CN117064349B - Gesture control method and system for linkage of millimeter wave radar and intelligent bed - Google Patents

Gesture control method and system for linkage of millimeter wave radar and intelligent bed Download PDF

Info

Publication number
CN117064349B
CN117064349B CN202311036633.3A CN202311036633A CN117064349B CN 117064349 B CN117064349 B CN 117064349B CN 202311036633 A CN202311036633 A CN 202311036633A CN 117064349 B CN117064349 B CN 117064349B
Authority
CN
China
Prior art keywords
information
heartbeat
target object
respiration
breathing
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
CN202311036633.3A
Other languages
Chinese (zh)
Other versions
CN117064349A (en
Inventor
杨绍分
袁文忠
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.)
Dexin Intelligent Technology Changzhou Co ltd
Original Assignee
Dexin Intelligent Technology Changzhou Co ltd
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 Dexin Intelligent Technology Changzhou Co ltd filed Critical Dexin Intelligent Technology Changzhou Co ltd
Priority to CN202311036633.3A priority Critical patent/CN117064349B/en
Publication of CN117064349A publication Critical patent/CN117064349A/en
Application granted granted Critical
Publication of CN117064349B publication Critical patent/CN117064349B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47C—CHAIRS; SOFAS; BEDS
    • A47C31/00—Details or accessories for chairs, beds, or the like, not provided for in other groups of this subclass, e.g. upholstery fasteners, mattress protectors, stretching devices for mattress nets
    • A47C31/12—Means, e.g. measuring means for adapting chairs, beds or mattresses to the shape or weight of persons
    • A47C31/123—Means, e.g. measuring means for adapting chairs, beds or mattresses to the shape or weight of persons for beds or mattresses
    • 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 
    • 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
    • A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
    • A61B5/0826—Detecting or evaluating apnoea events
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1116—Determining posture transitions
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1118—Determining activity level
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
    • 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
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4818—Sleep apnoea
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
    • A61B5/6891—Furniture
    • 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
    • A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
    • 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
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/7465—Arrangements for interactive communication between patient and care services, e.g. by using a telephone network
    • A61B5/747—Arrangements for interactive communication between patient and care services, e.g. by using a telephone network in case of emergency, i.e. alerting emergency services
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F5/00—Orthopaedic methods or devices for non-surgical treatment of bones or joints; Nursing devices; Anti-rape devices
    • A61F5/56—Devices for preventing snoring

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Surgery (AREA)
  • Pathology (AREA)
  • Biophysics (AREA)
  • Physiology (AREA)
  • Pulmonology (AREA)
  • Cardiology (AREA)
  • Artificial Intelligence (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Dentistry (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Nursing (AREA)
  • Critical Care (AREA)
  • Mathematical Physics (AREA)
  • Business, Economics & Management (AREA)
  • Fuzzy Systems (AREA)
  • Emergency Management (AREA)
  • Emergency Medicine (AREA)
  • Evolutionary Computation (AREA)
  • Otolaryngology (AREA)
  • Orthopedic Medicine & Surgery (AREA)
  • Vascular Medicine (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention provides a gesture control method and a gesture control system for linkage of a millimeter wave radar and an intelligent bed, which relate to millimeter wave radar technology and comprise the steps of acquiring echo information of the millimeter wave radar reflected by a target object on the intelligent bed, performing filtering processing on the echo information, and performing phase expansion on the filtered echo information to acquire target phase information of the target object; extracting heartbeat information and breathing information of the target object from the target phase information, and respectively extracting heartbeat characteristics from the heartbeat information and breathing characteristics from the breathing information by combining an adaptive filter with an adaptive signal processing method; and determining the sleep sign state of the target object based on a pre-constructed behavior classifier according to the heartbeat characteristic and the breathing characteristic, and controlling the intelligent bed to make corresponding actions by combining with a pre-determined sign gesture control corresponding relation.

