CN115952450A - Sleep apnea syndrome recognition method, device, computer and storage medium - Google Patents
Sleep apnea syndrome recognition method, device, computer and storage medium Download PDFInfo
- Publication number
- CN115952450A CN115952450A CN202310237594.7A CN202310237594A CN115952450A CN 115952450 A CN115952450 A CN 115952450A CN 202310237594 A CN202310237594 A CN 202310237594A CN 115952450 A CN115952450 A CN 115952450A
- Authority
- CN
- China
- Prior art keywords
- signal
- energy
- signals
- sleep apnea
- frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 201000002859 sleep apnea Diseases 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000000605 extraction Methods 0.000 claims abstract description 71
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 64
- 238000013145 classification model Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 14
- CIWBSHSKHKDKBQ-JLAZNSOCSA-N Ascorbic acid Chemical compound OC[C@H](O)[C@H]1OC(=O)C(O)=C1O CIWBSHSKHKDKBQ-JLAZNSOCSA-N 0.000 claims description 47
- 239000013598 vector Substances 0.000 claims description 45
- 238000004590 computer program Methods 0.000 claims description 31
- ZZZCUOFIHGPKAK-UHFFFAOYSA-N D-erythro-ascorbic acid Natural products OCC1OC(=O)C(O)=C1O ZZZCUOFIHGPKAK-UHFFFAOYSA-N 0.000 claims description 23
- 229930003268 Vitamin C Natural products 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 23
- 235000019154 vitamin C Nutrition 0.000 claims description 23
- 239000011718 vitamin C Substances 0.000 claims description 23
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 20
- 229910052760 oxygen Inorganic materials 0.000 claims description 20
- 239000001301 oxygen Substances 0.000 claims description 20
- 239000008280 blood Substances 0.000 claims description 19
- 210000004369 blood Anatomy 0.000 claims description 19
- 238000010606 normalization Methods 0.000 claims description 18
- 230000005236 sound signal Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 7
- 230000007958 sleep Effects 0.000 description 10
- 238000005259 measurement Methods 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 8
- 210000000707 wrist Anatomy 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 102000001554 Hemoglobins Human genes 0.000 description 4
- 108010054147 Hemoglobins Proteins 0.000 description 4
- 206010041235 Snoring Diseases 0.000 description 4
- 230000031700 light absorption Effects 0.000 description 4
- 238000013186 photoplethysmography Methods 0.000 description 4
- 230000029058 respiratory gaseous exchange Effects 0.000 description 4
- 238000012502 risk assessment Methods 0.000 description 4
- 210000004243 sweat Anatomy 0.000 description 4
- 238000010521 absorption reaction Methods 0.000 description 3
- 230000003321 amplification Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 210000001519 tissue Anatomy 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000007590 Disorders of Excessive Somnolence Diseases 0.000 description 1
- YJPIGAIKUZMOQA-UHFFFAOYSA-N Melatonin Natural products COC1=CC=C2N(C(C)=O)C=C(CCN)C2=C1 YJPIGAIKUZMOQA-UHFFFAOYSA-N 0.000 description 1
- 206010028347 Muscle twitching Diseases 0.000 description 1
- 102000004316 Oxidoreductases Human genes 0.000 description 1
- 108090000854 Oxidoreductases Proteins 0.000 description 1
- 206010062519 Poor quality sleep Diseases 0.000 description 1
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 206010041349 Somnolence Diseases 0.000 description 1
- 206010067775 Upper airway obstruction Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000006793 arrhythmia Effects 0.000 description 1
- 206010003119 arrhythmia Diseases 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 235000010323 ascorbic acid Nutrition 0.000 description 1
- 239000011668 ascorbic acid Substances 0.000 description 1
- 229960005070 ascorbic acid Drugs 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000036471 bradycardia Effects 0.000 description 1
- 208000006218 bradycardia Diseases 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 230000008909 emotion recognition Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 206010016256 fatigue Diseases 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- DRLFMBDRBRZALE-UHFFFAOYSA-N melatonin Chemical compound COC1=CC=C2NC=C(CCNC(C)=O)C2=C1 DRLFMBDRBRZALE-UHFFFAOYSA-N 0.000 description 1
- 229960003987 melatonin Drugs 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000000414 obstructive effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 208000019116 sleep disease Diseases 0.000 description 1
- 208000020685 sleep-wake disease Diseases 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention provides a sleep apnea syndrome recognition method, a device, a computer and a storage medium, wherein the method comprises the steps of collecting and acquiring various sample physiological signals of a plurality of users; inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features; establishing an energy characteristic data set based on each signal characteristic; and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome. After various sample physiological signals of the body of a user are acquired, signal characteristics are extracted by using a characteristic extraction model based on Mallat decomposition, and a K nearest neighbor model is trained by using an energy characteristic data set to obtain a classification model capable of identifying sleep apnea syndrome, so that the sleep apnea syndrome is identified, the type of the sleep apnea syndrome is also identified, and the identification is more efficient and more accurate.
