71 results about "Baseline wander" patented technology

The invention discloses a power grid multi-range intelligent sensing method and system based on MEMS integration, and relates to the technical field of intelligent sensing, and the method comprises the steps: connecting an MEMS sensing unit to three parallel measurement channels, and connecting the MEMS sensing unit to a controllable signal routing module in parallel; after gating, the signals are sent to a successive approximation analog-to-digital converter for digitalization through nonlinear gain amplification and anti-aliasing filtering; determining a measuring range based on a sampling sequence and a sliding window ratio, and automatically switching channels through a threshold value and a hysteresis mechanism; performing baseline correction on the switching data and performing weighted fusion according to sensitivity and bandwidth; and after the laboratory performs segmented calibration and consistency verification on the three channels, calibration parameters are written and stored, and are transmitted to an upper system through an isolation power supply according to a preset protocol. Automatic range switching is achieved through a sliding window and a hysteresis mechanism, baseline drift correction and weighting fusion according to the proportion of sensitivity and bandwidth are adopted after channel switching, and measurement continuity and precision consistency are ensured.

The invention belongs to the technical field of medical signal processing, and particularly relates to a heart sound and electrocardio combined coronary heart disease detection method based on time-frequency fusion, which comprises the following steps: S1, performing data preprocessing on PCG and ECG original signals, including noise reduction, baseline drift elimination, power line interference elimination and the like, and performing normalization processing on the PCG and ECG signals to obtain a normalized PCG and ECG signal; a Welch method is adopted to generate power spectrum signals of heart sound and electrocardio, and time domain signals and power spectrum signals of PCG and ECG are segmented into equal-length fragments. In order to effectively solve the problem of inaccurate diagnosis caused by poor single-modal data quality, a heart sound and electrocardio dynamic fusion module is constructed based on a time-frequency fusion result of two signals, dynamic weight distribution is carried out, a proper classifier is selected for classification, and the diagnosis accuracy is improved by supplementing frequency domain information. And the weight is distributed according to the contribution of the heart sound and the electrocardiosignal, so that the detection and classification result of the coronary heart disease is more accurate.

The various implementations described herein include techniques and apparatuses for multi-channel biopotential signal acquisition, biopotential signal pre-processing, and adaptive signal conditioning. In one aspect, an apparatus is provided for adaptive signal conditioning for biopotential acquisition. The apparatus includes an analog circuit configured to amplify biopotential signals, and a mixed-signal circuit (e.g., which can include an adaptive digital algorithm) coupled to the analog circuit and configured to suppress aggressor signals such as baseline wandering signals and power-line-induced noise in the biopotential signals before amplification of the biopotential signals.

The invention relates to a signal acquisition device of a cadmium zinc telluride detector based on multiple channels, which is characterized in that a multi-channel parallel processing unit, a dynamic baseline drift correction unit, a self-adaptive dead time control unit and an energy spectrum reconstruction and trailing suppression unit are mutually matched; reverse compensation current can be injected into each channel through the dynamic baseline drift correction unit so as to adjust the output of each channel, and low-frequency noise interference is eliminated in combination with a digital filtering algorithm. The dead time can be dynamically adjusted according to the current channel counting rate through the self-adaptive dead time control unit, multiple counters are started to work alternately in a first counting rate mode, and counter resources are combined in a second counting rate mode to improve the resolution; through the energy spectrum reconstruction and trailing suppression unit, a charge collection curve can be fitted through correlation analysis of timestamps and amplitude data, hole trailing signals are recognized, counter shielding logic is triggered, related noise interference is reduced on the whole, and signal collection accuracy is improved.

The invention belongs to the technical field of coal quality detection, and particularly relates to a method for rapidly predicting coal quality parameters based on Raman spectrum in combination with machine learning. According to the method, a Raman spectrum technology and machine learning are combined, a Raman spectrum systematic preprocessing process is adopted, an adaptive iteration reweighted least square method Air-PLS is applied, spectral signals and baseline drift are accurately separated, Savitzky-Golay filtering is applied, peak shape features are reserved, random noise is effectively suppressed, and the method is suitable for large-scale popularization and application. Maximum-minimum normalization or Z-score standardization processing is provided, and the intensity difference between samples is eliminated; moreover, a data-driven Raman spectrum intelligent feature screening mechanism is introduced, and an optimal feature wavelength subset which is highly related to coal quality parameters and low in redundancy is screened out through automatic iteration; according to the method, the data quality in Raman spectrum coal quality detection is improved, the feature correlation is enhanced while the feature dimension is reduced, the model precision and generalization ability are improved, and rapid, lossless, high-precision and high-robustness coal quality parameter prediction is realized.