Description

Gesture control method and system for linkage of millimeter wave radar and intelligent bed
Technical Field
The invention relates to millimeter wave radar technology, in particular to a method and a system for controlling the gesture of linkage of a millimeter wave radar and an intelligent bed.
Background
Sleep occupies most of the day for everyone, and high quality sleep has vital significance for physical health and daily life work. For the old people with the heart diseases, more and more old people select home-based or community-based old people, and for the old people living alone, the old people are not supervised at night in a sleeping state. In recent years, various diseases gradually show a trend of 'low age', and the more cases of sudden death caused by sudden abnormality of heart during night sleep are seen in young groups due to high-intensity work. The detection of the respiration, heart rate and abnormal physiological state of the human body in the sleeping process can provide important basis for the prevention of diseases and the evaluation of sleeping quality, so that how to effectively and accurately acquire the physiological parameters of the sleeping of the human body becomes a current research hot spot.
In the prior art, the accurate sleep related characteristic parameters cannot be obtained, or the parameters are simply obtained, so that the sleep quality cannot be interfered or the sleep quality of the target object cannot be improved.
Disclosure of Invention
The embodiment of the invention provides a gesture control method and a gesture control system for linkage of a millimeter wave radar and an intelligent bed, which at least can solve partial problems in the prior art, namely, the problems that in the prior art, either accurate sleep related characteristic parameters cannot be obtained or parameters are simply obtained, and sleep quality cannot be interfered or the sleep quality of a target object cannot be improved.
In a first aspect of an embodiment of the present invention,
the gesture control method for linkage of the millimeter wave radar and the intelligent bed comprises the following steps:
acquiring echo information of a millimeter wave radar reflected by a target object on an intelligent bed, performing filtering processing on the echo information, and performing phase unwrapping on the filtered echo information to acquire target phase information of the target object;
extracting heartbeat information and breathing information of the target object from the target phase information, and respectively extracting heartbeat characteristics from the heartbeat information and breathing characteristics from the breathing information by combining an adaptive filter with an adaptive signal processing method;
and determining the sleep sign state of the target object based on a pre-constructed behavior classifier according to the heartbeat characteristic and the breathing characteristic, and controlling the intelligent bed to make corresponding actions by combining with a pre-determined sign gesture control corresponding relation.
In an alternative embodiment of the present invention,
acquiring echo information of a millimeter wave radar reflected by a target object on an intelligent bed, performing filtering processing on the echo information, and performing phase unwrapping on the filtered echo information, wherein acquiring target phase information of the target object comprises:
and determining the phase angle of the echo information after the filtering processing by using a differential cross multiplication algorithm, performing phase unwrapping processing on the phase angle, and performing first-order differential processing on the echo information after the phase unwrapping processing to obtain target phase information of the target object.
In an alternative embodiment of the present invention,
extracting heartbeat features from the heartbeat information and extracting respiration features from the respiration information by an adaptive filter in combination with an adaptive signal processing method respectively comprises:
for each time step corresponding to the heartbeat information and the respiration information, carrying out dot multiplication on each weight of the adaptive filter and the heartbeat information and the respiration information of each time step, and adding dot multiplication results to obtain heartbeat filtering information corresponding to the heartbeat information and respiration filtering information corresponding to the respiration information respectively;
carrying out frequency domain analysis on the self-adaptive filtered signal, determining a heartbeat frequency component corresponding to the heartbeat filtering information and a respiratory frequency component corresponding to the respiratory filtering information, and determining a heartbeat peak value position and a respiratory peak value through a peak value detection algorithm;
calculating a heartbeat interval according to the heartbeat peak position respectively, and determining heartbeat characteristics; and calculating a respiration interval according to the respiration peak position, and determining a respiration characteristic.
In an alternative embodiment of the present invention,
the method further comprises the steps of:
for each time step corresponding to the heartbeat information and the respiration information, carrying out dot multiplication on each weight of the adaptive filter and the heartbeat information and the respiration information of each time step, and adding dot multiplication results to obtain heartbeat filtering information corresponding to the heartbeat information and respiration filtering information corresponding to the respiration information respectively;
determining heartbeat error information according to the heartbeat filtering information and the heartbeat information, determining breathing error information according to the breathing filtering information and the breathing information, and further determining a heartbeat covariance matrix corresponding to the heartbeat error information and a breathing covariance matrix corresponding to the breathing error information;
determining a heartbeat gain vector according to the heartbeat covariance matrix and the heartbeat information, and determining a respiration gain vector according to the respiration covariance matrix and the respiration information;
and integrating the heartbeat gain vector and the breathing gain vector to update the weight of the adaptive filter.
In an alternative embodiment of the present invention,
the method further includes training the behavior classifier:
based on a pre-acquired training data set, wherein the training data set comprises multi-category sample data, determining an initial category center of each category of the training data set, and calculating the spatial distance and the inter-category variance of any two categories of the training data set;