Description
Technical Field
The invention relates to the technical field of sleep apnea syndrome identification, in particular to a sleep apnea syndrome identification method, a sleep apnea syndrome identification device, a computer and a storage medium.
Background
Sleep Apnea Syndrome (SAS) is a sleep disorder in which breathing stops during sleep. The most common cause is upper airway obstruction, often ending with loud snoring, body twitching, or arm whipping. Sleep apnea is accompanied by sleep deficits, daytime sleepiness, fatigue, and bradycardia or arrhythmia and electroencephalogram wakefulness, and can be classified into central type, obstructive type, and mixed type.
SAS has great harm to human health and even possibly endangers life safety, so SAS risk assessment is crucial. SAS affects various physiological signals such as electroencephalogram (EEG), electrocardiogram (ECG), electrooculogram (EOG), electromyogram (EMG), respiration, posture, blood oxygen saturation, etc. Polysomnography (PSG) is a SAS risk assessment gold standard that can comprehensively record physiological changes of a person while sleeping. However, PSG is not applicable in everyday life because it requires specialized equipment and professional physician assistance, and is expensive.
Currently, there are some technologies available for SAS risk assessment in non-hospital environments, such as sleep monitoring technologies based on electroencephalogram, eye tracking. Changes of brain waves and eye movements can directly reflect the sleep state of a person, so that the risk of Sleep Apnea Syndrome (SAS) is revealed, and therefore, the evaluation accuracy is high. However, the two technologies require complicated equipment to wear, are high in price and are difficult to popularize.
At present, means for quickly and accurately identifying the type of the sleep apnea syndrome is lacked. Therefore, how to quickly and accurately identify the type of the sleep apnea syndrome needs to be solved.
Disclosure of Invention
In view of the above, it is necessary to provide a sleep apnea syndrome identification method, apparatus, computer and storage medium for addressing the above technical problems.
A sleep apnea syndrome identification method, comprising:
collecting and acquiring various sample physiological signals of a plurality of users;
inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features;
establishing an energy feature dataset based on each of the signal features;
and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
In one embodiment, the step of inputting the sample physiological signals of each class into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features includes:
and inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain the signal features based on time frequency.
In one embodiment, the step of inputting the sample physiological signals of each class into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features includes:
respectively cutting the various sample physiological signals according to a preset time interval to obtain a plurality of signal units;
and carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain the energy of a low-frequency signal and the energy of a high-frequency signal, carrying out normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signal to form an energy vector, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the performing five-layer Mallat decomposition on each signal unit through haar wavelet to obtain energy of a low-frequency signal and energy of a high-frequency signal, performing normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signal to form an energy vector, and the step of taking the energy vector as the signal feature of the signal unit includes:
carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain a low-frequency signal and a high-frequency signal;
normalizing the energy of the low frequency signal and the energy of the high frequency signal by using the following calculation formula:
wherein the content of the first and second substances,
is a firstjThe energy of the resolved signal->
Is as followsjWavelet coefficients for a decomposition signal>
Is as followsjThe normalized energy of the individual decomposed signals,
and obtaining a formed energy vector after normalization processing, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the step of creating an energy feature data set based on each of the signal features comprises:
and taking the energy vectors of the signal units of the signal characteristics of various types at the same time as a sample to be stitched, and establishing the energy characteristic data set.
In one embodiment, the sample physiological signals include heart rate, blood oxygen content, posture signals, sound signals, and vitamin C concentration signals.
A sleep apnea syndrome recognition apparatus, comprising:
the sample physiological signal acquisition module is used for acquiring various sample physiological signals of a plurality of users;
the signal characteristic extraction module is used for inputting various sample physiological signals to a characteristic extraction model based on Mallat decomposition for characteristic extraction to obtain signal characteristics;
an energy feature dataset establishing module for establishing an energy feature dataset based on each of the signal features;
and the recognition model generation module is used for training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for recognizing the sleep apnea syndrome.
A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of:
collecting and acquiring various sample physiological signals of a plurality of users;
inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features;
establishing an energy feature dataset based on each of the signal features;
and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
collecting and acquiring various sample physiological signals of a plurality of users;
inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features;
establishing an energy feature dataset based on each of the signal features;
and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
A computer program which, when executed by a processor, performs the steps of:
collecting and acquiring various sample physiological signals of a plurality of users;
inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features;
establishing an energy feature dataset based on each of the signal features;
and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
According to the sleep apnea syndrome recognition method, the device, the computer and the storage medium, after various sample physiological signals of the body of a user are acquired, the features of the signals are extracted by using the feature extraction model based on Mallat decomposition, and the K nearest neighbor model is trained by using the energy feature data set, so that the classification model capable of recognizing the sleep apnea syndrome is obtained, the sleep apnea syndrome can be recognized and recognized, the type of the sleep apnea syndrome can be recognized and recognized, and compared with a traditional monitoring means, the recognition effect is more efficient and more accurate.