The invention discloses an electrocardiosignal noise reduction method based on deep convolution and a sequential network, which comprises the following steps of: firstly, obtaining a pure electrocardiosignal through a synthetic function or a public data set, and constructing a pure-noisy electrocardiosignal pair by adding myoelectricity noise, power frequency noise, baseline drift or a combination of the myoelectricity noise, the power frequency noise and the baseline drift; designing a time sequence network structure comprising an input layer, a multi-level residual layer, a channel pruning layer, a full connection layer and an output layer, extracting time sequence features in the residual layer by using causal convolution, improving the performance of the model in combination with normalization, an activation function and a residual connection and discarding mechanism, training the model in a supervised learning mode, and obtaining a time sequence network structure; a mean square error or a mean absolute error is adopted as a loss function, network parameters are optimized through back propagation, and finally, the trained model is deployed on electrocardiogram monitoring equipment, so that real-time noise reduction processing on actual electrocardiogram signals is realized. According to the method, the time sequence characteristics of the electrocardiosignals can be effectively reserved, the noise reduction precision and robustness are improved, and the method is suitable for various medical and health monitoring scenes.

An interface circuit configured in accordance with certain aspects of this disclosure has a high-pass filter and a low-pass filter. The high-pass filter may include a capacitor coupled between an input of the interface circuit and an output of the interface circuit and a resistor coupled between the output of the interface circuit and a voltage reference source. The capacitor and resistor may be configured to provide a low-pass filter that couples the reference voltage source to the output of the interface circuit. The interface circuit provides a feedforward loop that includes the reference voltage source and an amplifier. The amplifier has an input coupled to the input of the interface circuit and an output coupled to the reference voltage source.

The invention relates to the technical field of digital medical treatment, and discloses an intelligent chronic disease screening method based on multi-source data fusion, which comprises the following steps: firstly, calculating a sensor credibility reference value based on the historical performance and real-time state of each sensor; performing quality evaluation on the physiological signal according to the credibility reference value, and identifying and marking a signal disturbance interval; then, performing frequency domain analysis and environment interference correlation verification on the marked disturbance interval, and dynamically adjusting the weight coefficient of each sensor; carrying out weighted fusion on the multi-source physiological signals by adopting the adjusted weight coefficient, and carrying out baseline drift correction on low-quality signals; and finally, extracting physiological feature parameters from the fusion signal, matching the physiological feature parameters with a health state pattern library, and outputting a chronic disease screening evaluation result. The problems that in a traditional monitoring system, data quality evaluation standards are not uniform, fusion strategies are rigid, and continuous optimization capacity is lacked are solved, and the accuracy and reliability of chronic disease screening are remarkably improved.

The invention discloses a heart rate measuring method based on a smart phone. The method comprises the following steps: (1) collecting fingertip pulse plethysmography (PPG) signals under the condition of preset camera parameters; (2) preprocessing the collected signals, removing baseline drift through a filtering method and the like, and suppressing noise; (3) evaluating the signal quality based on a template matching method, and when the signal quality score is lower than a preset threshold value, not outputting a heart rate result and giving an operation suggestion; and (4) carrying out time domain peak detection on the high-quality signal to obtain a heart rate estimation value. According to the invention, through systematic optimization in the links of signal acquisition, quality evaluation and peak value detection, the defects of low accuracy, easy interference and lack of reliability evaluation in a complex environment in the prior art are solved, and the heart rate measurement scheme is convenient, high in precision and high in robustness; and a more reliable and accurate mobile health monitoring solution is provided for the user.