determining the inter-class distance of any two classes according to the space distance and the inter-class variance, taking the two classes with the largest inter-class distance as a reference class, respectively converging samples of the rest classes to the reference class according to the principle of closest inter-class distance, and then recalculating the updated class centers of the new classes after converging;
and recursively updating all the class samples of the training data set until all the class samples are distributed, and finishing training the behavior classifier.
In an alternative embodiment of the present invention,
controlling the intelligent bed to make corresponding actions by combining the predetermined physical sign gesture control corresponding relation comprises:
if the sleep sign state of the target object is a first sign state, wherein the first sign state is that the body of the target object exceeds a preset angle threshold value relative to the body of the intelligent bed, the intelligent bed is controlled to incline at a small angle towards the reverse body overturning direction of the target object;
if the sleep sign state of the target object is a second sign state, wherein the second sign state is the target object apnea, controlling the intelligent bed to adjust the heights of the head and the legs of the target object, and promoting oxygen circulation;
and if the sleep sign state of the target object is a third sign state, wherein the third sign state is that the respiratory frequency and the heartbeat frequency of the target object exceed a preset frequency threshold, controlling the intelligent bed to adjust the head height of the target object and promoting oxygen circulation.
In a second aspect of an embodiment of the present invention,
provided is a attitude control system of millimeter wave radar and intelligent bed linkage, including:
the first unit is used for acquiring echo information of the millimeter wave radar reflected by the target object on the intelligent bed, performing filtering processing on the echo information, and performing phase expansion on the filtered echo information to acquire target phase information of the target object;
a second unit, configured to extract heartbeat information and respiration information of the target object from the target phase information, and extract heartbeat features from the heartbeat information and extract respiration features from the respiration information respectively by combining an adaptive filter with an adaptive signal processing method;
and the third unit is used for determining the sleep sign state of the target object based on a pre-constructed behavior classifier according to the heartbeat characteristic and the breathing characteristic, and controlling the intelligent bed to make corresponding actions by combining with the pre-determined sign gesture control corresponding relation.
In a third aspect of an embodiment of the present invention,
there is provided an electronic device including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method described previously.
In a fourth aspect of an embodiment of the present invention,
there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method as described above.
Millimeter wave radar is a technology for detecting a target object by transmitting and receiving microwave signals, and has a wide application prospect in the aspects of human body recognition, motion tracking and gesture detection; the intelligent bed is a bed integrated with a sensor and a control system, and can monitor the position, the posture, the movement and other information of a human body on the bed in real time. With millimeter wave radar and intelligent bed linkage, can realize more accurate gesture control and motion monitoring, through millimeter wave radar, can acquire the position and the gesture information of human body on the bed in real time, and intelligent bed then can carry out instantaneous adjustment and control according to these information to provide more comfortable sleep experience.
Drawings
FIG. 1 is a schematic flow chart of a method for controlling the posture of a millimeter wave radar and an intelligent bed in a linkage manner according to an embodiment of the invention;
fig. 2 is a schematic structural diagram of an attitude control system of a millimeter wave radar and an intelligent bed in accordance with an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Fig. 1 is a schematic flow chart of a gesture control method of linkage of a millimeter wave radar and an intelligent bed according to an embodiment of the present invention, as shown in fig. 1, the method includes:
s101, acquiring echo information of a millimeter wave radar reflected by a target object on an intelligent bed, performing filtering processing on the echo information, and performing phase unwrapping on the filtered echo information to acquire target phase information of the target object;
the vital sign detection method based on the radar mainly realizes the extraction of respiration and heartbeat signals by detecting the chest cavity movement, and echo phase information changes are caused by the changes of chest cavity positions caused by the heartbeat and the respiration. The working frequency of the frequency modulation continuous wave radar used for non-contact vital sign detection is generally between the millimeter wave and millimeter wave bands. Because the distance change caused by the chest cavity movement is very tiny, the phase shift caused by the signals with higher frequency ranges under the condition of the same distance change is larger, and the detection of vital sign information is more sensitive and accurate.
Information extraction for vital sign signals appears in the time domain to separate the respiratory and heartbeat signals. The main basis of separation is that the frequency of respiration and heartbeat signals are different, and in the recovery of time waveform, the heartbeat signal at breath holding position is known to be an impact signal which contains abundant harmonic waves, so that the fundamental frequency component is mainly extracted in the extraction of heartbeat information. The respiratory signal is easy to extract due to the large amplitude, but because the respiratory signal is not a single frequency component, the higher harmonic wave of the respiratory signal can fall into the frequency band of the heartbeat signal, so that interference is caused. The separation of vital signals therefore also requires a reduction of the effects of respiratory harmonics.
In an alternative embodiment of the present invention,
acquiring echo information of a millimeter wave radar reflected by a target object on an intelligent bed, performing filtering processing on the echo information, and performing phase unwrapping on the filtered echo information, wherein acquiring target phase information of the target object comprises:
and determining the phase angle of the echo information after the filtering processing by using a differential cross multiplication algorithm, performing phase unwrapping processing on the phase angle, and performing first-order differential processing on the echo information after the phase unwrapping processing to obtain target phase information of the target object.
Illustratively, millimeter wave radar vital sign detection mainly measures chest cavity motion of a human body, unlike doppler radar, which couples together with distance of a target, and requires preprocessing of signals before obtaining phase information to obtain distance of the target. The angle of the target is also required to be obtained when using the multiple-input multiple-output system so as to accurately accumulate the data of each antenna. At the same time, echo signals of stationary objects and noise interference are present in the actual scene, which can cause errors in the target detection.
The phase unwrapping can be performed on the filtered signal to solve the phase ambiguity problem. The phase unwrapping may use a fourier transform or other phase recovery algorithm to obtain phase information that is not properly represented. The embodiment of the application performs phase unwrapping through a differential cross multiplication algorithm.
Further, the phase angle is subjected to phase unwrapping treatment so as to solve the phase jump problem and ensure the continuity of the phase angle. Phase unwrapping may use some phase difference based algorithm, such as an unwrapping algorithm or fusing other sensor data to assist in unwrapping. The unwrapped phase information is first-order differenced to obtain target phase information of the target object, which facilitates extraction of motion or other dynamic information of the target object.
Optionally, phase information is extracted from the filtered signal. The phase angle can be calculated using an atan2 function, dividing the signal into a real part and an imaginary part, and then using an arctangent function, the phase angle obtained in this step typically being a jump comprising the phase. And calculating the phase difference of two adjacent sampling points by using a difference method, namely, carrying out difference operation on each phase angle to obtain the phase difference between the two adjacent sampling points.
Performing unwrapping operation on the calculated differential phase to ensure phase continuity, which is to solve the phase jump problem; the calculated unwrapped phase difference is multiplied by the complex conjugate of the filtered echo signal, which process re-introduces the phase difference into the signal to recover the correct phase. And using an arctangent function to the cross multiplication result to obtain a corrected phase angle.
The differential phase is unwrapped to ensure phase angle continuity. The goal of phase unwrapping is to reduce the periodic jump in phase angle, keeping the phase angle stationary. The method of unwrapping may be based on some algorithm, such as global minimization or fusion of other sensor data to solve the phase jump problem. One common unwrapping method is to iteratively adjust the differential phase to ensure that it is within a continuous range.
And performing first-order difference processing on the unwrapped phase information. The first order difference calculates the phase difference between two adjacent time points, and then divides the phase difference by the time interval to obtain the change rate of the phase. This can be used to calculate the characteristics of the target object's movement speed, heart rate, etc.
S102, extracting heartbeat information and breathing information of the target object from the target phase information, and respectively extracting heartbeat characteristics from the heartbeat information and breathing characteristics from the breathing information by combining an adaptive filter with an adaptive signal processing method;
illustratively, phase information of a target object is analyzed from echo signals of the millimeter wave radar, and phase unwrapping and unwrapping are performed through algorithms such as differential cross multiplication and the like to obtain phase angle information of the target; the heartbeat signal can be extracted from the target phase information by utilizing the tiny displacement caused by the beating of the heart; respiratory signals can be extracted from the phase information using phase changes caused by respiratory motion of the chest.
Adaptive filters are designed for the heartbeat and respiratory signals, respectively. Setting parameters of a filter according to the frequency characteristics of the heartbeat and respiratory signals; the target phase information is input to an adaptive filter, noise is attenuated by the filtering operation, and useful heartbeat and respiration signals are retained.
The target phase information is extracted through the millimeter wave radar, so that the heartbeat and respiratory signals of a target object can be accurately monitored in real time, the mode that the traditional sensor patch and the like need to be in direct contact with the skin is avoided, and more comfortable experience is provided; the self-adaptive filter is used for processing the heartbeat and respiratory signals, so that noise and interference can be effectively restrained, and the signal quality is improved, thereby extracting more accurate heartbeat and respiratory characteristics.
In an alternative embodiment of the present invention,
detecting periodic changes in the phase information using phase changes caused by respiratory motion of the chest; spectral analysis methods (such as fast fourier transforms) can be used to detect the major respiratory frequency components; extracting phase change information of the breathing signals, and obtaining continuous breathing phase information by using modes such as differential phase and the like; calculating respiratory rate and respiratory period by detecting periodic changes in respiratory phase; accordingly, the heart rate and the heart cycle can be calculated as well.
In an alternative embodiment of the present invention,
extracting heartbeat features from the heartbeat information and extracting respiration features from the respiration information by an adaptive filter in combination with an adaptive signal processing method respectively comprises:
for each time step corresponding to the heartbeat information and the respiration information, carrying out dot multiplication on each weight of the adaptive filter and the heartbeat information and the respiration information of each time step, and adding dot multiplication results to obtain heartbeat filtering information corresponding to the heartbeat information and respiration filtering information corresponding to the respiration information respectively;
