CN112450900B - Non-contact heartbeat detection method based on intelligent sound box - Google Patents

Non-contact heartbeat detection method based on intelligent sound box Download PDF

Info

Publication number
CN112450900B
CN112450900B CN202011427197.9A CN202011427197A CN112450900B CN 112450900 B CN112450900 B CN 112450900B CN 202011427197 A CN202011427197 A CN 202011427197A CN 112450900 B CN112450900 B CN 112450900B
Authority
CN
China
Prior art keywords
signal
heartbeat
sound box
frequency
contact
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011427197.9A
Other languages
Chinese (zh)
Other versions
CN112450900A (en
Inventor
张扶桑
金蓓弘
王志
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Software of CAS
Original Assignee
Institute of Software of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Institute of Software of CAS filed Critical Institute of Software of CAS
Priority to CN202011427197.9A priority Critical patent/CN112450900B/en
Publication of CN112450900A publication Critical patent/CN112450900A/en
Application granted granted Critical
Publication of CN112450900B publication Critical patent/CN112450900B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • 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
    • A61B5/0816—Measuring devices for examining respiratory frequency
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Cardiology (AREA)
  • Physiology (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Veterinary Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Pathology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Pulmonology (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Epidemiology (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

The invention relates to a non-contact heartbeat detection method based on an intelligent sound box, which utilizes the sound box to send sound wave signals and carries out signal analysis and processing on echo waves to realize non-contact human heartbeat perception. The principle is that a loudspeaker on a sound box emits a frequency modulation continuous wave signal, the signal is reflected back by a target human body and received by a microphone after reaching a target, and the received signal and the transmitted signal are subjected to frequency mixing operation and are processed by a low-pass filter. According to the frequency mixing result, a virtual sending signal is designed, the virtual sending signal and a receiving signal are mixed again to eliminate system delay, a target human body position is obtained, a signal is extracted at the position, a heartbeat signal is extracted by utilizing a complementary set empirical mode decomposition method, and the heartbeat signal is segmented by utilizing an expectation maximization algorithm to obtain a heart rate and a heartbeat interval. The invention realizes the application of household non-contact sensing, has accurate sensing capability on human breath and heartbeat detection, is easy to popularize, and is suitable for the fields of intelligent home, intelligent old-age care and the like.

