423 results about "Respiratory rate" patented technology

The invention relates to the technical field of health monitoring, and discloses a patient health monitoring method and system based on dynamic electrocardiogram analysis, and the method comprises the steps: synchronously obtaining multi-lead dynamic electrocardiogram data continuously collected by a patient within a preset duration, and related physiological parameters of exercise intensity, respiratory rate and body position change; performing dynamic self-adaptive preprocessing on the dynamic electrocardiogram data based on the associated physiological parameters to obtain standardized electrocardiosignals; extracting a multi-dimensional characteristic parameter set from the standardized electrocardiosignal, and sampling according to a preset time window to generate a characteristic parameter sequence with a timestamp; and inputting the characteristic parameter sequence into a dynamic optimization analysis model capable of iteratively updating parameters through real-time physiological parameter feedback, and performing graded evaluation on the health state of the patient to generate an evaluation result. The system corresponds to the method. By adopting the method and the system, the accuracy of dynamic electrocardiogram monitoring and the evaluation refinement level meet the dynamic monitoring requirement of cardiovascular health.

The invention relates to a human motion data processing method, and belongs to the technical field of data processing. Comprising the following steps: controlling a microwave radar to emit a detection signal, and detecting a heart rate signal and a respiration signal of a human body; performing clustering analysis on the data according to the collected heart rate and respiratory rate, and extracting heart rate, respiratory rate change, duration and exercise intensity characteristics; according to the extracted heart rate change, duration, exercise intensity and other characteristics, the exercise stage is recognized, and according to the neural network model library, an energy consumption result is output in combination with data analysis. According to the human motion data processing method provided by the invention, the microwave radar is combined with the intelligent wearable device, so that the detection precision of heart rate and respiration signals is remarkably improved, multi-modal data fusion is realized, personalized heart rate prediction is performed, motion stage division is optimized in combination with acceleration data, and the accuracy of motion data processing is improved. The accuracy of motion mode recognition is improved, and personalized motion suggestions can be provided for the user.

Systems, methods, and non-transitory computer-readable media containing instructions are disclosed for detecting and utilizing facial skin micro-motion. In some non-limiting embodiments, detection of facial skin micro-motion occurs using a speech detection system that may include a wearable housing, a light source (coherent light source or incoherent light source), a light detector, and at least one processor. The one or more processors may be configured to analyze light reflections received from the facial region to determine facial skin micromotion, and extract meanings from the determined facial skin micromotion. Examples of meanings that may be extracted from the determined facial skin micromotion may include words spoken by the individual (silent or voiced), an identity of the individual, an emotional state of the individual, a heart rate of the individual, a respiratory rate of the individual, or any other biometric, emotion or speech related indicator.

The invention particularly relates to a quartered sleep state monitoring method and a quartered sleep state monitoring system based on a non-contact vibration sensor. The quartered sleep state monitoring method and the quartered sleep state monitoring system are particularly suitable for realizing non-sensitive sleep quality evaluation through an intelligent bed in a family environment. Comprising the following steps that 1, vibration signals of a human body in the sleep process are continuously collected through a non-contact vibration sensor; step 2, preprocessing the vibration signal, including denoising and segmentation processing, to obtain time domain vibration data; step 3, performing frequency domain transformation on the time domain vibration data, and extracting frequency domain features including respiratory rate, heart rate and heart variability parameters; 4, time alignment is carried out on the frequency domain features and sleep staging labels synchronously obtained through a polysomnography, and a training data set is constructed; an XGBoost classification model based on time-frequency domain feature fusion is provided, fundamental frequency and harmonic energy proportions of respiratory signals are extracted through short-time Fourier transform, and quartering classification is achieved in combination with the LF / HF ratio of heart rate variability.

