CN113729641A - Non-contact sleep staging system based on conditional countermeasure network - Google Patents
Non-contact sleep staging system based on conditional countermeasure network Download PDFInfo
- Publication number
- CN113729641A CN113729641A CN202111186849.9A CN202111186849A CN113729641A CN 113729641 A CN113729641 A CN 113729641A CN 202111186849 A CN202111186849 A CN 202111186849A CN 113729641 A CN113729641 A CN 113729641A
- Authority
- CN
- China
- Prior art keywords
- time
- encoder
- frequency
- classifier
- discriminator
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/0507—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves using microwaves or terahertz waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Cardiology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Pulmonology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a non-contact sleep staging system based on a conditional countermeasure network in the field of physiological signal monitoring and deep learning, which comprises a millimeter wave radar, a sensor, a microprocessor and a display, wherein the millimeter wave radar is used for transmitting chirp signals with a plurality of frequencies increasing linearly along with time to obtain a thoracic cavity surface displacement signal s (t) caused by respiration and heartbeat; the signal preprocessing module is used for carrying out time-frequency analysis on the thoracic cavity surface displacement signal s (t) to obtain a time-frequency graph; the deep learning model is used for learning features irrelevant to individual differences of the testee and improving the universality of the model; the deep learning model comprises an encoder E, a classifier F and a discriminator D, wherein the encoder E is used for inputting the time-frequency graph to generate characteristics E (x), and the classifier F is used for obtaining the sleep stage class label according to the input characteristics E (x)Discriminator D for comparing E (x) withAs an input, the subject from which the sample is determined is outputThe non-contact sleep staging system does not need to wear a sensor, and does not influence daily life while ensuring the acceptable sleep staging accuracy.
Description
Technical Field
The invention relates to the field of physiological signal monitoring and deep learning, in particular to a non-contact sleep staging system based on a conditional countermeasure network.
Background
Sleep disorder refers to a subjective experience that the quality or time of sleep cannot meet normal physiological needs and affect day-to-day social functions due to difficulty in falling asleep or maintaining sleep, and is the most common sleep disorder. The American national Sleep foundation (AASM) has established a number of Sleep indices to interpret the large number of Sleep pattern data sets it collects and to assess the quality of Sleep of a subject. And the basis for calculating these sleep indices is the sleep stage.
The sleep stages can be roughly divided into a WAKE (WAKE) stage, a Rapid Eye Movement (REM) stage, and a non-rapid eye movement (NREM) stage. The NREM stage can be divided into DEEP sleep (DEEP) stage and LIGHT sleep (LIGHT) stage. When using a conventional Polysomnography (PSG) for sleep monitoring, the participants experience significant discomfort, which affects the quality of sleep. Therefore, polysomnography is not suitable for long-term sleep monitoring in daily life.
Based on the above, the present invention designs a non-contact sleep staging system based on a conditional countermeasure network to solve the above problems.
Disclosure of Invention
The present invention is directed to a non-contact sleep staging system based on a conditional countermeasure network to solve the above-mentioned problems.
In order to achieve the purpose, the invention provides the following technical scheme:
a non-contact sleep staging system based on a conditional countermeasure network comprises a millimeter wave radar for transmitting multiple frequencies which increase linearly with timeObtaining a thoracic surface displacement signal s (t) due to respiration and heartbeat; the signal preprocessing module is used for carrying out time-frequency analysis on the thoracic cavity surface displacement signal s (t) to obtain a time-frequency graph; the deep learning model is used for learning features irrelevant to individual differences of the testee and improving the universality of the model; the deep learning model comprises an encoder E, a classifier F and a discriminator D, wherein the encoder E is used for inputting a time-frequency graph to generate characteristics E (x), and the classifier F is used for obtaining sleep stage class labels according to the input characteristics E (x)The discriminator D is used for comparing E (x) withAs an input, the subject from which the sample is determined is output
Preferably, the millimeter wave radar is an FMCW radar, and the millimeter wave radar includes a receiving antenna Rx and a transmitting antenna Tx.
