27 results about "Respiratory frequency" patented technology

The application discloses a controllable breathing machine atomization processing circuit, which comprises a main control module, a display module, a carbon dioxide concentration detection module, a pressure detection module, a judgment module, an atomization output control module and an oscillation driving module; wherein the main control module is connected with the display module, the judgment module, the carbon dioxide concentration detection module and the pressure detection module respectively; the display module, the carbon dioxide concentration detection module and the pressure detection module are connected with the judgment module respectively; the judgment module is connected with the atomization output control module; and the atomization output control module is connected with the oscillation driving module. Through the cooperation of the main control module, the carbon dioxide detection module and the pressure detection module, the breathing frequency data of a patient can be accurately collected and fed back in real time; and through the atomization output control module and the input oscillation driving module, the vibration frequency of the atomization screen is regulated and controlled, so that the atomization screen can better adapt to the breathing frequency of the patient.

This application discloses a method for detecting living beings inside a vehicle and an alarm method for detecting children left behind in a vehicle. The main technical solution includes: acquiring radar echo signals from the interior environment of the target vehicle; analyzing the respiratory frequency of a living being based on the frequency characteristics of the radar echo signals to obtain respiratory frequency estimation information, wherein the frequency characteristics include frequency amplitude and / or frequency phase; and determining whether a living being exists in the vehicle's interior environment based on the respiratory frequency estimation information. This method can effectively identify weak, periodic respiratory signals from a noisy background, improving the accuracy and reliability of living being detection and effectively reducing the number of missed and false alarms regarding living beings left in the vehicle.

The utility model relates to a wearable mechanical flower based on arduino controller, including sensor, arduino controller and mechanical flower subassembly, the sensor is used for monitoring user respiratory frequency information, and will monitored frequency information send to arduino controller, arduino controller is used for receiving the frequency information of sensor transmission, to the frequency information of receiving processing and will handle the corresponding instruction signal transmission to servo motor, the mechanical flower subassembly includes transmission mechanism and a plurality of simulation petal, the input of transmission mechanism with servo motor's output is linked, the output of transmission mechanism with simulation petal is linked, servo motor controls simulation petal according to instruction signal with respiratory frequency repeatedly opens and shuts. The utility model discloses repeatedly open and shut action of simulation natural flower, with the physiological rhythm (respiratory frequency) of wearer synchronization, makes the user psychology peaceful, reaches the effect of relieving anxiety and enhancing mindfulness.

The utility model discloses an isolated respirator mask capable of monitoring the breathing of firemen, a monitoring assembly comprises an exhalation pressure monitoring device, a breathing frequency monitoring device and an exhalation temperature and humidity monitoring device, so that the monitoring assembly can monitor the exhalation airflow pressure, breathing frequency and exhalation airflow temperature and humidity of the firemen in the respirator mask respectively, thereby more comprehensively obtaining the breathing state of the firemen in the respirator mask, improving the monitoring reliability, and through the corresponding control of the air supply state of the respirator mask by the air supply adjusting assembly, ensuring that the firemen can breathe comfortably in the respirator mask, so as to improve the safety.

The application relates to a lonely old people safety monitoring system, belonging to the technical field of wisdom endowment, the system comprises a millimeter wave radar sensing module for generating three-dimensional point cloud data of a human body; a posture reconstruction unit reconstructs a skeleton and identifies a posture category through a PointNet++ network; a micro-motion feature extraction unit extracts a breathing frequency and a body motion micro-motion amplitude from radar echo; an environment semantic sensing module collects multi-source time sequence signals through sensors arranged in a household pipeline and household appliance nodes, and generates a behavior semantic vector through a Transform model; a multi-modal mutual verification unit, when an abnormal posture is detected, synchronously judges whether the breathing frequency is lower than a first preset threshold value, whether the body motion micro-motion amplitude is lower than the product of the average body motion amplitude in a normal activity state and a second preset threshold value, and whether the behavior semantic vector before the occurrence of the abnormality matches a preset rule library, and outputs a high-risk alarm when the three conditions are simultaneously satisfied.