The application discloses a double-lead finger clip electrode biological wave detection method and device, and belongs to the technical field of biomedical engineering, and comprises a mechanical contact terminal, an intelligent adaptive module and a display terminal; the mechanical contact terminal comprises left and right two finger clip electrodes and is used for receiving biological wave signals in real time; the intelligent adaptive module is used for pre-processing the received biological wave signals, dividing the biological wave signals into low, medium and high frequency bands to extract key features, calculating cross-correlation coefficients and baseline drift amplitudes, constructing a classification model, identifying a user age range and automatically adjusting mode parameters, checking contact stability through a fast resampling mechanism and a dynamic threshold, and performing impedance compensation; and the display terminal is used for decomposing biological wave signals, extracting multi-domain features, modeling through a space-time attention LSTM network, calculating a physiological age and a health risk index, and generating an intervention measure recommendation list.

The present application belongs to the field of intelligent medical treatment and health monitoring technology, and specifically relates to a heart-source sudden death risk monitoring and early warning system and method based on multi-source signal collaborative analysis. The method aims to solve the technical problem of signal quality degradation caused by motion artifact interference in existing wearable electrocardio monitoring. It includes: synchronously collecting electrocardio signals and three-axis acceleration signals through a wearable device, performing adaptive motion artifact filtering based on acceleration reference, power frequency notch filtering and baseline drift correction; performing QRS wave detection and feature extraction on the preprocessed waveform, combining with the motion intensity index to mark the candidate risk event segment; transmitting the structured event data packet to a mobile terminal, outputting the risk arrhythmia confidence degree by using a lightweight time sequence neural network model, and performing comprehensive risk assessment by fusing the event duration and frequency, the user real-time activity state and the individualized historical baseline; and performing differentiated response strategies according to the risk level.

This invention provides an FPGA-based encoding method for single-core cable logging, comprising: detecting whether the edge of the original transmitted signal changes; if the edge of the original transmitted signal changes, encoding the original transmitted signal using two pulse signals to obtain a final output signal in which positive and negative levels cancel each other out. This invention uses an FPGA module and an external driving circuit in synergy to encode the original transmitted signal, resulting in a final output signal in which positive and negative levels cancel each other out. This invention effectively avoids baseline drift-induced glitches that interfere with the signal and affect data accuracy, thus solving the problem of level fluctuations affecting the signal in single-core cable transmission for oil logging.

The invention discloses a sleep monitoring and intelligent early warning system and method based on a multi-modal time sequence signal, and the system comprises a multi-modal sensor module which is used for collecting an original heterogeneous time sequence signal of a subject in a sleep period; the time sequence data preprocessing module is used for performing timestamp alignment, band-pass filtering noise reduction, baseline drift correction and sliding window segmentation on the original heterogeneous time sequence signals and extracting multi-modal feature vectors; the sleep feature recognition module is used for receiving the multi-modal feature vector, performing deep feature learning and outputting sleep staging probability distribution and a sleep apnea event detection mark; the large language model module is used for performing joint coding on an output result, a historical sleep file of the subject and a clinical diagnosis text to generate a structured sleep quality assessment report and health risk association analysis; and the multi-level intelligent early warning and decision support module is used for triggering early warning signals of different levels and generating personalized sleep intervention suggestions.

This invention discloses a gas concentration detection method based on nonlinear fitting of second harmonic signals, comprising: 1. constructing the Voigt linear function of the second harmonic signal; 2. calculating initial fitting values, performing nonlinear fitting on the acquired second harmonic signals of the reference channel and the measurement channel to obtain the optimal fitting parameters; 3. calculating the fitted standard second harmonic signal and the peak value of the second harmonic signal based on the optimal fitting parameters, and using the peak value for concentration inversion. This invention, without increasing the hardware structure, solves the problems of signal baseline drift and signal deformation affecting measurement accuracy through a nonlinear fitting method of the second harmonic signal, thereby improving detection accuracy and ensuring the stability of the detection system.

This invention relates to a method and medium for processing chest impedance signals with adaptive optimization of VME parameters. The method includes the following steps: acquiring a collected chest impedance signal; extracting a baseline signal from the chest impedance signal using a first VME algorithm to obtain a baseline-de-baseline signal, wherein the penalty coefficient of the first VME algorithm is determined through adaptive selection; and performing denoising processing on the baseline-de-baseline signal to extract the respiratory component. Compared with existing technologies, this invention has advantages such as high signal processing efficiency and the ability to process data from different subjects under different conditions.

