45 results about "Heart rate change" patented technology

The invention discloses an intelligent temperature control mattress system based on multi-mode sensing and adaptive learning, and the system comprises a data collection module which is used for collecting a mattress surface vibration signal, a mattress surface temperature and a mattress surrounding environment parameter; the data analysis module is used for performing deep analysis on the time-frequency domain features according to a biological recognition model to obtain human body or non-human body classification, performing self-learning to obtain body movement changes, accurately recognizing various typical sleeping postures and filtering out error data; and the model prediction module is used for monitoring the physiological parameters of the user according to the spectral analysis, inputting the physiological parameters, the collected temperature and the parameters of the surrounding environment of the mattress into a temperature control model composed of three neural networks of LSTM, GNN and Transform for comprehensive analysis and decision making, and outputting an optimal temperature control strategy. According to heart rate changes or body heat fluctuations, the sleep stage and the sleep and waking time are intelligently recognized, and therefore sleep environment adjustment better conforming to the human body rhythm is achieved.

The invention discloses an emergency nursing system capable of dynamically adjusting priority, which belongs to the technical field of emergency nursing and comprises the following steps: acquiring heart rate detection data, blood pressure detection data and oxyhemoglobin saturation detection data of a patient at preset time intervals, and filtering; setting a sliding time window, and respectively calculating a heart rate change rate, a blood pressure change rate and an oxyhemoglobin saturation change rate for the filtered heart rate detection data, the filtered blood pressure detection data and the filtered oxyhemoglobin saturation detection data in the sliding time window; correlation analysis is conducted on the heart rate change rate, the blood pressure change rate and the blood oxygen saturation degree change rate, parameter correlation characteristics are obtained, and a comprehensive parameter deterioration index is calculated; the comprehensive parameter deterioration index is compared with a preset threshold value, and whether a priority improvement mechanism is triggered or not is judged; and executing the priority lifting mechanism. By establishing a dynamic monitoring mechanism based on the change rate of the physiological parameters, real-time capture and quantitative analysis of the change trend of the illness state of the patient are realized.

The invention relates to the technical field of resistance adjustment, in particular to a multifunctional spinning and a multifunctional spinning system, and the system comprises a pedaling frequency recognition module, a state judgment module, a stage control module, a load adjustment module and an output response module. According to the invention, through continuous analysis of the pedaling frequency and time information, accurate recognition of the rhythm fluctuation state, and combination of the linkage change of the flywheel rotation speed and the pedal pressure, the dynamic judgment of the motion stability and the matching mechanism of the training time and stage setting are realized; a resistance adjusting strategy is deduced according to the relation between flywheel acceleration and pedal pressure, the sensitivity and precision of regulation and control response are enhanced, the load weight is set by fusing the heart rate change trend, the resistance output is more matched with the individual physiological state, the load rhythm matching degree is optimized, and the training efficiency is improved. And the rhythm following capability, the resistance adjustment rationality and the training individuation level are integrally improved.

The invention discloses a children propofol anesthesia depth monitoring method based on permutation entropy and heart rate change, and belongs to the technical field of anesthesia depth monitoring, and the method comprises the following steps: extracting a children electroencephalogram, and carrying out preprocessing and spectral analysis on the children electroencephalogram to obtain permutation entropy; child heart rate data are extracted and processed to obtain the heart rate change degree; inputting the permutation entropy, the heart rate change degree and the age into the mixed prediction model to obtain a composite index, and indicating the narcotic depth of the propofol for the children. According to the children propofol anesthesia depth monitoring method based on the permutation entropy and the heart rate change, the mixed prediction model is constructed by combining the electroencephalogram permutation entropy, the heart rate change degree and the child patient age, and higher accuracy, real-time performance and reliability are shown in children propofol anesthesia depth monitoring; the anesthesia state change can be quickly responded, and the problem of misjudgment caused by age dependence and insufficient linear processing in the prior art is effectively solved.

