49 results about "Biomedical signal" patented technology

The application discloses a motor imagery electroencephalogram signal denoising method and device, medium and product, relates to the technical field of deep learning and biomedical signal processing, and the method comprises the following steps: acquiring a target electroencephalogram signal containing artifacts; inputting the target electroencephalogram signal containing artifacts into a trained electroencephalogram denoising model to obtain a final denoised electroencephalogram signal; wherein the electroencephalogram denoising model comprises an electroencephalogram denoising branch, an artifact prediction branch and an artifact representation interaction attention fusion reconstruction module; the electroencephalogram denoising branch comprises a multi-scale self-adaptive enhancement module, a frequency domain dynamic enhancement module and a feature extraction module. The application solves the problems of traditional electroencephalogram denoising methods in signal fidelity, spectral fidelity, spatial structure preservation and generalization ability.

The application provides a training method and system of an emotion classification model for multi-modal physiological signals, relates to the technical field of cross between artificial intelligence and biomedical signal processing, and the method comprises the following steps: collecting multi-modal physiological signals of a plurality of sample users; processing the multi-modal physiological signals of the plurality of sample users to obtain multi-modal physiological vectors of the plurality of sample users; using the multi-modal physiological vectors of the plurality of sample users to perform autoregressive pre-training on a large language model; using the multi-modal physiological vectors of the plurality of sample users and text vectors corresponding to emotion classification prompt texts to fine-tune the large language model subjected to the autoregressive pre-training, and obtaining an emotion classification model. In the process of emotion prediction, the problems of multi-modal signal mode loss, inconsistent sampling rates and non-uniform channel numbers can be effectively overcome, and the accuracy of emotion prediction is improved.

The application belongs to the technical field of biomedical signal processing and computer vision, and specifically discloses a child emotion analysis method and system based on eye movement and micro-expression association, which comprises the following steps: synchronously acquiring an eye movement data stream and a facial video stream, triggering a dynamic analysis process by identifying a mode conflict between high physiological arousal and low emotional expression intensity after generating a physiological arousal and emotion hypothesis through preliminary analysis, generating a guide strategy according to a conflict degree, and enhancing original data in a time domain or a space domain to facilitate deep analysis, capturing suppressed micro-expression signals in the enhanced data to correct the preliminary emotion hypothesis, and finally fusing a physiological arousal level, a corrected emotion category and a quantified expression inhibition degree to output a multi-dimensional psychological state analysis result containing an emotion category, a physiological arousal level and an expression inhibition degree, so as to realize quantitative and multi-dimensional evaluation of real emotions of children.

The present application relates to the technical field of biomedical signal processing and artificial intelligence, and provides a heart rate detection method based on a learnable wavelet transform and feature enhancement, comprising: acquiring radar phase signals collected by a millimeter wave radar and obtained after preprocessing; and performing a learnable wavelet transform, extracting time-frequency features, and through multi-scale decomposition on a physiological related frequency band, performing dynamic weighted fusion based on energy of each frequency band, and outputting a multi-scale fusion feature tensor; after projecting and fusing the multi-scale fusion feature tensor and the original radar phase signals, inputting the same into an LSTM-Transformer hybrid time series modeling network, and outputting a second-by-second heart rate estimation value sequence; in a training stage, a hybrid loss function is calculated by using a real heart rate label and the heart rate estimation value sequence, and an end-to-end optimization is performed on the network. Through the method, the accuracy and robustness of non-contact heart rate monitoring are improved.

This invention discloses a method for assessing hypoxia response based on dynamic evaluation of heart rate deceleration force and HRV, belonging to the field of biomedical signal processing. The method simultaneously acquires electrocardiogram (ECG) signals and environmental and blood oxygen parameters to dynamically correct the risk baseline; extracts frequency domain, time domain, and heart rate deceleration force features from the ECG signals and establishes a dual-channel cross-judgment logic; inputs the judgment results with the current blood oxygen saturation into a lightweight neural network inference output risk stratification; controls a wearable actuator to initiate multi-target stratified sequential stimulation including heat and vibration based on the stratification results, and adaptively updates the individualized hyperthermia prescription based on the intervention efficacy index, ultimately achieving dual-channel synergistic control of oxygen therapy and hyperthermia. This invention effectively solves the shortcomings of traditional methods, such as delayed early warning and inability to dynamically correct in non-networked environments, constructing a closed loop from precise monitoring to multi-target synergistic intervention, significantly improving the body's adaptability and resilience to hypoxia.