Description

Non-contact heartbeat detection method based on intelligent sound box
Technical Field
The invention belongs to the field of intelligent non-contact sensing, and particularly relates to a method for carrying out non-contact sensing by using sound wave signals in an intelligent loudspeaker box.
Background
Cardiovascular disease is currently the most common health problem facing people worldwide, and is one of the leading causes of morbidity and mortality worldwide [1-2 ]. In developing countries, cardiovascular disease causes about 1700 million deaths per year. Cardiovascular disease causes about 37 million deaths per year in the united states alone. Heart rate detection provides some information about the efficiency and function of the cardiovascular system. Traditionally, heart rate monitoring is a common practice in medicine, and plays a crucial role in assisting clinical diagnosis and assessing the overall health condition of patients. But the monitoring needs to be performed by a professional operating a dedicated device, for example, using an Electrocardiograph (ECG) [3 ]. While these devices can achieve high precision, they are often expensive and require specialized personnel to operate. In order to facilitate daily heartbeat monitoring of people at home, portable equipment and even wearable equipment [4,5] are emerging, and the equipment has the advantages of portability and low cost, but needs to be worn, causes discomfort to users and can be often forgotten to wear.
In recent years, wireless sensing becomes a research hotspot, and the key difference between the wireless sensing and the traditional sensor-based method is that the method does not need any special equipment, extracts human vital sign information from signals through the influence of human bodies on the signals, and has the advantages of non-intrusion, convenience in use and the like. In order to achieve the aim, the invention provides a non-contact heartbeat detection method based on an intelligent sound box, and the intelligent sound box can accurately monitor the heart rate of a user and more detailed heartbeat interval data in a non-contact mode no matter the user is in a sitting posture or a sleeping posture.
[1]2019.Heart Disease and Stroke Statistics-2019 At-a-Glance. https://healthmetrics.heart.org/wp-content/uploads/2019/02/At-A-GlanceHeart-Disease-and-Stroke-Statistics-％E2％80％93-2019.pdf.
[2]2020.Cardiovascular Diseases. https://www.who.int/health-topics/cardiovascular-diseases/#tab＝tab_1.
[3]Leonard S Lilly.2012.Pathophysiology of heart disease:a collaborative project of medical students and faculty.Lippincott Williams&Wilkins.
[4]2020.Fitbit wrist band.https://www.fitbit.com/.
[5]2020.Apple watch.https://www.apple.com/watch/.
Disclosure of Invention
The invention solves the problems: the defects of the prior art are overcome, and a non-contact heartbeat detection method based on an intelligent sound box is provided. The method comprises a sensing technology for measuring the submillimeter-level human heartbeat at high precision, and the influence of other human activities including respiration is separated and removed, so that accurate and reliable non-contact human heartbeat detection is realized in daily household scenes.
The technical scheme of the invention is as follows: a non-contact heartbeat detection method based on an intelligent sound box comprises the following steps:
sending a frequency modulation continuous wave signal by using an intelligent sound box and receiving by using a microphone;
carrying out band-pass filtering on the received signal to filter noise outside a required range;
performing a mixing operation on the transmission signal and the filtered reception signal;
eliminating system delay by performing spectral analysis on the mixed signal and using the proposed virtual transmit signal;
performing fast Fourier transform by using the signal without the system delay;
selecting signal phase change corresponding to the fast Fourier transform peak position;
extracting heartbeat signals by using a complementary set empirical mode decomposition method;
and (4) segmenting the heartbeat signal by using an expectation-maximization algorithm to obtain the heart rate and the heartbeat interval.
The frequency modulated continuous wave signal xtx(t) is described by the following formula 1:
Figure BDA0002825442640000021
wherein: t represents the time of signal generation, f0Representing the initial carrier frequency, f0>18 kHz; b represents the bandwidth of the frequency modulation band; t represents a frequency modulation period; a represents the frequency modulated signal strength.
Delay t in the virtual transmission signal elimination system delay algorithmwSaid t iswThe following were used:
Figure BDA0002825442640000022
wherein f isdRepresenting the frequency, t, of the mixing signaltRepresenting the true system delay.
And the complementary set empirical mode decomposition method extracts a heartbeat signal algorithm.
The expectation maximization heartbeat signal cutting algorithm uses a dynamic programming method to match and iteratively optimize a heartbeat segmentation template, and a heart rate and heartbeat interval is obtained.
According to the delay twCalculating a virtual transmit signal x'tx(t)，x′tx(t) is represented by the following formula:
Figure BDA0002825442640000031
compared with the prior art, the invention has the advantages that the sound box is utilized to send sound wave signals, and non-contact human heartbeat perception is realized by carrying out signal analysis and processing on echo waves. The principle is that a loudspeaker on a sound box emits a frequency modulation continuous wave signal, the signal is reflected back by a target human body and received by a microphone after reaching a target, and the received signal and the transmitted signal are subjected to frequency mixing operation and are processed by a low-pass filter. According to the mixing result, a virtual transmitting signal is designed and mixed with the receiving signal again to eliminate system delay, so that the target human body position is obtained. And extracting a signal at the position, extracting a heartbeat signal by using a complementary set empirical mode decomposition method, and then segmenting the heartbeat signal by using an expectation-maximization algorithm to obtain a heart rate and a heartbeat interval. The invention fully utilizes the widely used intelligent sound box equipment, does not need any special sensor, and can realize the household non-contact sensing application in a convenient mode. The invention has accurate perception capability on human breath and heartbeat detection, is easy to popularize and is suitable for the fields of intelligent home, intelligent old-age care and the like.