The invention discloses a temperature adjusting method and system for moxibustion equipment controlled by an intelligent chip, and the method comprises the steps: firstly, collecting a heart rate sequence of a user during moxibustion through the intelligent chip, decomposing a long-term trend item and a short-term fluctuation item, and calculating the instantaneous heart rate change; thirdly, a causal model of the instant heart rate change and a temperature sensitivity variable is built according to the instant heart rate change; secondly, extracting historical moxibustion temperature setting data from the equipment database, and analyzing temperature setting preferences of a user in different temperature sensitivity states; splitting a basic preset temperature and a fluctuation temperature regulation part based on preference characteristics, and determining fluctuation temperature regulation coefficients in different heart rate reaction modes according to heart rate changes; meanwhile, the preference and change of the user to the moxibustion part are analyzed in combination with historical use records; and finally, storing the personalized temperature adjustment data of the user in the intelligent chip, and updating the personalized temperature adjustment data in real time after the personalized temperature adjustment data is used each time. The method can effectively grasp personalized demands of users and improve the moxibustion experience and effect.

A cardiopulmonary management system includes a multi-sensor device and a controller. The multi-sensor device includes an elongated body having a first end and a second end, a first electrode disposed at the first end of the body, a second electrode disposed at the second end of the body, an electrical circuitry disposed near a middle of the body, and a sound sensor. The multi-sensor device is configured to be disposed on a skin of a subject and to measure cardiopulmonary parameters from the subject. The controller is configured to derive a score of sound change, heart rate change, thoracic impedance change, respiratory rate change, QRS wavelength change, QT interval change, electromechanical activation time change, and left ventricular systolic time change based on the measured cardiopulmonary parameters. The controller is further configured to control an operation of the system when the derived score is greater than a threshold.

The invention discloses a non-contact real-time heart rate detection method and system based on rPPG and wavelet enhancement, and belongs to the technical field of medical health. Face video signals are collected through the camera, a sensor or an electrode does not need to be worn, real non-contact physiological signal detection is achieved, and the comfort level and use convenience of a user are improved; discrete wavelet transform denoising and enhancement processing is introduced on the basis of pulse signals extracted by a POS algorithm, and high-frequency noise caused by illumination variation, camera quantization errors and facial movement is removed through multi-scale decomposition and threshold filtering, so that the signal-to-noise ratio of the pulse signals is remarkably increased; the fast Fourier transform is combined with a sliding window mechanism, so that real-time updating and continuous calculation of the heart rate can be realized; the signal after wavelet enhancement is clearer in periodicity, so that the heart rate calculation error is remarkably reduced, a dynamic visual interface of a heart rate change curve and a pulse waveform is provided, a user can observe physiological state changes in real time, and good interactive experience is achieved.

The invention provides an intelligent data analysis method for a pension information service system, relates to the technical field of physiological data processing, and aims to judge behavior stages according to the daily moving speed of the elderly and the continuity of the speed in time, select stable effective behavior stages through deterministic scores, and improve the accuracy of the behavior stages. Judging a corresponding behavior state according to the change characteristic of the heart rate in the effective behavior stage, identifying the body function expression of the old person in the corresponding state according to the change rate characteristic of the central rate of each behavior state, and judging the reaction intensity in the first behavior state and the flat intensity in the second behavior state; and a heart function change index is constructed by combining the long-term comprehensive expression of the reaction intensity, the flat intensity and the heart rate in the third behavior state, so that the overall body function change characteristics are reflected and quantified, and a guardian can conveniently know the overall body condition change of the old.

The present disclosure provides an information processing device, alcohol intake estimation device, method for calculating an indicator for estimating alcohol intake, alcohol intake estimation method, biological examination method, biological examination device, estimation device, learning model, estimation method, learning model generation method, and computer program. The information processing device comprises a processing unit that acquires a total heart rate change representing the total sum of heart rate changes, which are amounts by which a subject's heart rate has changed. The processing unit calculates a first indicator for estimating alcohol intake, said indicator representing the total heart rate change in a state in which the subject is inactive and a state in which the heart rate of the subject exceeds a reference heart rate.