The application discloses a kind of based on photoelectric volume pulse wave inhibits local interference autonomic nerve function evaluation method and system, belong to biomedical signal processing field.The method includes: obtaining PPG signal S (t) ;From it respectively extracts the first parameter of the oscillation component N (t) of characterizing blood vessel tension, and the second parameter of characterizing local time-varying gain factor G (t) ;The first parameter is associated with correction using the second parameter, to inhibit the local interference introduced by G (t), to correct and generate stabilized autonomic nerve function evaluation index, which corresponds to the pure evaluation of nerve component N (t).The present application overcomes the defects in the prior art that the evaluation index is easily disturbed by local physiological physical factors, and only single PPG signal can realize high robustness, high stability autonomic nerve function quantitative evaluation.

A state closed-loop recognition method and system based on force feedback and electroencephalogram signals. It relates to the field of biomedical signal processing and brain-computer interface technology, and specifically relates to a state closed-loop recognition method and system based on force feedback and electroencephalogram signals. The method synchronously acquires original electroencephalogram signal sequences and time-synchronized multi-channel force feedback data sequences, extracts dynamic contact state features and calculates the contact reliability of the corresponding channels, inputs the state recognition basic model after frequency band sensitive double drive feature fusion, obtains the state recognition result and the corresponding confidence, and generates channel contact state adjustment instructions to optimize the input data quality when the confidence is lower than the preset dynamic threshold. Then, the model is parameterized and efficiently online fine-tuned using the newly acquired data to generate a target personalized model. The problem that the brain-computer interface system cannot realize full-link coordinated adaptive response from physical acquisition to intelligent recognition when the signal quality fluctuates is solved.

This invention relates to the fields of biomedical signal processing, intelligent sleep monitoring, and multimodal machine learning, specifically to a method and system for sleep staging with missing modalities based on latent space distribution alignment. The method includes: acquiring complete EEG, EOG, and EMG data and preprocessing them; encoding single-modal features respectively; mapping each single-modal feature to a unified latent space to generate Gaussian latent distributions for each single modality; constructing a joint latent distribution based on the complete trimodal information; aligning the distributions by minimizing the KL divergence between each single-modal latent distribution and the joint latent distribution to establish a shared latent space; training a classifier based on the joint latent distribution; and, during the testing phase when modalities are missing, using only the latent distributions generated from the observable modalities for classification. This invention maintains high robustness and high accuracy in sleep staging even under modality-missing conditions, making it suitable for applications prone to modality loss, such as clinical monitoring, home sleep detection, and wearable devices.

The application discloses a lightweight single-channel electroencephalogram sleep staging method and system based on multi-level fusion, and relates to the technical field of biomedical signal processing and artificial intelligence. The method comprises the following steps: a time window sequence centered on a target period is constructed and input into a sleep staging prediction model to predict and output a sleep stage; the model is trained according to the following method: low-frequency features, medium-frequency features and high-frequency features are extracted, and then fused and abstracted to obtain a spatial feature vector; the spatial feature vector is subjected to time series modeling to obtain a time series feature vector; the spatial feature vector and the time series feature vector are fused to obtain a time-space complementary fusion feature; and the sleep stage of the target period is predicted and output. The method has the characteristics of lightweight high performance, high N1 stage recognition capability, cross-scale collaborative fusion, time-space complementary fusion and compliance with physiological rules.

The application relates to a dual cascade flow type processing method and system for removing artifacts from myoelectric signals and reconstructing the signals, and relates to the technical field of biomedical signal processing.The method comprises the following steps: extracting a standard stimulation artifact template from a noisy calibration myoelectric signal, calculating a decision threshold and a frequency domain noise floor baseline; transversely splicing a myoelectric signal data block with historical data in a time domain residual artifact cache, and performing artifact identification and cancellation based on the standard stimulation artifact template and a morphological gating mechanism; sending a time domain processing signal into a frequency domain splicing cache, performing fast Fourier transform after reaching a preset window length; dynamically generating a probability mask according to the frequency domain noise floor baseline, performing inverse fast Fourier transform, and obtaining a single-frame recovered signal; and obtaining a smooth and continuous reconstructed myoelectric signal by using an overlap-add method; and on the premise of not depending on high-performance hardware, accurate cancellation of stimulation artifacts is realized, and real physiological signals are protected.

A physiological mechanical signal monitoring system and method utilizing motion state to suppress artifacts, belonging to the field of biomedical signal monitoring and processing technology, aims to improve the existing distributed multi-node vibration and physiological signal acquisition systems, which suffer from severe crosstalk between multiple channels, signal aliasing caused by artifacts, and feature distortion, failing to meet the requirements of high-fidelity, multimodal dynamic acquisition. Key technical points: The signal monitoring system includes a multi-point distributed acquisition module, a motion state recognition module, an artifact detection and adaptive filtering module, and a main control and signal fusion module. The main control and signal fusion module is used to fuse and reconstruct the multi-channel physiological mechanical signals after artifact suppression processing, outputting high-fidelity physiological signals. This invention significantly reduces the coupling effect between different channels caused by environmental vibration, body motion impact, and matrix resonance through independent support of multiple spatial nodes and isolation of mechanical paths, significantly improving the spatial discrimination ability and original independence of the signals. This invention achieves multi-point physical isolation at the structural level, and then combines vector superposition to achieve preliminary noise reduction, effectively reducing artifacts caused by non-target actions and environmental disturbances.

This invention relates to the fields of biomedical signal processing and brain-computer interface technology, specifically a short-sleep cognitive recovery system and method based on lightweight deep learning. The system includes: an EEG signal acquisition module, a signal preprocessing module, a sleep staging inference module, a cognitive state assessment module, and a closed-loop acoustic intervention module. The EEG acquisition module employs a low sampling rate of 64Hz to ensure a target frequency band signal retention rate of ≥95%. The sleep staging inference module uses a dual-stream discriminant architecture, with the XGBoost model using SHAP to select Top-20 features, and the SleepTransformer model containing a 4-layer encoder and 8 attention heads. The cognitive state assessment module calculates the functional connectivity strength of specific brain regions based on the PLV / wPLI index, with preset scientific thresholds. The closed-loop acoustic intervention module dynamically adjusts acoustic parameters, with a response latency ≤100ms. This invention solves the problem of low staging accuracy under low sampling rates in portable devices, achieving precise closed-loop intervention based on neural mechanisms, and significantly improving the efficiency of short-sleep memory consolidation.

The application discloses a kind of based on heart sound double-flow feature coordination's intelligent identification method for children's congenital heart disease, belong to biomedical signal processing technical field.The method obtains child heart sound audio signal and carries out pretreatment, respectively extracts heart sound time-frequency energy feature and heart sound gamma pass feature, is coupled and is constructed double-flow multidimensional heart sound feature map after time domain resolution synchronous processing;Characteristic map is input hierarchical time-frequency analysis network, with noise suppression unit filters out environmental disturbance, with key feature focusing unit highlights abnormal heart sound feature;Combined with difficult and easy sample balance strategy training model, output classification prediction probability.The application is improved through double-flow feature complementation and multi-stage feature enhancement, heart sound feature expression and anti-interference ability, help to improve the stability and reliability of the intelligent identification of children's heart sound anomaly.

This invention discloses a method, system, and storage medium for atrial fibrillation detection based on a stacked waterfall plot of heartbeats on electrocardiograms, belonging to the field of biomedical signal processing and machine learning technology. The method extracts heartbeat waveform data using the R-wave position as an anchor point, performs individualized grayscale normalization using the voltage range of the PR segment as a reference, and stacks multiple normalized heartbeat waveforms vertically in chronological order to generate a two-dimensional grayscale waterfall plot image. Then, it achieves dense prediction per heartbeat through multiple independent sigmoid output nodes of a two-dimensional convolutional residual network. On a multi-center independent test set of approximately 5.9 million heartbeats, the method achieved an F1 score of 0.9944 and a recall rate of 99.88%. This invention preserves the original waveform morphology information, has good multi-device compatibility, and is suitable for electrocardiogram acquisition devices with various lead configurations.