The invention discloses a respiratory rehabilitation training management system based on an applet, and relates to the technical field of medical health, and the system comprises a data collection module which collects the physiological data of a user in real time through a sensor at an applet end, and comprises a respiratory rate, thoracic and abdominal movement displacement, airflow pressure and a physiological state calculation module; according to physiological data collected in real time, the actual breathing flow of each patient is dynamically calculated through a thoracico-abdominal movement-airflow dynamics combined equation. According to the respiratory rehabilitation training management system based on the applet, by adopting a thoracico-abdominal movement-airflow dynamics combined equation and a lightweight LSTM network, delay between physiological feedback and training instructions is reduced, the real-time performance and individuation of rehabilitation training are ensured, through local real-time processing and feedback, the problem of traditional cloud delay is avoided, and the system is suitable for popularization and application. And the training compliance and the rehabilitation effect of the patient are effectively improved.

The invention discloses a millimeter wave radar vital sign detection method based on an HHO-CEEMDAM algorithm, and the method comprises the steps: building a millimeter wave radar experiment system, and collecting an intermediate frequency signal of a human body echo; performing data reading and recombination, extracting phase features, and enhancing a target signal through non-coherent accumulation to determine the distance between the chest of the human body and the radar; recovering the phase of the vital sign signal from the incoherent accumulation FFT result by using the linear characteristic of arc tangent demodulation, and performing phase unwrapping and phase difference to obtain optimized phase information; setting a CEEMDAN parameter initialization range and designing a fitness function; a CEEMDAN parameter is optimized by using an HHO algorithm; performing CEEMDAN decomposition by using the optimized parameters, and screening breathing and heartbeat IMF components; and according to the IMF component, obtaining estimated values of the respiratory rate and the heart rate. The method improves the estimation precision of the respiratory rate and the heart rate of the millimeter wave radar in fatigue driving detection.

The pelvic floor muscle self-adaptive rehabilitation training system comprises a data acquisition unit, a data processing unit, a type identification unit, a degree evaluation unit and a training adjustment unit, and is used for acquiring rectus abdominis data, gluteus maximus data, respiratory rate data and the like of a user in a pelvic floor muscle rehabilitation training process as compensation identification data; then, the type recognition unit can process the compensation recognition data to obtain unconscious compensation types of the user in pelvic floor muscle rehabilitation training, the compensation types comprise abdominal muscle compensation, hip compensation and suffocation compensation, and meanwhile, the degree evaluation unit can evaluate the severity of the compensation types, so that the degree of the pelvic floor muscle rehabilitation training is improved. Finally, the training adjusting unit can generate a multi-modal strategy according to different compensation types and different severity degrees, the multi-modal strategy is used for guiding pelvic floor muscle rehabilitation training of the user, intervention on compensation is achieved, it is guaranteed that the user conducts complete rehabilitation training on pelvic floor muscles, invalid training and even injury are avoided, and the rehabilitation effect is enhanced.

The invention provides an electrocardiogram data analysis method, device, medium and equipment based on multi-modal fusion, which are applied to early warning of acute coronary syndrome (ACS). The method comprises the following steps: acquiring time sequence data of electrocardiosignals and ballistocardiogram signals as well as structural data such as heart rate, respiratory rate and oxyhemoglobin saturation by using a portable device, and preprocessing the data; constructing a double-branch global and local interactive feature extraction model, respectively extracting local and global features of the electrocardiosignal and the ballistocardiogram signal, and simultaneously bridging the isomerism of the two signal types; after feature mapping is carried out on the structural data, inputting the structural data and features of the time series data into a feature fusion model; and finally inputting the fused features into a disease early warning model, outputting an ACS risk probability, and comparing the ACS risk probability with a preset threshold value to realize real-time monitoring and early warning. The method is of great significance to prevention of ACS and guarantee of life health of high-risk groups with cardiovascular and cerebrovascular diseases.

Technologies directed to respiration monitoring based on noise channel state information (CSI) data are described. A method includes receiving CSI data representing channel properties of a wireless channel used by a first wireless device and a second wireless device located in a geographical region. The method generates a set of CSI samples by sampling the CSI data and removes one or more outlier CSI samples using a sparse outlier process, and removes a cluster of outlier samples using a cluster outlier process. The method determines Fast Fourier Transform (FFT) data for each channel subcarrier index and a signal-to-noise ratio (SNR) value for each channel subcarrier index, and identifies a first number of channel subcarrier indexes having highest SNR values to obtain a subset of FFT data, which represents a breathing spectrum. The method determines a respiratory rate of a user in the geographical region from the subset of the FFT data.