Drawings
FIG. 1 is a flow chart corresponding to the method of the present invention;
FIG. 2 shows the results of heartbeat segmentation;
FIG. 3 is a sensing device;
FIG. 4 is an electrocardiogram monitor;
fig. 5 is a non-contact heartbeat detection interface based on a smart speaker.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples.
As shown in FIG. 1, the method mainly comprises three steps of signal preprocessing, signal phase change extraction and heartbeat extraction. The first step, signal preprocessing, mainly including receiving signal band-pass filtering, signal mixing operation and eliminating system delay algorithm. And secondly, extracting signal phase change, which mainly comprises the steps of obtaining a target position through fast Fourier transform and extracting a waveform of the signal phase change. And thirdly, heartbeat extraction, which mainly comprises heartbeat signal separation, heartbeat waveform segmentation and acquisition of heart rate and heartbeat interval.
The individual steps of the system will be described in detail below.
The invention has the following implementation steps:
the first step is as follows: and (4) signal preprocessing. The Frequency Modulated Continuous Wave (FMCW) is adopted as a sending signal of the intelligent sound box and is marked as xtx(t), expressed as:
Figure BDA0002825442640000041
where t denotes the time of generation of the signal, [ phi ] (t) denotes the phase of the signal, [ A ] denotes the strength of the transmitted signal, f0The carrier frequency is represented by k, the chirp rate k is B/T, B represents the transmission signal bandwidth, and T represents the sweep period.
The system delay problem that exists among the intelligent audio amplifier is: the system delay exists in the loudspeaker hardware, so that the sequence of the direct path signal and the reflected path signal in the time domain is uncertain, the distance measurement error is caused, and the target cannot be positioned. In order to solve the above problem, we have devised a method for performing secondary signal mixing by a dummy transmission signal, by first performing a mixing operation on a reception signal and a transmission signal, and then passing the mixed signal through a low pass filter. Based on different system time delay amount, the energy ratio of direct path signal from the loudspeaker to the microphone is higher than that of reflected path from the chest of the human bodyThe path signal is much stronger and therefore the signal strength can be used to identify the direct path signal. Second, a frequency analysis is performed and the highest peak is selected. The delay of this highest peak is denoted tw. Constructing a virtual transmit signal, represented as:
Figure BDA0002825442640000042
where t denotes the time of generation of the signal, phi (t + t)w) Indicating the phase of the delayed signal, a indicating the strength of the transmitted signal, f0The carrier frequency is represented by k, the chirp rate k is B/T, B represents the transmission signal bandwidth, and T represents the sweep period.
Assuming that the distance between the target and the transceiver is R, the signal reaches the target and is reflected back to the receiver, and the received signal is delayed from the transmitted signal by
Figure BDA0002825442640000043
Of (c is the speed of light) expressed as:
Figure BDA0002825442640000044
wherein, A' represents the intensity of the received signal, and the other variables have the same meaning. Then, a second mixing operation is performed using the dummy transmission signal and the reception signal to obtain a mixed signal x'm(t) can be expressed as:
x′m(t)＝x′tx(t)·xrx(t)
the second step is that: and extracting the phase change of the signal. The twice mixed signal is passed through a low pass filter and a Fast Fourier Transform (FFT) operation is performed. If the FFT peak is at the start position, it indicates that the random time delay has been eliminated. If it occurs after the above operation, the direct-path signal is still not located at the start position. The original signal needs to be re-delayed by T-TwAnd T is the sweep period. After at most two steps of operation, the random system delay can be successfully eliminated and the direct path is solvedAnd the path reflection path reverses the sequence to locate the target position.
Suppose that the displacement of the human thorax due to breathing and heartbeat is Δ d, the mixed signal x'm(t) after passing through the low pass filter is expressed as:
Figure BDA0002825442640000045
where a' represents the strength of the received signal and R represents the distance of the target from the transceiving equipment. T represents the time of generation of the signal, A and A' represent the strength of the transmitted and received signals, respectively, f0Indicating carrier frequency, signal delay
Figure BDA0002825442640000051
k represents the chirp rate k ═ B/T, B represents the transmission signal bandwidth, and T represents the sweep period.
The above expression is decomposed into two terms, a first term ftIt can be used directly to calculate the distance, but since the heartbeat amplitude is much smaller than the frequency distance resolution, the heartbeat cannot be obtained directly by the first term. And the second term
Figure BDA0002825442640000052
Is the phase change of the mixing signal, which ranges from 0 to 2 pi]. A phase change of 2 pi corresponds to a distance change of 10.7 mm. Whereas the range of displacement of the thorax due to the heartbeat is 0.1mm-0.5 mm. Assuming that the heartbeat-induced thorax relief is 0.5mm, the corresponding phase change can be found as:
