the types of the first and second filters include wavelet transform or butterworth filtering.
In a specific embodiment, the characteristic peak extraction in the step 3 is specifically: extracting J peaks of each heartbeat, and further obtaining the distance between two adjacent heartbeats; the step 4 of eliminating the abnormal value of the characteristic peak specifically comprises the following steps: constructing a heart rate variability signal by using a continuous J-J interval sequence; and carrying out median filtering on the J-J interval sequence obtained after the characteristic peak extraction, wherein the width of a median filtering window is larger than 30 seconds, and if the difference between the J-J interval after median filtering and the original J-J interval is larger than a preset threshold value, the original J-J interval is an abnormal value, and the abnormal value is removed.
In a specific embodiment, the Lomb-Scargle algorithm computes the power spectral density as:
wherein,p (ω) is the periodic signal power at frequency ω, y (t) i ) For discrete experimental data, t i For the time of discrete experimental data, n is the statistics of experimental data, t 1 For the start time of the experimental data, t n Is the expiration time of the experimental data.
In a specific embodiment, the cardiopulmonary coupling analysis is performed on the respiratory signal and the heart rate variability signal in the step 6 to obtain a cardiopulmonary coupling intensity spectrum of the user, where the calculation formula of the cardiopulmonary coupling intensity is as follows:
cross＝P RR (ω)·P HRV * (ω)
CPC＝|mean(P RR (ω))| 2 ·coherence
wherein mean represents averaging, P RR (omega) and P HRV (omega) the power spectral density of the respiratory signal and the heart rate variability signal, respectively, cross being P RR (omega) and P HRV (omega) cross-power spectrum, where copherence is P RR (omega) and P HRV (ω) coherence, CPC is the cardiopulmonary coupling strength.
In a specific embodiment, the classifier model in machine learning comprises a support vector machine classifier or a deep neural network.
In a second aspect, embodiments of the present application provide an electronic device, including one or more processors and a storage device for storing one or more programs; the storage device stores a computer program which, when executed by the processor, causes the processor to perform the steps of:
step 1: collecting BCG signals of a user;
step 2: performing first filtering on the original BCG signal to obtain a respiration signal waveform;
step 3: performing second filtering on the original BCG signal, and extracting characteristic peaks;
step 4: removing abnormal values of the characteristic peaks to obtain heart rate variability signals;
step 5: carrying out power spectrum calculation on the respiratory signal and the heart rate variability signal by using a Lomb-Scargle algorithm to obtain power spectrum densities of the respiratory signal and the heart rate variability signal;
step 6: carrying out cardiopulmonary coupling analysis on the respiratory signal and the heart rate variability signal to obtain a cardiopulmonary coupling intensity spectrum of the user;
step 7: and classifying the heart-lung coupling strength by adopting a classifier model in machine learning, and analyzing the fatigue and sleep state.
In a third aspect, embodiments of the present application provide a computer readable medium having stored thereon a computer program which, when executed by a processor, causes the processor to perform the steps of:
step 1: collecting BCG signals of a user;
step 2: performing first filtering on the original BCG signal to obtain a respiration signal waveform;
step 3: performing second filtering on the original BCG signal, and extracting characteristic peaks;
step 4: removing abnormal values of the characteristic peaks to obtain heart rate variability signals;
step 5: carrying out power spectrum calculation on the respiratory signal and the heart rate variability signal by using a Lomb-Scargle algorithm to obtain power spectrum densities of the respiratory signal and the heart rate variability signal;
step 6: carrying out cardiopulmonary coupling analysis on the respiratory signal and the heart rate variability signal to obtain a cardiopulmonary coupling intensity spectrum of the user;
step 7: and classifying the heart-lung coupling strength by adopting a classifier model in machine learning, so as to analyze the fatigue and sleep state.