The invention relates to the technical field of medical instruments, and discloses an intelligent device for monitoring the cardio-pulmonary function of a heart failure patient, the intelligent device comprises a multi-mode sensor module, an AI analysis module, a biological feedback module and a wearable carrier, the multi-mode sensor module is used for collecting heart rate, respiratory rate, oxyhemoglobin saturation and body movement data in real time, and the AI analysis module is used for analyzing the heart rate, the respiratory rate, the oxyhemoglobin saturation and the body movement data; monitoring modes can be dynamically switched in rest, motion and sleep scenes; the AI analysis module is used for detecting abnormity based on real-time data and predicting a heart failure deterioration risk in combination with historical data; and the biological feedback module is used for providing personalized intervention in a vibration or audio mode according to the analysis result. The heart rate, the respiration rate, the blood oxygen saturation and the body movement data are collected at the same time through the multi-mode sensor module, sleep apnea or periodic respiration is recognized in combination with the AI analysis module, the defect of separation of cardiopulmonary function monitoring and sleep mode analysis in the prior art is overcome, and therefore early intervention and treatment adjustment are supported.

The invention relates to the technical field of health management and medical information, and discloses an all-dimensional intelligent cardiopulmonary health management system and method and electronic equipment, and the system comprises a biological sensing module which is used for continuously collecting key physiological indexes of the heart rate, the oxyhemoglobin saturation, the respiratory rate and the motion state of a user; the data processing module is used for storing the collected physiological data and historical exercise records of the user through a central database of a cloud computing platform; the deep learning analysis module is a prediction model built based on a deep learning framework and is used for analyzing the physiological data of the user and generating a personalized exercise plan; the real-time monitoring module is used for detecting the physiological state of the user and automatically adjusting the exercise intensity or type when the physiological state exceeds a preset threshold value. The technical scheme that the multi-mode biosensor is combined with the real-time monitoring module is adopted, and the technical effect of comprehensively monitoring the cardiopulmonary function state of the user in real time is achieved.

The invention discloses an all-directional monitoring and emergency treatment system for patients in the emergency department, which belongs to the technical field of diagnosis and monitoring of emergency surgery and comprises a data input and acquisition module, a data processing module, a data processing module, a data processing module, a data processing module and a data processing module, wherein the data input and acquisition module is used for acquiring emergency treatment features including external stimulation inducements and ages of a current patient before emergency treatment; the monitoring and evaluation module is used for acquiring an epilepsy risk evaluation value, a comprehensive evaluation value and a feedback adjustment value, and collecting all-dimensional monitoring characteristics of a current patient, including amygdalia activeness, a brain activity reference level, abnormal discharge intensity, heart rate, respiratory rate, systolic pressure value and diastolic pressure value, and the monitoring and evaluation module is used for acquiring and outputting the epilepsy risk evaluation value, the comprehensive evaluation value and the feedback adjustment value; the early warning module is responsible for carrying out early warning and inputting an adjusted first-aid strategy to the first-aid execution module when the epilepsy risk assessment value, the comprehensive assessment value and the feedback adjustment value are in a continuous monitoring rising trend on the visualization module, and comprehensive and real-time monitoring and accurate assessment of the illness state of a patient and timely adjustment of first-aid measures are achieved.

The invention discloses an animal quarantine method, and aims to solve the problems of high omission ratio, early warning lagging and lack of environment optimization of the traditional quarantine means. According to the method, multi-dimensional biological signals such as the heart rate, the respiratory rate, the body temperature and the acceleration of an animal are collected in real time through an ear tag type wearable device, and the anomaly detection precision is improved through a self-adaptive sampling mechanism; meanwhile, the environment monitoring module collects the temperature, humidity and ammonia gas concentration of the farm, and dynamically regulates and controls the temperature, humidity and ammonia gas concentration in case of abnormality. And the edge computing node adopts a long-short-term memory network to fuse and analyze data, outputs an epidemic disease risk probability, and optimizes the model through self-learning. The embodiment shows that the method can perform early warning and environment optimization in the incubation period, the quarantine time is shortened to 5-10 minutes per head, the omission ratio is lower than 5%, and an efficient and accurate epidemic disease prevention and control solution is provided for the breeding industry.