Figure BDA0002825442640000053
therefore, the heartbeat of the person is extracted by acquiring the phase of the signal.
The third step: heartbeat extraction: the different amplitudes and frequencies of human body movement are classified, the body movement can be mainly divided into four types, the heartbeat and the respiratory frequency are respectively [0.8-2Hz ] and [0.1-0.5Hz ], the slow movement frequency of the human body is [0.1-2Hz ], and the forward and backward inclination of the human body is mainly referred to. The frequency of the rapid movement of the human body is 0.5-5Hz, and mainly refers to the movement of some parts of the body, such as the shaking of hands or legs. It can be observed that the signal frequencies caused by the four types of motion overlap, so that simple band-pass filtering, i.e. a filter of a given frequency range, cannot filter out the interference signals caused by the respective components. Signal separation is performed by using a complementary set empirical mode decomposition method with adaptive noise.
Different types of sports Amplitude of Frequency of
Heartbeat movement 0.1-0.5mm 0.8-2Hz
Breathing exercise 1-12mm 0.1-0.5Hz
Body slow motion (forward/backward) Decimetre level 0.1-2Hz
Rapid body movement (hand/leg shaking) Centimeter level 0.5Hz-5Hz
Let x (t) be a signal superimposed by multiple motions of the human body, wherein the signal includes signal modes corresponding to different frequency components (respiration, heartbeat, other components, etc.), let Ci(t) is the ith modal component (IMF), n, obtained by complementary ensemble empirical mode decompositioni(t) is the I-th Gaussian white noise sequence signal, betaiTo control the noise figure ratio value. Let EkThe operation is to generate the kth mode by an Empirical Mode Decomposition (EMD) method, and the detailed steps of the heartbeat signal decomposition are as follows:
step 1: adding I-time white Gaussian noise to the heartbeat signal X (t) to be processed to construct a sequence Xi(t)＝x(t) + β0ni(t), I ═ 1, 2.., I, for each X using the EMD algorithmi(t) performing frequency decomposition until the 1 st IMF modal component can be decomposed, wherein the 1 st modal component is defined as:
Figure BDA0002825442640000054
step 2: in the first round (k ═ 1), the residual of the first modal component is calculated:
Figure BDA0002825442640000061
and step 3: at each i calculation, obtained by empirical mode decomposition, r1+β1E2(ni(t)), I ═ 1, 2., the first modal component of I, so that the 2 nd modal component of the original signal can be defined, the formula is as follows:
Figure BDA0002825442640000062
and 4, step 4: for K2, …, K, the residual of the K-th mode is calculated:
Figure BDA0002825442640000063
and 5: obtaining r by empirical mode decompositionk+βkEk(ni(t)), I ═ 1, 2.., the first modal component of I, while defining the (k + 1) th modal component, the formula is as follows:
Figure BDA0002825442640000064
step 6: and (5) making k equal to k +1, returning to the step (4) and continuing to execute until the residual of the last decomposition cannot be decomposed continuously. The final residual is:
Figure BDA0002825442640000065
k is also the number of modes of decomposition. Noise coefficient betak＝εkstd(rk) The selection of the signal-to-noise ratio (SNR) can be made at each stage. The method ensures the completeness of signal decomposition and provides a method for accurately reconstructing original data.
To obtain the heart beat interval, the present invention performs a heart beat dynamic segmentation using an expectation-maximization (EM) algorithm. The form of the heartbeat signal is considered to be repeated on the continuous waveform, the heartbeat interval time of the continuous heartbeat signal is dynamically adjusted, and a heartbeat segmentation template is matched and iteratively optimized by using a dynamic programming method. As shown in fig. 2, the segmentation results are plotted after using the EM algorithm. The results show that the segmented heart beat intervals are substantially consistent with the ECG, with an average deviation of only 0.05 seconds.
The embodiment of the invention adopts the non-contact heartbeat detection of a person in a lying or sitting posture. The system uses a commercial speaker (JBL Jembe, 6 watts, 80 db) and connects it to a notebook computer (MacBook Pro 2.6GHz, Intel Core i7, 16GB RAM) via a 3.5 mm audio interface (AUX), as in fig. 3. The speaker is used for sending voice signals, the notebook computer with the built-in microphone is used for receiving the signals, and the transceiver is placed at a position 60 cm away from a user. The sound box continuously sends frequency modulation continuous wave signals (the signal parameter is f)016kHz, B5 kHz, and T0.02 s), the notebook computer receives and processes signals in real time to monitor the heartbeat of the target human body with a sampling rate of 48 kHz. Adopts a 3-lead electrocardiogram monitor H as shown in figure 4The eal Force PC-80B measures the user's true electrocardiographic data and is used to calculate heart rate and heart beat interval. The processing of the steps 1 to 6 is carried out, the processing result is displayed on a front-end interface developed based on Web, as shown in figure 5, the interface displays the waveform and the frequency (times/minute) of the extracted respiration and heartbeat signals by using the method of the invention, the test scene is displayed on the upper right of the interface, and the true value of the heartbeat measured by an electrocardiograph is displayed on the lower right of the interface.
The above examples are provided only for the purpose of describing the present invention, and are not intended to limit the scope of the present invention. The scope of the invention is defined by the appended claims. Various equivalent substitutions and modifications can be made without departing from the spirit and principles of the invention, and are intended to be within the scope of the invention.

