12 results about "Abnormal heart rate" patented technology

The invention discloses a medical big data analysis blood pressure alarm system and device based on a block chain technology. The system comprises a data acquisition module, a block chain service unit, a central processing unit and a storage database; the data acquisition module is used for acquiring heart rate data and blood pressure data of a user and sending the acquired data to the block chain service unit; and the block chain service unit is used for sending the received heart rate data and blood pressure data to the central processing unit according to a block chain service node. The heart rate and blood pressure data of the elderly user in medical treatment are monitored based on the block chain technology, the monitored data are analyzed in real time, the blood pressure change condition of the elderly user is judged, when the heart rate and blood pressure abnormal condition occurs, the condition of the elderly user can be timely alarmed and reminded through a mobile phone APP and a short message, and the user experience is improved. Monitoring of old people with hypertension and timely treatment in case of conditions are effectively improved.

The application relates to an exposure method, a medical imaging system, an electronic device and a storage medium, wherein the exposure method comprises the following steps: acquiring heart rate data of an object to be exposed and an exposure period; selecting an exposure mode corresponding to the heart rate data according to the heart rate data; and exposing the object to be exposed according to the exposure mode and the exposure period. According to the application, the object to be scanned with abnormal heart rate and the object to be scanned with normal heart rate can be scanned, and the scanning accuracy is improved.

This invention discloses an abnormal heart rate diagnostic system based on a lightweight spiking neural network, comprising: a data denoising module for denoising the input electrocardiogram (ECG) signal; a data segmentation module for segmenting the denoised ECG signal; a network construction module for constructing a lightweight spiking neural network consisting of a feature extraction network and a classification network connected sequentially; wherein the feature extraction network includes multiple branches of feature extraction modules, each branch including several sequentially connected IFR modules; the classification network includes first and second layer SGRU modules connected sequentially; a network training module for training the constructed lightweight spiking neural network using the segmented ECG signal to obtain a trained lightweight spiking neural network; and a data diagnosis module for inputting the ECG signal to be diagnosed into the trained lightweight spiking neural network to obtain a diagnostic result. This invention improves the accuracy of ECG signal classification.

The utility model discloses an intelligent monitoring bed for a prison, which belongs to the technical field of prison equipment and comprises a bed frame with bed legs, a bed board is laid at the upper end of the bed frame, the intelligent monitoring bed further comprises a monitor used for monitoring heart rate and respiratory rate, and an embedding opening used for embedding the monitor is arranged on the surface of the bed board. A bearing frame used for bearing the monitor is fixedly arranged at the lower end of the bed frame, and a connecting assembly is fixedly arranged at the lower end of the monitor. The monitor is arranged to monitor the heart rate and the respiratory rate in real time, the physiological health condition of a supervised person is effectively mastered, early warning can be conducted in time once the heart rate is abnormal or the respiratory rate is disordered, a worker can rapidly take corresponding measures, safety risks caused by sudden health problems are greatly reduced, and the life safety of the supervised person is guaranteed.

This invention discloses a traditional Chinese medicine composition for assisting in the improvement of hand-foot-mouth disease in infants and young children, belonging to the field of traditional Chinese medicine technology. The composition consists of eight medicinal herbs: lotus leaf, coix seed, angelica dahurica, kudzu root, platycodon root, agastache rugosa, cimicifuga rhizome, and dandelion, with a defined optimal medicinal ratio. Based on the seasonal differences in the pathogenesis of hand-foot-mouth disease, this invention targets the core pathologies of winter (cold congestion of microvessels, water and sodium retention, and internal heat generation) and spring and summer (hypothalamic sympathetic activation, increased heart rate, and visceral heat overload). It also addresses the technical deficiencies of clinical Western medicine, cold-natured traditional Chinese medicine, calamine lotion, and diuretics, such as vasoconstriction, kidney damage, central nervous system disorders, increased skin exudation, and rebound water retention. This invention employs a combination of warming and cooling herbs, regulating the ascending and descending functions, and promoting diuresis and protecting the body's vital energy. The synergistic effects of these herbs can dilate spasmodic microvessels, improve renal perfusion, stabilize abnormal heart rates, stabilize the hypothalamic center, and assist in antagonizing enteroviruses. By targeting and reducing abnormal permeability of skin capillaries with Angelica dahurica and Platycodon grandiflorus, it reduces blood extravasation and inhibits the formation and exudation of herpes from the root cause. This invention has mild medicinal properties, is suitable for all seasons, and has high safety. It can effectively improve symptoms of hand-foot-mouth disease such as fever, herpes, irritability, and cold extremities, reduce the risk of severe illness, antagonize the toxic side effects of commonly used clinical drugs, and is suitable for the delicate constitution of infants and young children, possessing good prospects for clinical application and promotion.

A multifunctional sleep monitoring method based on a millimeter wave radar comprises the following steps: carrying out recombination, frame division and clutter removal on collected original ADC data, obtaining a target distance spectrum through one-dimensional FFT and inter-frame difference, and determining a target distance unit by adopting non-coherent accumulation. Extracting the phase information of the unit signal, unwrapping and differentiating to obtain a vital sign signal, separating breathing and heartbeat components by utilizing multi-mode decomposition and reconstruction, and obtaining the breathing frequency and the heart rate through Fourier transform; performing two-dimensional FFT and DBSCAN clustering on the data after inter-frame difference, generating three-dimensional point cloud data in combination with angle FFT, and inputting the three-dimensional point cloud data into a DGCNN and Transform cascade network to realize sleeping posture recognition; the system can analyze the vital signs and the sleeping posture state in real time, and when it is detected that apnea, abnormal heart rate or dangerous sleeping postures continuously exceed preset time, alarm information is automatically output. The method has the advantages of non-contact, high precision and real-time performance.

The invention provides intelligent equipment for assisting heart rate detection. The intelligent equipment comprises a main body structure, a direct-current power supply voltage line and a processor, and the direct-current power supply voltage line is arranged at a preset position on the main body structure; the processor is electrically connected with the direct-current power supply voltage line; the processor is used for periodically sampling the voltage of the direct-current power supply voltage line, responding to the condition that the ripple of the voltage meets a preset condition, and obtaining the heart rate of a user based on the ripple; wherein the ripples are caused by mechanical vibration generated when a user acts on the main body structure. No sensor needs to be added, the voltage of the direct-current power supply voltage line is monitored, mechanical vibration caused by heartbeat when the human body makes contact with the intelligent device can cause the voltage to generate ripples, the heart rate is in positive correlation with the ripples, and the higher the heart rate is, the larger the ripples are; the higher the heart rate is, the denser the crests and troughs of the ripples are; the heart rate of the user is calculated based on the ripples, heart rate abnormity can be found in an auxiliary mode, the user is prompted in time, and the hardware cost of a sensor is not increased.

The invention provides a heart rate anomaly detection method and system, computer equipment and a storage medium, and belongs to the field of health monitoring, and the method comprises the following steps: in different environments, collecting piezoelectric signals and heart rate data of different healthy people in different postures; mapping the piezoelectric signals to a plurality of random representation spaces by using a convolutional neural network, and extracting depth representation features of the piezoelectric signals; on each random representation space, recursive axis parallel partitioning is carried out by randomly selecting feature dimensions and segmentation threshold values, a plurality of isolated trees are constructed, and a deep isolated forest is formed through the plurality of isolated trees; the depth representation features and the heart rate data of the testee are input into a depth isolated forest, and the abnormal score of the heart rate data is calculated by counting the average path length of each piece of heart rate data in all isolated trees; and marking the heart rate data with the abnormal score higher than a threshold value as an abnormal heart rate event. According to the method, the abnormal heart rate event can be quickly recognized on the premise that a large number of abnormal samples do not need to participate in training.