Drawings
FIG. 1 is a diagram illustrating an application scenario of the sleep apnea syndrome recognition method in one embodiment;
FIG. 2 is a flow diagram illustrating a method for sleep apnea syndrome identification in one embodiment;
FIG. 3 is a block diagram showing the structure of a sleep apnea syndrome recognition apparatus according to an embodiment;
FIG. 4 is a diagram illustrating an internal structure of a computer device according to an embodiment;
fig. 5 is a schematic data processing process diagram of a sleep apnea syndrome identification method in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Example one
The sleep apnea syndrome identification method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 may be, but is not limited to, various personal computers, servers, laptops, smartphones, tablets, and portable wearable devices, for example, the terminal 102 is a smart wristband. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers. In this embodiment, the terminal 102 is a bracelet or a wristband, the terminal 102 acquires various sample physiological signals of a plurality of users and sends the various sample physiological signals to the server 104, and the server 104 inputs the various sample physiological signals to a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features; establishing an energy feature dataset based on each of the signal features; and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
Example two
In this embodiment, as shown in fig. 2, a method for identifying sleep apnea syndrome is provided, which includes:
In this embodiment, physiological signals of human bodies of different users are acquired through various sensor modules and used as sample physiological signals and samples of the model.
In one embodiment, the sample physiological signals include heart rate, blood oxygen content, posture signals, sound signals, and vitamin C concentration signals.
In this embodiment, each sensor module is disposed on the smart wristband, for example, the sensor includes a photoelectric sensing module, an Inertial Measurement Unit (IMU) sensing module, a sound sensing module, and a vitamin C sensing module. The photoelectric sensing module utilizes a photoplethysmography (PPG) to collect heart rate and blood oxygen content, the sound sensing module is used for collecting sound signals, the inertia measurement unit sensing module is used for collecting attitude signals, and the vitamin C sensing module is used for collecting vitamin C concentration signals.
In this embodiment, the smart wristband includes a power supply, a charging module, a microcontroller, a storage module, a photoelectric sensing module, an inertial measurement unit sensing module, a sound sensing module, and a vitamin C sensing module, and signals acquired by the sensors are converted into digital information and stored in the storage module. The control logic is as follows: the microcontroller controls the storage module and the four sensor modules, and at each sampling moment, the microcontroller polls and reads data collected by each sensor and integrates a data packet for storage. Before the next sampling moment comes, the microcontroller and the sensor module both enter a sleep state to reduce power consumption. When the timer interruption comes, each module recovers to normal work and repeats the sampling process.
The photoelectric sensor module utilizes a photoplethysmography (PPG) to acquire heart rate and blood oxygen information, and the principle is that when LED light irradiates the skinThe light reflected back through the skin tissue is received by the photosensitive sensor, and the received light signals are converted into electric signals by the photosensitive sensor and then converted into digital signals by AD. The LED light is attenuated after reflection, and when there is no large movement during measurement, the absorption of light by tissues such as muscles and bones is kept substantially constant and is contained only in the direct current portion of the electrical signal, while the absorption of light by arteries changes with the blood flow, which constitutes the alternating current portion of the electrical signal. Therefore, extracting the AC signal reflects the heart rate. Oxygenated hemoglobin HbO in blood 2 And the Hb content of hemoglobin exists in a certain proportion, and the percentage of oxygen and hemoglobin in the total hemoglobin is the blood oxygen. The light absorption coefficient of Hb to 600-800nm wavelength is higher, and the light absorption coefficient of HB02 to 800-1000 wavelength is higher. Therefore, hbO can be detected by using red light (600-800 nm) and infrared light (800-1000 nm) respectively 2 And Hb concentration, and then the blood oxygen value was obtained according to calculation formula (1).
The photoelectric sensor mainly comprises three modulatable LEDs, a photosensitive sensor, a filter, a signal amplification circuit and an analog-to-digital conversion circuit. The three LEDs emit green (550 nm), red (660 nm) and infrared (940 nm) light, respectively, and the light wavelength can be modulated according to the skin and blood vessel characteristics of the user. The light signal reflected by the blood vessel is received by the photosensitive sensor and converted into an electric signal, and after filtering and amplification, the electric signal is converted into a digital signal through the analog-digital conversion circuit and then output.