The application relates to the technical field of magnetic variable measurement, in particular to a magnetic induction electric field dynamic compensation control method based on online disturbance response, which comprises the following steps: injecting a characteristic test signal to the induction axis of a magnetism sensor, extracting an amplitude-phase deflection response characteristic by using a digital lock-in amplifier to construct a dynamic mapping matrix, and online identifying the gain, time constant and pure lag measurement model parameters of a calibration coil loop; an error processing unit sets an error offset coefficient and generates a reverse compensation control instruction to drive a loop to generate an offset magnetic field; the intensity of a multi-node parasitic induction electric field is obtained as a dynamic weight, a Steiner-Weber algorithm is used to solve a space equivalent interference radiation center, and the test duty ratio and calibration weight of each node are adjusted. The application actively injects orthogonal signals to online decouple a measurement baseline drift, and adaptively cooperates with a multi-node measurement array, so that wide-band and extremely low dynamic residual measurement of a large-space alternating magnetic field is realized.

The present application relates to the technical field of Pickleball, and specifically relates to an intelligent wearable system for monitoring sports posture. The system synchronously collects multi-axis acceleration and angular velocity original signals before and after the player hits the ball through the inertial measurement unit built in the wearable device, generates time series after time window interception and normalization processing; removes noise and baseline drift by wavelet transform; fuses time domain and frequency domain features to construct a high-dimensional comprehensive feature vector; realizes preliminary classification of actions through a long short-term memory network, refines similar action types by combining a convolutional neural network, and finally outputs accurate classification results through a support vector machine; dynamically optimizes model parameters based on a real-time feedback mechanism, and enhances local feature representation through a channel attention mechanism. The system can accurately identify more than fifteen Pickleball special technical actions, has high robustness and self-adaptive ability, can provide real-time posture specification guidance for athletes, and helps to improve training efficiency and prevent sports injuries.

The invention relates to an electrocardiosignal quality evaluation method and device, electronic equipment and a storage medium. The method comprises the steps that a first electrocardiosignal is obtained; determining a baseline drift index of the first electrocardiosignal and the number of target abnormal waves in the first electrocardiosignal; determining feature information of the first electrocardiosignal based on a variation parameter of the first electrocardiosignal, the baseline drift index and the number of the abnormal waves; performing at least one classification processing on the feature information to obtain at least one classification result; and based on each classification result, obtaining a target evaluation result corresponding to the first electrocardiosignal, so that the calculation complexity and resource loss are reduced while the accuracy of evaluating the quality of the first electrocardiosignal is improved.

The invention belongs to the field of blood oxygen self-adaptive monitoring, and particularly discloses a patient blood oxygen self-adaptive monitoring system based on wearable equipment, which comprises a bandage, a display screen, a green light diode, a red light diode, an infrared light diode, a photoelectric detector, a processing chip, a battery and a shell. According to the scheme, the green light diode is introduced into the wearable device, the green light PPG signal is used as the time sequence reference of the red light PPG signal and the infrared light PPG signal, the peak and trough periods of the green light signal are accurately extracted through the increment merging segmentation algorithm in combination with the adaptive threshold updating strategy, and the error rate of period detection is reduced; dynamic elimination of baseline drift is realized by using a multi-stage moving average filter, a PPG signal quality dynamic classification and reconstruction mechanism based on multi-dimensional quality parameters is designed, and the data availability of PPG signals in a motion state is improved.

The invention relates to the field of gas detection, in particular to a gas detection method and system based on an all-fiber oscillation interference absorption spectrum. High-frequency modulation is introduced through piezoelectric ceramics (PZT) to generate a stable oscillation interference absorption spectrum, so that an efficient gas detection method without laser intensity calibration, baseline fitting and background signal deduction is realized, the system adopts a 10Hz triangular wave signal to scan laser current, and the PZT is modulated through a 1KHz sine wave signal, so that the accuracy of the gas detection is improved. The gas concentration or absorption coefficient is inversed by analyzing the envelope of the oscillation interference absorption spectrum and calculating and demodulating the contrast degree (V) of the oscillation interference absorption spectrum by using the oscillation interference absorption spectrum to optimize the sensitivity and linear range of detection, so that the accuracy of the calculation result is improved, and the method can be applied to a more severe environment; the problems of laser intensity fluctuation, baseline drift and background signal interference of a traditional laser absorption spectrum technology under severe environment interference are solved.

