CN116473568A - Non-contact electrocardiosignal reconstruction method - Google Patents
Non-contact electrocardiosignal reconstruction method Download PDFInfo
- Publication number
- CN116473568A CN116473568A CN202310305312.2A CN202310305312A CN116473568A CN 116473568 A CN116473568 A CN 116473568A CN 202310305312 A CN202310305312 A CN 202310305312A CN 116473568 A CN116473568 A CN 116473568A
- Authority
- CN
- China
- Prior art keywords
- electrocardiosignal
- radar
- contact
- reconstruction
- data set
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 12
- 238000013507 mapping Methods 0.000 claims abstract description 7
- 230000015654 memory Effects 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 7
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 238000010276 construction Methods 0.000 claims abstract description 3
- 238000002592 echocardiography Methods 0.000 claims abstract description 3
- 230000006870 function Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 6
- 230000033001 locomotion Effects 0.000 claims description 4
- 230000003183 myoelectrical effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 10
- 238000004364 calculation method Methods 0.000 abstract description 3
- 210000004027 cell Anatomy 0.000 description 8
- 239000012528 membrane Substances 0.000 description 8
- 230000002107 myocardial effect Effects 0.000 description 8
- 230000002336 repolarization Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 230000028161 membrane depolarization Effects 0.000 description 6
- 230000000306 recurrent effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 150000001768 cations Chemical class 0.000 description 3
- 210000000170 cell membrane Anatomy 0.000 description 3
- 230000010287 polarization Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000000747 cardiac effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 210000002837 heart atrium Anatomy 0.000 description 2
- 230000010247 heart contraction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000000284 resting effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 150000001450 anions Chemical class 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004413 cardiac myocyte Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 210000001174 endocardium Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 230000002458 infectious effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention relates to a non-contact electrocardiosignal reconstruction method, which solves the technical problems of higher requirement, complex calculation and high cost of the existing non-contact electrocardiosignal monitoring hardware, and comprises the following specific steps: transmitting radar signals to the chest of a human body by using a millimeter wave continuous wave radar, receiving echoes and synchronously completing the acquisition of electrocardiosignals; performing signal filtering on the radar signal and the electrocardiosignal, eliminating part of interference information and completing construction of a data set; training the constructed data set through a bidirectional long-short-term memory cyclic neural network to obtain a reconstruction mapping model from the radar signal to the electrocardiosignal; and carrying out non-contact electrocardio reconstruction on the human body target by using the obtained model. The invention can be widely applied to non-contact electrocardiosignal reconstruction.
Description
Technical Field
The invention relates to the technical field of intelligent health monitoring, in particular to a non-contact electrocardiosignal reconstruction method.
Background
With the rapid development of China society, the aging condition of the society is also becoming serious, and people are paying attention to the health condition of the old and the vulnerable group not limited to the old. The electrocardiosignal ECG mainly depicts the electrical activity process of cardiac pacing, is an important biomedical signal and reflects the potential physiological characteristics of a human body, and is used for describing the heart activity, and the once complete depolarization and repolarization process of myocardial cells generates a cardiac cycle which consists of P waves, QRS wave groups, T waves and U waves, so that extremely rich heart information is provided. However, most of the electrocardiosignals are contact type devices, which need to be monitored in close fit or wearable devices, so that the electrocardiosignals are limited in application environment and use scene. The current rapidly-developed radar technology just makes up the defects of convenience and multiple targets brought by contact type equipment, and the detection of vital signals through the millimeter wave radar is suitable for a plurality of application scenes which are not suitable for contact, such as the aged sleeping in a monitoring room, the respiratory heartbeat of drunk people, critical patients, infectious patients, the signs of burn-out people and newborns.
The non-contact electrocardiogram monitoring method at the present stage adopts an FMCW frequency modulation continuous wave radar, extracts phase information by processing intermediate frequency signals, establishes a data set by using the phase information as data to reconstruct electrocardio, has higher requirements on hardware, and has the complex principle that an additional computing unit is required to be equipped for extracting the pre-information and extracting the phase, so that the computing amount is large, and the manufacturing cost is higher, and is unfavorable for deployment and transplanting to embedded equipment to operate.
