81 results about "Data Noise" patented technology

This invention proposes a method for observing ocean waves based on a binocular camera, belonging to the field of image processing technology. The method includes: S1: The binocular camera captures ocean wave images, generating ocean wave point cloud data at the current time t; S2: The ocean wave point cloud data in S1 is converted to ocean wave point cloud data in a geodetic coordinate system; S3: The ocean wave data in S2 undergoes quality screening and optimization, including: selecting the region of interest, quality screening, converting noisy data points to null values, null value filling, and Gaussian filtering; the quality screening classifies the ocean wave data into three levels: excellent, good, and poor; S4: Based on the excellent and good quality ocean wave point cloud data, the wave height, wavelength, and period at that time are calculated; S5: S1-S4 are repeated to obtain multiple frames of ocean wave point cloud data at different times, and the effective wave height, wavelength, period, and wave spectrum are calculated. This method can fill in null values, making the overall data more reasonable and the obtained elevation data more accurate.

The application discloses an online semantic momentum stabilization system and method using a Welford algorithm and an optimistic concurrent control. In view of the semantic centroid calculation deviation and timing conflict problems caused by data noise, distribution drift and distributed out-of-order writing in the process of continuous incremental input of a large-scale vector database, the application combines a Welford online iterative algorithm to realize high-precision incremental updating of the semantic centroid mean and variance under constant space complexity. Meanwhile, a distributed optimistic concurrent control mechanism is used to implement version revision number checking on semantic segments and block obsolete data coverage caused by cross-node out-of-order arrival. The application guarantees the numerical stability and timing consistency of semantic feature expression in a dynamic growing data environment.

The application provides a model training method and a model training device, and relates to the technical field of computers. The method comprises the following steps: obtaining target data; determining a sampling time in a training iteration, and performing disturbance sampling on the target data based on the sampling time to obtain noisy data; inputting the noisy data and the sampling time into a backbone network of an initial large language model to perform deep feature interaction and fusion, obtaining a hidden vector sequence output by the backbone network, and mapping the hidden vector sequence back to discrete codebook indexes of each modality through a decoding head to obtain predicted data; calculating a loss based on the predicted data and the target data to obtain a target loss; updating model parameters of the initial large language model based on the target loss, and obtaining a large language model that has completed training under the condition that a training termination condition is met. The application solves the problem that the prior art in the related art cannot simultaneously consider multi-modal understanding, generation and retrieval capabilities under a unified architecture.

The application discloses a kind of SPH steady flow processing method and related equipment, method includes the input entrance pressure data is converted into entrance speed data;Entrance speed data is based on setting virtual particle;And the data information of fluid particle is updated by the interaction between virtual particle and the fluid particle to be processed, and fluid particle data is judged based on setting parameter threshold, and the particle field information of output is obtained.The application embodiment can be converted into entrance speed data by the entrance pressure data, and virtual particle is set to simulate fluid particle, reduce the speed shock and data noise caused by particle simulation calculation based on entrance pressure, reduce the accumulation of entrance particle simultaneously, improve the stability of entrance boundary, so as to improve the convergence speed and processing efficiency of steady flow simulation.The application can be widely applied in computer simulation and data processing technical field.

This invention discloses a visual reconstruction method and system for remote sensing interpretation based on a generative diffusion model. The method includes: acquiring high-resolution and low-resolution remote sensing image data; adding different levels of Gaussian noise to the training data using a forward stochastic differential equation until pure Gaussian noise data is obtained; training a noise conditional scoring network to predict the scores corresponding to these noisy data; adding noise to the low-resolution image using a forward stochastic differential equation to finally obtain pure Gaussian noise; using a trained neural network to guide the random noise to gradually converge and generate a super-resolution remote sensing image; rapidly identifying land cover types on the generated remote sensing image; and delineating land cover patches on the original remote sensing image and assigning patch information based on the identified land cover categories. This invention achieves a super-resolution effect from low resolution without changing the land cover types and patch boundaries, thereby reducing interpretation costs and improving interpretation efficiency.

This invention discloses a long-term prediction method for deep-sea creep based on in-situ pore pressure observation using Bayesian-LSTM, relating to the fields of sediment dynamics and marine engineering. The method includes: deploying pore pressure sensors to collect pore water pressure data in real time, performing standardization processing, and calculating the pore pressure change rate; constructing a creep rate calculation model based on the effective stress principle and power law; building a time-series feature dataset using sliding window technology, constructing and training a Bayesian-LSTM network model, and introducing a Monte Carlo Dropout layer to assess prediction uncertainty; outputting a high-precision creep rate using a multiple sampling averaging strategy; calculating the cumulative creep distance through numerical integration, and constructing confidence intervals to achieve medium- and long-term trend prediction and risk analysis. This invention integrates physical mechanisms and data-driven approaches, effectively handling data noise and prediction uncertainty in the complex environment of the deep sea, significantly improving the accuracy and reliability of long-term creep prediction, and providing a scientific basis for deep-sea engineering safety assessment.