The invention has the following beneficial effects:
1. the power spectrum density calculation based on Lomb-Scargle is a method for estimating the frequency spectrum of unequal interval data, is insensitive to interference of abnormal points, can obtain higher frequency precision, and is unequal in HRV signals;
2. cardiopulmonary coupling describes the cooperative relationship and degree of coupling between the cardiovascular system and the respiratory system, and sleep and fatigue can be classified according to the number and frequency of couplings;
3. by means of classifier model classification in machine learning, the detection accuracy of the algorithm is improved, and the complexity of the algorithm is reduced;
4. the invention has wide application range, and is not only suitable for sleep analysis in a sleep state, but also suitable for mental fatigue analysis in a wake state.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some examples of the present application and therefore should not be considered as limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for analyzing fatigue sleep according to the present invention;
FIG. 2 is a flow chart II of a fatigue sleep analysis method according to the present invention;
FIG. 3 is a graph showing the result of performing a cardiopulmonary coupling spectrum calculation on BCG signals in an awake state according to an embodiment of the present invention;
fig. 4 is a graph showing the result of cardiopulmonary coupling spectrum calculation of BCG signals in a sleep state according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some of the embodiments of the present application, but not all of the embodiments. All other embodiments, based on the embodiments herein, which would be apparent to one of ordinary skill in the art without undue burden are within the scope of the present application.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners as well. The apparatus embodiments described above are merely illustrative, for example, flow diagrams and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. In addition, the functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Referring to fig. 1 and 2, the present application provides a fatigue and sleep analysis method based on a non-contact BCG signal, comprising the following steps:
step 1: collecting BCG signals of a user;
the acquisition mode of the BCG signals comprises, but is not limited to, mach-Zehnder interferometers, michelson interferometers and intermode interferometers.
The BCG signal is obtained from an intelligent cushion or an intelligent mattress.
Step 2: performing first filtering on the original BCG signal to obtain a respiration signal waveform;
step 3: performing second filtering on the original BCG signal, and extracting characteristic peaks;
types of the first and second filters include, but are not limited to, wavelet transform, butterworth filtering.
And extracting the characteristics, namely extracting J peaks of each heartbeat, and further obtaining the distance between two adjacent heartbeats, so that a heart rate variability signal is formed by using a continuous J-J interval sequence.
Step 4: removing abnormal values of the characteristic peaks to obtain heart rate variability signals;
and carrying out median filtering on the J-J interval sequence obtained after the characteristic peak extraction, wherein the width of a median filtering window is generally larger than 30 seconds, and if the difference between the J-J interval after median filtering and the original J-J interval is larger than a preset threshold value, the original J-J interval is an abnormal value, and the abnormal value needs to be removed.
Step 5: the respiratory signal and the heart rate variability signal are respectively subjected to spectrum analysis by using a Lomb-Scargle algorithm to obtain the power spectrum densities of the respiratory signal and the heart rate variability signal, wherein the formula for calculating the power spectrum density by using the Lomb-Scargle algorithm is as follows:
wherein,p (ω) is the periodic signal power at frequency ω, y (t) i ) For discrete experimental data, t i For the time of discrete experimental data, n is the statistics of experimental data, t 1 For the start time of the experimental data, t n Is the expiration time of the experimental data. With conventional fast Fourier transforms or AR spectrum estimationCompared with equal power spectrum calculation, the power spectrum density calculation based on Lomb-Scargle can process non-equidistant sampling signals, is insensitive to interference of abnormal points, and can obtain higher frequency precision.
Step 6: carrying out cardiopulmonary coupling analysis on the respiratory signal and the heart rate variability signal to obtain a cardiopulmonary coupling intensity spectrum of the user, wherein the calculation formula is as follows:
cross＝P RR (ω)·P HRV * (ω)
CPC＝|mean(P RR (ω))| 2 ·coherence
wherein mean represents averaging, P RR (omega) and P HRV (omega) the power spectral density of the respiratory signal and the heart rate variability signal, respectively, cross being P RR (omega) and P HRV (omega) cross-power spectrum, where copherence is P RR (omega) and P HRV (ω) coherence, CPC is the cardiopulmonary coupling strength.