Disclosure of Invention
The invention provides a non-contact electrocardiosignal reconstruction method with good universality and low cost, which aims to solve the technical problems of higher requirements, complex calculation and high cost of the existing non-contact electrocardiosignal monitoring hardware.
The invention provides a non-contact electrocardiosignal reconstruction method, which comprises the following specific steps:
step 1, transmitting radar signals to the chest of a human body by using a millimeter wave continuous wave radar, receiving echoes and synchronously completing the acquisition of electrocardiosignals;
step 2, carrying out signal filtering on the radar signal and the electrocardiosignal, eliminating part of interference information and completing construction of a data set;
step 3, training the constructed data set through a bidirectional long-short-term memory cyclic neural network to obtain a reconstruction mapping model from the radar signal to the electrocardiosignal;
and 4, performing non-contact electrocardiographic reconstruction on the human body target by using the obtained model.
Preferably, the specific steps of the step 1 are as follows: and controlling the ECG device and the continuous wave radar device to start simultaneously by compiling a script, and carrying out correlation alignment on the ECG device and the continuous wave radar device after acquiring signals so as to realize time synchronization.
Preferably, the specific method for writing the script is to write a mouse control script to capture an upper computer interface of the radar equipment and the ECG equipment, locate a starting button of the interface, and control the mouse to click the upper computer starting button at the same time after the script is started so as to reduce acquisition time delay.
Preferably, the specific steps of the step 2 are as follows: and performing continuous wavelet transformation on the radar signals to remove large motions, and performing power frequency noise, baseline noise and myoelectric noise filtering processing on the electrocardiosignals to obtain heart radar sensing signals covering the required information and corresponding electrocardiosignals as a sample data set.
Preferably, the bidirectional long-short-term memory cyclic neural network in the step 3 is composed of two unidirectional cyclic neural networks, and at each moment, the input is simultaneously provided to the two cyclic neural networks with opposite directions, and the output is determined by the two unidirectional cyclic neural networks.
Preferably, in the step 3, a loss function is further provided in the reconstruction mapping model, where the loss function is a mean square error loss function, and the formula of the mean square error loss function is as follows:
the beneficial effects of the invention are as follows:
based on a radar equation, the invention establishes a correlation between power (i 2+q 2) and distance, uses a time domain original intermediate frequency signal as data to establish a data set for electrocardiographic reconstruction, has stronger algorithm applicability, can be operated on any radar with continuous wave radar function, can be operated on a CW continuous wave radar, and also comprises an FMCW frequency modulation continuous wave radar.
The BiLSTM deep learning network has better bidirectional information semantic capturing capability, has natural advantages when processing time sequence, has larger advantages compared with the computation amount of a transformer network, and has better robustness and accuracy.
The invention uses the power information calculated by the iq two-way data to reconstruct the electrocardio, has small calculated amount, only needs to use the original iq two-way information, and does not need to extract the phase and carry out other preprocessing. The algorithm of the invention has higher universality, lower requirements on hardware equipment, easier deployment and capability of realizing the function of electrocardiographic reconstruction at low cost.
Drawings
FIG. 1 is a schematic diagram of a non-contact electrocardiographic reconstruction process according to the present invention;
FIG. 2 is a schematic diagram of the working principle and architecture of the present invention;
fig. 3 is a schematic view of the effect of the electrocardiographic reconstruction of the present invention.
Detailed Description
The present invention is further described below with reference to the drawings and examples so that those skilled in the art to which the present invention pertains can easily practice the present invention.
Examples:
as shown in fig. 1, a schematic diagram of a non-contact electrocardiographic reconstruction flow of the present invention is shown, and the specific steps of the present invention include:
1. and (5) erecting equipment. The continuous wave radar device is placed in front of the sitting human chest by 50cm and is connected with an Electrocardiosignal (ECG) device for electrocardiosignal acquisition.
2. And (5) data acquisition and time synchronization. The data set is established by synchronizing the radar signal and the electrocardiosignal in the time domain. Because the radar device and the ECG device are not the same terminal, the time for starting acquisition is different due to different transmission delays of signals acquired by the two channels, so that corresponding time stamps are different in the same time window, and the time deviation can cause the reduction of accuracy if the time deviation is not processed. It is therefore necessary to control the continuous wave radar device and the electrocardiographic signal device to start up simultaneously by programming a script and to perform correlation alignment after signals are acquired so as to achieve time synchronization.
