63 results about "Resampling" patented technology

The invention belongs to the field of power distribution automation, and relates to a power grid equipment frequency adaptive resampling method based on a dynamic scale factor, and the method comprises the steps: carrying out the point compensation through employing a linear interpolation method when a power grid equipment detects that the number of continuous lost points is smaller than or equal to 3; selecting a voltage signal channel or a current signal channel to carry out zero crossing point detection and real-time frequency calculation; when the real-time frequency obtained through calculation deviates from the nominal frequency, the power grid equipment introduces a dynamic scale factor for resampling, sampling points are increased when the real-time frequency is higher than the nominal frequency, and sampling points are reduced when the real-time frequency is lower than the nominal frequency; writing data obtained by resampling into a calculation annular cache region of the power grid equipment; and performing FFT calculation on the data in the calculation annular cache region to obtain power grid parameters. The sampling interval of the data acquisition unit is dynamically adjusted by increasing or reducing the sampling points, so that the sampling time sequence and the actual signal period are synchronized, the sampling frequency and the real-time frequency are adaptively matched, and the sampling distortion problem under the power grid frequency fluctuation is solved.

The invention discloses a small sample modeling stability evaluation method and system based on Bootstrap resampling, and particularly relates to the technical field of computers and data intellectualization, the method comprises the following steps: completing data preprocessing and stable stage identification under a unified time base, and forming a segment set; an average block length is used as a decision quantity, an SBB is optimized to construct a sample space, and an optimal block length is determined in combination with variance consistency and nominal coverage rate consistency criteria; carrying out re-sampling training around short / medium / long scales, and collecting layered indexes such as prediction, parameters and features; stability calculation and empirical coverage rate calibration are completed based on intra-scale statistics and inter-scale weighted mixing, and a pseudo-stationary diagnosis score is output; and finally, engineering judgment and backspacing optimization are carried out according to the coverage rate, the correlation maintenance and the risk threshold. The system records random seeds, block metadata and model version generation evidence pointers, has the characteristics of traceability and reverifiability, and is suitable for scenes of production lines, network traffic, finance and the like.

The invention relates to the technical field of numerical control machining measurement and correction, and discloses a machining surface correction method for a numerical control milling center. The method comprises the steps of establishing an original point cloud of a processing surface and extracting a feature structure; analyzing each feature structure to form a structured description list; inputting the list into a geometric growth model, and generating a virtual feature structure set according to rule iterative evolution; extracting and rasterizing the contour and the height field, carrying out registration fusion with a reference plane equation, and carrying out variation calculation to obtain a smooth middle geometric surface; performing adaptive resampling on the intermediate surface to generate an intermediate point cloud; and finally, according to the spatial frequency distribution of a topological residual field formed by the difference between the original point cloud and the intermediate point cloud, adaptively determining a weight, and carrying out weighted mixing on the original point cloud and the intermediate point cloud to generate an optimized surface point cloud. According to the method, intelligent evolution of the machined surface features and frequency domain self-adaptive data fusion are achieved, and the correction machining precision and the surface forming quality are improved.

The invention discloses a physical field data restoration method and system based on diffusion and iterative resampling, and the method comprises the steps: initialization: filling a missing region with random noise in to-be-restored physical field data, and obtaining an initial noisy field; forward diffusion: gradually adding noise into the complete data until the complete data becomes complete random noise data; noise model pre-training: training random noise added in each step in forward diffusion; inverse diffusion denoising: gradually restoring the image from the initial random noise through the noise predicted by the model and an iterative formula; and iterative resampling correction: in the reverse diffusion process, iterative circulation is carried out in a de-noising-noise adding-re-de-noising mode, so that the model can be effectively forced to spread information of a known area to a missing area, and the physical consistency and smooth transition of a repair result and a known data boundary are ensured. Any prior information of the missing area does not need to be preset, the repairing precision is high, and the physical consistency is good.