The heart rate signal represented by the green light is periodically changed from wave crest to wave trough, each pulse beat corresponds to the sudden change of the wave form, and the heart rate can be calculated by counting the wave crests. The algorithm is as follows: let S be the original signal and IMF be the eigenmode function. Performing empirical mode decomposition on the heart rate signal, wherein in a decomposition result: IMF (1) represents high-frequency noise and needs to be filtered; the frequency of the IMF (3) is close to the heart rate, and the IMF frequency is added to the original data to improve the power of the signal; IMF (4) represents low frequency motion artifacts that need to be filtered out. Thus, the signal ultimately used for peak extraction is S-IMF (1) -IMF (4) + IMF (3). Using a peak extraction algorithm, local peak points of the signal used for peak extraction are found, and the two peak points are separated by at least more than 0.3s (corresponding to a 180 bpm heart rate). And (4) taking the time interval average value of all peak events in the event sequence, and obtaining the heart rate according to the sampling rate.
The blood oxygen content is calculated according to Beer-Lambert's law, and assuming that the incident light intensity is I _0, the dc component in the reflected light intensity can be expressed by the following calculation formula (2):
wherein, the first and the second end of the pipe are connected with each other,
represents a non-arterial tissue absorption coefficient, < >>
Indicates its concentration, <' > or>
、/>
、/>
、/>
Respectively represent
And &>
Absorption coefficient and concentration, L denotes the optical path length. The alternating current component can be expressed as:
wherein
Indicating an increased optical path length of the arterial wave.
Assume that the two lights have a wavelength of
，/>
The calculation formula for calculating the blood oxygen is as follows:
wherein A and B are with HbO 2 The constants associated with the absorption coefficients of Hb for red and infrared light can be determined experimentally.
SAS affects the frequency and amplitude of user actions during sleep. The inertial measurement unit sensing module adopts a nine-axis IMU, and the nine-axis IMU comprises a three-axis gyroscope, a three-axis accelerometer and a three-axis magnetometer and is nine-axis motion tracking equipment. And carrying out ellipsoid calibration on the accelerometer and the magnetometer, and carrying out null shift calibration on the gyroscope. The sampling rate is set to 10Hz and the acquired signals are filtered.
The breathing and the snore can directly reflect the sleep state, and if the breathing and the snore are rapid and unstable and are easy to interrupt, the fact that the user is very likely to have the SAS is indicated. The sound sensing module comprises a MEMS microphone, a signal processing circuit and an analog-to-digital conversion circuit. The microphone collects human voice signals and converts the human voice signals into electric signals, the electric signals are transmitted to the signal processing circuit to be subjected to noise reduction and amplification, and the analog-to-digital conversion circuit converts analog signals into digital signals to be output.
The SAS patients have low vitamin C content and unbalanced redox. The vitamin C content in the body can be detected by collecting sweat. The vitamin C sensing module comprises an induction patch and a signal processing circuit, wherein the positive electrode of the induction patch contains ascorbic acid oxidase, the reaction of melatonin in sweat and oxygen can be catalyzed, redox current can be generated between the positive electrode and the negative electrode in the process, and the detection of the vitamin C in the sweat can be realized by detecting the current through the circuit. The current signal is amplified and converted by ADC, and the final measured value is in direct proportion to the content of vitamin C in sweat.
The intelligent wrist strap is susceptible to environmental noise and physiological artifacts, and electromagnetic interference exists among sensors, which all affect the sensing data. And designing a differential mode filter circuit, a common mode filter circuit and a 50Hz notch filter for filtering. And for the filtered signals, detecting abnormal points by adopting an adaptive threshold method, and replacing the values of the abnormal points by using a threshold value to finish the preprocessing of data.
And step 220, inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features.
It should be understood that different kinds of physiological signals can be divided into physiological signals of different dimensions, i.e. one kind of physiological signal is a physiological signal of one dimension. Due to the fact that the dimensionality of the acquired physiological signals is large, the overfitting problem is prone to being caused if the physiological signals are directly classified. Therefore, firstly, the collected heart rate, blood oxygen content, posture signal, sound signal and vitamin C concentration signal are subjected to feature extraction, so as to extract signal features.
An energy signature dataset is created based on each of the signal signatures, step 230.
In this embodiment, the signal features are stitched together to create an energy feature data set.
In one embodiment, the step of establishing an energy signature data set based on each of the signal signatures comprises: and taking the energy vectors of the signal units of the signal characteristics of various types at the same time as a sample to be stitched, and establishing the energy characteristic data set.
In this embodiment, the energy vectors of the signal units in the same time in each dimension are stitched together to be used as a sample, and a new energy feature data set is established.
And 240, training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
In this embodiment, the energy feature data set is used to train a K nearest neighbor model, an euclidean distance is selected as a distance metric, and an optimal K value is determined through grid search and cross validation, so as to generate a classification model that can be used for monitoring sleep apnea syndrome.
It should be understood that, the conventional sleep monitoring wristband can only judge whether the SAS exists or not based on the heart rate and the snore signal, and cannot distinguish the type of the SAS, so that the risk of the SAS of the user cannot be comprehensively evaluated. In the application, the K nearest neighbor model not only can realize the judgment of the SAS, but also can identify the type of the SAS, thereby effectively improving the clinical monitoring efficiency and enabling the monitoring result to be more accurate.