The invention belongs to the technical field of sleep quality analysis, and particularly relates to a sleep quality analysis system and method based on a medical bed sensor, so as to solve the technical problem that an existing method excessively depends on duration statistics and neglects sleep continuity and periodic rhythmicity. The analysis method comprises the following steps: S1, acquiring sign signal data acquired by a sensor on a medical bed in a sleep cycle, and dividing the sign signal data into a plurality of continuous time slices; s2, extracting physiological indexes of respiratory rate, heart rate and body movement amplitude in each time slice, and calculating variation depth of the corresponding time slice; s3, generating a variation depth baseline; calculating an unsteady state disturbance factor according to the occurrence frequency and the duration of the micro-awakening disturbance fragment; and S4, generating a sleep quality comprehensive score. According to the analysis method, the comprehensiveness and objectivity of the evaluation result are improved, and the sleep health condition is reflected more truly.

The invention belongs to the technical field of medical health monitoring, and provides a human health prediction method and system based on facial video physiological signal detection, and the method comprises the steps: collecting a facial video stream, and extracting time sequence physiological signals such as heart rate, HRV, respiratory rate and the like through an rPPG algorithm; constructing a graph database individual health portrait in combination with multi-scale time sequence alignment; adopting a dynamic threshold algorithm to detect instantaneous anomaly, and fusing nonlinear dynamics and waveform morphological characteristics to quantify anomaly; constructing a hybrid model, extracting space-time and high-order features, and modeling multi-parameter interaction; a prediction result is dynamically corrected based on a Bayesian algorithm, and health risk layering is realized through clustering; and outputting the visual health report. Through non-contact monitoring, multi-modal fusion and edge-cloud collaborative architecture, the problems that traditional equipment is low in compliance, non-contact technology is insufficient in precision and prediction is shallow are solved, dynamic health prediction and closed-loop management are achieved, and the system is suitable for scenes such as remote monitoring and chronic disease screening.

The invention discloses intelligent pasture livestock health monitoring equipment. The equipment comprises a vital sign monitoring mechanism worn on the legs of livestock, a behavior monitoring mechanism worn on the neck of the livestock and an environment monitoring mechanism vertically extending and arranged on the pasture ground; the vital sign monitoring mechanism comprises a vital sign monitoring fixing ring, a vital sign monitoring supporting shell with an upward opening is connected to the vital sign monitoring fixing ring, and a plurality of body temperature monitoring sensors are connected into the vital sign monitoring supporting shell; a pulse monitoring through hole penetrating in the radial direction of the physical sign monitoring fixing ring is formed in the side face of the physical sign monitoring fixing ring, and a pulse monitor is arranged at the pulse monitoring through hole; the behavior monitoring mechanism comprises a conventional monitoring camera, a high-speed monitoring camera and an infrared monitoring camera; the equipment can accurately collect various physiological data of livestock, such as body temperature, heart rate, respiratory rate and the like, as well as behavior data, such as activity amount, ingestion time, rumination times and the like, so that the accuracy and reliability of the data are ensured, and an accurate basis is provided for evaluating the health condition of the livestock.

The invention provides a terminal data management method and system for medicine sales. According to the method, medicine purchasing historical data, electronic health record data and allergy taboo data of customers are integrated to construct a medicine adaptive sign map, and the map establishes a dynamic association relationship between medicine indications and sign parameters. And acquiring heart rate and respiratory rate parameters of the customer in real time, and matching the heart rate and respiratory rate parameters with the physical sign parameters in the map to generate a physical sign parameter matching result. And generating a personalized recommendation instruction containing an initial recommended drug list and taboo prompts in combination with taboo rules and curative effect data in the drug indication library. According to the real-time change trend of the heart rate and the respiratory rate, the drug priority of the recommendation list is dynamically adjusted, finally, an updated recommendation drug list is generated and sent to the sales terminal equipment, and accurate drug recommendation based on the real-time health state is achieved. According to the technical scheme provided by the invention, the security and accuracy of terminal data management can be improved.

