514 results about "Ecg signal" patented technology

The invention belongs to the technical field of wireless sensing and artificial intelligence, and discloses a high-robustness non-contact accurate electrocardiogram monitoring method based on a millimeter wave radar. Firstly, the distance and angle of a potential target are obtained through distance fast Fourier transform and digital beam forming technologies, and static background removal and thoracic cavity position detection are achieved in combination with mean filtering and a two-dimensional constant false alarm rate algorithm. And then a continuous phase is extracted by using a differential cross multiplication method, a two-step heartbeat-related phase extraction scheme is designed, body micro-motion and breathing interference are removed by adopting B-spline fitting and differential operation respectively, and a stable heartbeat-related phase signal is obtained. A heart rate-guided adaptive wavelet decomposition method is designed to obtain multiband features, and time-frequency joint features are extracted through a double-branch attention mechanism and a gating fusion part. Finally, the time-frequency joint features are input into an electrocardiosignal time domain reconstruction module based on a TransUNet architecture, high-quality reconstruction of electrocardiosignals is achieved, and the method has the advantages of being non-contact, continuous and convenient.

The invention relates to the technical field of medical monitoring, and provides a high-precision sleep electrocardio continuous monitoring system and method.The high-precision sleep electrocardio continuous monitoring system and method.A modular closed-loop framework is adopted, and synchronous acquisition of electrocardio, movement and respiration signals is achieved through a multi-modal sensing and high-precision synchronous acquisition module; the signal quality multi-dimensional traceability diagnosis module performs feature extraction and noise classification on the input signal; the dynamic traceability filtering processing module intelligently calls a corresponding filtering algorithm to perform signal purification according to the noise type; and the intelligent output and self-adaptive resource management module outputs high-quality electrocardiosignals and realizes dynamic optimization of system power consumption. By establishing a complete signal quality evaluation system and an intelligent processing mechanism, the whole process optimization of the sleep electrocardiosignals from collection to output is realized, and the accuracy of monitoring data and the cruising ability of the system are remarkably improved.

The invention relates to the technical field of data fusion, in particular to a multi-source electrocardiosignal correction method and system based on adaptive fusion, and the method comprises the following steps: constructing a multi-channel input tensor, extracting local features through a weight calculation network, carrying out the adaptive weight fusion and dimension reduction of multiple paths of signals, and carrying out the correction of the multi-source electrocardiosignal. A nonlinear mapping relation is established through a deep reconstruction network, a standard waveform is reconstructed, and network parameters are optimized based on reconstruction error reverse iteration. According to the method, local neighborhood features of multichannel signals are extracted by constructing a weight calculation network, a dynamic channel weight sequence reflecting the real-time contribution degree of a signal source is constructed, the amplitude intensity is adaptively adjusted according to the signal quality, unstable channel noise interference is effectively inhibited, and high-quality signal components are enhanced; a deep reconstruction network is used for carrying out nonlinear feature transformation on a fusion sequence, accurate mapping from non-standard input to standard lead waveforms is established, and weight distribution and optimization of signal reconstruction parameters are achieved in combination with an error back propagation mechanism.

The invention discloses a multi-modal interaction evaluation system and method based on synchronous data acquisition, and relates to the technical field of biomedical engineering and man-machine interaction, and the method comprises the steps: generating a synchronous pulse sequence through a synchronous signal generator according to the same coding time base, and outputting the synchronous pulse sequence to an optical path and an electrical path at the same time; pulse events are recognized in the video and the electrophysiological data respectively, and observation pairs of counting numbers and timestamps are obtained; time drift is continuously estimated and compensated through robust regression in a sliding window, and a unified time axis is generated; furthermore, a dynamic time window of heart beat anchoring is constructed according to an R peak event of the electrocardiosignal, and consistent segmentation and feature extraction of cross-modal data are achieved.