This invention discloses a method for detecting respiratory signals using through-wall radar based on PCA and VMD. First, eigenvalue decomposition is performed on the ultra-wideband radar echo data matrix after removing the DC component. Then, mode decomposition is performed on the clutter-free dynamic signal matrix in the slow-time dimension. Relevant mode components within the respiratory frequency band are selected. The selected mode components are reconstructed. Fourier transform is performed in the slow-time dimension to construct a range-frequency spectrum. Finally, a two-dimensional Gaussian template conforming to the spectral characteristics of human respiration is constructed and matched. The range and frequency estimates of the human respiratory signal are calculated. This invention addresses the problems of weak anti-interference capability and high false alarm probability of single clutter suppression methods, thereby achieving accurate respiratory signal detection in strong clutter environments.

This invention discloses a respiratory rate extraction method based on multimodal pulse wave feature fusion, comprising: 1. filtering and windowing the pulse wave signal; 2. extracting four types of non-uniform sampling feature sequences from each signal window: respiratory induction amplitude variation, respiratory induction intensity variation, respiratory induction frequency variation, and respiratory induction continuous contraction difference variation; 3. converting each sequence to the frequency domain using a Lomb-Scargle periodogram, extracting the corresponding respiratory rate estimate, and calculating signal quality indices including main peak significance, in-band signal-to-noise ratio, and harmonic energy ratio; 4. constructing a four-dimensional feature vector based on the respiratory rate and quality indices corresponding to each feature, obtaining a preliminary frequency estimate through comprehensive confidence weighting, consensus cluster fusion, and harmonic correction, and then outputting the final respiratory rate after time-series smoothing. This invention can achieve complementary fusion of multiple features, thereby effectively improving the robustness and accuracy of respiratory rate estimation.

The application discloses an intelligent feedback and evaluation device for respiratory rehabilitation training and relates to the technical field of rehabilitation medical equipment, in particular to an intelligent feedback and evaluation device for respiratory rehabilitation training, which comprises a hard plate, flexible waistbands provided with adjustable buckles at both ends and a display panel arranged at the front end of the hard plate. The front end of the hard plate is provided with control buttons, the rear end is provided with an air pressure sensing bag, and the lower end is provided with a charging interface; the inner end is provided with a main control circuit board, a power module and a vibration motor. The inner end of the air pressure sensing bag is provided with a micro air pump, an electromagnetic valve and a reference air chamber. The flexible waistbands can be adjusted in length to adapt to different waist circumferences or chest circumferences. The display panel can display information such as respiratory frequency and depth in real time. The control buttons are convenient for inputting instructions. The air pressure sensing bag can sense the respiratory state. The internal components are compact to form a core unit, and the micro air pump and the like constitute an air pressure detection and regulation layout, so that the intelligent feedback and evaluation of the respiratory rehabilitation training are assisted.

This invention discloses a fine-grained respiratory monitoring method and device based on a diffusion generation model using millimeter-wave radar. The method includes: acquiring echo signals received by the millimeter-wave radar and calculating a one-dimensional range image; locating the range cell containing the human chest cavity and extracting continuous phase information; constructing a diffusion chain from phase observation to the respiratory truth value by using the phase as input to the forward diffusion process and the difference between the respiratory truth value and the phase as progressively added noise; designing a radar diffusion denoising device based on an attention mechanism and a feedforward neural network; training the radar diffusion denoising device according to the reverse diffusion process of the diffusion chain, iteratively optimizing the denoising device parameters by reducing the difference between the respiratory waveform output by the denoising device and the respiratory truth value; inputting the signal to be denoised into the radar diffusion denoising device to complete respiratory waveform denoising and calculate the respiratory frequency. This invention improves the accuracy of respiratory waveform reconstruction and the precision of respiratory frequency estimation.

This invention relates to the field of respiratory training equipment technology, and discloses a multi-level adjustable respiratory training mask for high-altitude hypoxic environment care. It includes a fixed support first, with an oxygen tank fixedly connected to its inner wall. A guide plate is fixedly mounted on the output end of the oxygen tank. A fixed support second is fixedly connected to the upper surface of the guide plate. A motor is fixedly mounted on the fixed support second, and a drive shaft is fixedly mounted on the output end of the motor. A large gear first is fixedly connected to the outer wall of the drive shaft. A guide post first is fixedly connected to the lower surface of the large gear first. A small gear first is meshed with the tooth end of the guide post first, and a gear ring first is meshed with the tooth end of the small gear first. By rotating the guide ring first, the through holes periodically overlap, adjusting the breathing rhythm of the mask body for high-altitude hypoxic breathing training. This not only guides the user's breathing frequency but also avoids wasting oxygen during exhalation.