The invention discloses an intelligent animal husbandry and veterinary diagnosis system based on machine learning, and particularly relates to the technical field of intelligent animal husbandry diagnosis. The livestock body surface temperature, the livestock chewing data and the livestock movement data are processed to obtain the real body temperature, the rumination time, the movement state and the movement speed of the livestock, and the livestock heart rate, the respiratory rate, the real body temperature, the rumination time and the movement speed are input into a livestock sign abnormity recognition model for abnormity recognition. The behavior data of the livestock is obtained through the multi-angle camera, the abnormal image data set is marked after a series of processing, the received livestock sign abnormal data set and the received livestock behavior abnormal image data set are input into the livestock health intelligent diagnosis model for health diagnosis, and the livestock illness state diagnosis efficiency and accuracy can be effectively improved.

The invention relates to the technical field of riding safety monitoring, in particular to a riding monitoring method, device and system and an electric vehicle. The method is applied to the electric vehicle and comprises the steps that physical sign information of a user in a riding task is obtained, and the physical sign information at least comprises the body temperature, the heart rate and the breathing frequency; vehicle state information of the target vehicle is obtained, the riding behavior level of the user is determined based on the vehicle state information, and the behavior level represents the intense degree of riding the target vehicle by the user; the vehicle state information at least comprises a vehicle body inclination angle, a driving speed, braking times and a braking speed; the riding risk level of the user is determined based on the physical sign information and the behavior level, an early warning instruction is generated when the riding risk level meets the set requirement, and the early warning instruction is used for conducting risk prompting on the user and / or conducting deceleration on the target vehicle. By the adoption of the scheme, the safety of a user in the riding process can be improved.

The invention discloses an interactive nursing teaching system for nurses and patients, relates to the technical field of nursing teaching, and aims to solve the problems that the traditional teaching is difficult to create a highly tense and complex emergency room atmosphere, students cannot deeply experience the pressure caused by time urgency, and serious consequences possibly caused by slightly poor information transmission. The nursing teaching system comprises a scene simulation module, an interaction module, an intelligent feedback module and a case management module. The scene simulation module utilizes virtual reality and augmented reality technologies to restore the environment of an emergency room and dynamically simulate patient condition changes, and the condition changes comprise dynamic adjustment of the heart rate, the blood pressure, the respiratory rate, the pain degree and the consciousness state of a patient in real time according to different emergency diseases; the interaction module comprises a voice interaction device and an action interaction device. The system has the advantages that the adaptation period of students entering clinical practice, especially emergency room work, is effectively shortened, and the nursing work efficiency and quality are guaranteed.

The present invention proposes a breathing frequency detection method based on time-frequency analysis of Hilbert-Huang transform. First, a WiFi link with strong environmental perception sensitivity is selected to construct a channel state information (CSI) ratio model. Secondly, the filtered CSI ratio time series is projected, and candidate sets of different breathing mode signals are generated by combining amplitude and phase information. Thirdly, the selected breathing modes are subjected to signal variational mode decomposition (VMD) and time-frequency analysis of Hilbert-Huang transform, so as to remove non-human breathing frequency components. On this basis, reconstruction is carried out, and the reconstructed signals are fused using principal component analysis (PCA). Finally, the breathing frequency is calculated through a false peak detection algorithm. The breathing frequency detection algorithm designed by the present invention not only expands the sensing range and eliminates "blind spots" while removing time-varying phase offsets and high-frequency noise and selecting the optimal subcarriers, but also improves the breathing frequency detection accuracy, providing a more accurate detection method for non-contact breathing frequency detection.