In this embodiment, after the classification model for identifying the sleep apnea syndrome is obtained, the physiological signals of the human body of the user are collected through the intelligent wrist strap worn by the user, so that the physiological signals of the human body of the user can be acquired in real time when the user sleeps at home, and the sleep apnea syndrome is monitored and identified.
In the embodiment, after various sample physiological signals of the body of the user are acquired, the signal characteristics are extracted by using the characteristic extraction model based on Mallat decomposition, and the K nearest neighbor model is trained by using the energy characteristic data set, so that the classification model capable of identifying the sleep apnea syndrome is obtained, the sleep apnea syndrome can be identified, the type of the sleep apnea syndrome can be identified, and compared with the traditional monitoring means, the identification effect is more efficient and more accurate.
The embodiment provides a wrist strap sensor based on heart rate, blood oxygen saturation, pose, sound and vitamin C, a classification model (Mallat-KNN) based on principal component analysis and random forest double-layer structure Mallat decomposition and K nearest neighbor fusion is constructed, the sleep state of a user is monitored, the risk that the user suffers from SAS is effectively evaluated, the type of the SAS is predicted, and the danger is avoided.
In one embodiment, the step of inputting the various types of sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features includes: and inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain the signal features based on time frequency.
In this embodiment, the time-frequency-based signal feature refers to a time-frequency-based signal feature, and the time-frequency-based signal feature can reflect a change of a signal in time frequency.
In one embodiment, the step of inputting the sample physiological signals of each class into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features includes: respectively cutting the various sample physiological signals according to a preset time interval to obtain a plurality of signal units; and carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain the energy of a low-frequency signal and the energy of a high-frequency signal, carrying out normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signal to form an energy vector, and taking the energy vector as the signal characteristic of the signal unit.
In this embodiment, the preset time interval is a time frequency for dividing the sample physiological signal, for example, the preset time interval is 30 seconds, and the sample physiological signal of each dimension is divided into a plurality of signal units according to a time length of 30 seconds. The method comprises the steps of carrying out five-layer Mallat decomposition on a signal unit through haar wavelet transformation to obtain 1 low-frequency signal and 5 high-frequency signals, calculating the energy of the 1 low-frequency signal and the energy of the 5 high-frequency signals to obtain the energy of the 1 low-frequency signal and the energy of the 5 high-frequency signals, and then carrying out normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signals to form an energy vector which is the characteristic of the signal unit.
In one embodiment, the performing five-layer Mallat decomposition on each signal unit through haar wavelet to obtain energy of a low-frequency signal and energy of a high-frequency signal, performing normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signal to form an energy vector, and using the energy vector as the signal feature of the signal unit includes: carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain a low-frequency signal and a high-frequency signal; normalizing the energy of the low frequency signal and the energy of the high frequency signal using the following equations (5), (6), and (7):
wherein the content of the first and second substances,
is as followsjThe energy of the resolved signal->
Is as followsjWavelet coefficients of the decomposition signal->
Is a firstjThe normalized energy of the individual decomposed signals,
and obtaining a formed energy vector after normalization processing, and taking the energy vector as the signal characteristic of the signal unit.
EXAMPLE III
In this embodiment, an intelligent wrist strap for SAS risk assessment is provided, as shown in fig. 5, the intelligent wrist strap is provided with a nine-axis inertial measurement unit, a photoelectric sensor, an MEMS microphone and a vitamin C sensor, the wrist strap acquires a user pose and a motion signal through the measurement unit, acquires a sound signal through the MEMS microphone, and the back of the wrist strap integrates the photoelectric sensor to monitor heart rate and blood oxygen information, and acquires the concentration of vitamin C of the user through the vitamin C sensor. The method can realize the discrimination of four states of no SAS risk, blocked SAS risk, central SAS risk and mixed SAS risk, thereby effectively preventing the SAS.
The SAS risk was classified using a double-layer mechanism model based on Mallat decomposition and KNN. And the first layer model extracts the time-frequency characteristics of the signals through Mallat decomposition, constructs a characteristic data set and inputs the characteristic data set into the second layer KNN model, and realizes classification and prediction of SAS risks. The data processing algorithm is as follows:
because the dimensionality of the collected signals is more, if the signals are directly classified, the problem of overfitting is easily caused. Therefore, firstly, the heart rate, the blood oxygen, the nine-axis posture data, the sound signal sequence and the concentration data of the vitamin C in the body after the pretreatment are subjected to feature extraction.
The data of all dimensions were sliced at intervals of 30s as one signal unit. And performing 5-layer Mallat decomposition on each signal unit through haar wavelet to obtain 1 low-frequency signal and 5 high-frequency signals, calculating the energy of the low-frequency signal and the high-frequency signal obtained after the signal unit decomposition by using a formula 5-7, normalizing the energy, and forming an energy vector as the characteristic of the signal unit.