The present application relates to the technical field of biomedical signal processing and artificial intelligence, and discloses a training method, an analysis method and equipment of an electroencephalogram signal analysis model, which comprises the following steps: obtaining an electroencephalogram signal sample set for training, wherein a relative comparison label is a label used to represent the relative comparison result between electroencephalogram signal pairs, and an absolute classification label is a label used to represent the comparison between the electroencephalogram signal sample and a preset comparison standard; extracting the signal features of the electroencephalogram signal sample set through a feature extraction module; calculating an output classification prediction result based on the signal features through a classification prediction module; calculating an absolute classification loss based on the classification prediction result and the absolute classification label, and calculating a relative ranking loss between the electroencephalogram signal pairs based on the classification prediction result and the relative comparison label; obtaining a loss function based on the preset constraint condition and the weighted absolute classification loss and relative ranking loss; updating the parameters of the classification prediction module and the feature extraction module based on the loss function to obtain an electroencephalogram signal analysis model.

This invention belongs to the field of biomedical signal processing technology, and relates to a method, system, device, and storage medium for recognizing electroencephalogram (EEG) signals in olfactory disorders. The method includes: S1: acquiring the raw multi-channel EEG signals to be processed, and preprocessing and slicing them to form an EEG slice sequence; S2: constructing a dual-path fusion model and pre-training the dual-path fusion model, inputting the EEG slice sequence into the pre-trained dual-path fusion model to extract fusion reconstruction features; S3: inputting the fusion reconstruction features into an improved KAN-GRU classification model after supervised classification training to generate the classification and recognition results of the EEG signals. This invention acquires the dynamic temporal features and static physiological features of EEG signals through a dual-path parallel architecture, effectively eliminating individual differences and phase delay interference. Combined with the strong nonlinear expression capability of the improved KAN-GRU, it significantly improves the accuracy and robustness of olfactory disorder classification.

The application discloses a non-invasive real-time evaluation method and system for blood fluidity and a wearable device, and belongs to the technical field of biomedical signal processing and intelligent health monitoring. The method comprises the following steps: acquiring an event timestamp of a blood blocking device and a physiological signal of a blood health measurement module; automatically intercepting a signal segment of a recovery stage based on the event timestamp; parallelly calculating a plurality of independent indexes characterizing the recovery process; performing validity checking on each index, and eliminating invalid or abnormal candidate values; and outputting a final recovery time after blocking by using a dynamic adaptive fusion strategy. The application further discloses a detection system and a wearable device for realizing the method. The application uses recovery kinetics after pressure relief to represent blood fluidity, realizes automatic and accurate detection of the recovery time through a multi-index cooperative judgment and a dynamic fusion mechanism, effectively suppresses noise interference and improves robustness, and can be used for non-invasive evaluation of vascular elasticity, blood viscosity and microcirculation function.

This invention discloses a non-invasive blood pressure reconstruction system and method based on physical decomposition and blood flow drift modeling, belonging to the field of biomedical signal processing technology. This invention decouples the absolute arterial blood pressure waveform reconstruction task into a waveform morphology reconstruction stage and a blood pressure drift calibration stage. The waveform morphology reconstruction stage outputs a normalized arterial blood pressure waveform based on photoplethysmography (PPG) pulse wave signals and individual characteristic information. The blood pressure drift calibration stage uses intermittent non-invasive blood pressure measurements as calibration anchors and predicts the blood pressure parameter drift by combining calibration timeliness information. The normalized arterial blood pressure waveform and the blood pressure parameter drift are synthesized into an absolute arterial blood pressure waveform. The waveform morphology reconstruction stage and the blood pressure drift calibration stage are trained separately. Trust window management is performed based on the calibration time interval, triggering safety output control when calibration information exceeds the effective timeliness. When a new intermittent measurement value arrives, the calibration anchor is updated and the calibration time interval is reset.

The application discloses a kind of based on heart sound double-flow feature coordination's intelligent identification method for children's congenital heart disease, belong to biomedical signal processing technical field.The method obtains child heart sound audio signal and carries out pretreatment, respectively extracts heart sound time-frequency energy feature and heart sound gamma pass feature, is coupled and is constructed double-flow multidimensional heart sound feature map after time domain resolution synchronous processing;Characteristic map is input hierarchical time-frequency analysis network, with noise suppression unit filters out environmental disturbance, with key feature focusing unit highlights abnormal heart sound feature;Combined with difficult and easy sample balance strategy training model, output classification prediction probability.The application is improved through double-flow feature complementation and multi-stage feature enhancement, heart sound feature expression and anti-interference ability, help to improve the stability and reliability of the intelligent identification of children's heart sound anomaly.