carrying out frequency domain analysis on the self-adaptive filtered signal, determining a heartbeat frequency component corresponding to the heartbeat filtering information and a respiratory frequency component corresponding to the respiratory filtering information, and determining a heartbeat peak value position and a respiratory peak value through a peak value detection algorithm;
calculating a heartbeat interval according to the heartbeat peak position respectively, and determining heartbeat characteristics; and calculating a respiration interval according to the respiration peak position, and determining a respiration characteristic.
Traversing each time step aiming at the heartbeat and respiratory signal data, and performing dot multiplication and addition operation to obtain filtered heartbeat and respiratory information; the filtered signal is subjected to frequency domain analysis, such as using FFT, to obtain the heartbeat and respiratory frequency components. The peak detection algorithm can determine the peak highest point in a certain time step range in the heartbeat frequency component, and the peak highest point is taken as the heartbeat peak position, and similarly, the respiration peak position can be confirmed.
After the peak position is obtained, determining a heartbeat interval according to the left time step and the right time step which are closest to the peak position, wherein the heartbeat interval can comprise a heartbeat frequency as a heartbeat characteristic; similarly, breathing characteristics may be determined.
In an alternative embodiment of the present invention,
the method further comprises the steps of:
for each time step corresponding to the heartbeat information and the respiration information, carrying out dot multiplication on each weight of the adaptive filter and the heartbeat information and the respiration information of each time step, and adding dot multiplication results to obtain heartbeat filtering information corresponding to the heartbeat information and respiration filtering information corresponding to the respiration information respectively;
determining heartbeat error information according to the heartbeat filtering information and the heartbeat information, determining breathing error information according to the breathing filtering information and the breathing information, and further determining a heartbeat covariance matrix corresponding to the heartbeat error information and a breathing covariance matrix corresponding to the breathing error information;
determining a heartbeat gain vector according to the heartbeat covariance matrix and the heartbeat information, and determining a respiration gain vector according to the respiration covariance matrix and the respiration information;
and integrating the heartbeat gain vector and the breathing gain vector to update the weight of the adaptive filter.
In practical application, the weight of the adaptive filter can distinguish the importance degree of the input information, and can effectively screen out the wanted characteristics, so the distribution of the weight value is particularly important, and therefore, the weight of the adaptive filter can be updated, and specifically:
the weights of the self-adaptive filter can be subjected to dot multiplication with the heartbeat information and the breathing information of each time step, and dot multiplication results are added to obtain heartbeat filtering information corresponding to the heartbeat information and breathing filtering information corresponding to the breathing information respectively;
and determining heartbeat error information according to the heartbeat filtering information and the heartbeat information, and determining respiratory error information according to the respiratory filtering information and the respiratory information, wherein the error information can be a phase difference between the two, and can also comprise an amplitude value and a frequency difference value, and the application is not limited herein.
Further, a heartbeat gain vector may be determined from the heartbeat covariance matrix and the heartbeat information, and a respiration gain vector may be determined from the respiration covariance matrix and the respiration information, wherein the gain vector is a key element in adaptive filtering, and represents how to multiply a current input signal with a weight vector to perform prediction. In the case of heartbeat and respiration signals, the gain vector determines how the filter is applied to the input signal to obtain the predicted heartbeat and respiration signal.
The calculation of the gain vector is based on the information of the current prediction error and the covariance matrix so as to realize the purpose of dynamically adjusting the weight vector, and the updating of the gain vector enables the filter to adapt to the change of the input signal, thereby realizing the effective extraction of the heartbeat and respiratory signals. The method for determining the gain vector in the embodiment of the present application may refer to an existing recursive least square algorithm, which is not limited in the embodiment of the present application.
And linearly combining the heartbeat gain vector and the respiratory gain vector according to a certain weight to obtain a comprehensive gain vector. The choice of weights can be adjusted according to specific needs to achieve a better balance in the extraction of the heartbeat and respiration signals. The updating method can be shown in the following formula:
new weight vector = old weight vector + composite gain vector [ heartbeat error information, respiratory error information ].
The weight of the self-adaptive filter is multiplied by and added with the heartbeat and respiration information to obtain heartbeat filtering information and respiration filtering information, so that noise and interference are further reduced, and the accuracy of signals is improved; the heartbeat and respiratory gain vectors are determined according to the heartbeat and respiratory covariance matrix, so that the weight of the self-adaptive filter can be dynamically adjusted according to the characteristics of signals, and the self-adaptive filter is suitable for different situations; the heart beat and the respiratory gain vector are synthesized, the weight of the adaptive filter is updated, the performance of the filter can be continuously stabilized, and the signal stability is improved.
S103, determining the sleep sign state of the target object based on a pre-constructed behavior classifier according to the heartbeat characteristic and the breathing characteristic, and controlling the intelligent bed to make corresponding actions by combining with a pre-determined sign gesture control corresponding relation.