Wherein, the first and the second end of the pipe are connected with each other,
is as followsjThe energy of the resolved signal->
Is as followsjWavelet coefficients of the decomposition signal->
Is as followsjNormalized energy of the individual decomposed signals.
And (4) stitching the energy vectors of the signal units in all dimensions in the same time to form a sample, and establishing a new energy characteristic data set. And training a K nearest neighbor model by using the data set, selecting Euclidean distance as distance measurement, and determining the optimal K value through grid search and cross validation so as to generate a classification model for monitoring the SAS disease risk and disease category.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.
Example four
In this embodiment, as shown in fig. 3, a sleep apnea syndrome recognition apparatus is provided, including:
a sample physiological signal acquisition module 310, configured to acquire sample physiological signals of various types of multiple users;
the signal feature extraction module 320 is configured to input various sample physiological signals to a feature extraction model based on Mallat decomposition for feature extraction, so as to obtain signal features;
an energy feature data set establishing module 330, configured to establish an energy feature data set based on each of the signal features;
and the identification model generation module 340 is configured to train the K nearest neighbor model by using the energy feature data set, so as to obtain a classification model for identifying sleep apnea syndrome.
In one embodiment, the signal feature extraction module is configured to input the various types of sample physiological signals to a feature extraction model based on Mallat decomposition for feature extraction, so as to obtain the signal features based on time frequency.
In one embodiment, the signal feature extraction module comprises:
the signal cutting unit is used for respectively cutting various types of sample physiological signals according to a preset time interval to obtain a plurality of signal units;
and the signal characteristic extraction unit is used for carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain the energy of the low-frequency signal and the energy of the high-frequency signal, carrying out normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signal to form an energy vector, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the signal feature extraction unit is further configured to perform five-layer Mallat decomposition on each signal unit through haar wavelet to obtain a low-frequency signal and a high-frequency signal; normalizing the energy of the low-frequency signal and the energy of the high-frequency signal by adopting the following calculation formula:
wherein the content of the first and second substances,
is a firstjThe energy of the resolved signal->
Is a firstjWavelet coefficients for a decomposition signal>
Is as followsjThe normalized energy of the individual decomposed signals,
and obtaining a formed energy vector after normalization processing, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the energy feature data set creating module is further configured to stitch together energy vectors of signal units of the signal features of each class at the same time as a sample to create the energy feature data set.
In one embodiment, the sample physiological signals include heart rate, blood oxygen content, posture signals, sound signals, and vitamin C concentration signals.
For specific limitations of the sleep apnea syndrome identifying apparatus, reference may be made to the above limitations of the sleep apnea syndrome identifying method, and details are not repeated here. The units in the sleep apnea syndrome recognition device can be wholly or partially realized by software, hardware and a combination thereof. The units can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the units.
EXAMPLE five
In this embodiment, a computer device is provided, and the computer device may be a portable wearable device, and in this embodiment, the computer device is an intelligent wristband. The internal structure of which can be seen in fig. 4. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores a computer program and is used for storing human physiological signals of a user. The internal memory provides an environment for running the computer program in the nonvolatile storage medium. The network interface of the computer device is used for communicating with other computer devices, such as connecting with a server, and the network interface is a wireless network interface which can access a mobile communication network and is connected with the server. The computer program is executed by a processor to implement a method of emotion recognition. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and in some embodiments, the input device includes a touch sensor, and the input device includes a photoelectric sensing module, an Inertial Measurement Unit (IMU) sensing module, a sound sensing module, and a vitamin C sensing module.
Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:
collecting and acquiring various sample physiological signals of a plurality of users;
inputting various sample physiological signals into a feature extraction model based on Mallat decomposition to perform feature extraction to obtain signal features;
establishing an energy feature dataset based on each of the signal features;
and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain the signal features based on time frequency.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
respectively cutting the various sample physiological signals according to a preset time interval to obtain a plurality of signal units;
and carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain the energy of a low-frequency signal and the energy of a high-frequency signal, carrying out normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signal to form an energy vector, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain a low-frequency signal and a high-frequency signal;
normalizing the energy of the low frequency signal and the energy of the high frequency signal by using the following calculation formula:
wherein the content of the first and second substances,
is a firstjEnergy of a decomposition signal>
Is a firstjThe wavelet coefficients of the individual decomposed signals,/>
is as followsjThe normalized energy of the individual decomposed signals,
and obtaining a formed energy vector after normalization processing, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the processor when executing the computer program further performs the steps of:
and taking the energy vectors of the signal units of the signal characteristics of various types at the same time as a sample to be stitched, and establishing the energy characteristic data set.
In one embodiment, the sample physiological signals include heart rate, blood oxygen content, posture signals, sound signals, and vitamin C concentration signals.
EXAMPLE six
In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, the computer program realizing the following steps when executed by a processor:
collecting and acquiring various sample physiological signals of a plurality of users;
inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features;
establishing an energy feature dataset based on each of the signal features;
and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain the signal features based on time frequency.