Cardiopulmonary coupling describes the cooperative relationship and degree of coupling between the cardiovascular system and the respiratory system, and sleep and fatigue can be categorized according to the number and frequency of couplings. There are several coupling types: high frequency coupling (high frequency coupling, HFC; 0.1-0.4 Hz), low frequency coupling (low frequency coupling, LFC; 0.01-0.1 Hz), elevated low frequency coupling (elevated low frequency coupling, e-LFC; a subset of LFC), elevated narrowband low frequency coupling (elevated low frequency coupling narrow-band, e-LFCNB) and very low frequency coupling (very low frequency coupling, VLFC; 0.0039-0.01 Hz). HFC is a reliable index for stable sleep, and is positively correlated with quality of life and negatively correlated with apnea hypopnea index (apnea hypopnea index, AHI) and age; if HFC is reduced, cardiovascular problems may exist; LFC reflects unstable and disturbed sleep, has a strong genetic factor, is associated with poor quality of life, and is positively correlated with AHI and age. Researchers also commonly use the ratio of high frequency coupling to low frequency coupling (HFC/LFC) to determine the presence of sleep disorders. Heart rate coupling analysis can obtain clearly separated coupling states, and the stage of sleep and the determination of fatigue state can be distinguished.
Usually, the heart-lung coupling spectrum in the awake state is mostly concentrated below 0.01Hz, and the heart-lung coupling spectrum in the sleep state is mostly concentrated between 0.2Hz and 0.3 Hz.
As shown in fig. 3, fig. 3 shows the result of performing cardiopulmonary coupling spectrum calculation on the BCG signal in the awake state according to an embodiment of the present invention, the signal length of each cardiopulmonary coupling intensity spectrum calculation is 512 seconds, each sliding is performed for 30 seconds, the abscissa is the number of times of calculation, and the ordinate is the frequency. It can be seen that the heart-lung coupling spectrum in the awake state is mostly concentrated below 0.01Hz, and the brighter the area in the figure indicates a greater number of frequencies distributed at this frequency.
As shown in fig. 4, fig. 4 is a result of performing cardiopulmonary coupling spectrum calculation on BCG signals in a sleep state according to an embodiment of the present invention. It can be seen that the cardiopulmonary coupling spectrum in the sleep state is mostly concentrated between 0.2Hz and 0.3 Hz.
Step 7: and classifying the heart-lung coupling strength by adopting a classifier model in machine learning, so as to analyze the fatigue and sleep state.
Further, the machine learning classifier model includes, but is not limited to, a support vector machine classifier, a deep neural network.
Preferably a support vector classifier.
The support vector classifier is a supervised machine learning algorithm suitable for solving modeling problems of small samples and high-dimensional data. A support vector classifier is constructed by training a training sample set and each sample in the test sample set is classified using a classifier model.
The embodiment of the application also provides electronic equipment, which comprises one or more processors and a storage device, wherein the storage device is used for storing one or more programs; the storage device stores a computer program which, when executed by the processor, causes the processor to perform the steps of:
step 1: collecting BCG signals of a user;
step 2: performing first filtering on the original BCG signal to obtain a respiration signal waveform;
step 3: performing second filtering on the original BCG signal, and extracting characteristic peaks;
step 4: removing abnormal values of the characteristic peaks to obtain heart rate variability signals;
step 5: carrying out power spectrum calculation on the respiratory signal and the heart rate variability signal by using a Lomb-Scargle algorithm to obtain power spectrum densities of the respiratory signal and the heart rate variability signal;
step 6: carrying out cardiopulmonary coupling analysis on the respiratory signal and the heart rate variability signal to obtain a cardiopulmonary coupling intensity spectrum of the user;
step 7: and classifying the heart-lung coupling strength by adopting a classifier model in machine learning, so as to analyze the fatigue and sleep state.