The application provides a smart monitoring mattress with a graphene self-heating sleep-aiding function, and relates to the field of smart home and health monitoring.The smart monitoring mattress comprises a mattress main body, a graphene self-heating layer, sleep-aiding traditional Chinese medicine, a piezoelectric film sensor array, a main control unit, a communication module, a display module and a reminding module.The graphene self-heating layer is arranged inside the mattress main body and is used for releasing far infrared radiation under the stimulation of human body temperature.The sleep-aiding traditional Chinese medicine is arranged inside the mattress main body and is located outside the graphene self-heating layer and is spatially coupled with the graphene self-heating layer to form a composite sleep-aiding structure.The graphene self-heating material and the sleep-aiding traditional Chinese medicine are innovatively combined to form a composite sleep-aiding system with a synergistic effect.The piezoelectric film sensor array is integrated to realize the real-time and non-contact detection of core physiological characteristic data of a user, such as heart rate, breathing frequency and body movement.

The application discloses a device for CPD dummy breathing movement, and relates to the technical field of in-vehicle living body detection targets, which is arranged in a chest cavity of a CPD dummy and comprises a driving motor, a driving gear, a driving rack, a sliding shaft mounting seat, a linear motion bearing, a sliding shaft and a breathing push plate. The driving motor is fixed with the driving gear through a driving shaft thereof, the driving rack is fixed on the sliding shaft in an axial direction, the driving gear is engaged with the driving rack, the sliding shaft is slidably connected with the sliding shaft mounting seat through the linear motion bearing, and the breathing push plate is fixed on one side of the sliding shaft. The driving motor drives the driving gear to rotate clockwise or counterclockwise, and drives the sliding shaft to move linearly through the meshing transmission of the gear and the rack, so that the breathing movement of the dummy is realized. The technical scheme of the application adopts the motor driving and gear and rack transmission mode to realize the breathing movement simulation, has small operation difficulty and good flexible adjustment, and can be applied to application scenes with high requirements on breathing frequency and amplitude.

The utility model provides a kind of monitor capable of displaying pulse breath ratio parameter, including monitor body, still including respiratory data acquisition unit and pulse measurement unit, both are connected with control unit, control unit is connected with display unit in monitor body;Respiratory data acquisition unit is configured to collect the respiratory data of patient, and it is transmitted to control unit after being converted into digital signal, control unit can obtain the respiratory frequency of patient per minute;Pulse measurement unit is configured to be able to collect the pressure signal of patient when measuring pulse, and it is transmitted to control unit after being converted into digital signal, control unit can obtain the pulse number of patient per minute according to pressure signal;Control unit divides the ratio of pulse number per minute by respiratory frequency per minute and transmits to display unit to show, the ratio of pulse number per minute by respiratory frequency per minute is pulse breath ratio parameter. The above-mentioned monitor can display pulse breath ratio parameter on monitor display interface.

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.

The application relates to the technical field of atomizer control, and discloses a child intelligent atomizer capable of quantitatively guiding a breathing mode and a control system, which comprises a user analysis unit used for receiving real-time breathing frequency and body temperature data of a user through a mobile terminal, comparing and analyzing the collected real-time breathing frequency and body temperature data of the user with a standard database, identifying the use condition of the user, and generating a control instruction; the application increases the interactive feeling through voice guidance, pacifies the emotion, guides the breathing, and makes the small children naturally calm down through music; the light prompts abnormal conditions, sets up the atmosphere, effectively reduces the fear of the children for treatment, compared with common atomizers, the application can prompt correct breathing modes, the medicine deposition effect is better, in addition, the music is self-defined, the childlike and lovely appearance is matched, the atomizer is more like a music toy, the attention of the children can be transferred from the discomfort of treatment, and the cooperation degree is improved.

