80 results about "Noise removal" patented technology

The pickup device (1) includes: an adaptive filter (141) that generates a speculative noise signal from a reference signal representing the noise signal component contained in the input signal acquired by the microphone (11); a noise removal signal generation unit (15) that generates a noise removal signal after subtracting the speculative noise signal from the input signal; a filter coefficient update unit (142) that updates the filter coefficients of the adaptive filter (141) using the noise removal signal; and a sample position determination unit (162) that determines at least one signal sample position from the signal sample position with the largest absolute value of the noise removal signal up to the predetermined largest signal sample position, wherein the filter coefficient update unit (142) updates the filter coefficients at the at least one signal sample position determined by the sample position determination unit (162).

This invention relates to the field of remote sensing image processing technology, specifically disclosing a building change detection method based on a dual-branch encoder and multi-feature fusion. By modeling the building body and edges separately, this invention elevates edge information to an equal level of importance with body information, providing a new design approach to solve the long-standing problems of boundary adhesion and ambiguity in building change detection, and facilitating the handling of irregular boundaries. A feature cross-fusion module effectively promotes the fusion of building integrity, ensuring the semantic consistency and accuracy of the results. In the decoder section, a hierarchical feature fusion noise removal module maximizes the identification and removal of abnormal image patches. This invention achieves efficient and high-precision building change detection by inputting the acquired dual-temporal remote sensing image (including the preceding and following temporal images) into the constructed building change detection model and outputting the building change detection results.

The present invention relates to a method for detecting and removing a motion artifact of a functional near-infrared spectroscopy signal. Disclosed are a method and a device for detecting and removing a motion artifact of a near-infrared spectroscopy signal in real time on the basis of an artificial neural network model, the method comprising: a conversion step of converting time series data of functional near-infrared spectroscopy signals measured through a plurality of channels from a target into image data; a detection step of detecting whether noise is present in the converted image data using a pretrained detection model; and a removal step of removing noise from image data where noise has been detected using a pretrained noise removal model.

The patent application provides a complex environment three-dimensional scene reconstruction method based on a multi-view neural network, and the method mainly comprises two steps: scene information capturing: obtaining scene data from a plurality of views through a high-resolution camera, and ensuring that all details of a complex scene are covered; the captured image is standardized, including color correction and noise removal, to ensure image quality and consistency. And three-dimensional model reconstruction: performing three-dimensional reconstruction on the acquired scene data by using a neural network. Firstly, light sampling is performed on a scene through camera parameters and pose information, and an occupancy grid is created to optimize the sampling efficiency. Thirdly, decomposing the sampling data into feature vectors and inputting the feature vectors into a neural network which is divided into a density network and a color network and is used for generating volume density and color information of the scene; and finally, obtaining a three-dimensional scene model through a volume rendering technology. The method has the advantage that a high-precision three-dimensional model can be quickly generated in a complex environment through an efficient sampling and data processing technology.

The application provides a building label alignment method, device, equipment, storage medium and program product, and relates to the technical field of remote sensing image processing. The method comprises the following steps: obtaining a remote sensing image and a label to be aligned; inputting the remote sensing image and the label to be aligned into a pre-trained label alignment model, performing multi-step iterative reasoning, and obtaining target base position labeling and target roof position labeling output by the label alignment model; the label alignment model is obtained by performing noise training on an initial model based on a sample remote sensing image, a sample building label corresponding to the sample remote sensing image, and a sample correction vector corresponding to the sample building label. Through the above method, the model has good label correction capability and noise removal capability, effectively improves the accuracy of label alignment, and is more suitable for actual remote sensing image application scenarios.

This invention discloses a digital identification system and method for high-pressure testing instrument detection data. The system includes: a data acquisition and conversion module for acquiring and converting analog signals; a data preprocessing module for noise removal and anomaly detection; a key parameter extraction module for extracting and optimizing key parameters; a data analysis and identification module for analyzing data and issuing early warnings of anomalies; a feedback adjustment module for optimizing test parameters; and a display and control module for displaying data, analysis results, and alarm prompts. This invention combines sliding window time series analysis, Kalman filtering, temporal convolutional neural networks, and adaptive fuzzy logic control algorithms to intelligently analyze and process the detection data of high-pressure testing instruments, enabling fault early warning, precise optimization, real-time adjustment, and maintenance decision-making. The system features high precision, strong real-time response capabilities, and significant optimization and maintenance effects, significantly improving data processing capabilities and decision-making efficiency during high-pressure testing.

The application discloses an image denoising method and device, electronic equipment and storage medium, and relates to the technical field of artificial intelligence, wherein the image denoising method comprises the following steps: receiving a document image to be processed, and preprocessing the document image; removing first frequency noise in the preprocessed document image by using a preset deep learning network, extracting image features after noise removal processing to obtain a first image feature set, extracting image features conforming to second frequency noise in the document image by using a preset deep residual network to obtain a second image feature set, fusing the first image feature set and the second image feature set, inputting a feature map obtained after fusion into a target convolutional neural network, and outputting a target document image. The application solves the technical problem that image blurring is easily caused when a document image is denoised in the related art.

This invention provides a method and system for analyzing database performance indicators based on a large model, relating to the field of data processing technology. The method includes: acquiring performance indicator data of the database during operation, and performing time-series generation and noise removal on the performance indicator data to form standardized indicator sequence data; vectorizing the indicator sequence data and calculating the correlation strength between each performance indicator; performing semantic modeling processing through a large model to extract nonlinear coupling features between multi-dimensional performance indicators, forming bottleneck identification data containing coupling relationship levels; constructing a resource conflict resolution mechanism to determine the scheduling priority between computing resources and storage resources, generating scheduling instruction data containing resource adjustment magnitude and execution order; and updating the multi-dimensional feature representation data based on the performance feedback results after database execution. This invention improves the accuracy of database performance indicator analysis.

Various problems in a wire rope, such as internal defects, fatigue damage, wear, and corrosion, are nondestructively analyzed by momentarily magnetizing a wire rope with a permanent magnet for detection and detecting, via sensors, magnetic flux leakage signals that are generated in the magnetized state, but issues arise: defect signals are not clearly delineated due to environmental noise and trends contained in raw magnetic flux leakage signals; and signal distortion caused by the dynamic state of a rope must be removed to detect defects more accurately. To address these issues, data preprocessing comprises: a channel trend removal step for removing low-frequency signals below a threshold after acquiring signal data from a plurality of Hall sensors; a channel noise removal step for identifying high-frequency signals above the threshold as noise and removing same from the signal data that has undergone the trend removal step; a change point detection step for removing the effect of the wire rope moving upward, downward, or being stationary, to distinguish states and calculating information for detecting defects; and a Hilbert transform step for making the signs of the signals to be the same on the basis of the threshold so that the defects of the wire rope can be detected.

The application provides a low-resource multilingual large model training method and system for personalized course learning, and belongs to the technical field of large language models, and comprises the following steps: S1: collecting training samples in multiple languages; each sample is subjected to deduplication and noise removal processing, then the data format is unified, and a language attribute is added as a language label; S2: initializing parameters of an adaptive sampling scheduler and a dynamic loss scheduler; S3: using a pre-trained large language model as a base model, and adding the adaptive sampling scheduler and the dynamic loss scheduler in the training process. The method can reduce the dependence on low-resource language labeled data, can adaptively balance the training weights of different language samples, and dynamically matches the difficulty of multilingual tasks and the learning progress of the model.

This invention discloses an industrial carbon emission detection and prediction method and system. It collects multi-source heterogeneous data from industrial production processes, and sequentially performs standardization, noise removal, outlier removal, and data fusion on the multi-source heterogeneous data to obtain initial carbon emission data. A hybrid detection and prediction model is constructed, employing an encoder to extract multi-factor correlation features from the multi-source data and a long short-term memory network to extract temporal fluctuation features of the carbon emission data. An attention mechanism is introduced to weight the correlation features and temporal fluctuation features. An improved IWOA whale optimization algorithm is used to optimize the hyperparameters of the hybrid detection and prediction model to obtain a target hybrid detection and prediction model. The initial carbon emission data is input into the target hybrid detection and prediction model, and the prediction results are output, including the current carbon emission detection value and the carbon emission prediction sequence. This improves the accuracy of carbon emission prediction results and the efficiency of carbon emission detection.

This invention relates to the field of data processing technology, and in particular to a method and system for processing imbalanced data based on nearest neighbor constraints and consistency screening. The method includes acquiring industrial fault detection data; performing data preprocessing based on the acquired industrial fault detection data; constructing a minority class MNN skeleton based on DenMune clustering and performing two-layer noise removal; local adaptive oversampling based on MNN sparsity double-layer weights and MNN neighborhood constraint interpolation; dual-threshold screening based on source sub-cluster consistency and original sample dominance; and using a trained model to predict and classify fault samples. This effectively suppresses the introduction of new noise during oversampling, making the final training dataset more stable near the local structure and decision boundary, which is beneficial for improving the stability and robustness of the industrial fault detection model in imbalanced scenarios.

This invention pertains to data processing technology for seismic exploration of sandstone-type uranium deposits, specifically an adaptive denoising method for sandstone-type uranium deposit seismic data based on sparse transform. The method includes: inputting noisy raw two-dimensional seismic data y; initializing the maximum number of iterations I, setting the outer iterative accumulator i=1, and designing a search range J for the denoising coefficient truncation percentage; for each i, calculating the curvelet transform coefficients s of y; for each j within the search range, applying hard thresholding for denoising, and performing an inverse curvelet transform on the denoised coefficients to obtain the denoised seismic data y. j ; Calculate the noise removal ε corresponding to each j j The entropy; compare the calculated noise ε removed for each j. j The entropy is calculated, and the percentage corresponding to the maximum entropy within the search range is taken as the optimal denoising effect, and the corresponding seismic data is output. If i reaches the maximum number of iterations, the loop is exited, and the denoised seismic data corresponding to the current maximum entropy value is used as the output result. This invention can protect the effective signal while suppressing random noise.

This invention provides a multimodal incremental railway fastener defect detection method and system under severe weather conditions, belonging to the field of target recognition technology. Step 1: Sequentially construct training and validation sets for multimodal railway fasteners under rain, snow, fog, strong light, low light, and normal weather conditions; construct a global test set containing multimodal railway fastener data for all six weather conditions. Step 2: Construct a full-cycle closed-loop mechanism for multimodal target detection to achieve continuous learning in continuously evolving scenarios. Step 3: Propose a dual-space replay screening strategy for meta-features to extract challenging and representative high-value samples for inclusion in the replay pool. Step 4: Propose a wavelet-guided non-adversarial detail injection module to resolve the adversarial conflict between noise removal and style preservation in incremental learning. This invention can continuously adapt to various severe weather changes in railway scenarios, effectively alleviate the problem of catastrophic forgetting, and achieve accurate detection of fastener defects under various severe weather conditions.

A machine-learning based (ML-based) system and method for automatically extracting one or more data fields from one or more documents, are disclosed. The ML-based system includes a document obtaining subsystem to obtain documents, a document pre-processing subsystem to generate pre-processed data, a field identifying subsystem to identify data fields using a trained ML model, and a field extracting subsystem to extract financial information. The ML-based system also comprises an output subsystem to deliver the extracted data to end users via user interfaces. The ML model is trained using historical documents, labelled data fields, and features such as distance-based features, direction-based features, dimension-based features, positional features, and value-based features. The M-based system employs hyperparameter optimization, noise removal, and accuracy assessment mechanisms to enhance performance. This ML-based system provides a scalable, accurate, and automated solution for financial information extraction, ensuring efficiency, adaptability, and seamless integration with enterprise systems.

The present application relates to oil and gas seismic exploration data acquisition technical field, specifically to the observation scheme optimization method based on uniformity index. The method comprises the following steps: S10, collecting and arranging the observation parameters of the optimization scheme; S20, optimizing the design of the observation scheme parameters to obtain N optimization observation schemes; S30, calculating the noise removal response value corresponding to the N optimization observation schemes; S40, calculating the noise suppression response value corresponding to the N optimization observation schemes; S50, based on the noise removal response value and the noise suppression response value corresponding to the N optimization observation schemes, calculating the denoising response value corresponding to the N optimization observation schemes; S60, calculating the pre-stack time migration response value corresponding to the N optimization observation schemes; S70, based on the signal-to-noise ratio spectrum and the effective high frequency of the N optimization observation schemes, combining the index requirements of the target layer signal-to-noise ratio and the highest frequency, selecting the final scheme from the N optimization observation schemes.

The application provides a noise elimination method, device, equipment and medium to solve the technical problem of ear pressure caused by noise elimination in the prior art, which leads to user discomfort. The method comprises: acquiring a noise sound wave, wherein the noise sound wave is used to reflect the noise condition in the car; generating a noise reduction sound wave based on the noise sound wave, wherein the noise reduction sound wave is opposite in phase and the same in amplitude to the noise sound wave; determining an optimal noise reduction area and a user head position; and correcting the position of the optimal noise reduction area by adjusting the noise reduction sound wave, so that the corrected optimal noise reduction area does not coincide with the user head position.

The present application relates to the technical field of image processing, more particularly to a kind of infrared image multiscale stripe noise removal method, system and storage medium. Including the first infrared image is carried out N times downsampling, obtains the first infrared image;The first infrared image is carried out one-dimensional single side gray filtering 1*n in the first direction, obtains the low-frequency first infrared image, by filtering out low-frequency first infrared image, the stripe amplitude in the second direction of high-frequency first infrared image is obtained;High-frequency first infrared image second direction stripe amplitude is upsampled, and the stripe amplitude of the original width of first infrared image is obtained;The pixel point in the first direction of first infrared image is subtracted from the original width of the stripe amplitude of the corresponding position of first infrared image, and the first infrared image after removing vertical stripe is obtained. The quality of infrared image is effectively improved by the present application.

This invention belongs to the field of image processing, specifically disclosing a precise gastrointestinal lesion identification system based on image processing. The system includes an image acquisition module, an image preprocessing module, a lesion identification module, and a result output module. This solution achieves precise noise removal from gastrointestinal images while fully preserving the detailed features of lesion areas by constructing a standardized noisy dataset through noise simulation, employing a 4-level feature pyramid fully convolutional encoder-decoder architecture, incorporating deep-width residual blocks, multi-head attention, and convolutional gating mechanisms, and using L1 pixel reconstruction loss to train the model. A customized deep learning model is built based on EfficientNetB5, incorporating multiple regularization constraints, and employing an Adamax optimizer and classification cross-entropy loss for training, achieving efficient extraction of fine-grained features of gastrointestinal lesions, effectively suppressing model overfitting, and accelerating training convergence.

This invention provides an adaptive optimization control method for the heat-sealing splicing process parameters of umbrella canopies, comprising: collecting raw data such as heat conduction, deformation, and energy consumption using a multi-source heterogeneous sensor array; obtaining high-precision multi-dimensional process data through time-series calibration, noise removal, and data alignment; decoupling key thermodynamic features based on physical mechanisms to construct a searchable process semantic fingerprint and establishing a mapping library between states and optimal heat-sealing parameters; combining a lightweight meta-policy network, achieving parameter migration and online fine-tuning through minimal calibration learning to meet the rapid adaptation requirements of new materials or abrupt changes in working conditions; and integrating quality feedback throughout the process to achieve parameter optimization and closed-loop process control. This invention can effectively improve the quality and production efficiency of heat-sealing splicing, ensuring no warping at splicing edges, continuous adhesive lines, and controllable thermal damage.

This invention relates to a method for highlighting spike discharge data of intracranial electroencephalogram (EEG) signals. The method involves collecting background noise data from the patient's brain without neuronal discharges, preprocessing the background noise data, automatically selecting the optimal order of an autoregressive (AR) model using the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), estimating the AR model coefficients using the Yul-Walker equation, and constructing a background noise model. The intracranial EEG signals to be processed are then subjected to high-pass filtering. A short-time Fourier transform (STFT) and window-based frame-by-frame processing strategy are used to subtract the spectrum of the signal from the noise. By adjusting the parameters of the spectral subtraction, noise removal and preservation of neuronal signal features are achieved.

This application relates to a method, apparatus, computer device, and computer-readable storage medium for generating fiber Raman spectroscopy preprocessing models. The method includes: determining the true noise spectrum and random noise of the target object; generating a clean spectrum corresponding to the true noise spectrum based on a spectral synthesis method; generating fluorescence background data corresponding to the true noise spectrum based on a fluorescence background synthesis strategy; training a model using the true noise spectrum, clean spectrum, and fluorescence background data to obtain a trained background removal model; and training a multi-channel model based on random noise and clean spectrum to obtain a trained noise removal model. By employing this method, a reliable model processing foundation can be provided for background separation processing of Raman spectral signals and for collaborative denoising in both the spectral and frequency domains, improving the generation efficiency and quality of training datasets and achieving efficient and high-quality spectral processing in complex environments.

This application relates to the field of remote sensing image processing technology, and in particular to a method, apparatus, device, and medium for stripe noise removal from remote sensing images. The method includes: decomposing the remote sensing image into a low-frequency first frequency sub-band and a high-frequency second frequency sub-band, and extracting first image features and second image features respectively; inputting the first image features into a first processing network to extract multi-scale features and enhancing the stripe region through an attention mechanism to obtain a first feature map; inputting the second image features into a second processing network, processing the stripe noise through sparse convolution and striped window attention, and reconstructing it through inverse wavelet transform to obtain a second feature map; finally, fusing the two to obtain a remote sensing image with stripe noise removed. This solves the problems of related technologies that rely on manual parameter adjustment or modeling for specific noise, cannot preserve details, and cannot effectively remove and suppress unwanted noise.

This invention belongs to the field of secondary equipment testing and maintenance technology in power distribution networks. Specifically, it relates to a portable automatic testing method, system, and device for protection circuits adapted to FTUs, DTUs, and sectionalizing switch terminals. Relying on handheld equipment, it is compatible with dual-condition testing and completes fully automatic testing through five steps: preliminary screening of appearance and insulation, coarse screening of circuit continuity and impedance, fine screening of electrical steady-state characteristics, fault condition logic verification, and risk rating and archiving. The fine screening stage employs differential scanning, multi-parameter acquisition, noise removal, and fingerprint database comparison to achieve pin-level fault location. Combined with fault simulation and risk rating models, it completes circuit reliability verification. This invention features an integrated hardware and software design, effectively solving the pain points of traditional testing methods. It offers precise positioning, portability, and interference resistance, is suitable for on-site power distribution network operations, and has engineering promotion value.

This application provides an intelligent noise removal method and apparatus based on multi-feature deep fusion, relating to the field of petroleum geophysical exploration data processing technology. The method includes: designing an observation system according to a pre-defined geological task; dividing seismic gather data into N regions and selecting low signal-to-noise ratio (SNR) shots; identifying data above the first arrival time window as the first type of noise data; selecting labeled shots and standardizing and quality-evaluating the labeled shot data; adding noise data from a noise database to the labeled shots according to a set weight ratio, forming noisy shot gather data through data fusion technology, adding gain, and standardizing; constructing a deep neural network model; generating training samples based on the labeled shot data through data augmentation and sample partitioning techniques; and removing noise through feature analysis and learning of the input data using the model to obtain high-quality data. The modular process and flexible parameter configuration of this application facilitate integration with existing processing systems, demonstrating strong engineering practicality and promotional value.

This invention discloses an automatic update method for engineering GIS based on multi-source data fusion, comprising: acquiring multi-source data, performing coordinate unification and time alignment, and performing noise removal and format standardization processing; constructing a historical state mirror, differentiating it with the current multi-source data, and forming candidate change objects and change types; constructing a construction state evolution chain, inverting theoretically existing geometric connection states, and screening candidate update objects; constructing an evidence spatiotemporal superposition, forming an evidence band structure, and determining geometric attribute topology candidate update actions; generating reversible topology patches, constructing a patch sandbox, and performing consistency verification and rollback recoverability verification; submitting the patch to complete the GIS update, generating version and rollback records, and blocking the output of audit results if the update fails. This invention achieves accurate, secure, and automatic updates of engineering GIS data through construction time-series constraint inversion, multi-source evidence spatiotemporal superposition, and reversible topology patch sandbox verification.

Disclosed is a noise removal device capable of coping with high currents while having a pair of current-carrying members that has a simpler shape and improved assemblability and having a smaller size as a whole.　A noise removal device 10 comprises: an annular magnetic body 14 having an inner hole 16; and a pair of current-carrying members 12, 12 extending through the inner hole 16 of the magnetic body 14. The pair of current-carrying members 12, 12 are composed of a formable metal wire material and extend through the inner hole 16. In the inner hole 16, the pair of current-carrying members 12, 12 are arranged next to each other leaving a gap therebetween. Connection parts 18, 20 to which mating members 17, 19 can be assembled are provided at both ends of each of the current-carrying members 12, 12.

This invention discloses a method and system for detecting the cross-sectional contour of bridge components based on point cloud data. The method includes: acquiring three-dimensional point cloud data of the bridge component; extracting local point clouds of feature parts that meet preset conditions; determining and standardizing the component's axial direction through feature analysis; constructing an end face plane perpendicular to the axis; and projecting the three-dimensional point cloud to obtain a two-dimensional projection point set. A density evaluation standard based on the spatial relationship between points and their nearest neighbors is established; spatial indexing is used to optimize query efficiency; an adaptive filtering threshold is determined through statistical analysis; and a high-density contour point set is formed after noise removal. An initial fitted point set is selected, and auxiliary control points are set to form a complete control point sequence; a fitted curve is constructed, and outliers are removed; the optimal fitted contour is iteratively selected. A local coordinate system is constructed to complete coordinate transformation; actual control points are extracted; deviation indices are calculated by comparing with design control points; and irregular contour detection is completed. This method ensures the quality and structural safety of bridge engineering.

The application provides a tea garden risk prediction method and system based on multi-modal data, comprising: based on risk correlation constraints, high-dimensional survival analysis and contribution degree filtering and noise removal are performed on a tea garden multi-modal data set, and space-time feature parallel extraction is performed, to obtain a multi-modal space-time feature set; based on a dynamic causal discovery algorithm, loop-free causal constraints are performed on the multi-modal space-time feature set, to obtain a modal causal graph; a time delay response kernel matrix is extracted from a lag causal matrix of the modal causal graph, the time delay response kernel matrix is taken as a prior constraint, cross-modal feature fusion is performed on the multi-modal space-time feature set based on a causal attention mechanism, to obtain a fused multi-modal feature; based on a hybrid expert architecture, multi-task risk analysis is performed on the fused multi-modal feature, to obtain a comprehensive risk vector; contribution degree attribution is performed on the comprehensive risk vector, to obtain a contribution heat map, cross verification is performed on the comprehensive risk vector in combination with the modal causal graph, and a tea garden risk report is generated.

To provide a building cost estimation system and method that can accurately recognize building elements and significantly reduce the effort required for calculating the necessary building materials. [Solution] A building cost estimation system 100 for estimating the amount of building materials needed from building drawing data D, comprising: dimension acquisition means 1 for obtaining dimension data D1 included in the drawing data D; element recognition means 2 for recognizing building elements E to be estimated from the drawing data D; noise removal means 3 for removing noise N within the surrounding region A1 surrounded by the building elements E recognized by the element recognition means 2; and cost estimation means 4 for estimating the amount of building materials needed from the noise removal region A2 obtained by the noise removal means 3 and the dimension data D1.