The method for reducing the acquisition time delay is to write a mouse control script to capture the upper computer interface of the radar equipment and the ECG equipment, locate the starting button of the interface, and control the mouse to click the upper computer starting button at the same time after the script is started so as to reduce the acquisition time delay.
Wherein, electrocardiosignal generation principle: the myocardial cell membrane in the heart is a semi-permeable membrane, and in a resting state, a certain number of positively charged cations are arranged outside the membrane, the same number of negatively charged anions are arranged inside the membrane, and the outer membrane potential is higher than the inner membrane, which is called a polarization state. In the resting state, since the myocardial cells at each part of the heart are in a polarized state, no potential difference exists, and the potential curve traced by the current recorder is flat, namely the equipotential line of the body surface electrocardiogram. When the myocardial cells are stimulated by a certain strength, the permeability of cell membranes is changed, and a large amount of cations flow into the membranes in a short time, so that the potential in the membranes is changed from negative to positive, and the process is called depolarization. For the whole heart, the potential change of myocardial cells in the sequential depolarization process from endocardial to epicardial is called depolarization wave, i.e. the P wave of the atrium and the QRS wave of the ventricle on the surface electrocardiogram. After the cell is depolarized, the cell membrane discharges a large amount of cations, so that the potential in the membrane is changed from positive to negative and the original polarization state is restored, and the process is carried out from epicardium to endocardium, which is called repolarization. Also the potential changes during repolarization of the cardiomyocytes are described by a current recorder as repolarization waves. Because the repolarization process is relatively slow, the repolarization wave is lower than the depolarization wave. The repolarization wave of the atrium is low and buried in the depolarization wave of the ventricle, so that the surface electrocardiogram is not easy to identify. The repolarization wave of the ventricle appears as a T wave on the body surface electrocardiogram. After the whole myocardial cells are all repolarized, the polarization state is restored again, no potential difference exists among the myocardial cells at all parts, and the body surface electrocardiogram is recorded to an equipotential line.
The radar equation is a relation describing the radar received power versus the radar cross section of the target. The relationship between radar range and characteristics of a transmitter, a receiver, an antenna and a target is used for describing the relation between radar receiving power and radar scattering cross section of the target.
Let the radar transmit power be Pt, the receive power be Pr, the radar and target distance be R, the radar cross section be σ, the effective area of the receiving antenna be Ae, the antenna gain be G, then the radar equation is as follows:
from the above, it can be derived that if the transmitting power Pt, the radar scattering cross section σ, the effective area of the receiving antenna is Ae, and the antenna gain is G, the intensity of the receiving power Pr and the target distance form a nonlinear negative correlation, that is, the farther the target distance, the smaller the Pr, the closer the target distance, and the larger the Pr.
3. And (5) signal preprocessing. And performing Continuous Wavelet Transform (CWT) on the radar signals to remove large motions, and performing power frequency noise, baseline noise and myoelectric noise filtering processing on the electrocardiosignals so as to obtain heart radar sensing signals covering the required information and corresponding electrocardiosignals as a sample data set.
4. And constructing a network training model to train an electrocardio reconstruction model. The network structure adopts a bidirectional long and short time memory cyclic neural network (Bi-LSTM). Long Short-Term Memory (LSTM) is a time Recurrent Neural Network (RNN), a special RNN that learns Long-Term dependencies. The main structure of the bi-directional recurrent neural network (BILSTM) is composed of two unidirectional recurrent neural networks. At each time t, the input is simultaneously provided to the two opposite-direction recurrent neural networks, and the output is jointly determined by the two unidirectional recurrent neural networks, thereby ensuring the memory capacity of the unidirectional recurrent neural networks in combination with the context. After training by the neural network, the mapping reconstruction relation between the radar signal and the electrocardiosignal can be obtained and used as a module for independently reconstructing and reusing electrocardiosignals subsequently, so that electrocardiographic monitoring is carried out by separating from the contact electrocardiograph equipment.