A method includes obtaining at least one breathing audio sample of a user captured using earbuds worn by the user. The method also includes converting the at least one breathing audio sample to a breathing spectrogram configured as an image. The method further includes processing the breathing spectrogram using a trained multi-task convolutional neural network (CNN) to identify a breathing rate and a breathing depth of the user. In addition, the method includes outputting the breathing rate and the breathing depth of the user.

This invention discloses an intelligent head-mounted fire self-rescue respirator for GPS-denied environments and its fire rescue information support method. The respirator includes a mask body, a breathing-driven energy capture-sensing linkage mechanism, an edge processing module, a multi-parameter detection module, and an adaptive communication and positioning module. The impeller generator of the linkage mechanism connects to a power management unit and a breathing frequency sensing unit, achieving coupling of energy capture and breathing monitoring. The multi-parameter detection module includes a photoelectric sensor array and a smoke concentration sensor. The communication and positioning module integrates fusion calculation and automatic relay node switching units. The method includes breathing-vitality coupled data acquisition, threat gradient-driven dynamic positioning, topology adaptive networking, fire situation-driven path planning, and multimodal adaptive feedback. This invention achieves self-powered endurance and dynamic power consumption matching, forming a closed-loop rescue support through end-edge-cloud collaboration, improving the efficiency and safety of self-rescue guidance in GPS-denied fire environments.

The application discloses a respiratory disease psychological intervention and sleep improvement system based on five-tone therapy, relates to the cross field of respiratory disease rehabilitation technology, traditional Chinese medicine five-tone therapy and intelligent medical equipment; the system collects respiratory parameters of a patient in a sleep state at night in real time and without contact through a 60G millimeter wave radar module, including key indexes such as apnea frequency, apnea duration, respiratory frequency and blood oxygen saturation, and through a multi-parameter coupling judgment algorithm, the system can accurately judge the current respiratory state of the patient, such as a pre-apnea symptom, an apnea state and a relief state, and accordingly generate corresponding five-tone adjustment instructions; the accurate monitoring and dynamic intervention mechanism effectively improves the pertinence and timeliness of intervention, and significantly improves the respiratory state and sleep quality of the patient.

The application aims to provide a respiratory training and monitoring integrated device, comprising: a sensor acquisition module, an oral-nasal mask or a blow nozzle type sensor acquires the respiratory data of a patient; a frequency sensor for monitoring the respiratory frequency of the patient; an adjustable resistance valve module located in the airflow channel of the device, comprising two key components, an inhalation resistance valve and an exhalation resistance valve, which are respectively arranged in the inhalation and exhalation channels, and the airflow resistance is changed by adjusting the valve opening degree; a data processing unit receives and processes the real-time data from the sensor acquisition module, and outputs a control signal to the resistance valve module after calculation; an algorithm model calculates a training resistance value suitable for the current lung function condition of the patient through a formula; and a feedback module is used for feeding back the data processed by the intelligent control system to the patient or medical staff. The device can adjust the inhalation and exhalation resistance in real time during the respiratory training process, and provide dynamic training feedback and progress.

The application provides a non-contact respiratory signal extraction method based on infrared thermal imaging video data, comprising the following steps: step 1, using a face detection and face key point positioning model on the original infrared video frame, and combining a sparse optical flow method to obtain the key point coordinates of each frame; step 2, obtaining a final region of interest; step 3, mapping the final region of interest back to the original infrared video frame without enhancement to obtain an original signal sequence; step 4, performing empirical mode decomposition on the original signal sequence to obtain an intrinsic mode function; according to the respiratory frequency characteristics, selecting the intrinsic mode function obtained by decomposition to reconstruct a reconstructed signal, performing band-pass filtering on the reconstructed signal to obtain a final respiratory signal; analyzing the power spectrum of the final respiratory signal, identifying the peak frequency point with the maximum amplitude, and calculating the final respiratory rate. The application has high motion robustness, and solves the common loss of lock problem in non-contact measurement through the cascade of multiple tracking mechanisms.