The embodiment of the invention provides a data processing method and device and electronic equipment, and relates to the technical field of data processing.The method comprises the steps that multi-lead electrocardiosignal data are obtained and subjected to standardization processing; dividing the patch into a plurality of non-overlapping patches; converting each patch data into a first embedded vector by using a multi-head attention mechanism; extracting attention results of each first embedded vector at a plurality of attention heads, and splicing to obtain global feature representation; performing embedding processing on the patch data by utilizing a sliding window attention mechanism to obtain a second embedding vector; dividing into a plurality of window vectors containing overlapped parts, and extracting an attention result at a single attention head to obtain local feature representation; calculating a difference value between the global feature representation and the local feature representation; and comparing the difference value with a preset difference threshold value to obtain an abnormal detection result of the electrocardiosignal data. According to the embodiment of the invention, the accuracy of abnormal electrocardiosignal recognition is improved.

The embodiment of the invention provides a self-supervised emotion recognition method based on a heart and brain combined codebook and related equipment, and belongs to the technical field of physiological signal processing and artificial intelligence. The method comprises the following steps: respectively defining heart beats of electrocardiosignals and electroencephalogram signal segments with equal lengths as words, and constructing sentences; a shared heart and brain joint codebook is created and trained, and electrocardio and electroencephalogram words are mapped to a unified discrete semantic space through vector quantization so as to learn cross-subject general characterization; then, discretizing a signal sentence by using the codebook, and combining space and position embedding and inputting a Transform encoder to carry out mask pre-training so as to learn context semantics of the signal; and finally, finely tuning the pre-training model for an emotion recognition task. According to the method, deep semantic fusion of heart and brain signals is realized through signal structuring and codebook sharing, dependence on labeled data is effectively overcome, and emotion recognition accuracy and cross-subject generalization ability are remarkably improved.

The invention relates to the technical field of image or video recognition or understanding, and discloses a bus driver driving state evaluation method, which comprises the following steps: acquiring a face image, an electrocardiosignal and voice audio data of a bus driver, performing timestamp alignment and preprocessing, and constructing a multi-mode driving state data set; extracting multi-modal features of the collected data, and mapping the multi-modal features to a unified feature space; fusing multi-modal features through a cross-modal attention mechanism, dynamically adjusting attention weight based on an emotional change difficulty index, and extracting emotional change key features; and predicting a two-dimensional continuous emotion value of the driver by using the fusion features, calculating a long-time-sequence emotion driving risk score based on an emotion stimulation dynamic model, and performing evaluation and early warning of a driving state. The problems of single-mode analysis, lack of long-period early warning and driving state static recognition in the prior art are solved, and the purposes of accurate evaluation, high safety, multi-mode fusion and long-time-sequence prediction are achieved.

The invention relates to an emotion regression recognition method based on multi-modal signals. The method comprises the steps that original electroencephalogram signals and data fragments of all modals of electrocardiosignals are obtained; inputting the modal data fragments into corresponding shallow layer encoders and fusing the modal data fragments to obtain shallow layer fusion features; inputting the shallow spatio-temporal features of each mode into a corresponding Transform deep encoder to obtain deep features, and performing deep fusion on the deep features and the shallow fusion features to obtain deep fusion features; splicing the deep fusion features and the feature-activated manual features to obtain final features; and outputting an emotion continuous value regression result through the multi-layer perceptron network. According to electroencephalogram and electrocardiosignals, original signals and manual features are combined, step-by-step extraction is carried out in the feature learning process, a multi-modal fusion mechanism of the network is utilized, the performance and generalization ability of the model are improved, meanwhile, continuous prediction of the emotional state is achieved, fine fluctuation of the emotion is more accurately captured, and the application prospect is wide.