The invention provides a vital sign detection method and device based on a millimeter wave radar, electronic equipment and a storage medium. The method comprises the following steps: obtaining a distance frequency domain signal based on a radar echo signal; performing spectral analysis on the distance frequency domain signal, positioning the position of the to-be-detected object, and extracting phase information at the position; filtering through a band-pass filter to obtain a breathing frequency band interval signal and an initial heartbeat frequency band interval signal; performing real-time respiration rate estimation based on the respiration frequency band interval signal to obtain a respiration frequency, and eliminating respiration harmonics in the initial heartbeat frequency band interval signal by using an adaptive wave trap based on the respiration frequency to obtain a heartbeat frequency band interval signal; and with the minimum fuzzy entropy as an optimization target, decomposing the heartbeat frequency band interval signal by using a variational mode decomposition algorithm to obtain a heartbeat signal, and carrying out real-time heart rate estimation based on the heartbeat signal to obtain a real-time heart rate. According to the method, the device, the electronic equipment and the storage medium provided by the invention, the accuracy of heart rate measurement can be improved.

An apparatus for vital sign extraction. The apparatus may receive a vital signal of a subject from a sensing device. The apparatus may also perform a preprocessing procedure on the vital signal via bandpass filtering and normalization to obtain a preprocessed signal. The apparatus may also perform a time-frequency analysis of the preprocessed signal, and estimate a heart rate of the subject from a dominant component of the preprocessed signal by finding location of a maximum spectral energy of the time-frequency analysis. In addition, the apparatus may identify guard components in the preprocessed signal in view of the dominant component, and derive a respiratory rate of the subject from a length of an interval between the dominant component and each of the guard components.

A non-contact, non-invasive health monitoring device and method utilizing advanced artificial intelligence (AI) and machine learning techniques. This system captures real-time image data of a user's face using a high-resolution camera and processes the data to extract physiological signals, including Photoplethysmography (PPG, iPPG, and rPPG) and Ballistocardiography (BCG and iBCG). By leveraging facial landmark detection and deep learning models such as Convolutional Neural Networks (CNNs) and Transformers, the device predicts vital signs such as heart rate, respiratory rate, blood pressure, and oxygen saturation, alongside wellness metrics like stress levels and metabolic health. The device employs robust feature construction and signal processing modules to ensure accurate metrics under varying conditions, with error margins below 5%. Outputs are displayed in real time and integrated with external systems using standardized healthcare protocols. Applications include telehealth, fitness monitoring, public health screening, and automotive safety systems.

The invention discloses an infant state recognition method and system based on traditional Chinese medicine five-tone monitoring analysis, and the method comprises the steps: synchronously collecting the crying sound, physiological signals and behavior videos of an infant, extracting the Mel-frequency cepstral coefficient of the audio, the heart rate variability, galvanic skin response and respiratory rate of the physiological signals, and the facial expression and limb movement features, and carrying out the recognition of the state of the infant through the Mel-frequency cepstral coefficient of the audio, the heart rate variability, galvanic skin response and respiratory rate. Performing structured integration by using a multi-modal feature fusion model; in combination with the five-tone theory of traditional Chinese medicine, a corresponding relation between audio features and five-organ states is established, and the robustness of five-tone and five-organ mapping is improved through fuzzy reasoning and a Bayesian mechanism; the system dynamically adjusts the weight coefficient of each mode, adapts to the individual and emotion historical trend, achieves more accurate emotion recognition and physiological evaluation, achieves cross-mode and multi-layer information fusion, improves the accuracy and interpretation ability of infant emotion and five-internal-organ state recognition, and provides a scientific basis for clinical evaluation and health management.

The invention relates to the technical field of emergency triage, in particular to an intelligent pre-examination triage method and system for an emergency child patient, and the method comprises the steps: collecting the vital sign data, symptom complaint information and past medical history of the emergency child patient in real time through a medical Internet of Things device; an illness crisis degree evaluation model is constructed, an illness crisis coefficient K of the child patient is calculated based on a multivariate parameter fusion algorithm, and the parameters comprise a respiratory rate abnormal value delta R, a blood oxygen saturation degree deviation degree S, a consciousness state classification C and a pain index P; according to the method, the predicted available time T of the doctor can be calculated according to the coefficient eta of the doctor resource dynamic evaluation matrix, and the predicted available time T is matched with the illness state critical coefficient K of the child patient, so that reasonable distribution of the child patient and the doctor is realized; therefore, doctors with high professional ability and low workload can be distributed to the child patients with critical illness, the treatment efficiency and quality are improved, and meanwhile, the doctor-patient problem caused by the fact that the child patients with serious illness cannot be treated in time is also avoided.