The invention relates to the technical field of data processing, in particular to a preoperative anxiety relieving method and system based on the virtual reality technology, and the method comprises the steps: obtaining preoperative physiological rhythm data of a patient, the physiological rhythm data at least comprising respiratory frequency and heart rate change information; constructing a virtual natural scene with dynamic light and shadow changes based on the physiological rhythm data, wherein the virtual natural scene comprises light and shadow fluctuation elements corresponding to the respiratory frequency; a patient wears a VR head-mounted display and a bone conduction earphone, the equipment automatically loads a customized virtual scene, breathing key points are prompted in real time through virtual guidance, and the patient is helped to establish perception association of rhythm elements; the physiological data of the patient is analyzed in real time to obtain the respiratory rate, the heart rate variability and the skin electrical activity value, and when the difference value between the light and shadow fluctuation frequency and the respiratory rate exceeds a threshold value, the light and shadow frequency is adjusted step by step to approach the respiratory rate. According to the multi-dimensional evaluation system, the anxiety state of the patient is reflected more comprehensively, and insufficient intervention caused by evaluation deviation is avoided.

The invention discloses a swimming pool automatic alarm system based on electrocardio monitoring, and relates to the field of electrocardio monitoring, and the system comprises a collection module which is used for collecting electrocardio data and equipment position correlation signals output by equipment worn by a swimmer in real time; the fusion module is used for carrying out de-noising processing on the collected two types of data, extracting heart rate change features and position movement features and generating a fusion feature data set; according to the method, relevant data are synchronously collected in real time and accurately denoised, key features of heart rate change and position movement are fully extracted, the abnormal linkage rule of the heart rate and the position is quantitatively analyzed, and the drowning state of the swimmer is accurately judged.

The present application relates to the technical field of non-contact vital sign monitoring, and specifically discloses a heart signal detection method based on feature decoupling millimeter wave radar based on contrast learning. The present application realizes the automatic separation of the rhythm feature and the morphological feature of the heart signal from the millimeter wave radar signal by constructing an adaptive filtering module, a sample generator, a multi-scale feature extraction module, a double-path feature decoupling module, a physical constraint module and a contrast learning loss function. The present application uses contrast learning to construct a positive sample pair, guides the model to learn a feature representation that is invariant to heart rate changes and waveform deformation, and combines physiological prior constraints to improve the robustness and interpretability of the features. The present application effectively solves the shortcomings of traditional methods in signal separation, noise suppression and generalization ability, and can be widely applied to heart rate variability analysis, arrhythmia detection and other heart health monitoring tasks.

The invention discloses an intelligent motion state recognition method and system based on big data analysis, and relates to the technical field of motion feature recognition, and the method comprises the steps: obtaining motion sensor information, obtaining user historical motion data according to the motion sensor information, classifying motion state types on the basis of the user historical motion data, and obtaining a motion state classification result; and obtaining motion state classification information. According to the method, different motion states are divided into multiple categories through the motion state classification information, a basis is provided for follow-up motion state recognition, the heart rate change condition of each motion state type is accurately analyzed through the heart rate difference reference coefficient, and the motion state recognition accuracy is improved. A data standard is provided for the time interval of heart rate change condition analysis through the heart rate increase reference time, the user motion state is recognized through the user motion state recognition index, the motion state recognition efficiency is improved, and the stability and accuracy of motion state recognition are ensured.

To improve the accuracy of fatigue assessment in subjects. [Solution] The calculation unit 36 ​​calculates, from the changes in the heart rate of a subject who has taken actions to recover after a temporary increase in heart rate, at least the RRI overshoot ratio, which is the ratio of the increase in RRI to the decrease in RRI, as a characteristic quantity of heart rate change. The determination unit 44 then determines the fatigue of the subject based on the characteristic quantity of heart rate change calculated by the calculation unit 36.

The embodiment of the invention discloses a non-contact special post competency assessment method and device and a medium, and the method comprises the steps: determining the movement data and flicker frequency of a target point location based on the work task information of a current special post, so as to control the target point location to carry out the first-stage movement; superimposing interference information on the first-stage movement based on a preset interference condition so as to carry out second-stage movement; canceling the interference information to control the target point location to move in the third stage; collecting pupil time sequence data of each stage of a tester through a preset eye tracker, collecting heart rate change data of each stage according to a preset camera, and determining input data corresponding to each stage according to the pupil time sequence data and the heart rate change data; and taking the input data as a data set, obtaining a psychological competency assessment model based on multi-layer perceptron training of a preset artificial neural network model, and inputting the input data of the current tester into the psychological competency assessment model to obtain a psychological competency assessment result.