The invention discloses a similarity measurement-based few-sample electrocardiosignal classification method. The method comprises the following steps of: acquiring an electrocardiosignal sequence from a public library and dividing the electrocardiosignal sequence into a support and query set according to a few-sample format; performing normalization processing and zero filling operation on the obtained sequence; inputting the sequence data with the uniform length into a parameter-shared one-dimensional convolutional neural network to extract a time sequence embedded feature vector; after the vectors are spliced and multiplied, weighting the vectors into weighted features through an attention network; inputting the weighted features into a multi-layer perceptron to calculate a similarity score, and training and fixing a neural network by using positive and negative sample pairs; and calculating the maximum similarity between the query sample and the support set, and outputting a prediction category. According to the method, the electrocardiosignal labeling cost can be remarkably reduced, the accuracy and efficiency of abnormal heart rhythm detection can be improved, dependence on large-scale labeling data is reduced, the practicability and expandability of electrocardiosignal classification are improved, and the method is applied to the field of medical signal processing and has important significance in the aspects of abnormal heart rhythm detection, disease diagnosis, wearable equipment application and the like.

The utility model provides an electrocardiogram electrode patch. The electrocardiogram electrode patch comprises a transmission part, a first attaching part and a connecting wire, the transmission part is used for being detachably connected with electrocardiogram detection equipment, and the first attaching part is used for being attached to a to-be-detected first target position; the transmission part is connected with the first attaching part through the connecting line; the transmission part comprises a shielding grounding contact and a first transmission contact; the first attaching part comprises a first flexible circuit board, and the first flexible circuit board comprises a first shielding layer and a detection contact layer; the connecting line comprises a signal transmission core and a second shielding layer wrapping the signal transmission core. The first shielding layer is connected with the shielding grounding contact through the second shielding layer, and the detection contact layer is connected with the first transmission contact through the signal transmission core. By means of the configuration, signals and interference signals can be transmitted independently, and the stability of electrocardiosignal transmission can be effectively improved.

The invention discloses a cross-crowd wearable ECG emotion recognition method based on a hybrid convolution-Mama network. The method comprises the following steps: S1, constructing a multimedia emotion induction experiment normal form for old people and cognitive impairment groups, and collecting wearable ECG data; s2, the collected original electrocardiosignals are subjected to standardization preprocessing; s3, constructing a hierarchical scale perception convolution module to perform multi-scale morphological feature extraction on the preprocessed electrocardiogram data; s4, performing physiological baseline remodeling on the feature map by using a non-local channel convolution attention mechanism; s5, constructing a bidirectional state space model based on a Mamba2 architecture, and carrying out long-time-history time sequence dependence modeling; and S6, fusing the spatio-temporal features to carry out emotion category probability prediction and implement personalized model fine tuning. According to the method, core challenges in ECG emotion recognition can be successfully solved, and a complete processing link from multi-dimensional sensing of signals to individualized noise filtering to efficient context understanding is constructed.

The invention discloses a wearable electrocardiogram monitoring method based on composite lead and intelligent reconstruction. Belongs to the technical field of medical signal processing and wearable medical instruments, and solves the technical problems of insufficient multi-lead information amount, poor lead stability, motion artifact interference, unreliable missing lead complementation and the like of the existing wearable electrocardio equipment. According to the technical scheme, the method comprises the steps that a plurality of non-inductive electrodes are arranged on a trunk to achieve multi-channel collection of composite leads; the front end uses an analog front end (AFE); multi-stage denoising is carried out cooperatively at the equipment end and the edge end; when the lead is missing or poor in quality, complementing the lead by using a deep reconstruction network of cross-lead attention and fuzzy gating; and finally, inputting the purified or reconstructed electrocardiosignal into a multi-label deep learning classifier. According to the method, the wearing comfort, the information integrity, the transmission efficiency and the real-time diagnosis capability are considered, and the method is suitable for multi-scene long-time electrocardiogram monitoring and early warning in families, hospitals, exercise rehabilitation and the like.

The invention relates to the technical field of artificial intelligence, and discloses a self-supervised learning-based electrocardiosignal anomaly detection system, which comprises an electrocardiosignal acquisition module, a data preprocessing module, a feature coding module, a self-supervised comparative learning module, an anomaly score calculation module and an anomaly judgment module which are in communication connection, the electrocardiosignal acquisition module is used for acquiring an original electrocardiosignal and transmitting the original electrocardiosignal to the data preprocessing module; the data preprocessing module is used for conducting denoising, baseline drift correction and standardization processing on original electrocardiosignals and transmitting the processed signals to the feature coding module. According to the invention, through a dynamic negative sample selection unit in the self-supervised contrast learning module, depending on technologies such as feature queue maintenance, feature distance calculation, clustering analysis and the like, samples which have significant difference from positive sample feature distribution and are different in category are screened as negative samples, so that the model can accurately learn real similarity between similar electrocardiosignal samples; and feature learning confusion is avoided.