And a loss function is also arranged in the reconstructed mapping model and used for evaluating the degree of the difference between the predicted value and the true value of the model, and the difference between the forward calculation result of each iteration of the neural network and the true value is calculated, so that the next training is guided to be carried out in the correct direction. The loss function formula used in the invention is a mean square error loss function, which calculates the Euclidean distance between the predicted value and the true value, and the closer the predicted value and the true value are, the smaller the mean square error of the predicted value and the true value is. The loss function adopts the mean square error loss function of the electrocardio prediction data and the reference electrocardio data at each time point. The mean square error loss function formula is as follows:
the electrocardiosignal detects potential change of myocardial cells due to beating, radar signals can receive all comprehensive motion information comprising whole heart beating according to a radar equation after directional irradiation, and the radar signals are derived from the heart beating, so that the homologous electrocardiosignal can be reconstructed in a contactless manner from the received radar intermediate frequency time domain power signals.
5. And non-contact monitoring is carried out on the human body target electrocardiosignal by using the model after training and learning. The working principle and the architecture diagram of non-contact electrocardiogram monitoring based on millimeter wave radar are shown in the following figure 2, vital sign information acquisition is carried out on a human body target in a monitoring range through wireless electrocardiogram reconstruction equipment, acquired data are sent to back-end computing equipment for signal processing and electrocardiogram reconstruction, and finally human body ECG information is displayed through an upper computer.
As shown in fig. 3, the invention has the effect after the electrocardiograph reconstruction, the prediction electrocardiograph signal output after the electrocardiograph reconstruction is compared with the standard electrocardiograph signal, the prediction signal and the standard signal have the same periodicity, and in detail characteristics, such as the electrocardiograph P wave crest, the R wave crest, the S wave trough and the T wave crest can be corresponding to high similarity in amplitude and time scale.
When the problems of complex operation, environmental limitation and the like of the contact type electrocardio monitoring system are solved, the invention provides a deep learning algorithm based on a millimeter wave radar to reconstruct electrocardiosignals in a non-contact way, so that the problems of difficult installation, excessively complex operation and incapability of operation of patients with special and difficult contact conditions caused by contact type equipment can be well avoided, and a better electrocardiosignal output effect can be realized under a loose condition. This result was also confirmed by an actual measurement experiment. Therefore, the method disclosed herein can be used as an effective and feasible way to perform convenient reconstruction of the electrocardiosignal.
The above description is only for the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the scope of the claims of the present invention should fall within the protection scope of the present invention.
Claims (6)
1. A non-contact electrocardiosignal reconstruction method is characterized by comprising the following specific steps:
step 1, transmitting radar signals to the chest of a human body by using a millimeter wave continuous wave radar, receiving echoes and synchronously completing the acquisition of electrocardiosignals;
step 2, carrying out signal filtering on the radar signal and the electrocardiosignal, eliminating part of interference information and completing construction of a data set;
step 3, training the constructed data set through a bidirectional long-short-term memory cyclic neural network to obtain a reconstruction mapping model from the radar signal to the electrocardiosignal;
and 4, performing non-contact electrocardiographic reconstruction on the human body target by using the obtained model.
2. The non-contact electrocardiosignal reconstruction method as claimed in claim 1, wherein the specific steps of the step 1 are as follows: and controlling the ECG device and the continuous wave radar device to start simultaneously by compiling a script, and carrying out correlation alignment on the ECG device and the continuous wave radar device after acquiring signals so as to realize time synchronization.
3. The non-contact electrocardiosignal reconstruction method of claim 2 wherein the script writing method is to write a mouse control script to capture an upper computer interface of the radar device and the ECG device, locate a start button of the interface, and control the mouse to click the upper computer start button at the same time after the script is started so as to reduce acquisition time delay.
4. The non-contact electrocardiosignal reconstruction method as claimed in claim 1, wherein the specific steps of the step 2 are as follows: and performing continuous wavelet transformation on the radar signals to remove large motions, and performing power frequency noise, baseline noise and myoelectric noise filtering processing on the electrocardiosignals to obtain heart radar sensing signals covering the required information and corresponding electrocardiosignals as a sample data set.
5. The method according to claim 1, wherein the two-way long-short-term memory cyclic neural network in step 3 is composed of two unidirectional cyclic neural networks, and at each moment, the input is simultaneously provided to the two cyclic neural networks with opposite directions, and the output is determined by the two unidirectional cyclic neural networks.