Claims (4)

1. A non-contact heartbeat detection method based on an intelligent sound box is characterized by comprising the following steps:
sending a frequency modulation continuous wave signal by using an intelligent sound box and receiving by using a microphone;
carrying out band-pass filtering on the received signal to filter noise outside a required range;
performing a mixing operation on the transmission signal and the filtered reception signal;
eliminating system delay by performing spectral analysis on the mixed signal and using the proposed virtual transmit signal;
performing fast Fourier transform by using the signal without the system delay;
selecting signal phase change corresponding to the fast Fourier transform peak position;
extracting heartbeat signals by using a complementary set empirical mode decomposition method;
segmenting the heartbeat signal by using an expectation maximization algorithm to obtain a heart rate and a heartbeat interval;
delay t in the virtual transmission signal elimination system delay algorithmwThe calculation is as follows:
Figure DEST_PATH_IMAGE002
wherein f isdRepresenting the frequency, t, of the mixing signaltRepresenting the real system delay, T representing the frequency modulation period, and B representing the frequency modulation bandwidth;
according to said delay twCalculating a virtual transmit signal x'tx(t)，x′tx(t) is represented by the following formula:
Figure DEST_PATH_IMAGE004
t represents the time of signal generation and a represents the frequency modulated signal strength.
2. The non-contact heartbeat detection method based on the smart sound box according to claim 1, characterized in that: the frequency modulated continuous wave signal xtx(t) is described by the following formula:
Figure 913128DEST_PATH_IMAGE002
wherein: t represents the time of signal generation, f0Representing the initial carrier frequency, f0>18 kHz; b represents the bandwidth of the frequency modulation band; t represents a frequency modulation period; a represents the frequency modulated signal strength.
3. The non-contact heartbeat detection method based on the smart sound box according to claim 1, characterized in that: and the complementary set empirical mode decomposition method extracts a heartbeat signal algorithm.
4. The non-contact heartbeat detection method based on the smart sound box according to claim 1, characterized in that: the expectation maximization heartbeat signal cutting algorithm uses a dynamic programming method to match and iteratively optimize a heartbeat segmentation template, and a heart rate and heartbeat interval is obtained.
CN202011427197.9A 2020-12-09 2020-12-09 Non-contact heartbeat detection method based on intelligent sound box Active CN112450900B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011427197.9A CN112450900B (en) 2020-12-09 2020-12-09 Non-contact heartbeat detection method based on intelligent sound box

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011427197.9A CN112450900B (en) 2020-12-09 2020-12-09 Non-contact heartbeat detection method based on intelligent sound box

Publications (2)

Publication Number Publication Date
CN112450900A CN112450900A (en) 2021-03-09
CN112450900B true CN112450900B (en) 2021-10-01

Family

ID=74800343

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011427197.9A Active CN112450900B (en) 2020-12-09 2020-12-09 Non-contact heartbeat detection method based on intelligent sound box

Country Status (1)

Country Link
CN (1) CN112450900B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113842123B (en) * 2021-09-26 2023-05-26 中国科学院软件研究所 Non-contact heartbeat detection method and system based on microphone array
CN114469178A (en) * 2022-02-25 2022-05-13 大连理工大学 Blink detection method based on sound wave signals and applicable to smart phone

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108113706A (en) * 2017-12-19 2018-06-05 清华大学无锡应用技术研究院 A kind of rhythm of the heart method, apparatus and system based on audio signal
CN110327029A (en) * 2019-07-03 2019-10-15 上海交通大学 A kind of heart rate and heart rate variability monitoring method based on microwave perception
CN111568399A (en) * 2020-05-15 2020-08-25 中国人民解放军陆军军医大学 Radar-based respiration and heartbeat signal detection method and system
WO2021001818A1 (en) * 2019-07-01 2021-01-07 Omer Eshet Contact-free acoustic monitoring and measurement system