The invention discloses a health anomaly detection system supporting long-term tracking, and relates to the technical field of health management, and the system comprises a historical data processing end, a dynamic health baseline modeling end, a real-time deviation quantification end, and an analysis evaluation and output end. The system obtains historical heart rate data of a user, constructs a sequence according to a period and analyzes the sequence, and establishes a personalized standard heart rate change curve as a health baseline; in the real-time monitoring process, the system collects current heart rate data and compares the current heart rate data with a baseline, and health abnormal events are recognized by calculating the deviation area between curves; in addition, the system can also distinguish continuous abnormal events and sudden abnormal events in combination with historical abnormal records, and finally pushes analysis results to the user and related medical personnel, so that long-term and automatic health risk monitoring and early warning are realized.

The application provides a heart rate monitoring and incentive device, which comprises a ring-shaped packaging shell, the inside of the ring-shaped packaging shell comprises, from top to bottom, a polarized piezoelectric film, a magnetoelastic film, an electromagnetic coil, a charge collection module, a Bluetooth module and a power module in sequence, the polarized piezoelectric film is connected with an electrode, the electrode is electrically connected with the charge collection module, the electromagnetic coil is electrically connected with the power module, the diameter of the polarized piezoelectric film is 17-19 mm, and the thickness is 2-4 mu m. The device can accurately detect the heart rate change of the human body, timely remind when the heart rate is abnormal, avoid accidents, and effectively solve the problems that the existing detection device cannot be portable real-time monitoring, the detection is inaccurate, and there is no wake-up function.

The invention relates to the technical field of physiological monitoring, in particular to a mental state real-time feedback system based on intelligent wearable equipment, which comprises a sequence construction module, a weight analysis module, a weight correction module, an index generation module and a hierarchical judgment module. According to the method, the multi-dimensional breathing fluctuation sequence containing the amplitude difference of the inspiration section, the duration of the expiration section and the change of the breathing rate is constructed, the multi-dimensional breathing fluctuation sequence and the heart beat interval sequence are mapped into the same multi-dimensional space, the Euclidean distance between the multi-dimensional breathing fluctuation sequence and the heart beat interval sequence is calculated to serve as the dynamic weighting coefficient, and the coupling strength between the cardiopulmonary systems can be quantified; therefore, the adjustment state of the autonomic nervous system is disclosed more deeply, state misjudgment possibly generated due to the fact that breathing activities cannot be associated when heart rate changes are analyzed in an isolated mode is avoided, meanwhile, the system can actively detect electrocardiosignal baseline drift and breathing waveform abnormal fluctuation, and the weighting coefficients are screened and corrected based on the interference degree.

The present application relates to the technical field of nursing decision, specifically to a nursing scheme auxiliary selection system for orthopedic patients, in the present application, in the rehabilitation training process, the moving track of the patient is collected in real time and deviation analysis is conducted with the ideal path, the deviation risk fragment set is established by means of the spatial coordinate sequence and the Hurst index calculation mode, the identification and positioning of the deviation trend of the rehabilitation action are strengthened, and the accuracy of the walking control stability evaluation is enhanced. The heart rate signal is mapped to a multi-dimensional density space, the local abnormal interval in the heart rate change is accurately calibrated through the local abnormal factor operation mode under the sliding window, and the identification of the slight physiological change is facilitated. The heart rate abnormal interval is classified and processed according to the duration, a heart rate fluctuation typing system is constructed, the transient physiological fluctuation and the continuous stress state can be effectively distinguished, and the identification degree of the pain inducement is improved.

This invention relates to a protective device, and more particularly to a protective device for impulsive behavior in patients with mental disorders. It includes a clothing-type airbag, an air pump, a deflation valve, and a fastening mechanism. The clothing-type airbag, when inflated, restricts the movement of the patient. The air pump is installed on the rear side of the clothing-type airbag, and its outlet communicates with the airbag. The deflation valve is also installed on the rear side of the clothing-type airbag, and a fastening mechanism for securing the airbag is located on the front side. This invention involves wearing the clothing-type airbag on the patient with a mental disorder. By monitoring the patient's heart rate changes with a heart rate monitor, it can detect impulsive behavior in real time. The inflating of the clothing-type airbag restricts the patient's movement, thus protecting people and objects around the patient without requiring medical personnel to approach, providing a high level of safety.