Preferably, the obtaining method of the thoracic surface displacement signal s (t) is to continuously send chirp at a frequency of 250Hz and extract a phase corresponding to the frequency at the highest amplitude.
Preferably, the time-frequency diagram is obtained by performing time-frequency analysis on the thoracic cavity surface displacement signal s (t) by using a Mexican Hat wavelet basis.
Preferably, theIs a source category label, which represents the subject from which the sample is derived.
Preferably, the E (x) is obtained by that the encoder E extracts features from the chest surface body motion signal of 30 seconds by a residual error network ResNet34 of 34 convolutional layers, and the output features are input into an LSTM network learning time sequence feature after passing through a Flatten layer.
Preferably, the classifier F and the discriminator D are a classification network formed by two fully connected layers.
Preferably, the classifier F and the encoder E play a cooperative game, and the encoder E and the discriminator D play a competing game therebetween for preventing decoding of the source tag s from the encoded representation, and the encoder E learns features independent of individual subject variability, thereby improving the versatility of the model.
Preferably, the deep learning model is trained by using time-frequency graph data and sleep stage class labelsAnd source category labelAs a training set, performing N iterations, and outputting E, F, D weight thetae,θfAnd thetad。
Compared with the prior art, the invention has the beneficial effects that:
the invention monitors the micro displacement signal of the chest surface of the human body caused by heartbeat and respiration by adopting a frequency modulation continuous wave radar (FMCW). According to the heart-lung coupling theory, the heartbeat signal and the respiratory signal reflect the states of cardiovascular and cardiopulmonary system regulation mechanisms under different psychophysiological conditions to a certain extent, have important significance on sleep staging, and are used as input signals of an algorithm sleep staging algorithm. Because the design adopts the convolutional neural network to build a deep learning network model, the wavelet time-frequency analysis is used for converting signals into a time-frequency graph which is used as the input of the network. The design is a non-contact sleep staging method, a testee does not need to wear any sensor, and a sleep monitoring scheme suitable for daily life is provided while the acceptable sleep staging accuracy is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram showing the relative position of the thorax and the radar of the present invention as a function of respiration and heartbeat;
FIG. 2 is a schematic diagram of a sleep staging network according to the present invention;
fig. 3 is a schematic diagram of a sleep staging network training process according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, the present invention provides a technical solution:
a non-contact sleep staging system based on a conditional countermeasure network comprises a millimeter wave radar, a pulse signal acquisition module and a sleep staging module, wherein the millimeter wave radar is used for transmitting a plurality of chirp signals with frequencies increasing linearly along with time to obtain a thoracic cavity surface displacement signal s (t) caused by respiration and heartbeat; the signal preprocessing module is used for carrying out time-frequency analysis on the thoracic cavity surface displacement signal s (t) to obtain a time-frequency graph; the deep learning model is used for learning features irrelevant to individual differences of the testee and improving the universality of the model; the deep learning model comprises an encoder E, a classifier F and a discriminator D, wherein the encoder E is used for inputting a time-frequency graph to generate characteristics E (x), and the classifier F is used for obtaining a sleep stage class label according to the input characteristics E (x)Said discriminator D is used for comparing E (x) withAs an input, the subject from which the sample is determined is output
Signal acquisition: the invention utilizes a millimeter wave radar to collect body motion signals on the surface of a chest, and the specific principle is that the FMCW radar transmits a plurality of chirp signals with the frequency linearly increasing along with time. When a signal is reflected off a single object at a distance s, the signal received by the receiver will have a time delay at. The signal of the receiving antenna Rx and the signal of the transmitting antenna Tx are mixed to obtain an intermediate frequency signal, and a single reflecting surface generates a single peak on the frequency spectrum of the intermediate frequency signal.
The spectral components generated by the reflection of the static reflecting surface remain constant over time, so that the interference of the static reflecting surface can be removed by subtracting the average value. During sleep, the human body remains still for most of the time, and the part with the greatest physical movement is the surface of the thoracic cavity along with breathing. Therefore, the position corresponding to the frequency component with the highest amplitude is the position of the thoracic cavity, the chirp signal is continuously transmitted at the frequency of 250Hz, and the phase corresponding to the frequency with the highest amplitude is extracted, so that the thoracic cavity surface displacement signal s (t) caused by respiration and heartbeat can be obtained (see fig. 1). Since the wavelength of the millimeter wave radar is about 3.8mm, a slight displacement can cause a significant phase change.