In an alternative embodiment of the present invention,
the method further includes training the behavior classifier:
based on a pre-acquired training data set, wherein the training data set comprises multi-category sample data, determining an initial category center of each category of the training data set, and calculating the spatial distance and the inter-category variance of any two categories of the training data set;
determining the inter-class distance of any two classes according to the space distance and the inter-class variance, taking the two classes with the largest inter-class distance as a reference class, respectively converging samples of the rest classes to the reference class according to the principle of closest inter-class distance, and then recalculating the updated class centers of the new classes after converging;
and recursively updating all the class samples of the training data set until all the class samples are distributed, and finishing training the behavior classifier.
Illustratively, the behavior classifier of the present application is built based on a combination of decision trees and support vector machines, and for each class, an initial class center may be determined by calculating a feature mean of the class sample. Assuming that the number of categories of training data sets is C,
the initial category center for each category may be expressed as follows:
；
wherein the number of kindsEach type of sample is，/>For the number of samples of each type;
euclidean distance between any two types of samples:
；
the inter-class variance of a sample can be expressed as:
；
the inter-class distance can be expressed as follows:
；
in practical application, the class center of each class sample can be calculated first, and two classes with the largest distance between classes can be found; then, the samples of the remaining classes are respectively drawn close to the two classes according to the principle of nearest inter-class distance, and the class center is recalculated until all the classes are divided into two class clusters; and finally, recursively repeating the operation on each class cluster until all the classes are distributed to be leaf nodes, and completing the training of the behavior classifier.
In an alternative embodiment of the present invention,
controlling the intelligent bed to make corresponding actions by combining the predetermined physical sign gesture control corresponding relation comprises:
if the sleep sign state of the target object is a first sign state, wherein the first sign state is that the body of the target object exceeds a preset angle threshold value relative to the body of the intelligent bed, the intelligent bed is controlled to incline at a small angle towards the reverse body overturning direction of the target object;
if the sleep sign state of the target object is a second sign state, wherein the second sign state is the target object apnea, controlling the intelligent bed to adjust the heights of the head and the legs of the target object, and promoting oxygen circulation;
and if the sleep sign state of the target object is a third sign state, wherein the third sign state is that the respiratory frequency and the heartbeat frequency of the target object exceed a preset frequency threshold, controlling the intelligent bed to adjust the head height of the target object and promoting oxygen circulation.
Illustratively, the smart bed of the present application may include an adjustable motor, support structure and sensors, and a control unit, wherein the control unit may analyze data transmitted from the radar module and determine how to adjust the attitude of the bed; the smart bed may also include a user interface allowing a user to customize settings such as sensitivity, type of reaction;
millimeter wave radar continuously monitors minute movements generated on the human body, in particular, up-and-down movements (respiration) of the chest and abdomen and minute muscle twitches (heart beats); after the control unit collects the data, the breathing and heartbeat modes of the user are identified; in addition, other irregular movements, such as snoring, may be detected; normal breathing, rapid breathing, slow breathing and the like can be distinguished, and whether apnea occurs or not is detected;
if snoring is detected, the bedframe may slightly adjust the height of the head to open the airway and reduce or eliminate snoring; if an apnea or dyspnea is detected, the bed frame may raise the user's head and legs slightly to promote better oxygen flow; the user can set his own preferences through the interface, for example adjusting the reaction speed, sensitivity of the bed or selecting different reaction modes; the user can also check the sleep data of the user to know the breathing quality, snoring frequency and the like; if the system continuously detects an apnea or other serious problem, an alert may be issued or emergency contacts may be dialed directly through the connected smart home system.
In a second aspect of an embodiment of the present invention,
fig. 2 is a schematic structural diagram of a gesture control system of linkage of a millimeter wave radar and an intelligent bed according to an embodiment of the present invention, including:
the first unit is used for acquiring echo information of the millimeter wave radar reflected by the target object on the intelligent bed, performing filtering processing on the echo information, and performing phase expansion on the filtered echo information to acquire target phase information of the target object;
a second unit, configured to extract heartbeat information and respiration information of the target object from the target phase information, and extract heartbeat features from the heartbeat information and extract respiration features from the respiration information respectively by combining an adaptive filter with an adaptive signal processing method;
and the third unit is used for determining the sleep sign state of the target object based on a pre-constructed behavior classifier according to the heartbeat characteristic and the breathing characteristic, and controlling the intelligent bed to make corresponding actions by combining with the pre-determined sign gesture control corresponding relation.
In a third aspect of an embodiment of the present invention,
there is provided an electronic device including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method described previously.
In a fourth aspect of an embodiment of the present invention,
there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method as described above.
The present invention may be a method, apparatus, system, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for performing various aspects of the present invention.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims (8)

1. The gesture control method for linkage of the millimeter wave radar and the intelligent bed is characterized by comprising the following steps of:
acquiring echo information of a millimeter wave radar reflected by a target object on an intelligent bed, performing filtering processing on the echo information, and performing phase unwrapping on the filtered echo information to acquire target phase information of the target object;
extracting heartbeat information and breathing information of the target object from the target phase information, and respectively extracting heartbeat characteristics from the heartbeat information and breathing characteristics from the breathing information by combining an adaptive filter with an adaptive signal processing method;
determining the sleep sign state of the target object based on a pre-constructed behavior classifier according to the heartbeat characteristic and the breathing characteristic, and controlling a corresponding relation by combining with a pre-determined sign gesture to control an intelligent bed to make a corresponding action;
the method further comprises the steps of:
for each time step corresponding to the heartbeat information and the respiration information, carrying out dot multiplication on each weight of the adaptive filter and the heartbeat information and the respiration information of each time step, and adding dot multiplication results to obtain heartbeat filtering information corresponding to the heartbeat information and respiration filtering information corresponding to the respiration information respectively;
determining heartbeat error information according to the heartbeat filtering information and the heartbeat information, determining breathing error information according to the breathing filtering information and the breathing information, and further determining a heartbeat covariance matrix corresponding to the heartbeat error information and a breathing covariance matrix corresponding to the breathing error information;
determining a heartbeat gain vector according to the heartbeat covariance matrix and the heartbeat information, and determining a respiration gain vector according to the respiration covariance matrix and the respiration information;
and integrating the heartbeat gain vector and the breathing gain vector to update the weight of the adaptive filter.
2. The method of claim 1, wherein acquiring echo information of a millimeter wave radar reflected by a target object located on an intelligent bed, performing a filtering process on the echo information, and performing a phase unwrapping on the filtered echo information, and acquiring target phase information of the target object comprises:
and determining the phase angle of the echo information after the filtering processing by using a differential cross multiplication algorithm, performing phase unwrapping processing on the phase angle, and performing first-order differential processing on the echo information after the phase unwrapping processing to obtain target phase information of the target object.
3. The method of claim 1, wherein extracting heartbeat features from the heartbeat information and respiratory features from the respiratory information, respectively, by an adaptive filter in combination with an adaptive signal processing method comprises:
for each time step corresponding to the heartbeat information and the respiration information, carrying out dot multiplication on each weight of the adaptive filter and the heartbeat information and the respiration information of each time step, and adding dot multiplication results to obtain heartbeat filtering information corresponding to the heartbeat information and respiration filtering information corresponding to the respiration information respectively;
carrying out frequency domain analysis on the signals subjected to self-adaptive filtering, determining heartbeat frequency components corresponding to the heartbeat filtering information and respiratory frequency components corresponding to the respiratory filtering information, and determining the heartbeat peak position and the respiratory peak position through a peak detection algorithm;
calculating a heartbeat interval according to the heartbeat peak position respectively, and determining heartbeat characteristics; and calculating a respiration interval according to the respiration peak position, and determining a respiration characteristic.
4. The method of claim 1, further comprising training the behavior classifier:
based on a pre-acquired training data set, wherein the training data set comprises multi-category sample data, determining an initial category center of each category of the training data set, and calculating the spatial distance and the inter-category variance of any two categories of the training data set;
determining the inter-class distance of any two classes according to the space distance and the inter-class variance, taking the two classes with the largest inter-class distance as a reference class, respectively converging samples of the rest classes to the reference class according to the principle of closest inter-class distance, and then recalculating the updated class centers of the new classes after converging;
and recursively updating all the class samples of the training data set until all the class samples are distributed, and finishing training the behavior classifier.
5. The method of claim 1, wherein controlling the smart bed to take the corresponding action in conjunction with the predetermined physical sign gesture control correspondence comprises:
if the sleep sign state of the target object is a first sign state, wherein the first sign state is that the body of the target object exceeds a preset angle threshold value relative to the body of the intelligent bed, the intelligent bed is controlled to incline at a small angle towards the reverse body overturning direction of the target object;
if the sleep sign state of the target object is a second sign state, wherein the second sign state is the target object apnea, controlling the intelligent bed to adjust the heights of the head and the legs of the target object, and promoting oxygen circulation;
and if the sleep sign state of the target object is a third sign state, wherein the third sign state is that the respiratory frequency and the heartbeat frequency of the target object exceed a preset frequency threshold, controlling the intelligent bed to adjust the head height of the target object and promoting oxygen circulation.
6. A millimeter wave radar and smart bed linked attitude control system for implementing the millimeter wave radar and smart bed linked attitude control method according to any one of the preceding claims 1 to 5, characterized by comprising:
the first unit is used for acquiring echo information of the millimeter wave radar reflected by the target object on the intelligent bed, performing filtering processing on the echo information, and performing phase expansion on the filtered echo information to acquire target phase information of the target object;
a second unit, configured to extract heartbeat information and respiration information of the target object from the target phase information, and extract heartbeat features from the heartbeat information and extract respiration features from the respiration information respectively by combining an adaptive filter with an adaptive signal processing method;
and the third unit is used for determining the sleep sign state of the target object based on a pre-constructed behavior classifier according to the heartbeat characteristic and the breathing characteristic, and controlling the intelligent bed to make corresponding actions by combining with the pre-determined sign gesture control corresponding relation.
7. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method of any of claims 1 to 5.
8. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1 to 5.
CN202311036633.3A 2023-08-17 2023-08-17 Gesture control method and system for linkage of millimeter wave radar and intelligent bed Active CN117064349B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311036633.3A CN117064349B (en) 2023-08-17 2023-08-17 Gesture control method and system for linkage of millimeter wave radar and intelligent bed

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311036633.3A CN117064349B (en) 2023-08-17 2023-08-17 Gesture control method and system for linkage of millimeter wave radar and intelligent bed

Publications (2)

Publication Number Publication Date
CN117064349A CN117064349A (en) 2023-11-17
CN117064349B true CN117064349B (en) 2024-02-06

Family

ID=88707380

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311036633.3A Active CN117064349B (en) 2023-08-17 2023-08-17 Gesture control method and system for linkage of millimeter wave radar and intelligent bed

Country Status (1)

Country Link
CN (1) CN117064349B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117331047A (en) * 2023-12-01 2024-01-02 德心智能科技(常州)有限公司 Human behavior data analysis method and system based on millimeter wave radar

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112137604A (en) * 2020-10-22 2020-12-29 温州大学 Respiration and heartbeat detection method and system based on continuous wave Doppler radar
CN114027809A (en) * 2021-12-14 2022-02-11 宁夏芯锐智联科技有限公司 Milk cow respiratory heart rate monitoring method based on millimeter wave radar
CN114081459A (en) * 2021-11-22 2022-02-25 庚辰科技(宁波)有限公司 Multi-person breathing state monitoring method and system based on radar technology
WO2022095869A1 (en) * 2020-11-04 2022-05-12 蓬托森思股份有限公司 Contactless breathing or heartbeat detection method
CN114732384A (en) * 2022-06-14 2022-07-12 亿慧云智能科技（深圳）股份有限公司 Heart health monitoring method and device based on microwave radar and storage medium
CN115736854A (en) * 2022-11-09 2023-03-07 德心智能科技(常州)有限公司 Respiration and heartbeat monitoring system based on millimeter wave radar
CN115770149A (en) * 2022-11-17 2023-03-10 东华理工大学 Novel multi-functional old man's wisdom bed
CN115969351A (en) * 2022-12-05 2023-04-18 四川启睿克科技有限公司 Method for calculating respiration in real time based on millimeter wave radar
CN116058820A (en) * 2023-02-13 2023-05-05 山东师范大学 Vital sign monitoring method and system based on radar
CN116077044A (en) * 2022-12-05 2023-05-09 四川启睿克科技有限公司 Vital sign detection method based on millimeter wave radar
WO2023102966A1 (en) * 2021-12-07 2023-06-15 中国科学院苏州生物医学工程技术研究所 Vital sign monitoring method and system based on millimeter-wave radar

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11412937B2 (en) * 2017-03-29 2022-08-16 Texas Instruments Incorporated Multi-person vital signs monitoring using millimeter wave (mm-wave) signals

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112137604A (en) * 2020-10-22 2020-12-29 温州大学 Respiration and heartbeat detection method and system based on continuous wave Doppler radar
WO2022095869A1 (en) * 2020-11-04 2022-05-12 蓬托森思股份有限公司 Contactless breathing or heartbeat detection method
CN114081459A (en) * 2021-11-22 2022-02-25 庚辰科技(宁波)有限公司 Multi-person breathing state monitoring method and system based on radar technology
WO2023102966A1 (en) * 2021-12-07 2023-06-15 中国科学院苏州生物医学工程技术研究所 Vital sign monitoring method and system based on millimeter-wave radar
CN114027809A (en) * 2021-12-14 2022-02-11 宁夏芯锐智联科技有限公司 Milk cow respiratory heart rate monitoring method based on millimeter wave radar
CN114732384A (en) * 2022-06-14 2022-07-12 亿慧云智能科技（深圳）股份有限公司 Heart health monitoring method and device based on microwave radar and storage medium
CN115736854A (en) * 2022-11-09 2023-03-07 德心智能科技(常州)有限公司 Respiration and heartbeat monitoring system based on millimeter wave radar
CN115770149A (en) * 2022-11-17 2023-03-10 东华理工大学 Novel multi-functional old man's wisdom bed
CN115969351A (en) * 2022-12-05 2023-04-18 四川启睿克科技有限公司 Method for calculating respiration in real time based on millimeter wave radar
CN116077044A (en) * 2022-12-05 2023-05-09 四川启睿克科技有限公司 Vital sign detection method based on millimeter wave radar
CN116058820A (en) * 2023-02-13 2023-05-05 山东师范大学 Vital sign monitoring method and system based on radar

Also Published As

Publication number Publication date
CN117064349A (en) 2023-11-17

Similar Documents

Publication Publication Date Title
Paalasmaa et al. Adaptive heartbeat modeling for beat-to-beat heart rate measurement in ballistocardiograms
CN117064349B (en) Gesture control method and system for linkage of millimeter wave radar and intelligent bed
Sopic et al. Real-time classification technique for early detection and prevention of myocardial infarction on wearable devices
JP6310401B2 (en) Method, system and computer program for processing a signal representing a physiological rhythm
WO2020226638A1 (en) Sleep tracking and vital sign monitoring using low power radio waves
Han et al. UWB radar for non-contact heart rate variability monitoring and mental state classification
CN112998689B (en) Non-contact multi-person real-time respiration condition evaluation system, device and storage medium
WO2019216378A1 (en) Calculation device, detection device, calculation method, and computer program
CN114246563B (en) Heart and lung function intelligent monitoring equipment based on millimeter wave radar
Bali et al. Performance comparison of ANN classifiers for sleep apnea detection based on ECG signal analysis using hilbert transform
CA3139034A1 (en) System and method for filtering time-varying data for physiological signal prediction
CN114767064B (en) Child sleep monitoring method, system and electronic device
CN113633268A (en) Physiological signal detection method and device and data processing equipment
WO2020133562A1 (en) Mobile monitoring device, and physiological signal adjustment and processing method
JP2021535817A (en) Providing time information of the target person
US20160000336A1 (en) Improvements in heart activity monitoring during physical exercise
US20220323023A1 (en) Method for determining respiratory rate
Roy et al. Reconstruction of corrupted and lost segments from photoplethysmographic data using recurrent neural network
JP2022151111A (en) Blood pressure measuring device, vehicle device, and blood pressure measuring program
Zhang et al. Radar-Beat: Contactless beat-by-beat heart rate monitoring for life scenes
EP4203782A1 (en) Contactless device for respiratory health monitoring
Yan et al. Research on an anti-motion interference algorithm of blood oxygen saturation based on AC and DC analysis
US20210275048A1 (en) Biometric information processing apparatus and biometric information processing method
Zamrath et al. Robust and computationally efficient approach for Heart Rate monitoring using photoplethysmographic signals during intensive physical excercise
CN111588373B (en) Data processing method and device, computer storage medium and electronic equipment

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