1. The name of the design product: smart ring (saddle). 2. The use of the design product: for wearing decoration and monitoring user's heart rate changes and other physical data. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

The present application relates to the technical field of data processing, in particular to a patient rehabilitation scheme design method and system based on multi-modal fusion, comprising: acquiring physiological rhythm data of a patient before surgery, the physiological rhythm data at least including respiratory frequency and heart rate variability information; constructing a virtual natural scene with dynamic light and shadow changes based on the physiological rhythm data, the virtual natural scene containing light and shadow fluctuation elements corresponding to the respiratory frequency; wearing a VR headset and a bone conduction earphone for the patient, the device automatically loading a customized virtual scene, and real-time prompting of breathing points through a virtual guide to help the patient establish a perception association of the rhythm elements; real-time analysis of the patient's physiological data to obtain the respiratory frequency, heart rate variability and skin electrical activity value, and step-by-step adjustment of the light and shadow frequency to approach the respiratory frequency when the difference between the light and shadow fluctuation frequency and the respiratory frequency exceeds a threshold value. The multidimensional evaluation system of the present application more comprehensively reflects the anxiety state of the patient and avoids insufficient intervention caused by evaluation bias.

The present application relates to a kind of anti-noise PPG biological recognition methods based on spectrum-KAN discretization and multi-scale convolution cooperation, belong to the field of biological feature recognition, including: physiological feature front-end extraction is carried out to single-channel PPG original sequence, and is mapped into high-dimensional feature tensor;Double-flow collaborative feature model is constructed, and high-dimensional feature tensor is obtained by double-flow collaborative feature model, global average pooling The final embedding vector;Embedding vector is input into classification head, and training optimization is carried out using joint loss function.The present application can effectively adapt to the non-stationary heart rate variation of PPG signal, overcome distribution deviation problem, significantly improve the anti-noise robustness, and have very low calculation delay and resource consumption, satisfy the real-time deployment needs of wearable device.

The application discloses a kind of driving style quantitative evaluation method based on multi-modal perception and knowledge graph, through multi-modal data source, which contains various sensor data, vehicle motion data and physiological response and behavior data (such as heart rate change when emergency brake, operation intervention frequency) of driver and passenger in real scene, model constructs user emotion mapping algorithm, subjective experience is converted into quantifiable numerical index (such as "trust index" "comfort score"), combined with the driving behavior knowledge graph constructed, the driving style deviation index (SDI) is calculated using algorithm, the quantitative evaluation of brand driving gene is realized, data-driven basis is provided for function and algorithm optimization, and personalized intelligent driving mode is realized.Therefore, the driving style quantitative evaluation method based on multi-modal perception and knowledge graph of the application has the advantages of high degree of intelligentization and high degree of personalization.

The invention relates to the technical field of control methods of upper limb strength training devices, and provides a control method of an upper limb strength training device in the first aspect, and the method comprises the steps: collecting and obtaining basic information and training target parameters of a user, and obtaining a parameter set set by the user; constructing a training parameter control database; inputting the user setting parameter set into the training parameter control database to obtain an initial resistance setting parameter; according to the training parameter control database and the user set parameter set, a parameter adjustment model used for user real-time training control is constructed, and the parameter adjustment model comprises a resistance adjustment module and a heart rate compensation module; the method has the beneficial effects that in the centrifugal stage, a composite control strategy combining feed-forward control and feedback control is adopted, and the PID algorithm based on heart rate change rate parameter self-adaption is combined, so that the problem of resistance fluctuation caused by sudden speed change or fatigue of a user is solved, and the stability and accuracy of resistance application are ensured.

The invention provides a millimeter wave radar heart rate monitoring method and system based on multi-modal data fusion, and belongs to the technical field of biomedical signal processing, and the method comprises the steps that S10, at least three pieces of phase information for monitoring the heart rate of a patient are constructed, and the phase information comprises echo signals of a millimeter wave radar; s20: analyzing the echo signals, including analyzing the time required for the millimeter wave radar to pass through the fat layer of the patient and the monitored changes in the heart rate when passing through fat layers of different thicknesses, and generating a data set regarding each echo signal. Through the phase unwrapping algorithm and the phase difference filtering technology, phase distortion caused by the fat layer to the millimeter wave radar echo signal is effectively eliminated, so that the peak value of the heartbeat signal is detected more accurately, the heart rate change is obtained, and the accuracy of heart rate monitoring is ensured.