6. The method according to claim 1, wherein the step 3 further comprises a loss function in the reconstructed mapping model, the loss function is a mean square error loss function, and the formula of the mean square error loss function is as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310305312.2A CN116473568A (en) | 2023-03-24 | 2023-03-24 | Non-contact electrocardiosignal reconstruction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310305312.2A CN116473568A (en) | 2023-03-24 | 2023-03-24 | Non-contact electrocardiosignal reconstruction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116473568A true CN116473568A (en) | 2023-07-25 |
Family
ID=87220338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310305312.2A Pending CN116473568A (en) | 2023-03-24 | 2023-03-24 | Non-contact electrocardiosignal reconstruction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116473568A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116849684A (en) * | 2023-08-29 | 2023-10-10 | 苏州唯理创新科技有限公司 | Signal source space positioning method of multichannel sEMG based on independent component analysis |
| CN117731298A (en) * | 2024-01-05 | 2024-03-22 | 长春理工大学 | Non-contact electrocardiosignal inversion method based on FMCW radar |
-
2023
- 2023-03-24 CN CN202310305312.2A patent/CN116473568A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116849684A (en) * | 2023-08-29 | 2023-10-10 | 苏州唯理创新科技有限公司 | Signal source space positioning method of multichannel sEMG based on independent component analysis |
| CN116849684B (en) * | 2023-08-29 | 2023-11-03 | 苏州唯理创新科技有限公司 | Signal source space positioning method of multichannel sEMG based on independent component analysis |
| CN117731298A (en) * | 2024-01-05 | 2024-03-22 | 长春理工大学 | Non-contact electrocardiosignal inversion method based on FMCW radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116473568A (en) | Non-contact electrocardiosignal reconstruction method | |
| Yin et al. | ECG monitoring system integrated with IR-UWB radar based on CNN | |
| Chen et al. | Contactless electrocardiogram monitoring with millimeter wave radar | |
| US11475998B2 (en) | Data preparation for artificial intelligence-based cardiac arrhythmia detection | |
| CN106108889A (en) | Electrocardiogram classification method based on degree of depth learning algorithm | |
| CN105054926A (en) | Electrocardiosignal feature information extraction method and device | |
| CN114052740B (en) | Non-contact electrocardiogram monitoring method based on millimeter wave radar | |
| CN114305355B (en) | Breathing heartbeat detection method, system and device based on millimeter wave radar | |
| CN109318207A (en) | A kind of lower extremity movement readiness potential detection system and method using myoelectricity timing | |
| CN114259213A (en) | Method for detecting adjacent multi-target vital signs of millimeter wave MIMO radar under clutter background | |
| KR20140041327A (en) | Method and system for determining qrs complexes in electrocardiogram signals | |
| CN112307996A (en) | Fingertip electrocardiogram identity recognition device and method | |
| Marhoon et al. | A new real-time resource-efficient algorithm for ECG denoising, feature extraction and classification-based wearable sensor network | |
| CN115024716B (en) | Heart attack graph signal reconstruction method based on heart rate label generation | |
| CN101766486A (en) | Toughness adaptive detection method for evoked potential latency extension | |
| CN104799858A (en) | ECG (electrocardio), breathing and periphery portal control system for magnetic resonance system | |
| Shdefat et al. | A survey study of the current challenges and opportunities of deploying the ECG biometric authentication method in IoT and 5G environments | |
| CN108095714A (en) | A kind of Dynamic Heart Rate detection method | |
| CN114861706A (en) | Electrocardio identity recognition method based on quality evaluation and deep transfer learning | |
| WO2018023698A1 (en) | Fetal-electrocardiogram separation method and device | |
| Shoaib et al. | Digital pacer detection in diagnostic grade ecg | |
| CN106598243A (en) | Multimode adaptive cursor control method and system | |
| KR101526774B1 (en) | A method for transmitting an electrocardiography signal using compressed sensing and a monitoring system using thereof | |
| CN112686213A (en) | OSAHS diagnostic system based on recurrent neural network and millimeter waves | |
| Joshi | Fundamentals of Electrocardiografia (ECG) With Arduino Uno |
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 |