The invention belongs to the technical field of tunnel construction, and particularly relates to tunnel operator health monitoring equipment and an intelligent scheduling method.The tunnel operator health monitoring equipment comprises a smoke exhaust pipeline, air exhaust mechanisms are arranged on the outer surface of a supporting column pipeline at the lower end of the smoke exhaust pipeline in an array mode, and an electric sliding rail is fixedly connected to the outer surface of the upper end of a smoke exhaust pipeline network; a conductor rail is arranged on one side of the electric sliding rail, and the upper end of the conductor rail is fixedly connected with the outer surface of the upper end of the smoke exhaust pipeline. According to the monitoring equipment, the gas sensor and the temperature sensor are arranged at the upper end of the mounting block, and the health monitoring ring worn by an operator is arranged, so that synchronous acquisition of tunnel environment data and personnel physiological data is realized. The controller data processing module analyzes and compares data in real time, risks such as excessive harmful gas, abnormal temperature or abnormal heart rate and blood oxygen of people are warned in advance, safety accidents caused by environmental deterioration or non-timely discovery of potential health hazards are avoided, and a dual safety defense line is built for tunnel operation.

This invention discloses a method and system for detecting atrial fibrillation (AF) on electrocardiograms based on the fusion of time-series and waterfall plot models, belonging to the fields of biomedical signal processing and deep learning technology. This method simultaneously constructs two complementary data representations of the same electrocardiogram signal: a fixed-duration one-dimensional time-series segment and a two-dimensional heartbeat stacked grayscale waterfall plot aligned with the R-wave. These are respectively input into independently trained one-dimensional and two-dimensional convolutional residual networks for classification. Finally, the outputs of the two models are aligned at the heartbeat time granularity, and the final AF detection result is obtained through a configurable fusion strategy (intersection, union, or weighted voting). The time-series model excels at capturing abnormal heart rate rhythms, while the waterfall plot model excels at identifying abnormal waveform morphology; the two are significantly complementary in boundary cases. In 2,433,594 heartbeat tests with balanced distribution of AF and NAF samples (AF accounting for 43.7%), the false alarm rate decreased from 4.30% to 1.30% and the missed alarm rate decreased from 1.07% to 0.59% after adopting the intersection fusion strategy. The prediction conflict rate between the two models was only 2.43%, which proves that the two-dimensional fusion has a significant complementary gain effect under neutral distribution conditions.

The invention relates to the technical field of data acquisition and management, in particular to a multi-modal data acquisition and management system and intelligent method for old people, and the system comprises a multi-modal data acquisition unit, an edge computing gateway, an acousto-optic voice alarm unit and a cloud analysis and decision unit. The multi-modal data acquisition unit comprises a physiological data acquisition module, an environment data acquisition module, a behavior activity data acquisition module and a video and audio data acquisition module; the physiological data acquisition module acquires heart rate and gait data through wearable equipment; the environment data acquisition module acquires indoor temperature and humidity and illumination data through an environment sensor; local real-time analysis and privacy protection are achieved, audio and video collection is triggered only under the emergency conditions such as suspected tumble and abnormal heart rate, the privacy risk of continuous monitoring is avoided, the personalized recognition requirement is met, and an active health monitoring and safety guarantee scheme with low cost and high reliability is provided for old people.

The invention relates to the technical field of health management, in particular to health management monitoring equipment which comprises a wearable shell, a circulation pipeline is arranged in the wearable shell, an upper water bag cavity and a lower water bag cavity are formed in the front side of the wearable shell, the circulation pipeline is communicated with the upper water bag cavity and the lower water bag cavity, and a control mechanism is arranged between the upper water bag cavity and the lower water bag cavity; a heart rate detector is further arranged on the front side of the wearable shell; an adjusting switch is arranged in the circulation pipeline on the rear side of the wearable shell, knocking reminding assemblies are arranged at the two ends of the upper side of the wearable shell, and the adjusting switch is connected with the knocking reminding assemblies. The wearable device further comprises a rotary adjusting assembly arranged on the front side of the wearable shell, and the rotary adjusting assembly is connected with the control mechanism and the heart rate detector. In combination with the influence of sitting postures on the heart rate, the effect of reminding and adjusting the sitting postures in three directions to improve the heart rate when the sitting postures are bad is achieved, when the heart rate of old people is too slow, the control mechanism is triggered to achieve heating so as to promote heart rate recovery, and the health problem caused by abnormal heart rate is solved.