The invention discloses a health recommendation result generation method based on artificial intelligence, and relates to the technical field of neural network and intelligent health recommendation, and the method comprises the steps: collecting heart rate data and height data of a user, calculating a heart rate reserve, and recognizing a vertical rising activity segment; calculating a vertically related physiological response amount based on the heart rate change and the height increment in the rising process, and carrying out statistical analysis on the response amount to obtain a quantitative parameter used for representing the user rising load sensitivity; calculating the target vertical height and the metabolic energy demand, and forming input data reflecting the individual physiological ability and the energy consumption level of the user; and constructing the input data into a feature vector and inputting the feature vector into a pre-trained feedforward neural network model to generate a health recommendation result. According to the invention, personalized health suggestions can be generated according to the vertical activity expression, and the accuracy and suitability of health management are improved.

The application aims at the problem that learners are difficult to evaluate their attention state in real time, and discloses a learning attention state evaluation method based on a multi-dimensional feature fusion network.The method comprises the following steps: 1) acquiring video resources of learners collected by a binocular imaging device (a short-wave infrared camera and a laser radar scanner) on a desk, and dividing the video resources into multiple frames of images; a hand wearable device acquires blood oxygen saturation and heart rate signals of the learners; 2) positioning a face region and facial feature points of the learners on the SWIR image of the learners; and segmenting a head region 3D point cloud set; 3) inputting the face region SWIR image and the head 3D point cloud set into corresponding feature extraction networks to obtain feature topology graphs; after fusion through a self-attention weighting module, inputting a Cauchy label distribution regression module to obtain a head posture angle of the learners; extracting blood oxygen saturation and heart rate change features to judge a fatigue grade of the learners; 4) comprehensively evaluating an attention state according to the head posture angle of the learners, facial feature point changes and the fatigue degree, and reminding the learners if they are not concentrated; and 5) statistically analyzing the attention state in a learning process, and feeding back a statistical analysis report.The application helps the learners to improve concentration and cultivate good learning habits by comprehensively evaluating and statistically feeding back the attention state of the learners.

This application relates to the field of medical device technology and discloses a cardiac scanning method for a medical device, comprising: acquiring a first heart rate based on the real-time heart rate; acquiring an estimated remaining time for cardiac scanning when the first heart rate is lower than a second heart rate; wherein the second heart rate represents a reference heart rate before scanning; acquiring an estimated remaining thermal capacity corresponding to the estimated remaining time; and adjusting the current scanning parameters when the estimated remaining thermal capacity is greater than the actual remaining thermal capacity, so that the thermal capacity corresponding to the adjusted scanning parameters within the estimated remaining time is not greater than the actual remaining thermal capacity. By adjusting the scanning parameters, the risk of scanning failure due to thermal capacity limitations is reduced, ensuring that even if heart rate changes cause scanning time to be extended, scanning will not be interrupted due to insufficient thermal capacity. This application also discloses a cardiac scanning device and a medical device for use in medical devices.

The invention relates to an intelligent oxygen supply method for plateau construction. The method comprises the steps that external environment data and user physiological data are obtained, and the user physiological data comprise the oxyhemoglobin saturation, the heart rate and the activity amount; evaluating a state result of the external environment data and the user physiological data based on a preset three-dimensional evaluation model; the metabolic state of the user is determined on the basis of the heart rate change rate and the activity change rate within the preset time, a predictive result is obtained on the basis of the metabolic state of the user, and the predictive result is used for determining the mode of an oxygen supply instruction; based on the state evaluation result and the predictive result, outputting an oxygen supply instruction of a corresponding mode; after the oxygen supply instruction is executed, the updated oxyhemoglobin saturation and heart rate data are collected regularly, and a flow adjusting valve is adjusted or an acousto-optic alarm of a safety alarm unit is triggered based on the updated oxyhemoglobin saturation and heart rate data.