Signal preprocessing: and performing time-frequency analysis on the thoracic cavity surface displacement signal s (t) by using a Mexican Hat wavelet basis to obtain a time-frequency graph.
Model structure: the deep learning model is composed of an encoder E, a classifier F and a discriminator D, as shown in fig. 2. x is the time-frequency diagram of the input, E (x) is the feature generated by the input encoder E,the classifier F obtains a sleep stage class label according to the input characteristics E (x).Referred to as source class labels, represent the subjects from which the samples came. The discriminator D uses E (x) and the output result y of the classifier F as input to judge the subject from which the sample comes
Wherein, the encoder E extracts the characteristics from the time-frequency diagram of the chest surface body movement signal of 30 seconds by a residual error network ResNet34 of 34 convolutional layers, and the output characteristics are input into an LSTM network learning time sequence characteristic after passing through a Flatten layer to obtain E (x). And predictor F and discriminator D are a classification network of two fully connected layers.
Optimization function: the network loss function is:
V(E,F,D)=Lf(F;E)-λLd(D;E)
s.tλ>0
wherein L isf(F; E) the cross-entropy loss between the sleep stage class label predicted by classifier F and the true sleep interval label. L isd(D; E) is the cross entropy loss between the source class label predicted by discriminator D and the true source class label. The training process can be viewed as a grand mini game of E, F, D. The encoder E and the classifier F carry out cooperative game, and the classifier F is improved to use the encoded characteristics E (x) to predict the sleep stage more accurately. A challenge game between encoder E and discriminator D prevents it from decoding the source tag s from the encoded representation. In this way, the encoder E can learn features unrelated to individual differences of the testees, thereby improving the universality of the model. The optimization objectives are as follows:
training process: the training set with m samples provided with sleep interval class labels and source class labels isA total of N iterations. E. F, D are weighted by thetae,θfAnd thetadThe learning rates are eta respectivelye、ηf、ηd. The training flow is shown in FIG. 3, where δdTagging sources categoriesEntropy of (2).
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (9)
1. A non-contact sleep staging system based on a conditional countermeasure network, characterized by: the method comprises the steps that a millimeter wave radar is used for transmitting chirp signals with a plurality of frequencies increasing linearly along with time, and thoracic cavity surface displacement signals s (t) caused by respiration and heartbeat are obtained; the signal preprocessing module is used for carrying out time-frequency analysis on the thoracic cavity surface displacement signal s (t) to obtain a time-frequency graph; the deep learning model is used for learning features irrelevant to individual differences of the testee and improving the universality of the model; the deep learning model comprises an encoder E, a classifier F and a discriminator D, wherein the encoder E is used for inputting a time-frequency graph to generate characteristics E (x), and the classifier F is used for obtaining sleep stage class labels according to the input characteristics E (x)The discriminator D is used for comparing E (x) withAs an input, the subject from which the sample is determined is output
2. The system of claim 1, wherein the system comprises: the millimeter wave radar is an FMCW radar, and comprises a receiving antenna Rx and a transmitting antenna Tx.
3. The system of claim 1, wherein the system comprises: the obtaining method of the thoracic cavity surface displacement signal s (t) is to continuously send a chirp signal at the frequency of 250Hz and extract the phase corresponding to the frequency at the highest amplitude.
4. The system of claim 1, wherein the system comprises: the time-frequency diagram is obtained by performing time-frequency analysis on a thoracic cavity surface displacement signal s (t) by using a Mexican Hat wavelet basis.
6. The system of claim 1, wherein the system comprises: and E (x) is obtained by extracting features of the encoder E from the chest surface body motion signal of 30 seconds by a residual error network ResNet34 of 34 convolutional layers, and inputting the output features into an LSTM network learning time sequence feature after passing through a Flatten layer.