The invention is suitable for the technical field of intelligent wearable devices and biological signal processing, and provides a heart rate monitoring method and system of an intelligent wearable device, and the method comprises the following steps: detecting the wearing state and the connection state of the device; waking up the sensor module to collect multi-modal data according to the wearing state and the connection state of the equipment; the multi-modal data comprises an ECG signal, a PPG signal and motion data; the multi-modal data is preprocessed, then the ECG signals and the PPG signals are corrected according to the motion data, motion interference is eliminated, and the corrected ECG signals and PPG signals are obtained; selecting a heart rate calculation mode according to the motion data and the corrected ECG signal and PPG signal, and performing real-time calculation to obtain heart rate data; abnormal recognition is carried out on the real-time heart rate data, and multi-level early warning response is carried out. According to the invention, the power consumption defect in the prior art can be solved, the interference of a motion scene is reduced, the health monitoring accuracy and reliability are improved, and the user experience and health management efficiency can be optimized.

The invention provides an electrocardiograph fault self-diagnosis method and system based on lead wire automatic identification, and the method comprises the steps: triggering a frequency sweep generator according to an equipment starting signal, carrying out the pre-conduction detection of lead wires, then applying an excitation signal in a continuous frequency range to each lead wire, recording the signal collection time length of each frequency point in real time, and carrying out the real-time detection of the signal collection time length of each frequency point; obtaining response voltage and current data to determine a real-time impedance spectrum; performing frequency point alignment processing on the real-time impedance spectrum and a corresponding standard fingerprint, selecting frequency points in a key frequency band of the electrocardiosignal, and comparing amplitudes and phase deviation values of the real-time impedance spectrum and the corresponding standard fingerprint on the key frequency points to obtain a spectrum difference vector; and if the amplitude deviation of the spectrum difference vector exceeds a preset disconnection threshold value, judging that the lead wire has a disconnection fault, performing reverse signal back test on an interface end corresponding to the faulted lead wire, and recording a judgment result in a fault log to obtain a disconnection identification mark.

The invention discloses an arrhythmia detection method based on a pulse neural network. The method comprises the following steps: performing incremental modulation pulse coding and pooling operation on a target electrocardiosignal to obtain a corresponding pulse sequence; and inputting the pulse sequence into a trained multi-level pulse neural network classification model to obtain an arrhythmia detection result. Wherein the multi-level pulse neural network classification model comprises a weight sharing layer and a plurality of cascaded classifiers, the weight sharing layer is used for extracting electrocardiosignal feature information from the pulse sequence, and the plurality of classifiers are used for obtaining an arrhythmia detection result based on the electrocardiosignal feature information. According to the method, on the premise that the accuracy is equivalent, the classification result is more refined, and the requirements for hardware storage resources and computing resources are reduced.

The invention relates to a remote electrocardio telemetering method and system, a terminal and a medium, and belongs to the technical field of electrocardio monitoring. The remote electrocardio telemetering method comprises the steps that a cloud end distributes monitoring equipment and initial parameters according to patient information; the edge end receives real-time electrocardiogram data, obtains environment data in combination with the position of a patient, collects physiological data through a wearable sensor, constructs a spatio-temporal context sensing map, fuses the data to generate situation enhanced electrocardiogram signal representation, inputs a comprehensive risk prediction model to obtain a dynamically updated prediction risk value and uploads the prediction risk value; the cloud judges the predicted risk value, if the predicted risk value is larger than a threshold value, a matched disease type is called, and differential prompts are generated and pushed to the patient and the doctor in combination with the co-disease relation network; if the electrocardiogram data does not exceed the threshold value, carrying out deep analysis on the electrocardiogram data, identifying abnormity, determining an abnormity level, generating a personalized report in combination with treatment history, pushing the personalized report, and triggering a clinical response protocol. The method has the beneficial effect of feeding back the abnormal electrocardiogram condition of the patient in time.

A pad carrying an array of ECG electrodes can be used to measure ECG signal amplitudes and AMSA, a signal analyzer determines a cardiac position with respect to the pad, and an indication of cardiac position with respect to indicia can be provided on a top surface of the pad for output to the user to guide in performing chest compressions during CPR. The pad may integrate a defibrillator electrode. The apparatus may be an automated external defibrillator (AED).

The invention discloses an ear electroencephalogram acquisition sleep monitoring device based on conductive leather and a personalized audio intervention method of the ear electroencephalogram acquisition sleep monitoring device, and aims to solve the problems that existing sleep assisting equipment is poor in wearing comfort and inaccurate in monitoring, and an intervention scheme is lack of personalization. The device comprises preparation of a conductive leather electrode and integration of the conductive leather electrode, an earplug, a loudspeaker and other devices. According to the conductive leather electrode, a conductive polymer (such as poly (3, 4-ethylenedioxythiophene) and a derivative thereof) is combined with natural leather through an in-situ polymerization method to form a flexible electrode material with high biocompatibility. The electrode is combined with an earplug, a loudspeaker and other devices and can be stably attached to the ear canal, and high-signal-to-noise-ratio sleep physiological electric signal (such as myoelectricity, electroencephalogram or electrocardiosignals) collection is achieved. The sleep stage is identified through machine learning, and the loudspeaker module is controlled to play different types of sleep-aiding audios. The core lies in that the device can synchronously evaluate sleep physiological signal changes of a user under different audio stimulation, so that personalized sleep-aiding audios which are most effective for the individual are screened out, and an exclusive scheme library is established. The system has the advantages of being comfortable to wear, high in signal quality, wide in applicability and the like, and can be widely applied to the fields of health monitoring, human-computer interaction, medical diagnosis and the like.

The invention discloses an obstructive sleep breathing state detection method based on joint denoising, and the method comprises the steps: firstly carrying out the preprocessing of an input original ECG signal, obtaining a standardized feature matrix, and completing the data set division; secondly, a hybrid model based on enhanced DenseNet-Transformer is used for carrying out deep feature learning and classification processing on the extracted feature matrix; and finally, performing forward reasoning on the ECG signal to be detected through the trained model, and outputting a detection result. According to the method, the technical problems that an existing OSA detection method depends on a fixed parameter filter, and noise and effective physiological signals are difficult to distinguish are effectively solved, and accurate and efficient obstructive sleep breathing state detection is carried out.

The invention discloses an ECG classification method based on lightweight ShuffleNetV2, and relates to the technical field of medical health monitoring, and the method comprises the steps: obtaining a multi-lead electrocardiosignal, and carrying out the data preprocessing; an ISNetV2 network model is constructed; the ISNetV2 network model is subjected to light weight improvement on the basis of an original ShuffleNetV2 network model; the preprocessed electrocardiosignals are used for training an ISNetV2 network model; and classifying the electrocardiosignals by using the trained ISNetV2 network model, and outputting classification results of different types of arrhythmia. The method has the advantages that the ECG classification accuracy is effectively improved while the light weight of the model is kept, computing resource consumption is remarkably reduced, and the method is suitable for deployment of a mobile terminal or embedded equipment.