This application discloses a method and electronic device for analyzing heart sounds, relating to the field of biomedical signal processing technology. The method includes: acquiring a target electrocardiogram (ECG) signal, a target heart sound signal, and a target pulse signal; determining a first heart sound and a second heart sound from the target heart sound signal based on a first time point corresponding to the R-wave peak point in the target ECG signal and a second time point corresponding to the trough point in the target pulse signal, and determining the first heart sound envelope peak value and the second heart sound envelope peak value; identifying three valid heart sound peak points in the first heart sound based on the first heart sound envelope peak value, and identifying two valid heart sound peak points in the second heart sound based on the second heart sound envelope peak value; and performing heart sound analysis based on the five valid heart sound peak points to obtain the heart sound analysis result. This application can more accurately resolve heart sound signals in low signal-to-noise ratio environments, thereby improving the practicality and reliability of heart sound signals in health monitoring and clinical decision support.

The application discloses a kind of multi-modal information fusion based on pulse neural network emotion recognition method, belong to artificial intelligence, brain-like intelligence and biomedical signal processing technical field.The purpose of the present application is to introduce mutual mode dynamic threshold adjustment and collaborative coordinate attention mechanism, improve the accuracy, robustness and energy efficiency of multi-modal emotion recognition, realize the efficient alignment and adaptive deep fusion of heterogeneous physiological signals in pulse domain based on pulse neural network multi-modal information fusion emotion recognition method.The application respectively inputs each mode signal into the pulse encoder with the same structure and parameter-configurable to extract aligned features, inputs the mutual attention output of two directions after splicing into collaborative coordinate attention module to generate joint pulse gating map, and finally performs selective gating and fusion on enhanced features.The application effectively eliminates the inherent spatial noise and time-domain artifacts in physiological electrical signals, while ensuring the sparsity of pulse features, greatly improving the information density of the fused features.

This invention proposes a method and system for real-time monitoring and assessment of cervical dilation based on the LP labor monitoring system. It belongs to the interdisciplinary technical fields of intelligent obstetric monitoring, biomedical signal processing, and clinical decision support. The method includes: deploying an FBG-BIS flexible patch at the cervix of the parturient woman to directly collect cervical deformation micro-strain signals, generating raw cervical dilation data; simultaneously collecting uterine contraction pressure signals and fetal heart rate signals, generating raw uterine contraction data and raw fetal heart rate data; performing ternary time-series alignment processing on the raw cervical dilation data, raw uterine contraction data, and raw fetal heart rate data using a dynamic time warping algorithm, generating aligned cervical dilation data, uterine contraction data, and fetal heart rate data; and directly measuring cervical dilation using the FBG-BIS flexible patch, improving the accuracy and comprehensiveness of cervical dilation data acquisition and more realistically reflecting the labor process.

This invention discloses a method and apparatus for attenuation correction of dynamically acquired PET cardiac images, relating to the field of biomedical signal processing. The method includes: simultaneously acquiring cardiac and respiratory signals and PET data; preprocessing the data to divide a joint phase interval; segmenting the heart, lung, and chest wall regions; constructing a dynamic attenuation baseline sequence; and optimizing the attenuation coefficient map by incorporating tracer metabolic kinetics characteristics; achieving attenuation compensation through phase matching and projection correction; reconstructing PET images of each phase and fusing them to generate a dynamic sequence; and judging the quality of the results through evaluation indicators, iteratively adjusting model parameters if the results do not meet the standards. The advantages of this invention are: avoiding artifacts by dividing the joint phase interval through simultaneous acquisition of motion signals; optimizing attenuation correction by incorporating tracer metabolic characteristics; and combining this with an evaluation iteration mechanism, thus efficiently improving the accuracy and quality of PET cardiac image correction.