7. The system of claim 1, wherein the system comprises: the classifier F and the discriminator D are a classification network formed by two fully-connected layers.
8. The system of claim 7, wherein the system comprises: the classifier F and the encoder E carry out a cooperative game, a countermeasure game is carried out between the encoder E and the discriminator D, the countermeasure game is used for preventing the source label s from being decoded from the coded representation, and the encoder E is used for learning features irrelevant to the individual difference of the testee, so that the universality of the model is improved.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111186849.9A CN113729641A (en) | 2021-10-12 | 2021-10-12 | Non-contact sleep staging system based on conditional countermeasure network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111186849.9A CN113729641A (en) | 2021-10-12 | 2021-10-12 | Non-contact sleep staging system based on conditional countermeasure network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113729641A true CN113729641A (en) | 2021-12-03 |
Family
ID=78726469
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111186849.9A Pending CN113729641A (en) | 2021-10-12 | 2021-10-12 | Non-contact sleep staging system based on conditional countermeasure network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113729641A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114098679A (en) * | 2021-12-30 | 2022-03-01 | 中新国际联合研究院 | Vital sign monitoring waveform recovery method based on deep learning and radio frequency perception |
CN114246563A (en) * | 2021-12-17 | 2022-03-29 | 重庆大学 | Intelligent heart and lung function monitoring equipment based on millimeter wave radar |
CN115422976A (en) * | 2022-09-14 | 2022-12-02 | 湖南万脉医疗科技有限公司 | Artificial network-based cardiopulmonary coupling relationship analysis method and monitoring system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108388912A (en) * | 2018-02-08 | 2018-08-10 | 南京理工大学 | Sleep stage method based on multisensor feature optimization algorithm |
CN109480787A (en) * | 2018-12-29 | 2019-03-19 | 中国科学院合肥物质科学研究院 | A kind of contactless sleep monitor equipment and sleep stage method based on ULTRA-WIDEBAND RADAR |
CN109934089A (en) * | 2018-10-31 | 2019-06-25 | 北京航空航天大学 | Multistage epileptic EEG Signal automatic identifying method based on supervision gradient lifter |
CN111938613A (en) * | 2020-08-07 | 2020-11-17 | 南京茂森电子技术有限公司 | Health monitoring device and method based on millimeter wave radar |
US20200397365A1 (en) * | 2015-07-17 | 2020-12-24 | Feng Zhang | Method, apparatus, and system for wireless sleep monitoring |
CN112263242A (en) * | 2020-10-26 | 2021-01-26 | 哈尔滨工业大学 | Respiration detection and mode classification method based on FMCW radar |
KR20210089782A (en) * | 2019-01-03 | 2021-07-16 | 엘지전자 주식회사 | sleep inducer |
CN113208566A (en) * | 2021-05-17 | 2021-08-06 | 深圳大学 | Data processing method and device, electronic equipment and storage medium |
-
2021
- 2021-10-12 CN CN202111186849.9A patent/CN113729641A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200397365A1 (en) * | 2015-07-17 | 2020-12-24 | Feng Zhang | Method, apparatus, and system for wireless sleep monitoring |
CN108388912A (en) * | 2018-02-08 | 2018-08-10 | 南京理工大学 | Sleep stage method based on multisensor feature optimization algorithm |
CN109934089A (en) * | 2018-10-31 | 2019-06-25 | 北京航空航天大学 | Multistage epileptic EEG Signal automatic identifying method based on supervision gradient lifter |
CN109480787A (en) * | 2018-12-29 | 2019-03-19 | 中国科学院合肥物质科学研究院 | A kind of contactless sleep monitor equipment and sleep stage method based on ULTRA-WIDEBAND RADAR |
KR20210089782A (en) * | 2019-01-03 | 2021-07-16 | 엘지전자 주식회사 | sleep inducer |
CN111938613A (en) * | 2020-08-07 | 2020-11-17 | 南京茂森电子技术有限公司 | Health monitoring device and method based on millimeter wave radar |
CN112263242A (en) * | 2020-10-26 | 2021-01-26 | 哈尔滨工业大学 | Respiration detection and mode classification method based on FMCW radar |
CN113208566A (en) * | 2021-05-17 | 2021-08-06 | 深圳大学 | Data processing method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
MINGMINZHAO等: "LearningSleepStagesfromRadioSignals:AConditionalAdversarialArchitecture", 34THINTERNATIONALCONFERENCEONMACHINELEARNING, pages 1 - 10 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114246563A (en) * | 2021-12-17 | 2022-03-29 | 重庆大学 | Intelligent heart and lung function monitoring equipment based on millimeter wave radar |
CN114246563B (en) * | 2021-12-17 | 2023-11-17 | 重庆大学 | Heart and lung function intelligent monitoring equipment based on millimeter wave radar |
CN114098679A (en) * | 2021-12-30 | 2022-03-01 | 中新国际联合研究院 | Vital sign monitoring waveform recovery method based on deep learning and radio frequency perception |
CN114098679B (en) * | 2021-12-30 | 2024-03-29 | 中新国际联合研究院 | Vital sign monitoring waveform recovery method based on deep learning and radio frequency sensing |
CN115422976A (en) * | 2022-09-14 | 2022-12-02 | 湖南万脉医疗科技有限公司 | Artificial network-based cardiopulmonary coupling relationship analysis method and monitoring system |
CN115422976B (en) * | 2022-09-14 | 2023-11-21 | 湖南万脉医疗科技有限公司 | Cardiopulmonary coupling relation analysis method and monitoring system based on artificial network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113729641A (en) | Non-contact sleep staging system based on conditional countermeasure network | |
Wang et al. | A survey on human behavior recognition using channel state information | |
Wang et al. | Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner | |
Guo et al. | An XGBoost-based physical fitness evaluation model using advanced feature selection and Bayesian hyper-parameter optimization for wearable running monitoring | |
CN112716474B (en) | Non-contact sleep state monitoring method and system based on biological microwave radar | |
KR102237466B1 (en) | Sleep stage classification device and method using pulse oximeter | |
CN112998701A (en) | Vital sign detection and identity recognition system and method based on millimeter wave radar | |
Zhang et al. | Sleep stages classification by CW Doppler radar using bagged trees algorithm | |
US20240081705A1 (en) | Non-contact fatigue detection system and method based on rppg | |
CN114376564A (en) | Sleep staging method, system, device and medium based on cardiac shock signal | |
Chaw et al. | Sleep apnea detection using deep learning | |
de Goederen et al. | Radar-based sleep stage classification in children undergoing polysomnography: a pilot-study | |
CN112998689B (en) | Non-contact multi-person real-time respiration condition evaluation system, device and storage medium | |
Zhang et al. | Human identification driven by deep CNN and transfer learning based on multiview feature representations of ECG | |
TW201424683A (en) | Assessment system and method for pulse and constitution health risks | |
Liu et al. | Evaluating quality of photoplethymographic signal on wearable forehead pulse oximeter with supervised classification approaches | |
Gupta et al. | Automatic contact-less monitoring of breathing rate and heart rate utilizing the fusion of mmWave radar and camera steering system | |
Diraco et al. | Review on human action recognition in smart living: Sensing technology, multimodality, real-time processing, interoperability, and resource-constrained processing | |
CN115474901A (en) | Non-contact living state monitoring method and system based on wireless radio frequency signals | |
Desquins et al. | A survey of photoplethysmography and imaging photoplethysmography quality assessment methods | |
Fernandes et al. | A survey of approaches to unobtrusive sensing of humans | |
Wang et al. | HeRe: Heartbeat signal reconstruction for low-power millimeter-wave radar based on deep learning | |
Zhang et al. | An overview of algorithms for contactless cardiac feature extraction from radar signals: Advances and challenges | |
Lu et al. | Pulse feature extraction based on improved gaussian model | |
Taghizadegan et al. | Prediction of obstructive sleep apnea using ensemble of recurrence plot convolutional neural networks (RPCNNs) from polysomnography signals |
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 |