The invention discloses a multi-modal electrocardiosignal and arrhythmia recognition system and method. The system comprises a signal acquisition module, a preprocessing module, a space-time alignment module, a feature extraction module, a self-adaptive fusion module, a multi-modal fusion module, a classification risk assessment module and a visual report module. The recognition method comprises the following steps: S1, synchronously acquiring an electrocardiosignal and a heart sound signal, and preprocessing the electrocardiosignal and the heart sound signal; s2, establishing a time corresponding relation between the electrical activity and the mechanical activity; s3, calculating a mechanical shrinkage efficiency index; s4, evaluating the quality of the electrocardiosignal and the heart sound signal in real time, and dynamically adjusting contribution weights of the electrocardiosignal and the heart sound signal in a fusion process according to the quality; s5, adopting a multi-head attention mechanism to generate a joint feature vector for classification; s6, inputting the joint feature vector into a classification network model, and outputting an arrhythmia type and a quantitative risk level at the same time by the classification network model; and S7, generating a visual atlas and a structured diagnosis report.

The invention discloses a medical signal generation method and system based on a time-frequency double-domain constraint generative adversarial network. According to the method, a multi-category electrocardiosignal generation model is designed on the basis of a conditional generative adversarial network, global attention interaction is carried out by utilizing a learnable potential feature prototype and position-coded signal features through an adaptive neural representation module, and long-distance time sequence dependence of electrocardiosignals is modeled; through the adaptive spectrum sensing module and the dynamic mask mechanism of energy sensing, the discriminator intensifies the discrimination of the consistency of signal frequency domain information while paying attention to the time domain form, thereby effectively inhibiting the non-natural high-frequency artifacts in the generation process, and ensuring the high fitting of the generated signal and the real signal. Experiments show that the fidelity and diversity of generation of various types of electrocardiosignals can be remarkably improved.

An AR algorithm computing unit for electrocardio event prediction based on RRAM, comprising a coefficient storage array, which is composed of p groups of 24-bit RRAM storage units, for storing autoregressive coefficients and being read / written by control logic and coefficient addressing units; an excitation storage array, which is composed of p groups of 24-bit RRAM storage units, for storing electrocardio signal samples and being read / written by control logic and excitation addressing units; multiplication logic, one end of which is connected with the data output of the RRAM storage unit at the corresponding address bit in the coefficient storage array for receiving the corresponding coefficient, and the other end of which is connected with the data output of the RRAM storage unit at the corresponding address bit in the excitation storage array for receiving the electrocardio signal sample corresponding to the coefficient, to realize the element-by-element multiplication operation of the coefficient vector and the excitation vector; and addition logic, which adds all the multiplication results to output the multiplication result of the current excitation vector and the coefficient vector as the electrocardio event prediction result.

The invention relates to an electrocardio atrial fibrillation classification detection method, system and device capable of resisting individual difference and a storage medium. The system comprises a signal acquisition module used for acquiring ECG signals; the invention discloses an anti-individual-difference preprocessing circuit. The signal segment reading module is used for reading a signal segment according to an overlapping segmentation strategy, the Hanning window weighting module is used for performing window function weighting on the signal segment and only storing a first half coefficient through address mapping multiplexing by utilizing the symmetry of a window function, and the FFT frequency domain transformation module is used for converting a time domain signal into a frequency domain; the QRS frequency domain enhancement filtering module is used for enhancing QRS spectrum components and attenuating individual difference frequency components, the IFFT time domain reconstruction module is used for converting frequency domain signals back to a time domain, and the amplitude normalization output module is used for eliminating signal amplitude differences among individuals; and the deep learning classification module is used for performing atrial fibrillation detection on the standardized signal. Based on a CPU and FPGA heterogeneous architecture, the accuracy and robustness of atrial fibrillation detection are improved, and the method is suitable for the fields of wearable monitoring, telemedicine and the like.

The invention relates to a method for preventing and monitoring blood pressure based on terahertz radar electrocardiogram heart rate variation parameters, and belongs to the field of terahertz radar signal processing. The method comprises the steps that a human thoracic cavity micro-motion signal is collected through a terahertz radar, an intermediate frequency signal is obtained through ADC sampling, distance dimension Fourier transform and phase unwrapping processing are carried out, and a target object is obtained; extracting a chest displacement signal containing heartbeat information; band-pass filtering is adopted to preliminarily separate respiration and heartbeat signals, and variation mode decomposition optimized by an ant colony algorithm is introduced to effectively suppress respiration harmonic interference; inputting the heartbeat signal into a multi-modal deep learning framework fusing a convolutional neural network, a long-short-term memory network and a multi-head attention mechanism to realize end-to-end high-precision reconstruction from a radar mechanical vibration signal to a standard electrocardio waveform; r peak detection is conducted on the reconstructed radar ECG signals, and time domain and frequency domain heart rate variability parameters are calculated and used for evaluating the autonomic nerve function state. The method has the effect of improving the monitoring comfort of special crowds.