The application discloses a contactless breathing monitoring method and system for a newborn. Firstly, an infrared temperature image set is generated by a sliding time window, and a temperature change parameter set is read according to the infrared temperature image set, and then a real-time temperature change period model is generated by fitting. Subsequently, extreme value recognition is performed on the real-time temperature change period model, a breathing frequency parameter and a temperature parameter are calculated, the infrared temperature image set is analyzed, a breathing intensity parameter is calculated, and finally a comprehensive breathing score is generated according to the breathing frequency parameter, the temperature parameter and the breathing intensity parameter, and a breathing state monitoring result is output in combination with a standard judgment model. Based on the characteristics of the fixed posture of the newborn, the breathing of the newborn will cause rhythmic changes in temperature in a certain fixed area, and the above rules can be captured by analyzing the infrared temperature images of the above area, and the analysis of the breathing frequency, body temperature and breathing intensity is realized, and further, the contactless monitoring of the breathing of the newborn is realized.

This application provides an ultrasonic safety threshold monitoring method and related equipment. In this method, a control processing unit first acquires an impedance value sequence during the calibration period after the waist belt massager is started and calculates the average impedance value of the sequence. Then, the control processing unit acquires the current impedance value and calculates the impedance deviation relative to the average impedance value. When the impedance deviation exceeds an impedance deviation threshold, the control processing unit extracts impedance time-domain waveform data within a preset sliding window and extracts the peak interval frequency. Utilizing the inherent range of human respiratory frequency, it distinguishes between normal respiratory fluctuations and abnormal fluctuations. Finally, for abnormal fluctuations, the control processing unit acquires a temperature value sequence within the sliding window, calculates the heat accumulation rate, and uses a heat accumulation rate threshold to determine whether it is a true anomaly, avoiding misjudgments. This method alleviates the problem of inaccurate status recognition caused by respiratory interference in waist belt massagers and improves the accuracy of anomaly identification.

The application discloses an active respiratory synchronization guiding method based on an olfactory stimulator, which is applied to an olfactory stimulation system, wherein the olfactory stimulation system comprises a respiratory frequency sensor, an olfactory stimulator and a respiratory guiding audio-visual device, the respiratory frequency sensor, respiratory guiding software and a device are simultaneously used to realize the method, and bus communication is used between the devices; aiming at the difference of respiratory frequencies of different testers, a respiratory frequency detection sensor is used, the tester's respiratory frequency is collected before the test, and a guiding frequency is set according to the respiratory frequency; an active respiratory guiding mode is used, through the coordination between the devices, each stimulation can be realized in the time period when the tester inhales under the guidance of the respiratory guiding interface; a special respiratory guiding audio-visual device is designed to realize the communication function with other devices and the guiding interface function; the visual guiding interface can be designed into a breathing guiding picture and an added concentration video to guide the breathing and improve the concentration.

This invention provides a diving equipment testing machine, comprising: a workbench, a housing body bolted to the upper part of the workbench, a housing cover mounted on the upper part of the housing body, and a control frame mounted on the housing cover; a PCB function control center and a power adapter are housed inside the housing body, and an air intake pump body is located below the workbench, with an air intake pipe connected to one side of the air intake pump body. This diving equipment testing machine uses an electric actuator to set the water entry and exit points, achieving airtightness testing, reducing labor costs. It is equipped with high-pressure and medium-pressure gauges for intuitive display and recording, and the built-in air intake pump simulates human breathing frequency, highly replicating real breathing. Simple setup and rapid simulation: In terms of operation, this testing workbench provides a simple and intuitive operating interface. Operators only need to input the desired simulated breathing frequency and other parameters on the control interface, and the air intake pump will quickly operate according to the settings; the overall structure is simple, easy to install and disassemble, and has low maintenance costs.

The application discloses a multi-target respiratory signal separation method, system, device and storage medium, which is applied to the technical field of non-contact vital sign monitoring, and the method comprises the steps of: acquiring a training data set, wherein the training data set is generated by linear superposition of multiple respiratory source signals in a complex domain; constructing a deep learning separation model, wherein the deep learning separation model comprises a radar encoder module, a radar separator module and a radar decoder module which are connected in sequence; training the deep learning separation model based on the training data set by using a permutation-invariant training strategy; inputting the acquired respiratory phase signal into the trained deep learning separation model, and outputting separated target independent respiratory waveforms; and the application can separate and reconstruct the target independent respiratory waveforms in a complex scene with multiple people overlapping in space and similar respiratory frequencies, has strong noise robustness, and provides an effective solution for low-cost and non-contact health monitoring.