A method and an apparatus are provided in which an analog signal may be sampled by an analog-to-digital converter (ADC) to generate digital signal samples affected by baseline wander. Digital signal processing (DSP) may be performed on the digital signal samples to generate a recovered signal with corrected baseline wander. The DSP is performed using a first adaptable coefficient for a current digital signal sample and a second adaptable coefficient for a previous digital signal sample.

This invention relates to the field of signal data processing technology, specifically to an anti-interference connector for automotive electronic systems. This application first analyzes the characteristic behavior of the spectrum within the time period of arc flicker interference in the original signal, obtaining the arc flicker frequency band and arc flicker influence coefficient. Based on the arc flicker influence coefficient, and combined with baseline drift and signal fluctuation in the time series, the influence of electromagnetic interference, i.e., arc flicker interference, is more accurately quantified using the determined electromagnetic interference characteristic values. Furthermore, a sensitivity weight is determined to characterize the impact of the anti-interference connector's aging accumulation. Based on the sensitivity weights characterizing the interference components and the electromagnetic interference characteristic values, the simulated signal to be processed is corrected, making the obtained corrected simulated signal more accurate and improving the accuracy of anomaly monitoring in automotive electronic systems based on the corrected simulated signal.

This invention discloses a polarity testing method for metering devices suitable for high-noise environments, belonging to the field of metering device testing technology. The method includes: generating a square wave excitation signal with preset parameters based on algorithm control and applying it to the primary side of the metering device; acquiring the secondary side induced response signal, which is then synchronously transmitted after filtering, baseline drift correction, and amplitude scaling preprocessing; integrating the excitation and preprocessed signals, extracting phase difference, delay time, and amplitude characteristic parameters, and sequentially performing polarity, phase sequence, and on / off determination to obtain a preliminary comprehensive result; based on the preliminary result and characteristic parameters, outputting the determination result and confidence level through an improved CNN model, and obtaining the final polarity conclusion through weighted fusion; and visually outputting the final conclusion. This invention, through the collaborative design of precise excitation, anti-interference preprocessing, multi-dimensional preliminary determination, and AI-fused final determination, effectively suppresses noise interference, improves the accuracy and stability of polarity determination, and is suitable for high-noise scenarios such as industrial sites and substations.

The invention discloses a period-phase optimized robot tactile signal segmentation and alignment method, which can quickly extract effective signal segments when a robot contacts an object, and solves the problems of unstable tactile signal form, baseline drift, uncertain period length and the like. The method provides a joint optimization normal form: firstly, estimating the average period of a tactile signal through self-correlation analysis; then, unified modeling is carried out on the segmentation tangency points and the fragment duration under structural constraints to form variables to be optimized, and an aggregation similarity objective function with normalized mutual measurement standards is constructed; and finally, iteratively solving the optimal segmentation point and phase of the time sequence signal in the contact process by maximizing the objective function. Compared with a traditional non-global optimization method, the method can be suitable for non-fixed-length quasi-periodic signals with unstable forms, has high robustness for amplitude drift and periodic jitter, is higher in segmentation precision and universality, and can provide accurate contact segment effective signals for robot touch recognition.

The application provides an arrhythmia signal detection method and system based on expert knowledge, wherein the method comprises the following steps: performing signal filtering on an acquired electrocardio signal to filter out high-frequency noise and baseline drift in the electrocardio signal; performing P-QRS-T positioning detection on the signal-filtered electrocardio signal to obtain a QRS complex and P / T wave; performing expert-knowledge-based feature mapping on the obtained QRS complex and P / T wave to obtain a category feature of the electrocardio signal; comparing the obtained category feature of the electrocardio signal with a preset threshold to determine an arrhythmia signal, thereby completing detection of the arrhythmia signal. Meanwhile, a corresponding terminal and medium are provided. The application improves the detection accuracy; fully considers the morphology of an abnormal heartbeat and the timing of positioning the P / T wave, can effectively avoid the case that the P-QRS-T positioning is inaccurate due to the abnormal heartbeat, has high robustness, and has low computational complexity.