The utility model discloses a kind of postoperative atrial fibrillation monitoring alarm systems, it is related to the technical field of atrial fibrillation monitoring, and it includes: main control module, detection module, storage module, display module, input-output module and alarm module;Detection module detects the electrocardiosignal, pulse voltage signal and heart sound signal of postoperative patient, sends to main control module;Main control module carries out sampling to electrocardiosignal, pulse voltage signal and heart sound signal, and stores to storage module;According to the instruction of input-output module, the signal after selection sampling is displayed through display module, and the signal stored is selected from storage module and is displayed through display module;Threshold comparison unit of main control module sends signal to alarm module according to heart rate signal, pulse signal, heart sound signal and threshold value, and alarm module sends alarm prompt.The utility model can monitor the sign data of postoperative patient and send alarm, remind medical staff to handle in time, reduce the influence of postoperative atrial fibrillation on patient recovery.

The present disclosure provides a QRS wave form detection method and system based on electrocardiogram QRS wave position, relates to the technical field of electrocardiogram signal processing, and comprises the following steps: acquiring electrocardiogram data to be detected, and pre-processing the electrocardiogram data; identifying the start and end point positions of QRS waves in the electrocardiogram data, and intercepting the QRS wave segments corresponding to all the identified QRS wave start and end point positions; performing a shift operation on the QRS wave segments to record the QRS wave data positions, sequentially numbering, then cutting the QRS wave data according to the recorded position data points and the front and rear two position data points, calculating the absolute value of the cut QRS wave data, taking the maximum value, and judging the current QRS wave form according to a threshold value; and the present disclosure can improve the efficiency of QRS wave form detection.

The invention discloses a multi-sensor monitoring system and method based on time alignment, and belongs to the technical field of multi-sensor monitoring, and the system comprises a sensor collection module which is used for obtaining an electrocardiosignal, a photoelectric volume pulse wave signal, a heart sound signal and a respiratory impedance signal containing a main clock receiving timestamp; the time alignment module is used for performing acquisition time alignment on the electrocardiosignal, the pulse oximeter signal, the heart sound signal and the respiratory impedance signal containing the main clock receiving timestamp to form the electrocardiosignal, the pulse oximeter signal, the heart sound signal and the respiratory impedance signal which are in time alignment; the multi-modal fusion analysis module is used for extracting local morphological features in the electrocardiosignal, the pulse oximeter signal, the heart sound signal and the respiratory impedance signal after time alignment to form a feature map, and extracting dynamic weights between different signals and between different time points / features in the same signal; according to the invention, the interpretability and accuracy of judgment are improved.

This invention discloses a real-time arrhythmia detection method based on morphological fidelity consistency constraints, comprising the following steps: S1, preprocessing continuous electrocardiogram (ECG) signals and dividing them into overlapping sliding time windows; S2, inputting each time window into an ECG signal encoder obtained through joint training to obtain a latent representation vector for that time window; the joint training is specifically defined as: simultaneously optimizing the encoder parameters using supervised classification signals, contrast consistency signals, and morphological fidelity signals during the training phase; S3, inputting the latent representation vector into a classifier and outputting the class probability of the time window belonging to each arrhythmia category; S4, based on the class probability, outputting real-time detection results using an online decision strategy of threshold hysteresis and cross-window consistency. This invention can simultaneously achieve robust identification under dynamic interference, accurate preservation of clinically critical waveform details, and efficient real-time deployment at the edge. This invention also provides a real-time arrhythmia detection system and device based on morphological fidelity consistency constraints.