The embodiments of the present application provide a computer readable medium having stored thereon a computer program which, when executed by a processor, causes the processor to perform the steps of:
step 1: collecting BCG signals of a user;
step 2: performing first filtering on the original BCG signal to obtain a respiration signal waveform;
step 3: performing second filtering on the original BCG signal, and extracting characteristic peaks;
step 4: removing abnormal values of the characteristic peaks to obtain heart rate variability signals;
step 5: carrying out power spectrum calculation on the respiratory signal and the heart rate variability signal by using a Lomb-Scargle algorithm to obtain power spectrum densities of the respiratory signal and the heart rate variability signal;
step 6: carrying out cardiopulmonary coupling analysis on the respiratory signal and the heart rate variability signal to obtain a cardiopulmonary coupling intensity spectrum of the user;
step 7: and classifying the heart-lung coupling strength by adopting a classifier model in machine learning, so as to analyze the fatigue and sleep state.
The working principle of the fatigue sleep analysis method is as follows: based on a fatigue and sleep analysis algorithm of a non-contact Ballistocardiogram (BCG) signal, firstly, acquiring a BCG signal of a user, and then, performing first filtering on an original BCG signal to obtain a respiration signal waveform; performing second filtering on the original BCG signal, and extracting characteristic peaks; removing abnormal values of the characteristic peaks to obtain heart rate variability signals; carrying out power spectrum calculation on the respiratory signal and the heart rate variability signal by using a Lomb-Scargle algorithm to obtain power spectrum densities of the respiratory signal and the heart rate variability signal; carrying out cardiopulmonary coupling analysis on the respiratory signal and the heart rate variability signal to obtain a cardiopulmonary coupling intensity spectrum of the user; and finally, classifying the heart-lung coupling strength by adopting a classifier model in machine learning, so as to analyze the fatigue and sleep state. Compared with the traditional power spectrum calculation such as fast Fourier transform or AR spectrum estimation, the power spectrum density calculation based on Lomb-Scargle can process non-equidistant sampling signals and is insensitive to interference of abnormal points, and higher frequency precision can be obtained. The algorithm improves the detection precision of the algorithm, reduces the complexity of the algorithm, has wide application range, is suitable for sleep analysis in a sleep state and mental fatigue analysis in a waking state, and is suitable for popularization and use.
It should be noted that the embodiments of the present invention can be realized in hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those of ordinary skill in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device of the present invention and its modules may be implemented by hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., as well as software executed by various types of processors, or by a combination of the above hardware circuitry and software, such as firmware.
The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. A method for analyzing fatigue sleep, comprising the steps of:
step 1: collecting BCG signals of a user;
step 2: performing first filtering on the original BCG signal to obtain a respiration signal waveform;
step 3: performing second filtering on the original BCG signal, and extracting characteristic peaks;
step 4: removing abnormal values of the characteristic peaks to obtain heart rate variability signals;
step 5: carrying out power spectrum calculation on the respiratory signal and the heart rate variability signal by using a Lomb-Scargle algorithm to obtain power spectrum densities of the respiratory signal and the heart rate variability signal;
the Lomb-Scargle algorithm calculates the power spectral density as:
wherein,p (ω) is the periodic signal power at frequency ω, y (t) i ) For discrete experimental data, t i For the time of discrete experimental data, n is the statistics of experimental data, t 1 For the start time of the experimental data, t n The expiration time of the experimental data;
step 6: carrying out cardiopulmonary coupling analysis on the respiratory signal and the heart rate variability signal to obtain a cardiopulmonary coupling intensity spectrum of the user;
the calculation formula of the heart-lung coupling strength is as follows:
cross＝P RR (ω)·P HRV * (ω)
CPC＝|mean(P RR (ω))| 2 ·coherence
wherein mean represents averaging, P RR (omega) and P HRV (omega) the power spectral density of the respiratory signal and the heart rate variability signal, respectively, cross being P RR (omega) and P HRV (omega) cross-power spectrum, where copherence is P RR (omega) and P HRV (ω) coherence, CPC is cardiopulmonary coupling strength;
step 7: classifying the heart-lung coupling strength by using a classifier model in machine learning, and analyzing fatigue and sleep states;
the characteristic peak extraction in the step 3 specifically comprises the following steps: extracting J peaks of each heartbeat, and further obtaining the distance between two adjacent heartbeats; the step 4 of eliminating the abnormal value of the characteristic peak specifically comprises the following steps: constructing a heart rate variability signal by using a continuous J-J interval sequence; and carrying out median filtering on the J-J interval sequence obtained after the characteristic peak extraction, wherein the width of a median filtering window is larger than 30 seconds, and if the difference between the J-J interval after median filtering and the original J-J interval is larger than a preset threshold value, the original J-J interval is an abnormal value, and the abnormal value is removed.