The application provides a road slope measurement method and system based on mobile crowd sensing, comprising the following steps: S1: dividing a to-be-predicted area and a predicted area, assigning a data collection task, and collecting data to the cloud; S2: after the cloud multi-modal sensing data is time-space aligned, performing frame-by-frame correlation matrix operation, fusing the coordinate and the attitude vector of the mobile device, and dividing the space position into a training set and a test set after removing data noise; S3: extracting time-domain features and frequency-domain features from the training set and the test set data, and calculating individual independent features; S4: training and testing the model by using the individual independent features, and further performing data aggregation and result optimization on the preliminary prediction result. The application is beneficial to efficiently and low-costly realizing large-scale road slope sensing, beneficial to establishing a city three-dimensional map, further enriching the content of the current digital map, and shortening the data updating cycle.

This invention discloses a method for full lifecycle health monitoring of marine platform structures based on digital twins, comprising: constructing a digital twin of the marine platform including geometric, physical, and behavioral models; collecting structural response and environmental load data during the design, construction, operation, and decommissioning stages; eliminating data noise through Kalman filtering and removing outliers using the 3σ criterion; dynamically updating the twin parameters using a parameter iteration algorithm to achieve dynamic mapping between the physical platform and the digital twin; calculating a health index based on a multi-index fusion algorithm to classify health status levels; implementing graded early warning and stage-specific adaptive decisions according to the levels; predicting structural residual value and monitoring dismantling stress during the decommissioning stage; and employing blockchain encryption and role-based access control to ensure data security. This invention achieves seamless full lifecycle monitoring, improves monitoring accuracy and decision-making scientific rigor, adapts to multiple scenarios, and effectively ensures the safety and economic benefits of marine platforms.

The present application provides a kind of geologic multi-source constraint adaptive full waveform inversion method and system, constructs multiple complementary constraint norms, organically fuses multiple modal prior information, forms unified multi-source constraint framework, compared with traditional single type prior constraint, the present application can more comprehensively utilize available prior information, guide inversion to the direction that both conforms to geophysical data and geological understanding converges;While introducing adaptive regularization parameter strategy based on Bayes theory, realize the adaptive update of weight factor, avoid the subjectivity and randomness caused by the dependence of regularization parameter on experience selection in traditional method, make the inversion result more stable, and do not need tedious manual parameter adjustment, can dynamically adjust the constraint strength according to the data noise level, enhance the guiding role of prior constraint in low signal-to-noise ratio, more rely on observation data in high signal-to-noise ratio;At the same time, through the combination of model compression and forward simulation calculation, the calculation efficiency is greatly improved.

The application provides a seismic data noise attenuation method and device, the method comprising: obtaining seismic data to be denoised; inputting the seismic data into a pre-constructed artificial neural network to output noise intensity data; the artificial neural network is a seismic data noise intensity prediction model obtained by training seismic data samples based on a machine learning algorithm; limiting noisy seismic data based on Casado filtering setting space parameters, determining the size of the Hankel matrix in Casado filtering; obtaining noise intensity data limited by Casado filtering setting space parameters; performing Casado filtering on the noisy seismic data limited by the setting space parameters with the number of ranks to complete random noise attenuation of the seismic data; and performing iterative cycles with the setting space parameters to complete random noise attenuation of all seismic data. The application converts the noise intensity of the seismic data into the number of ranks, so that the rank of the Casado filtering changes with the signal-to-noise ratio of the seismic data, and the random noise attenuation effect is good.

The application relates to the technical field of intelligent management of transformer substations, in particular to a modular prefabricated cabin transformer substation intelligent comprehensive management system with multi-source data integration and collaborative management functions.The system comprises a multi-source data acquisition unit, an edge intelligent processing unit is used for locally preprocessing, feature extraction and abnormal early warning of collected transformer substation multi-source heterogeneous data, and through a lightweight AI algorithm and a mixed communication protocol carried by an edge computing terminal module, data noise reduction, abnormal identification and equipment health degree evaluation are realized; and a data integration and collaboration unit.Through an adaptive sampling strategy and a multi-modal feature fusion mechanism of the multi-source data acquisition unit, multidimensional data such as power parameters, dynamic environment, fire safety and security are integrated into a monitoring system, feature layer correlation analysis is realized by relying on Jousselme distance and Dempster synthesis rules, the evaluation limitation of traditional schemes with single equipment and single-dimensional data is broken through, and a more comprehensive state basis is provided for equipment health degree judgment.

This invention relates to the field of oil and gas exploration and development technology, and discloses a method and apparatus for well logging data completion based on a generative deep learning model. The method progressively adds Gaussian noise to missing well logging data to be restored, obtaining noisy well logging data. The data to be restored includes known well logging data and missing data, while the noisy well logging data includes known well logging data and noisy data. Based on a created observation mask, zeros are filled into the missing well logging data to be restored and the known well logging data of the noisy well logging data, respectively, to obtain first mask data and second mask data. The first mask data and second mask data are concatenated to construct a hybrid tensor. Based on the complete logging data corresponding to the data to be restored, the hybrid tensor, and the trained generative deep learning model, the noisy well logging data is denoised to obtain the completed well logging data. This invention can effectively improve the accuracy of well logging data completion.

The application provides an underground pipeline construction damage single classification early warning method and system, which comprises the following steps: collecting and saving third-party construction audio data and noise data to a database; processing the third-party construction audio data and noise data to obtain abnormal value processing data; performing Fourier transform and inverse Fourier transform to complete data noise reduction and obtain noise reduction data; performing feature extraction to obtain time domain features and frequency domain features, analyze the noise reduction data, and obtain preset dimension features; performing feature standardization on the preset dimension features to obtain standard dimension features; performing dimension reduction processing and fusion compression to obtain fusion compression features; and taking the fusion compression features as training data to train an applicable single classification early warning model. The application solves the technical problems of low early warning accuracy of third-party construction damage events in complex environments with sound source and vibration source noise interference and dependence of training on non-target type samples.

The application discloses a panoramic video view angle prediction method based on a neural network, belongs to the technical field of image processing, and is used for interactive video processing, comprising the following steps: acquiring a panoramic video of an existing public data set, then constructing a panoramic video view angle prediction model based on structured attention to perform training, and predicting a saliency prediction view angle of the panoramic video based on the panoramic video view angle prediction model based on structured attention which has completed the training. The panoramic video view angle prediction model based on structured attention is constructed, original sparse and noisy data is converted into more robust supervision signals, the deviation of single local fixation is overcome, comprehensive modeling of scene saliency and accurate prediction of user view angle are realized, and the accuracy and robustness of view angle prediction in virtual reality application are improved.

A method and device for generating a training dataset of a bio-signal denoising artificial intelligence (AI) model are provided. According to an embodiment, the method includes receiving first bio-signal data measured in a non-noise-suppressed environment and second bio-signal data measured in a noise-suppressed environment, performing component analysis of the first bio-signal data, and determining noise component data by separating target component data from the first bio-signal data, generating third bio-signal data by combining the noise component data with the second bio-signal data, and determining the second bio-signal data as ground truth data of the training dataset and determining the third bio-signal data as noisy data of the training dataset to determine the training dataset.

This invention discloses an online education group question-and-answer matching method based on user style and time awareness, relating to the field of question-and-answer matching using deep learning natural language processing technology. The method involves constructing a BigData dataset; dividing the BigData dataset into training, validation, and test sets; building user style-aware and time-aware question-and-answer matching models; training the models using the training set and obtaining performance metrics using the validation set to find the optimal hyperparameters; and inputting the test set into the final user style-aware and time-aware question-and-answer matching model to obtain the matching results. This invention enhances question extraction by recognizing user style through user style awareness, reducing the impact of noise caused by severe imbalances between the number of questions and other types of dialogue. It also reduces the noise caused by a large number of potential answers to a single question through time awareness. Compared with other traditional question-and-answer matching models, this method improves the model's question-and-answer matching performance and reduces the impact of data noise.

This invention discloses a visualization and interactive device for geophysical data evaluation, relating to the field of data processing technology. It includes an intent input parsing module for acquiring and parsing user input information to obtain preliminary geological intent features; an example feature extraction module for generating a high-dimensional feature vector representing the user's geological intent as the geological intent feature vector; multi-dimensional features including the internal physical property statistical features, external geometric morphology features, spatial context relationship features, and derived attribute features of the example area; a matching degree generation visualization module for calculating the similarity between the geological intent feature vector and each geophysical data unit within the target work area, generating a three-dimensional geological similarity volume; and an iterative optimization module for receiving user feedback based on the visualization results. This invention significantly improves the accuracy of target identification and effectively avoids the problems of missing key targets or interference from noisy data.

A system and method for prediction of failures and optimization, that can provide solution available for unsupervised learning models based on limited data that can predict different types of failure and pre-failure instances. The solution provides improvement upon previous methods of labelling by marking certain days data ahead of failure as belonging to failure data which will result in reduction of noisy data and improves good working condition data. The present invention helps with improved data quality due to labelling as the proposed method models complex distributions of feature vectors accurately and are better at finding deviations from normal data distribution which is used for detecting failures. The novel solution help to analyse and categorise the type of failures for PC Pumps currently deployed in CBM Fields for which failure days in advance can be predicted.

This application discloses a data denoising method and related equipment. The method utilizes artificial intelligence technology to denoise data. Any one of the target denoising operations performed on noisy data includes: generating distribution information corresponding to the target denoising operation based on first and second prediction information. The first prediction information indicates the predicted noise between the second noisy data and clean data, and the second prediction information indicates the square of the predicted noise between the second noisy data and clean data, or the square of the predicted distance between the first prediction information and the actual noise, where the actual noise includes the actual noise between the second noisy data and clean data; and sampling the denoised data from the distribution space pointed to by the distribution information. Since the distribution information corresponding to the denoising operation is not directly learned, the number of denoising operations performed on the noisy data is not constrained by the training phase, improving the flexibility of the inference phase.

The embodiment of the invention provides a content generation method and related equipment, and the method comprises the steps: indicating the execution of a calling reasoning model through business indication information related to a content generation business, when de-noising processing is carried out on corresponding input content coding characteristics of the noisy data content under a time step tj in the T time steps under the constraint of the first data content, obtaining a cache type for cache multiplexing according to content analysis parameters indicated by a cache multiplexing strategy related to the time step tj; and if the cache type is an inter-step cache type, multiplexing a predicted noise feature corresponding to a time step ti having an inter-step multiplexing relationship with the time step tj, performing denoising processing on an input content coding feature corresponding to the time step tj, and performing content generation based on an output content coding feature corresponding to the time step tj obtained by the denoising processing, the second data content is obtained. Therefore, the model reasoning speed can be effectively improved, and waste of computing resources is avoided.

The application discloses a kind of soft bag welding sealing detection methods based on deep learning, comprising: obtaining the first point cloud data set after filtering;Determine the core load area of weld main body and corresponding main shaft direction data;Obtain the preliminary spacing distribution information between adjacent welds;Output high-risk area positioning data;According to high-risk area positioning data, analyze the connection state of weld edge transition area, if the continuity of edge transition area is lower than the preset standard, it is determined that the sealing weak link, generate the distribution atlas of weak link;For weak link distribution atlas and high-risk area positioning data, the distribution state of weld dense area is simulated using spatial geometry optimization algorithm, to determine whether there is the possibility of local thermal degradation, output the final weld quality evaluation report.The application can effectively suppress background interference under the condition that weld distribution is complex and point cloud data noise is large, and accurately position the core load area and main shaft direction of weld.

Methods, apparatus, devices, and media for updating a decoder model are provided. In one method, a reference image is acquired, having first reference features determined by an encoder model. Based on noisy data and the reference image, second reference features of the reference image are determined, the second reference features being different from the first reference features. A predicted reference image associated with the reference image is determined by a decoder model corresponding to the encoder model, based on the second reference features. The decoder model is updated based on the difference between the reference image and the predicted reference image. Using some implementations of this disclosure, adding noise information to the second reference features can reduce the quality of the second reference features. In this way, the decoder model can be updated in a direction that enables the decoder model to generate higher-quality images from lower-quality features.

The application discloses a kind of self-adaptive balance estimation and uncertainty decomposition method of traffic state, it is related to traffic management technical field, mainly includes the following steps: first, construct a double-output neural network that can simultaneously output traffic state mean and variance, and design mixed loss function that fuses data and physical constraints.In training, the variance of each loss gradient is calculated to adaptively adjust its weight, to balance the optimization process.Further, the parameter update is modeled as an underdamped Langevin dynamics process, noise is injected for posterior sampling, and multiple sets of model parameters are obtained.Finally, these parameters are used for multiple inferences, and by aggregating and statistically analyzing the prediction results, the accidental uncertainty from data noise and the cognitive uncertainty from model cognitive deficiency are separated and quantified.The application realizes high-precision probability estimation of traffic state under sparse observation data, providing a quantitative basis for traffic monitoring optimization and risk assessment.

The application discloses a kind of underground cavern group complex construction ventilation environment space-time prediction method based on deep learning, including data acquisition, data cleaning, data noise reduction and normalization processing: construct and include sequence perception global Token generation module, graph structure learning module, graph aggregation module, time coding module and trend perception attention module's space-time prediction model: normalized data is divided into training set, verification set and test set, constructs joint loss function, utilizes optimization algorithm to train the space-time prediction model, and adopts swarm intelligence optimization algorithm to automatically optimize hyperparameter;Real-time monitoring data is input after pre-processing into trained space-time prediction model, and the wind speed, dust concentration prediction value of future time step is output, and the operating frequency of fan of ventilation system is dynamically adjusted according to prediction value.

This invention discloses a method for identifying stony glaciers based on machine learning. The method comprises the following steps: S1: Interpreting different geomorphic features on stony glacier optical images to obtain identification results; S2: Enhancing the reliability of different types of stony glaciers using the InSAR method to obtain vector data of residual and complete stony glaciers; S3: Slicing images based on the vector data, masking non-stony glacier areas to obtain images with only stony glacier features, and cleaning noisy data; S4: Importing the InSAR-enhanced dataset into RF, SVM, LR, DT, KNN, and ResNet models for training, obtaining the accuracy of different machine learning models in identifying stony glaciers, and obtaining the optimal machine learning model. The method proposed in this invention overcomes the problems of low efficiency and high subjectivity in existing stony glacier state classification, thus achieving automatic classification of complete and residual states of stony glaciers. Furthermore, this method can compensate for the lack of complete and residual state attributes in many existing stony glacier catalogs.

This invention provides a data processing method, apparatus, device, computer program product, and computer-readable storage medium. The method considers that the preference data used in DPO training may have noisy labels that negatively impact training performance. It proposes a noise-aware metric to indicate the probability that the preference label of a pair of preference data is a noisy label, and incorporates this metric into the DPO training objective function. This incorporates the quality of the preference data into the DPO training process, thereby identifying and mitigating the impact of noisy preference data on DPO training performance. This method effectively identifies noisy data in the preference data used in DPO training and effectively reduces the impact of noisy data on training performance by introducing a noise-aware metric into the DPO objective function, thus improving DPO training performance. Furthermore, this method is widely applicable to various large models, including LLM and DM, to improve the DPO training performance of these large models.

The application relates to the field of quantum precision measurement, and discloses a fluorescence data noise reduction demodulation method and a related device, which are applied to a process of sensing based on a diamond NV color center and using a photodetection magnetic resonance method. The fluorescence data noise reduction demodulation method provided by the scheme can move the center line of fluorescence digital signal data under different carrier frequencies to the vicinity of a zero axis, effectively reduces data offset, ensures the accuracy of quantum precision measurement, and the data used for calculating the zero axis offset value and the data used for filtering demodulation are fluorescence digital signal data under the same carrier frequency, so that the calculated zero axis offset value is very accurate and is not easily affected by external environment.

The application discloses a data integration analysis management platform, relates to the technical field of medical data analysis and processing, and has the technical scheme as follows: a multi-source data acquisition module acquires basic medical data and epidemic detection data; a data cleaning and fusion module acquires the basic medical data and the epidemic detection data and outputs standardized medical data and standardized epidemic data; a data standardization processing module acquires the standardized medical data and generates unified format medical data and a historical medicine consumption data set; and an intelligent decision analysis module outputs a medicine demand prediction index and a stock early warning index based on the unified format medical data and the historical medicine consumption data set. The data cleaning and fusion module can greatly reduce data noise and significantly improve data quality; and the intelligent decision analysis module can predict demand fluctuation in advance, actively prompt replenishment or clearance of accumulated goods, effectively reduce the medicine shortage rate and the expired and scrapped rate according to actual seasonal demand.

The application is a concrete compaction degree quick identification method and a self-adaptive intelligent identification device, which comprises the following steps: synchronously collecting time sequence signals of two acceleration sensors respectively installed on the side of a vibrating device and the side of concrete materials; pre-processing the collected time sequence signals through data noise reduction and filtering; extracting time domain and frequency domain features from the pre-processed signals to construct a multi-dimensional feature vector; inputting the feature vector into an interpretable XGBoost model optimized through training to obtain a concrete compaction degree prediction result; using a SHAP interpreter to perform interpretable analysis on the prediction result, calculating the contribution of each feature and outputting a confidence score; and generating a self-adaptive control instruction according to the prediction result, the feature contribution and the confidence score to prompt the vibrating state. The application solves the problem that the traditional vibrating compaction degree determination relies on artificial experience, is subjective and inefficient, and realizes accurate, quick, objective and interpretable intelligent identification of the vibrating compaction degree.