In one embodiment, the computer program when executed by the processor further performs the steps of:
respectively cutting the various sample physiological signals according to a preset time interval to obtain a plurality of signal units;
and carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain the energy of a low-frequency signal and the energy of a high-frequency signal, carrying out normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signal to form an energy vector, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain a low-frequency signal and a high-frequency signal;
normalizing the energy of the low-frequency signal and the energy of the high-frequency signal by adopting the following calculation formula:
wherein the content of the first and second substances,
is as followsjThe energy of the resolved signal->
Is as followsjWavelet coefficients for a decomposition signal>
Is as followsjThe normalized energy of the individual decomposed signals,
and obtaining a formed energy vector after normalization processing, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and taking the energy vectors of the signal units of the signal characteristics of various types at the same time as a sample to be stitched, and establishing the energy characteristic data set.
In one embodiment, the sample physiological signals include heart rate, blood oxygen content, posture signals, sound signals, and vitamin C concentration signals.
EXAMPLE seven
In this embodiment, a computer program is provided, and when executed by a processor, the computer program implements the following steps:
collecting and acquiring various sample physiological signals of a plurality of users;
inputting various sample physiological signals into a feature extraction model based on Mallat decomposition to perform feature extraction to obtain signal features;
establishing an energy feature dataset based on each of the signal features;
and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain the signal features based on time frequency.
In one embodiment, the computer program when executed by the processor further performs the steps of:
respectively cutting the various sample physiological signals according to a preset time interval to obtain a plurality of signal units;
and carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain the energy of a low-frequency signal and the energy of a high-frequency signal, carrying out normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signal to form an energy vector, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain a low-frequency signal and a high-frequency signal;
normalizing the energy of the low-frequency signal and the energy of the high-frequency signal by adopting the following calculation formula:
wherein the content of the first and second substances,
is as followsjThe energy of the resolved signal->
Is as followsjWavelet coefficients of the decomposition signal->
Is a firstjThe normalized energy of the individual decomposed signals,
and obtaining a formed energy vector after normalization processing, and taking the energy vector as the signal characteristic of the signal unit.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and taking the energy vectors of the signal units of the signal characteristics of various types at the same time as a sample to be stitched, and establishing the energy characteristic data set.
In one embodiment, the sample physiological signals include heart rate, blood oxygen content, posture signals, sound signals, and vitamin C concentration signals.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (10)
1. A method for sleep apnea syndrome identification, comprising:
collecting and acquiring various sample physiological signals of a plurality of users;
inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain signal features;
establishing an energy feature dataset based on each of the signal features;
and training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for identifying the sleep apnea syndrome.
2. The method as claimed in claim 1, wherein the step of inputting the various types of the sample physiological signals into a features extraction model based on Mallat decomposition for feature extraction, and obtaining signal features comprises:
and inputting various sample physiological signals into a feature extraction model based on Mallat decomposition for feature extraction to obtain the signal features based on time frequency.
3. The method according to claim 2, wherein the step of inputting the sample physiological signals of each class into a feature extraction model based on Mallat decomposition for feature extraction, and obtaining signal features comprises:
respectively cutting the various sample physiological signals according to a preset time interval to obtain a plurality of signal units;
and carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain the energy of a low-frequency signal and the energy of a high-frequency signal, carrying out normalization processing on the energy of the low-frequency signal and the energy of the high-frequency signal to form an energy vector, and taking the energy vector as the signal characteristic of the signal unit.
4. The method according to claim 3, wherein the step of performing five-layer Mallat decomposition on each signal unit through haar wavelet to obtain energy of low-frequency signals and energy of high-frequency signals, and performing normalization processing on the energy of the low-frequency signals and the energy of the high-frequency signals to form energy vectors, and the step of using the energy vectors as the signal features of the signal units comprises:
carrying out five-layer Mallat decomposition on each signal unit through haar wavelet to obtain a low-frequency signal and a high-frequency signal;
normalizing the energy of the low-frequency signal and the energy of the high-frequency signal by adopting the following calculation formula:
wherein the content of the first and second substances,
is as followsjThe energy of the resolved signal->
Is as followsjWavelet coefficients of the decomposition signal->
Is as followsjThe normalized energy of the individual decomposed signals,
and obtaining a formed energy vector after normalization processing, and taking the energy vector as the signal characteristic of the signal unit.
5. The method of claim 1, wherein the step of creating an energy signature dataset based on each of the signal signatures comprises:
and taking the energy vectors of the signal units of the signal characteristics of various types at the same time as a sample to be stitched, and establishing the energy characteristic data set.
6. The method of claim 1, wherein the sample physiological signals include heart rate, blood oxygen content, posture signals, sound signals, and vitamin C concentration signals.