The invention discloses personal life support equipment in a high-altitude environment and a cooperative control method thereof, and relates to the technical field of personal life support equipment, and the equipment comprises a respiration sensor which is arranged on a mask and is used for detecting respiration frequency and phase; the blood oxygen and heart rate sensor is worn on the wrist of the user and used for detecting the blood oxygen saturation degree and the heart rate; the body temperature sensor is attached to the chest of the user and used for detecting the core body temperature; the automatic oxygen supply device is used for providing oxygen; the intelligent heating device comprises partition heating pieces attached to the chest and the four limbs of the user and is used for partition heating; the microcontroller unit is used for formulating an optimal life support strategy according to the sensor data and intelligently and cooperatively controlling the working states of the automatic oxygen supply device and the automatic heating device according to the optimal life support strategy; the sensor data comprises respiratory frequency and phase, oxyhemoglobin saturation, heart rate and core body temperature, and dynamic oxygen supply and body temperature adjustment can be cooperatively controlled.

The invention aims to provide a portable automatic adjustment negative pressure sputum suction device based on multi-parameter monitoring, which comprises a negative pressure sputum suction device main body used for generating adjustable negative pressure and connected to an airway of a patient through a sputum suction pipe; the respiratory rate sensor is mounted at the inlet of the sputum suction tube and used for monitoring the respiratory rate of the patient in real time; the sputum suction resistance sensor is mounted in the sputum suction tube and used for monitoring the resistance change in the tube in the sputum suction process in real time; the sputum viscosity sensor is arranged between the sputum suction tube and the sputum collection bottle and is used for monitoring the viscosity of sputum in real time; the control unit controls the negative pressure sputum suction device main body to output corresponding negative pressure; the sputum suction device aims at monitoring the respiratory rate, the sputum suction resistance and the sputum viscosity of a patient in real time, a dynamic negative pressure adjusting mode is adopted, the sputum suction efficiency can be improved, and meanwhile damage of excessive suction to an airway can be avoided.

Various example of the present disclosure provide sensing apparatuses configured for wearable and wireless use for deep tissue physiological monitoring. The sensing apparatuses may be embodied by a thin flexible patch configured to conform with a skin surface of a subject. A sensing apparatus may include a plurality of microneedles oriented to extend towards and penetrate into the subject to a shallow depth. The microneedles may be configured as waveguides for a given sensing modality (e.g., light, ultrasound), such that sensing wave signals propagate to deep tissues. For the sensing, the sensing apparatus includes waveform generators (e.g., light-emitted diodes) and waveform detectors (e.g., photodiodes). Machine learning models may be used to process and denoise sampled data from the waveform detectors and to generate accurate and reliable physiological measurements, including heart rate, respiratory rate, pulse intensity, respiratory intensity, blood oximetry, tissue oximetry, blood flow rate, and / or the like.

The invention discloses a multi-view fusion millimeter wave radar breath and heartbeat monitoring method. The method comprises the following steps of 1, performing data preprocessing on collected millimeter wave radar original data, and obtaining time domain data, frequency domain data, real number data and imaginary number data from the radar original data; 2, using a backbone network of a channel attention convolution module to process the preprocessed data in parallel, and extracting effective features of each part; and step 3, processing a low-dimensional spatial feature # imgabs0 # or a high-dimensional spatial feature # imgabs1 # through a cross-domain fusion convolution Transform module. And 4, dynamically adjusting the importance of each part of the low-dimensional spatial feature # imgabs2 # and the high-dimensional spatial feature # imgabs3 # by using weight fusion, and generating a final fusion feature. And 5, performing multi-loss joint learning to optimize the prediction model by using the proposed fusion distance alignment harmonic index loss of the dynamic weight, the mean square error and the negative Pearson correlation loss. And 6, predicting the respiratory rate and the heart rate in parallel by the model by sharing the bottom fusion features.