This invention provides a denoising model training method, a denoising method, and an electronic device, relating to the field of biomedical signal processing technology. The method includes: simulating and generating multiple pure hemodynamic response signals, and adding noise to each pure hemodynamic response signal to form multiple noisy functional near-infrared spectral signals; wherein each pure hemodynamic response signal corresponds one-to-one with each noisy functional near-infrared spectral signal to form a training sample set; using the training sample set, training an initial denoising model with a first loss function to obtain an intermediate denoising model; using the training sample set, training the intermediate denoising model with a second loss function to obtain a target model; this application constructs the training sample set based on a data-driven simulation method, and combines a two-stage training strategy, improving model accuracy and reducing damage to the morphological and amplitude details of real HRF signals.

This invention relates to the field of biomedical signal processing technology, and discloses a method and system for inferring peaks in calcium ion imaging signals based on deep learning. The method includes the following steps: generating a recovered sequence by segmenting the original noisy calcium ion signal time series through interval sampling, and training a one-dimensional U-Net neural network model; processing historical noisy calcium ion signal time series using the one-dimensional U-Net neural network model to obtain historical denoised signals, and training a one-dimensional convolutional neural network model using the historical denoised signals; inputting the denoised original noisy calcium ion signal time series to be processed into the one-dimensional convolutional neural network model to infer the absolute peak rate sequence of neurons. This invention suppresses noise without external ground truth data through self-supervised denoising, improves the signal-to-noise ratio using a two-stage framework, and accurately calculates discrete firing events of neurons, solving the problems of existing technologies that rely on ground truth databases and have low inference accuracy under low signal-to-noise ratios.

The invention belongs to the technical field of wearable medical monitoring equipment, flexible electronic technology, biomedical signal detection and processing technology and dysphagia auxiliary diagnosis, and discloses a flexible magnetic-electric bimodal swallowing function real-time dynamic monitoring system and a flexible magnetic-electric bimodal swallowing function real-time dynamic monitoring method. The real-time dynamic monitoring system comprises a flexible sensing assembly, a magnet assembly, an impedance acquisition module, a magnetic signal acquisition module, a main control processing module and a diagnosis output module, synchronously acquires a biological impedance signal and a magnetic induction intensity vector signal in a swallowing process, reconstructs a laryngeal movement process, and performs real-time dynamic monitoring on the swallowing process. The method comprises the following steps: extracting rheological characteristics of a food mass passing process from a biological impedance signal, carrying out self-adaptive compensation on motion artifacts in the biological impedance signal by utilizing a magnetic induction intensity vector signal, and calculating a time delay parameter to realize swallowing coordination evaluation, swallowing starting delay identification and mistaken suction risk early warning. The device has the advantages of flexible structure attachment, dual-mode synchronous detection, high motion interference resistance, suitability for continuous non-invasive monitoring and the like.

This invention relates to the fields of biomedical signal processing and artificial intelligence, and discloses a blood glucose detection method based on a PPG-based cross-modal attention fusion network. The method includes acquiring raw PPG signals from the human body and preprocessing the raw PPG signals to obtain effective PPG signal segments. Based on the same PPG signal segment, at least two different modal feature representations are constructed, including at least: a first modal feature, which is a temporal feature constructed based on the PPG signal segment, including the original temporal signal and its derivative features and frequency domain features; and an image feature obtained by mapping the PPG signal segment to a two-dimensional temporal image. This invention, by constructing temporal and image dual-modal features from the same PPG signal segment, can simultaneously mine the temporal dynamics, frequency domain characteristics, and two-dimensional spatial morphological information of the signal, overcoming the limited expressive power of traditional single temporal features, and achieving a more comprehensive and deeper representation of blood glucose-related physiological information.

The application discloses a channel optimization method for configuring an electroencephalogram monitoring device, and belongs to the technical field of biomedical signal processing and artificial intelligence. The method obtains high-density multi-channel electroencephalogram data and a depression risk label of a subject group, pre-processes and segments the electroencephalogram data, extracts multi-domain features such as time domain, frequency domain, nonlinear entropy value and inter-channel connectivity of each physical channel, and trains a machine learning classification model in a cross-validation framework. Further, a channel-level grouping permutation importance strategy is used to calculate channel contribution, and a minimum optimal channel combination is determined based on contribution ranking and a performance threshold to generate an algorithm deployment package containing a channel mask index and a lightweight classification model. The application significantly reduces the number of electroencephalogram channels, reduces hardware complexity, power consumption and computing load under the premise of ensuring the performance of depression risk assessment, and is suitable for engineering deployment of low-density electroencephalogram monitoring devices.