The application relates to the technical field of data collection, and relates to a sports movement data collection system based on a wearable device, which comprises a signal synchronization fusion module, a reference modeling and calibration module, a signal enhancement and segmentation module, a feature matching and extraction module, a deviation quantization module and a comprehensive scoring module. In the progress process of a body measurement project, original inertia signals of a tested person are acquired; waveform features of standard actions are analyzed, baseline drift compensation is carried out on the analyzed reference waveforms, and measurement reference data are obtained; principal component signal reconstruction is carried out on the original inertia signals, and action stage signal segments of the tested person are segmented; the action stage signal segments are mapped to the measurement reference data, and key kinematic parameters are obtained; the key kinematic parameters are quantized, and action deviation degrees are obtained; comprehensive movement evaluation is carried out on the action deviation degrees, and movement performance data are obtained; and the application can improve the efficiency of sports movement data collection based on a wearable device.

The invention provides a baseline drift correction circuit, a baseline drift correction method and a communication system, and relates to the technical field of communication, the baseline drift correction circuit comprises a compensator, a decision device, an adaptive updater, a low pass filter and a multiplier; the compensator outputs a compensated signal according to the acquired current receiving signal and a previous compensation signal output by the multiplier; the decision device outputs a current decision signal corresponding to the compensated signal; the self-adaptive updater performs self-adaptive updating of the gain and the time constant through a gradient descent algorithm according to the compensated signal and the current judgment signal to obtain the current gain and the current time constant; the low-pass filter outputs a current low-pass filtering signal according to the current time constant and the current judgment signal; and the multiplier outputs a current compensation signal according to the current gain and the current low-pass filtering signal. According to the invention, a gradient descent algorithm is adopted, two-dimensional optimization of gain and cut-off frequency is realized, and the accuracy of offset compensation is improved.

The invention discloses a cross-modal silent voice reconstruction method and system based on ear canal air pressure micro-motion sensing, and belongs to the technical field of man-machine interaction and wearable computing. The method comprises the following steps: acquiring a non-acoustic air pressure sequence caused by vocal organ movement by using a micro air pressure sensing unit arranged in the in-ear earphone; constructing a robust feature space through adaptive baseline drift suppression and rhythm perception data enhancement processing; and further mapping the TPVS into a high-fidelity acoustic Mel spectrum by using an end-to-end deep neural network including domain adversarial adaptation, cross-modal semantic alignment, coarse-grained Mel spectrum generation and residual detail correction. The technical bottleneck that low-frequency mechanical signals lack high-frequency acoustic features is effectively broken through, and high-precision silent voice instruction analysis in a mobile and noise scene is achieved; and coupling quality evaluation gating and trigger type start / stop control are introduced at a reasoning end, so that invalid reasoning is inhibited and power consumption is reduced under the condition of poor wearing or no trigger.

Embodiments herein relate to techniques for baseline wander (BLW) compensation. The technique may include identifying a data stream that is to be modulated by a ring modulator of an optical transmitter, wherein the data stream has a frequency operable to cause thermal-based BLW of an optical output of the optical transmitter. The technique may further include adjusting a time-varying direct current (DC) voltage bias of the ring modulator based on the frequency of the data stream. Other embodiments may be described and / or claimed.

The present disclosure provides an ultrasonic bolt pretightening force detection method and system based on improved CEEMDAN-wavelet threshold, relating to the technical field of bolt pretightening force detection, comprising: obtaining ultrasonic echo original signals under different loads; performing improved CEEMDAN decomposition on the ultrasonic echo original signals to obtain IMFs (Intrinsic Mode Functions) without modal aliasing; calculating MPE values of each IMF, classifying the components through a double-threshold quantization method to obtain to-be-de-noised components, effective reserved components and baseline drift components; introducing an improved threshold function with smoothing characteristics, accurately de-noising the to-be-de-noised components through the improved threshold function, and reconstructing to obtain de-noised IMFs; fusing the de-noised IMFs and the effective reserved components, reconstructing a pure ultrasonic echo signal and extracting a time-of-flight feature; calculating the acoustic time difference between a reference signal and a measurement signal using a cross-correlation method, and finally obtaining an accurate bolt pretightening force. The present disclosure ensures high-precision dynamic monitoring of bolt pretightening force in harsh engineering environments.