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11051702B2 (en) * 2014-10-08 2021-07-06 University Of Florida Research Foundation, Inc. Method and apparatus for non-contact fast vital sign acquisition based on radar signal
CN104434059A (en) * 2014-10-29 2015-03-25 上海无线电设备研究所 Method for detecting vital signs in non-contact mode by terahertz waves
US11234675B2 (en) * 2016-03-28 2022-02-01 Robert Bosch Gmbh Sonar-based contactless vital and environmental monitoring system and method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108113706A (en) * 2017-12-19 2018-06-05 清华大学无锡应用技术研究院 A kind of rhythm of the heart method, apparatus and system based on audio signal
WO2021001818A1 (en) * 2019-07-01 2021-01-07 Omer Eshet Contact-free acoustic monitoring and measurement system
CN110327029A (en) * 2019-07-03 2019-10-15 上海交通大学 A kind of heart rate and heart rate variability monitoring method based on microwave perception
CN111568399A (en) * 2020-05-15 2020-08-25 中国人民解放军陆军军医大学 Radar-based respiration and heartbeat signal detection method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
《Acousticcardiogram: Monitoring Heartbeats using Acoustic Signals on Smart Devices》;Kun Qian et al.;《IEEE INFOCOM 2018》;20181011;全文 *
《面向健康的非干预式体征感知关键技术研究》;王天本;《中国博士学位论文全文数据库工程科技Ⅱ辑》;20200215;全文 *

Also Published As

Publication number Publication date
CN112450900A (en) 2021-03-09

Similar Documents

Publication Publication Date Title
JP6386327B2 (en) Cardiopulmonary parameter monitoring apparatus and cardiopulmonary parameter monitoring system
Zhang et al. Your Smart Speaker Can" Hear" Your Heartbeat!
US20100249630A1 (en) Systems and methods for respiratory rate measurement
CN112450900B (en) Non-contact heartbeat detection method based on intelligent sound box
CN108577815A (en) A kind of assay method of human body respiration rate and heart rate based on ULTRA-WIDEBAND RADAR
US11311202B2 (en) Robust real-time heart rate monitoring method based on heartbeat harmonics using small-scale radar
Shi et al. Neural network based real-time heart sound monitor using a wireless wearable wrist sensor
Rong et al. Is radar cardiography (rcg) possible?
CN111685760B (en) Human body respiratory frequency calculation method based on radar measurement
Murshed et al. A CNN based multifaceted signal processing framework for heart rate proctoring using millimeter wave radar ballistocardiography
Rong Remote sensing for vital signs monitoring using advanced radar signal processing techniques
Chourasia et al. Wireless data acquisition system for fetal phonocardiographic signals using BluetoothTM
WO2018032610A1 (en) Heart rate measurement device and method
Kew et al. Wearable patch-type ECG using ubiquitous wireless sensor network for healthcare monitoring application
Zhao et al. T-HSER: Transformer Network Enabling Heart Sound Envelope Signal Reconstruction Based on Low Sampling Rate Millimeter Wave Radar
Gao et al. A new direction for biosensing: RF sensors for monitoring cardio-pulmonary function
Pham et al. Noncontact detection of cardiopulmonary activities of trapped humans in rescue relief events
Wang et al. Exploiting Passive Beamforming of Smart Speakers to Monitor Human Heartbeat in Real Time
Pan et al. A spectrum estimation approach for accurate heartbeat detection using Doppler radar based on combination of FTPR and TWV
Obeid et al. Touch-less heartbeat detection and measurement-based cardiopulmonary modeling
Erdoğan et al. Microwave noncontact vital sign measurements for medical applications
Walid et al. Accuracy assessment and improvement of FMCW radar-based vital signs monitoring under Practical Scenarios
Qiao et al. Spectral Unmixing Successive Variational Mode Decomposition for Robust Vital Signs Detection Using UWB Radar
Walid Accuracy Assessment and Improvement of FMCW Radar-based Vital Signs Monitoring under Practical Scenarios
Pan Vital signs monitoring based on UWB radar

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant