89 results about "Heart frequency" patented technology

The invention provides a life detection method and system based on radar signal processing, and relates to the technical field of radar signal processing, and the method comprises the steps: collecting a radar echo signal of a target region, controlling a phased array radar transmitting antenna array to transmit an orthogonal frequency division multiplexing dual-frequency continuous wave radar signal, and transmitting the dual-frequency continuous wave radar signal. Inputting the processed radar echo signal into an orthogonal demodulation module for synchronous coherent demodulation to obtain a baseband signal; inputting the feature vector into a multi-task deep learning network integrated with an attention mechanism for feature fusion and target recognition to obtain a second processing signal; obtaining a target characteristic frequency spectrum by calculating the time-frequency distribution of the second processing signal, and judging whether a life body exists in the target area or not according to the time-varying characteristics of the respiratory frequency component and the heartbeat frequency component and the amplitude fluctuation rule; and calculating three-dimensional space coordinates of the life body through a multi-base-station cooperative positioning algorithm, and outputting a detection result containing the three-dimensional space coordinates and the life body feature information.

A system for AI-based analysis of student behavior, consisting of: a variety of data collection devices, including cameras, microphones and wearable sensors; a central processing unit (CPU) that is communicatively connected to the data acquisition devices; and a behavioral analysis engine, wherein: (a) the cameras are configured to capture visual data indicating student behavior, including facial expressions, body language and eye movements, with the captured visual data being processed using computer vision techniques to detect certain emotional and engagement-related indicators such as stress, boredom, attention or excitement; (b) the microphones are configured to capture audio data, including speech patterns, tone of voice, volume and level of participation, the captured audio data being processed using natural language processing (NLP) techniques to assess the mood, engagement and verbal participation of students in classroom activities; (c) the wearable sensors are configured to collect biometric data, including heart rate, skin temperature and movement, with the biometric data being analyzed to detect physiological signs of emotional stress, fatigue or engagement; (d) The behavioral analysis engine is configured to process the captured visual, auditory, and biometric data in real time to create a behavioral profile of each student. It uses machine learning models to correlate certain patterns with academic performance, emotional well-being, and social engagement. (e) the system is also configured to create predictive models based on historical data to identify pupils at risk of declining performance, social isolation or emotional distress, and to send alerts to teachers, counselors or the administration to enable timely intervention to address the identified problems.

Method and system for biometric identification. A cardiac signal, such as a ballistocardiogram signal, obtained from a reference subject is segmented into heartbeat segments over selected time duration. Cardiac signal may be obtained using remote non-invasive millimeter-wave radar detector. Linear mapping is applied to each heartbeat segment to produce a respective heartbeat frequency encoding, which is assigned an identification label relating to reference subject. Machine learning process is applied to a collection of heartbeat frequency encodings during a modelling stage to generate a model for subject classification. Model is applied to input heartbeat frequency encoding during an identification stage, to classify input heartbeat frequency encoding as belonging to a reference subject if a matching classification is obtained or to determine that the input heartbeat frequency encoding belongs to a non-reference subject if no matching classification is obtained. Subject identification may be utilized for healthcare monitoring applications.

The invention relates to a breathing heart rate detection method and device based on an FMCW radar, and belongs to the technical field of signal processing.The breathing heart rate detection method based on the FMCW radar comprises the steps that FMCW radar detection signals are preprocessed, and thoracic cavity phase signals are obtained; performing time sequence data decomposition on the thoracic cavity phase signals, and determining a target signal from the thoracic cavity phase signals after time sequence data decomposition based on the reference range of the respiratory frequency and the heartbeat frequency of the target population; performing multi-scale decomposition on the target signal, and separating a target respiration signal and a target heartbeat signal from the target signal; and based on a spatial spectrum estimation algorithm, determining the breathing frequency and the heartbeat frequency of the to-be-detected person from the target breathing signal and the target heartbeat signal. According to the method, the respiratory heart rate detection is realized, the influence of noise on the detection result is reduced, and the accuracy of the respiratory heart rate detection is further improved.

The invention belongs to the technical field of remote health monitoring, medical diagnosis and intelligent health equipment, and discloses a non-contact heartbeat monitoring method and system based on millimeter wave signals. According to the non-contact heartbeat monitoring system, heartbeat monitoring is achieved by transmitting and receiving millimeter wave signals reflected from the chest of the human body through the millimeter wave radar technology. Tiny movement generated by cardiac pulsation can cause tiny changes of the chest of the human body, and the changes are shown through reflected millimeter wave signals. By processing and analyzing the reflected signals in real time, the influence of heartbeat on the signals can be accurately extracted, so that the heartbeat frequency and physiological indexes related to the electrocardiogram can be deduced.

The present invention provides a life detection method and system based on radar signal processing, which relates to the technical field of radar signal processing. The method and system include collecting radar echo signals in a target area, controlling a phased array radar transmitting antenna array to transmit an orthogonal frequency division multiplexed dual-frequency continuous wave radar signal, inputting the processed radar echo signal into an orthogonal demodulation module for synchronous coherent demodulation to obtain a baseband signal; inputting a feature vector into a multi-task deep learning network with an integrated attention mechanism for feature fusion and target recognition to obtain a second processed signal; obtaining a target feature spectrum by calculating the time-frequency distribution of the second processed signal, judging whether there is a life form in the target area according to the time-varying characteristics of a respiratory frequency component and a heartbeat frequency component and the law of amplitude fluctuation; if it is determined that there is a life form in the target area, calculating the three-dimensional spatial coordinates of the life form through a multi-base station collaborative positioning algorithm, and outputting a detection result containing the three-dimensional spatial coordinates and the life form feature information.

The present invention discloses a dynamic early warning system for cardiac arrest based on multimodal data fusion, belonging to the field of medical information technology. Specifically, it includes: a non-contact sensing module for continuously acquiring the physiological parameters of a user based on non-contact devices; an active wearing module for starting the acquisition of contact physiological parameters when the user actively triggers the wearing device; a scene adaptive module for constructing a physiological parameter baseline only based on non-contact sensing data when the wearing device is not triggered; when the user triggers the wearing device, cross-verifying the contact data and the non-contact data and correcting the calibration parameters of the non-contact data; a risk decision module for starting a forced verification process of contact data when the non-contact detection detects an abnormal heart rate; if the verification fails or there is no response, generating a corresponding risk level early warning based on the continuous abnormal duration and the fluctuation pattern; the present invention realizes dynamic early warning based on multimodal data.

The invention relates to the technical field of rehabilitation equipment, in particular to a treatment method and system based on automatic frequency spectrum infrared rehabilitation equipment, and the method comprises the steps that an infrared thermogram of the body of a patient is collected, the credibility of the infrared thermogram is calculated, and the credibility is in negative correlation with the heartbeat frequency and the current room temperature of the patient; acquiring an image of which the credibility of the infrared thermogram is greater than a preset threshold within a preset time period as a target image, and performing graying processing on the target image to obtain a grayscale image; and carrying out edge detection on the grayscale image, and extracting a focus area. According to the method, the abnormal degree of the focus area is calculated through the maximum value of the gray values of the pixel points in the focus area and the variance of the gray values of all the pixel points, and the abnormal degree of the focus area is used for performing weighted correction on the power emitted by the spectrum infrared equipment, so that the treatment effect on the focus area of a patient is improved.

The present application discloses a vital sign evaluation system based on data analysis, which relates to the field of vital sign monitoring technology. The specific scheme includes: mixing the echo signals from the target area to obtain two intermediate frequency signals, and then amplifying them to obtain the first signal and the second signal; then performing respiratory filtering and heartbeat filtering to obtain the third signal and the fourth signal, and then determining the respiratory frequency and the heartbeat frequency, and then updating the respiratory filter parameters and the heartbeat filter parameters; obtaining the respiratory frequency and the heartbeat frequency at the current moment, as well as multiple historical respiratory frequencies and multiple historical heartbeat frequencies, determining the heart rate variability and respiratory depth changes corresponding to the current moment, and then determining the vital sign evaluation results based on the vital sign evaluation score formula. The present disclosure can solve the problem in the prior art that the filtering processing cannot follow the frequency changes of the vital sign signal in real time, resulting in inaccurate vital sign data, and improve the accuracy of the vital sign evaluation results.

The invention belongs to the field of non-contact vital sign detection, and particularly relates to a millimeter wave radar arrhythmia detection method based on particle swarm optimization variational mode decomposition and deep learning, and the method specifically comprises the steps: S1, obtaining a human chest micro-motion signal through a millimeter wave radar, performing static clutter filtering, phase extraction, unwrapping and detrending processing on the radar echo signal to obtain a chest displacement signal containing heartbeat and breathing information; s2, aiming at the thoracic cavity displacement signal, constructing a variational mode decomposition model, and carrying out adaptive optimization on a mode number and a penalty factor through a particle swarm optimization algorithm to obtain an optimal decomposition parameter and complete signal decomposition; s3, according to the center frequency and the energy distribution characteristics of each modal component, screening the modal components in the heartbeat frequency range and reconstructing the modal components to obtain heartbeat characteristic signals representing heart mechanical activities; s4, carrying out time sequence segmentation on the heartbeat characteristic signals, extracting local heart beat morphological characteristics by utilizing a convolutional neural network, and carrying out modeling on a long-time rhythm dependency relationship of the heartbeat signals in combination with a time sequence modeling network based on an attention mechanism to obtain heart rhythm depth characteristic representation; and S5, inputting the heart rhythm depth features into a heart rhythm discrimination model, analyzing the heart rhythm state of the detected person, and outputting an arrhythmia detection result. According to the method, adaptive selection of variational mode decomposition parameters is realized by introducing a particle swarm optimization mechanism, heartbeat signals and respiration and motion interference components are effectively separated, modeling is carried out on rhythm characteristics in combination with a deep learning model, and non-contact detection of arrhythmia is realized. The method does not need to wear an electrode or contact a human body, has the advantages of strong anti-interference capability, good adaptability and high detection precision, and has a good application prospect in the fields of heart rhythm health monitoring, disease screening and the like.

The invention discloses a sudden cardiac arrest dynamic early warning system based on multi-modal data fusion, and belongs to the technical field of medical information, and the system specifically comprises a non-contact sensing module which is used for continuously obtaining physiological parameters of a user based on a non-contact device; the active wearing module is used for starting contact type physiological parameter acquisition when a user actively triggers the wearable equipment; the scene self-adaption module is used for constructing a physiological parameter base line only based on the non-contact sensing data when the wearable equipment is not triggered; when the user triggers the wearable device, performing cross validation on the contact data and the non-contact data, and correcting calibration parameters of the non-contact data; the risk decision module is used for starting a contact type data forced verification process when the heartbeat frequency is detected to be abnormal in a non-contact manner; if verification fails or no response is made, corresponding risk level early warning is generated based on the continuous abnormal duration and the fluctuation mode; according to the invention, dynamic early warning is realized based on multi-modal data.

The invention discloses a dangerous driving monitoring method and system based on an optical camera and a millimeter-wave radar, and the method comprises the steps: adjusting the optical camera and the millimeter-wave radar to enable the image centers of the optical camera and the millimeter-wave radar to be aligned, and then maintaining the relative pose to be fixed; based on the position of the cardiopulmonary part on the optical image, adjusting the pose of the camera and the radar carrier to enable the antenna center of the millimeter wave radar to be aligned with the cardiopulmonary part, and adjusting the focal length of the optical camera to enable the eyes of the driver to be within the view field range; continuous optical images and echo signals are respectively obtained by using an optical camera and a radar; judging whether the eyes are closed or not by calculating the aspect ratio of the eyes in the optical image, and judging whether the driver is in fatigue driving or not according to the eye closing duration; the breathing and heartbeat frequencies of the driver are extracted according to the radar echo signals, and then whether the driver currently drives in danger or not is judged again. The problem that the detection precision of an optical camera is limited due to the illumination condition is effectively solved, and dangerous driving behaviors can be accurately recognized.

The invention discloses a household linkage system based on multi-dimensional fusion of personal physiology, environment and astronomy. A method for acquiring time series of physiological parameters (heartbeat frequency values, blood pressure values, blood oxygen saturation and blood glucose level values) of a user, time series of environmental parameters (temperature values, humidity values and illumination intensity values) and astronomical data (solar electromagnetic activity and lunar attraction) by using an AI-based data processing and analysis algorithm time sequence implicit correlation feature analysis and semantic correlation degree calculation are performed on the time sequence, so that whether the indoor illumination intensity is reduced or not is automatically judged according to multi-modal time sequence joint coding features among multiple parameters in the data. Thus, the system can collect and comprehensively analyze physiological data, indoor environment parameters and astronomical information of the user in real time, precise regulation and control and intelligent adjustment of the intelligent home equipment are achieved, a more precise and personalized home environment adjustment scheme is provided for the user, and the overall living experience is improved.

This invention discloses a method for monitoring human vital signs in motion scenarios. It receives radar reflection signals reflected from the human body, mixes these signals with the transmitted radar signal to obtain a raw intermediate frequency (IF) signal, performs a Fourier transform on the IF signal to construct feature spectrum data, and uses a sliding window sampling method to extract the feature spectrum according to a preset window length and step size. This extracted spectrum is then input into a trained classifier network model to identify motion or non-motion states, and the type of motion within the motion state. During non-motion states within the motion period, it monitors respiratory or heart rate. This invention utilizes millimeter-wave radar to monitor human vital signs, offering advantages such as low light dependence, good privacy protection, high monitoring sensitivity, and non-contact operation.

The application discloses a kind of based on neural network's acoustic user identification and heartbeat monitoring earphone system and method, the system includes the earphone with microphone, acoustic analog-digital conversion equipment, the back-end service equipment at least includes: data acquisition module is used for acoustic signal transmission and reception;Data processing module is used to obtain preprocessed received signal;Human ear canal feature extraction module is used to extract MFCC feature and ear canal feature based on transfer function;User identity identification module is used to obtain trained neural network model;Heartbeat information extraction module is used to obtain processed phase information;Self-interference elimination module obtains phase signal not containing direct path interference;Heartbeat frequency calculation module is used to obtain heartbeat frequency.The application can reduce the cost of identity recognition and heartbeat monitoring, and robustness, high robustness.

The invention discloses a signal processing method and system, and the method comprises the steps: continuously transmitting a pulse signal which is used for detecting the breath of a target user and the heartbeat of the target user; receiving an echo signal of the pulse signal; based on the echo signal processing, obtaining a first respiratory frequency for representing the respiration of the target user, a first heartbeat frequency for representing the heartbeat of the target user, and a confidence coefficient for representing the first respiratory frequency and the first heartbeat frequency for representing the credibility of the respiration and the heartbeat of the target user; and at least outputting a second respiratory rate and a second heartbeat rate based on the first respiratory rate, the first heartbeat rate and the confidence.

The application discloses a kind of multi-person vital sign monitoring method and system based on space-time coding hypersurface, utilize the harmonic wave beam scanning area of attention generated by space-time coding hypersurface to carry out human detection, and allocate the beam of frequency orthogonal for each detected human target, to accurately estimate their respiratory and heartbeat rate.The system can monitor the vital sign of multiple people simultaneously, and accurately estimate the respiratory and heartbeat frequency of human target.The control ability of space-time coding hypersurface used in the application can reduce the noise reflected by non-related objects, thereby improving the signal-to-noise ratio of human chest echo.The application uses wireless signals, has unique advantages such as not easily disturbed by environmental factors and protecting visual privacy.Compared with traditional vital sign monitoring instruments, the non-contact characteristics of the application can reduce the stress and interference on the user, and can be used for long-term, remote health monitoring.

To provide a motion discrimination device capable of detecting a state that a user raises his or her upper body on a bed.SOLUTION: A motion discrimination device 10 for discriminating a motion of a user U on a bed 20 includes: a sensor 30 arranged at a position corresponding to the body of the user U; and a processing device 40 for receiving and processing an output signal output by the sensor 30. The sensor 30 detects a change in a load that the user U applies to the sensor 30. The processing device 40 includes an arithmetic device 41 and a discrimination device 42. The arithmetic device 41 generates a respiration frequency signal including a frequency component corresponding to the respiration of the user U on the basis of the output signal, and generates a heartbeat frequency signal including a frequency component corresponding to the heartbeat of the user U on the basis of the output signal. The discrimination device 42 discriminates a raised state in which the user U raises his or her upper body on the bed 20 on the basis of at least one of the respiration frequency signal and the heartbeat frequency signal.SELECTED DRAWING: Figure 1

The invention discloses an embryo screening method and device based on a millimeter-wave radar, and the method comprises the steps: transmitting a frequency-modulated continuous wave by the millimeter-wave radar to irradiate an embryo egg, receiving an echo signal, and mixing the echo signal with a transmitted signal to obtain an intermediate-frequency signal; the intermediate frequency signal is sent to a computer signal processing terminal through a signal acquisition device; preprocessing the radar signal, including performing circle fitting by using a correlation optimized least square method, eliminating direct current offset, and suppressing a static clutter component by using a phasor mean cancellation algorithm; constructing a distance-angle diagram, and positioning a plurality of embryo eggs by adopting a constant false alarm rate (CFAR); phase information of a target is extracted from the preprocessed signal, the heartbeat frequency of the embryo is obtained, and the embryo incubation state is judged in real time in combination with the embryo type and incubation duration. The internal heartbeat frequency of the embryo egg can be accurately detected in real time in a non-contact mode, the incubation state of the to-be-detected embryo is judged, the detection efficiency is effectively improved, and resource consumption is reduced.

This application discloses a method and apparatus for acquiring human feature data. The method includes: using an ultra-wideband (UWB) radar array, the acquisition device performs real-time identification of a target human body within a signal-detectable area, and determines a three-dimensional upper body model for the identified target human body; based on the three-dimensional upper body model, the chest and abdomen region of the target human body is determined, and the chest and abdomen region is detected; based on the set of data points obtained from the detection, a contour model of the chest and abdomen region and monitoring control points in the contour model are determined; the monitoring control points include respiratory monitoring control points and / or heart rate monitoring control points; using the UWB radar array, the chest and abdomen region is detected in real time, and based on the coordinate changes of the detected monitoring control points, the respiratory rate and / or heart rate of the target human body are determined. Using this application can improve the comfort of the user being tested during human feature data acquisition.

The invention relates to a non-inductive interaction intelligent mobile health sign monitoring method and system. The method comprises the following steps: emitting a composite waveform formed by time division multiplexing of a frequency-modulated continuous wave signal and an index modulation orthogonal frequency division multiplexing signal; the receiving end carries out frequency mixing, moving target display filtering, distance dimension fast Fourier transform and phase unwrapping processing on the echo signal, and a phase signal representing thoracic cavity micro-displacement is extracted; a marine predator algorithm with envelope entropy minimization as a fitness function is innovatively adopted, the modal number and penalty factor parameters of a variational modal decomposition model are adaptively optimized, and phase signals are decomposed by using the optimized model; finally, breathing and heartbeat signals are separated from the intrinsic mode function based on the physiological frequency range and the energy screening criterion, and the breathing frequency and the heartbeat frequency are output through spectral analysis. High-precision non-contact vital sign monitoring is realized, and the user experience is remarkably improved.

The invention relates to the technical field of computers, and provides a wearable heartbeat monitoring device and method, and the device comprises a central processing unit, an electrode plate unit, an R wave detection unit, a heartbeat frequency monitoring unit, and a heartbeat abnormity monitoring unit. The electrode slice unit is used for collecting electrocardiosignals of a user in real time; the R-wave detection unit is used for splitting the electrocardiosignal into a plurality of electrocardiosignal segments and carrying out R-wave feature point detection on each electrocardiosignal segment to obtain an R-wave feature point of each electrocardiosignal segment; the heartbeat frequency monitoring unit is used for determining a heartbeat cycle based on the time interval of the R-wave feature points of the two adjacent electrocardiosignal segments and determining the current heartbeat frequency of the user based on a plurality of continuous heartbeat cycles; and the abnormal heartbeat monitoring unit is used for comparing the current heartbeat frequency with a preset normal heartbeat frequency range and judging whether the user is in an abnormal heartbeat state or not. According to the embodiment of the invention, the heartbeat monitoring accuracy and reliability are improved.

The present invention provides a heart rate estimation method based on millimeter wave radar. The method comprises the following steps: sampling a human body by using a millimeter wave radar to obtain a plurality of frequency modulated continuous wave sweep signals; forming a distance-slow time matrix and locating the distance between the human body and the radar; extracting the human body phase by using an inverse tangent function, unfolding the phase whose phase change exceeds a set threshold by using a phase unwrapping function, obtaining the phase difference of adjacent frames, and smoothing the difference exceeding the threshold by using an interpolation method; removing the noise of the smoothed phase signal by using a wavelet transform, and obtaining a reconstructed phase signal; combining an EEMD-ICA method to separate a heartbeat signal, a respiratory signal, a respiratory harmonic and noise in the reconstructed phase signal, and obtaining a heartbeat waveform; constructing a spatial spectrum function by using a multi-signal classification algorithm, and estimating the heartbeat frequency by searching the spectrum peak; the method can accurately separate the heartbeat signal and greatly improve the accuracy of the heartbeat frequency estimation.

The application discloses a walking state vital sign monitoring method and device, equipment and a storage medium, and relates to the technical field of vital sign monitoring. The specific scheme comprises the following steps: determining an anchor distance gate according to the first K frames in N frames of FMCW radar echo signals; performing a processing step on each frame of FMCW radar echo signal after the Kth frame to obtain a plurality of third signals, a plurality of target distance gates, and then determining a plurality of second signals, and then determining a respiratory frequency and a heartbeat frequency and sending the respiratory frequency and the heartbeat frequency to an upper computer to monitor the vital signs of a human body. The processing step comprises the following steps: updating the anchor distance gate according to the target distance gate corresponding to the last frame of the current frame of FMCW radar echo signal; determining the target distance gate according to the plurality of first signals and the anchor distance gate; and determining the third signal according to the plurality of first signals and the target distance gate. The present application can solve the problem that it is difficult to accurately monitor the vital signs of a human body in a walking state, expand the application scenarios of vital sign monitoring, and improve the accuracy of vital sign monitoring.

The application discloses a kind of non-contact multimodal data acquisition and emotion monitoring method, device, system, equipment, medium and product, it is related to emotional recognition technical field.The method is first to start man-machine interaction program and target personnel are interviewed, and receive by millimeter wave biological radar module and audio and video acquisition module in the process of interview the human vital sign signal and audio and video signal collected by target personnel, then on the one hand to human vital sign signal sequentially pre-processing, signal separation processing and frequency estimation processing, obtain respiratory rate and heartbeat frequency, on the other hand to audio and video signal carries out feature extraction processing, obtains audio feature and video feature, finally according to respiratory rate, heartbeat frequency, audio feature and video feature, comprehensive analysis obtains the emotional state of target personnel, thereby can provide high-quality data support for subsequent artificial intelligence emotion early warning and evaluation model establishment, realize higher accuracy and higher reliability of emotional state analysis.

This invention discloses a millimeter-wave radar heartbeat signal extraction method resistant to respiratory harmonic interference. Addressing the challenge of estimation errors caused by high-order harmonics from large-amplitude breathing overlapping the heartbeat frequency in the frequency domain, this invention proposes a time-domain regression cancellation scheme. The method first removes echo clutter and locates the target, acquiring phase micro-motion data; then, empirical mode decomposition (EMD) is used to lock the fundamental respiratory frequency, constructing an interference matrix containing the fundamental frequency and high-order harmonics; subsequently, least squares (OLS) is used for adaptive fitting in the time domain and respiratory harmonics are removed to obtain a clean residual; finally, differential enhancement and adaptive wavelet packet transform (WPD) are combined to reconstruct the weak heartbeat signal. This invention effectively overcomes the shortcomings of traditional frequency-domain filtering in separating overlapping frequencies, eliminates "false positive" interference, and significantly improves the accuracy and robustness of heartbeat monitoring under complex respiratory backgrounds.

A method for resolving sinus arrhythmia aliasing in a signal containing heartbeat and respiratory information is provided. The method determines a plurality of variable time intervals between successive heartbeats from a sensor providing a signal that includes heartbeat information. The sensors can generate signals from an electrocardiogram, a photoplethysmography, an echocardiographic, an impedance based assessment, and a ballistocardiography signal device. From the signal a respiratory sinus arrhythmia signal from the plurality of variable time intervals between successive heartbeats are generated. From this data a sinus arrhythmia periodogram is generated. A respiration rate from a respiration sensor providing a respiration signal containing a direct physical measurement of a person's respiration is generated, and a respiration rate is determined. The respiration sensor includes an accelerometer, a gyroscope, an air motion sensor, a microphone, an impedance based assessment, and a video camera. The respiration rate and heartbeat rate are used in resolving the aliasing in the sinus arrhythmia periodogram.

The invention relates to the technical field of situation awareness of edge computing, and discloses a grassroots community public security event awareness linkage system based on edge computing, which comprises a plurality of edge devices, state interaction is carried out on a public channel according to the frequency change of heartbeat pulse signals, and when any device makes low-confidence judgment on a potential high-risk event, the potential high-risk event is subjected to state interaction. The method comprises the following steps: when a plurality of devices respond to each other to form channel resonance, instantaneously increasing heartbeat frequency to wake up adjacent devices to carry out cross validation, and when the plurality of devices respond to form channel resonance, completing distributed confirmation of events and generating a linkage instruction. According to the invention, complex event content collaboration among the plurality of edge devices is converted into common perception of a single physical channel state; therefore, the response mode of the system is converted from a passive lag type of waiting for single strong evidence to an active prediction type of gathering multi-point weak evidence, and high-reliability early warning can be completed in the extremely early stage of a disaster.

The invention discloses a method for extracting vital signs features of Doppler radar based on second-order instantaneous moment, comprising: 1. obtaining a baseband signal of orthogonal sampling received by Doppler radar, wherein the baseband signal is a signal obtained by mixing the echo of the radar transmission signal and the transmission signal of the target; 2. performing mean filtering on the baseband signal to obtain a baseband signal with a DC component removed; 3. taking the complex data after mean filtering as an observed quantity, adopting the second-order instantaneous moment method to obtain a demodulated vital sign signal waveform; 4. passing the demodulated vital sign signal waveform through a bandpass filter of [0.1, 0.6] and [0.8, 2.5] Hz respectively to obtain a respiratory and heartbeat time domain signal; 5. performing Fourier transform processing on the extracted respiratory and heartbeat time domain waveforms to obtain the spectrum of the respiratory waveform and the heartbeat waveform respectively, and estimating the respiratory and heartbeat frequency parameters based on the threshold detection technology. The invention improves the estimation accuracy of respiratory rate and heart rate parameters.

The present invention discloses a method and system for suppressing respiratory harmonics in a UWB impact bio-radar heartbeat signal, and belongs to the field of human heartbeat signal detection. The method comprises: obtaining the position of respiratory harmonics based on the fundamental frequency of respiration, judging whether the respiratory harmonics and the main peak of the heartbeat coincide with each other through a correlation analysis method, and then determining the respiratory harmonics to be removed; and suppressing each harmonic of respiration using a feedback notch filter optimized by a genetic algorithm. The method causes little loss to the radar heartbeat signal and can automatically remove each harmonic, thereby providing a more refined radar heartbeat signal for extracting cardiac motion features. The method effectively improves notch performance in terms of bandwidth, overshoot, etc., considers the processing method for the coincidence of the respiratory harmonics and the main peak frequency of the heartbeat, and retains the heartbeat frequency component to the greatest extent, thereby providing a new method for radar heartbeat signal extraction and analysis.