2. The method of claim 1, wherein the acquisition of BCG signals in step 1 is obtained by one of the following means: mach-Zehnder interferometers, michelson interferometers, or intermode interferometers.
3. The method according to claim 2, wherein the acquisition of BCG signals in step 1 is obtained through an intelligent cushion or an intelligent mattress.
4. A method of analyzing tired sleep as claimed in claim 1, characterized in that, the type of the first filtering and the second filtering comprises wavelet transform or butterworth filtering.
5. The method of claim 1, wherein the classifier model in machine learning comprises a support vector machine classifier or a deep neural network.
6. An electronic device, comprising:
one or more processors;
a storage means for storing one or more programs;
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-5.
7. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111221674.0A CN113925496B (en) | 2021-10-20 | 2021-10-20 | Fatigue sleep analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111221674.0A CN113925496B (en) | 2021-10-20 | 2021-10-20 | Fatigue sleep analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113925496A CN113925496A (en) | 2022-01-14 |
| CN113925496B true CN113925496B (en) | 2023-12-19 |
Family
ID=79280838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111221674.0A Active CN113925496B (en) | 2021-10-20 | 2021-10-20 | Fatigue sleep analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113925496B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114588471A (en) * | 2022-03-28 | 2022-06-07 | 武汉工程大学 | Intelligent sleep assisting system, sleep state classification method and storage medium |
| CN114732391B (en) * | 2022-06-13 | 2022-08-23 | 亿慧云智能科技（深圳）股份有限公司 | Microwave radar-based heart rate monitoring method, device and system in sleep state |
| CN114947754B (en) * | 2022-06-30 | 2024-08-16 | 北京京东拓先科技有限公司 | Method and apparatus for determining sleep data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104545883A (en) * | 2014-11-18 | 2015-04-29 | 南京丰生永康软件科技有限责任公司 | Electrocardiosignal-based sleep quality detection equipment and service thereof |
| AU2015249207A1 (en) * | 2011-07-06 | 2015-11-19 | Ge Global Sourcing Llc | System and method for predicting mechanical failure of a motor |
| CN105640530A (en) * | 2014-12-01 | 2016-06-08 | Imec 非营利协会 | System and method for heart rate detection |
| WO2016142793A1 (en) * | 2015-03-12 | 2016-09-15 | Quattrone Aldo | Portable electronic device to process a signal acquired from a living body and method thereof |
| CN107569226A (en) * | 2017-09-27 | 2018-01-12 | 广州中科新知科技有限公司 | HRV method and application is obtained based on piezoelectric sensing |
| CN109044301A (en) * | 2018-07-02 | 2018-12-21 | 西北工业大学 | A kind of BCG signal analysis method towards high blood pressure disease detection |
| CN209996316U (en) * | 2018-11-13 | 2020-01-31 | 杭州菲诗奥医疗科技有限公司 | mattress and detection system for detecting heart rate variability based on non-contact |
| CN110742585A (en) * | 2019-10-10 | 2020-02-04 | 北京邮电大学 | Sleep staging method based on BCG (BCG-broadcast) signals |
| CN112294264A (en) * | 2020-10-31 | 2021-02-02 | 无锡中物云信息科技有限公司 | Sleep staging method based on BCG and blood oxygen saturation rate |
-
2021
- 2021-10-20 CN CN202111221674.0A patent/CN113925496B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2015249207A1 (en) * | 2011-07-06 | 2015-11-19 | Ge Global Sourcing Llc | System and method for predicting mechanical failure of a motor |
| CN104545883A (en) * | 2014-11-18 | 2015-04-29 | 南京丰生永康软件科技有限责任公司 | Electrocardiosignal-based sleep quality detection equipment and service thereof |
| CN105640530A (en) * | 2014-12-01 | 2016-06-08 | Imec 非营利协会 | System and method for heart rate detection |