7. A sleep apnea syndrome recognition apparatus, comprising:
the sample physiological signal acquisition module is used for acquiring various sample physiological signals of a plurality of users;
the signal characteristic extraction module is used for inputting various sample physiological signals to a characteristic extraction model based on Mallat decomposition for characteristic extraction to obtain signal characteristics;
an energy feature dataset establishing module for establishing an energy feature dataset based on each of the signal features;
and the recognition model generation module is used for training the K nearest neighbor model by using the energy characteristic data set to obtain a classification model for recognizing the sleep apnea syndrome.
8. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
10. A computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310237594.7A CN115952450A (en) | 2023-03-14 | 2023-03-14 | Sleep apnea syndrome recognition method, device, computer and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310237594.7A CN115952450A (en) | 2023-03-14 | 2023-03-14 | Sleep apnea syndrome recognition method, device, computer and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115952450A true CN115952450A (en) | 2023-04-11 |
Family
ID=87289904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310237594.7A Pending CN115952450A (en) | 2023-03-14 | 2023-03-14 | Sleep apnea syndrome recognition method, device, computer and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115952450A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104545818A (en) * | 2015-01-29 | 2015-04-29 | 吉林大学 | Sleep apnea syndrome detection method based on pulse and blood oxygen signals |
| CN113243890A (en) * | 2021-05-10 | 2021-08-13 | 清华大学深圳国际研究生院 | Sleep apnea syndrome recognition device |
-
2023
- 2023-03-14 CN CN202310237594.7A patent/CN115952450A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104545818A (en) * | 2015-01-29 | 2015-04-29 | 吉林大学 | Sleep apnea syndrome detection method based on pulse and blood oxygen signals |
| CN113243890A (en) * | 2021-05-10 | 2021-08-13 | 清华大学深圳国际研究生院 | Sleep apnea syndrome recognition device |
Non-Patent Citations (3)
| Title |
|---|
| TİMUŞ, OĞUZHAN ET AL.: "k-NN-based classification of sleep apnea types using ECG", 《TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES》 * |
| 伍智萱 等: "基于Matlab工具箱的脑一机接口数据处理", 《电脑知识与技术》 * |
| 黄雪莹: "基于LSTM-CNN睡眠呼吸暂停低通气检测算法研究", 《万方》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bsoul et al. | Apnea MedAssist: real-time sleep apnea monitor using single-lead ECG | |
| US11678838B2 (en) | Automated detection of breathing disturbances | |
| US20190133468A1 (en) | Method and apparatus for high accuracy photoplethysmogram based atrial fibrillation detection using wearable device | |
| JP6159250B2 (en) | System control method and program for predicting patient survival | |
| KR100455286B1 (en) | Method and apparatus for understanding the condition of animal using acquisition and analysis of physiological signal of the animal | |
| Bozkurt et al. | Detection of abnormal respiratory events with single channel ECG and hybrid machine learning model in patients with obstructive sleep apnea | |
| CA2747057A1 (en) | Method and apparatus for determining heart rate variability using wavelet transformation | |
| JP2011517982A (en) | Sleep / wake state evaluation method and system | |
| Bellos et al. | Extraction and Analysis of features acquired by wearable sensors network | |
| Shen et al. | Multitask residual shrinkage convolutional neural network for sleep apnea detection based on wearable bracelet photoplethysmography | |
| Suresh et al. | Feature selection techniques for a machine learning model to detect autonomic dysreflexia | |
| Shi et al. | Apnea MedAssist II: A smart phone based system for sleep apnea assessment | |
| CN115952450A (en) | Sleep apnea syndrome recognition method, device, computer and storage medium | |
| Enamamu et al. | Transparent authentication: Utilising heart rate for user authentication | |
| Pantelopoulos et al. | A formal language approach for multi-sensor wearable health-monitoring systems | |
| Kandukuri et al. | Constant Q–Transform–Based Deep Learning Architecture for Detection of Obstructive Sleep Apnea | |
| Akbari et al. | Supervised classification of sleep events suitable for a minimized home-operated recording system | |
| Pflugradt et al. | Improved signal quality indication for photoplethysmographic signals incorporating motion artifact detection | |
| Zhao et al. | Intelligent Gateway Based Human Cardiopulmonary Health Monitoring System | |
| CN115952449A (en) | Sleep stage monitoring method and device, computer and storage medium | |
| Peng et al. | A distributed multimodality sensor system for home-used sleep condition inference and monitoring | |
| US20220375591A1 (en) | Automatic sleep staging classification with circadian rhythm adjustment | |
| Almazaydeh | An interactive, real-time, high precision and portable monitoring system of obstructive sleep apnea | |
| Salem et al. | Pervasive detection of sleep apnea using medical wireless sensor networks | |
| Li | Sleep Apnea Detection Using Multi-Bio Signals and Machine Learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230411 |
|
| RJ01 | Rejection of invention patent application after publication |