| WO2016142793A1 (en) * | 2015-03-12 | 2016-09-15 | Quattrone Aldo | Portable electronic device to process a signal acquired from a living body and method thereof |
| CN107569226A (en) * | 2017-09-27 | 2018-01-12 | 广州中科新知科技有限公司 | HRV method and application is obtained based on piezoelectric sensing |
| CN109044301A (en) * | 2018-07-02 | 2018-12-21 | 西北工业大学 | A kind of BCG signal analysis method towards high blood pressure disease detection |
| CN209996316U (en) * | 2018-11-13 | 2020-01-31 | 杭州菲诗奥医疗科技有限公司 | mattress and detection system for detecting heart rate variability based on non-contact |
| CN110742585A (en) * | 2019-10-10 | 2020-02-04 | 北京邮电大学 | Sleep staging method based on BCG (BCG-broadcast) signals |
| CN112294264A (en) * | 2020-10-31 | 2021-02-02 | 无锡中物云信息科技有限公司 | Sleep staging method based on BCG and blood oxygen saturation rate |
Non-Patent Citations (2)
| Title |
|---|
| "MetaCycle: an integrated R package to evaluate periodicity in large scale data";Gang Wu;《Bioinformatics》;全文 * |
| LF Power Reflects Baroreflex Function, Not Cardiac Sympathetic Innervation;Faisal Rahman;《Clinical autonomic research》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113925496A (en) | 2022-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113925496B (en) | Fatigue sleep analysis method and device | |
| Paalasmaa et al. | Adaptive heartbeat modeling for beat-to-beat heart rate measurement in ballistocardiograms | |
| CN104720746B (en) | A kind of sleep stage determines method and system | |
| CN110742585B (en) | Sleep staging method based on BCG (BCG-broadcast) signals | |
| Karthikeyan et al. | Detection of human stress using short-term ECG and HRV signals | |
| Kortelainen et al. | Sleep staging based on signals acquired through bed sensor | |
| Fonseca et al. | Cardiorespiratory sleep stage detection using conditional random fields | |
| KR101868888B1 (en) | Classification of Sleep/Wakefulness using Nasal Pressure for Patients with Sleep-disordered Breathing | |
| Bianchi et al. | Processing of signals recorded through smart devices: sleep-quality assessment | |
| EP2818111B1 (en) | Sleep quality estimation device and sleep quality estimation method. | |
| US20160367198A1 (en) | Apparatus and method for detecting and removing artifacts in optically acquired biological signals | |
| Tataraidze et al. | Sleep stage classification based on respiratory signal | |
| CN105942974A (en) | Sleep analysis method and system based on low frequency electroencephalogram | |
| Charbonnier et al. | On-line segmentation algorithm for continuously monitored data in intensive care units | |
| Chung et al. | Wakefulness estimation only using ballistocardiogram: Nonintrusive method for sleep monitoring | |
| Yang et al. | Sleep stage recognition using respiration signal | |
| Alivar et al. | Motion artifact detection and reduction in bed-based ballistocardiogram | |
| Babaeian et al. | Real-time driver drowsiness detection using wavelet transform and ensemble logistic regression | |
| Lin et al. | A physiological information extraction method based on wearable PPG sensors with motion artifact removal | |
| Gerla et al. | Multivariate analysis of full-term neonatal polysomnographic data | |
| Motin et al. | Sleep-wake classification using statistical features extracted from photoplethysmographic signals | |
| Yu et al. | Automatic sleep stage classification based on ECG and EEG features for day time short nap evaluation | |
| Haritha et al. | Automating anxiety detection using respiratory signal analysis | |
| Navarro et al. | Artifact rejection and cycle detection in immature breathing: application to the early detection of neonatal sepsis | |
| Dey et al. | Wearable PPG sensor based alertness scoring system |
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 |