The invention discloses an alluvial island instantaneous waterline segmentation method fusing MobileViT and dynamic resampling. The method comprises the steps that a remote sensing image, shot by an unmanned aerial vehicle, of an alluvial island area is acquired and preprocessed; and inputting the preprocessed remote sensing image into the trained semantic segmentation model for processing, and accurately and efficiently obtaining a segmentation result of the instantaneous waterline in the remote sensing image. The semantic segmentation model is a lightweight ALISEg model constructed based on a DeepLabv3 + framework, a MobileViT structure is introduced into an encoder part, local modeling advantages and global perception capability are integrated, so that local detail recognition capability and global context perception capability are greatly enhanced, a DSC-ASPP module is designed, depth separable cavity convolution and a CBAM attention mechanism are combined, and the semantic segmentation model has the advantages of being high in robustness, high in robustness and high in robustness. And multi-scale spatial features can be fully captured. And meanwhile, a DySample module and an H-RAMi module are introduced into a decoder part, so that the up-sampling precision and the multi-scale feature fusion effect are improved, and the details of the water edge line are better reduced.

The invention discloses a sensitivity-based network intrusion detection resampling method, system and device and a medium, and relates to the technical field of data detection, and the method comprises the steps: obtaining network data containing normal traffic and attack traffic; prior probabilities and class condition probabilities of the two classes of data are calculated respectively, then posterior probabilities are obtained, and the sensitivity weight of each sample is calculated; carrying out putting-back undersampling on a normal flow sample according to the sensitivity weight; carrying out replacement oversampling on the attack traffic sample according to the sensitivity weight; a sampling process is repeated to generate a plurality of balance training subsets, and a base classifier is trained based on each subset; and calculating voting weights based on the performance evaluation indexes of the base classifiers on the verification set, and obtaining weighted voting results based on the voting weights to classify new data. Random undersampling neglects the importance of boundary samples to decision boundary learning, and sensitivity weighted sampling can guide the model to sample the boundary samples, so that important information is prevented from being lost.

Some embodiments are directed to a resource allocation analysis system implemented via a back-end application computer server. A resource data store may contain electronic records associated with a set of resource types, each electronic record including an electronic record identifier and resource parameter. The back-end application computer server may receive, from the resource data store, information about a set of resource types to be analyzed, including the associated resource parameters. The computer server may then execute a differential evolutionary algorithm to optimize the set of resource types based on at least one non-linear constraint and generate resource analysis results. The back-end application computer server may, according to some embodiments, perform a resampling process that uses non-parameterized historical data, regression on at least one resource type, and moment matching.

The application discloses a kind of power electronic system fault diagnosis methods combined with resampling and integrated learning, belong to power electronic equipment fault diagnosis technical field, the method includes real-time sampling electric power electronic system in the current data of one-half fundamental period, current data is normalized, and normalized data is obtained;According to the normalized data, based on fast fourier transform algorithm, the frequency domain characteristics of normalized data are obtained;According to the frequency domain characteristics, the feature vector of normalized data is obtained by feature extraction selector;According to the feature vector of normalized data, the fault class label is obtained using integrated classification model, and the electric power electronic system fault diagnosis is completed.The application solves the technical problems that the original data sample is unbalanced in the existing fault diagnosis method, which leads to inaccurate diagnosis and even wrong judgment of the existing machine learning model, effectively realizes the diagnosis of various fault types of sensors and power devices of electric power electronic system.

The invention discloses an injection molding quality soft measurement method for staged resampling and quality enhancement, which belongs to the technical field of injection molding and comprises the following steps: acquiring a process data set and a quality data set; normalizing the process data set and the quality data set to obtain a normalized process data set and a normalized quality data set; performing clustering, staged resampling and merging on the normalized process data set to obtain a low-resolution process data set; and inputting the low-resolution process data set and the normalized quality data set into a quality enhancement prediction network to obtain a prediction result of the injection molding quality. The accuracy of injection molding quality soft measurement is improved.

The chain system fixed-point resampling method belongs to the technical field of rotating machinery signal processing, and aims to solve the problems that the time domain signal regularity of a single chain link is poor, the dynamics characteristics of the whole system are difficult to directly reflect, and the frequency domain feature extraction cannot be performed. The method comprises the following steps: extracting original data of discrete motion units from multi-body dynamics simulation results; at the preset data monitoring point position of the system, the nearest discrete motion unit is searched as a monitoring unit in real time by calculation; according to the data type, one of a direct method, a synthetic method and an average method is adopted to process the original data of the monitoring unit, and feature data representing the dynamics state of the fixed position are generated; and finally, the feature data are written into a file in time sequence. The time sequence data of the fixed position are collected through the fixed-point resampling method, and the problems that the data is strong in contingency, poor in regularity, and difficult to perform in-depth frequency domain and statistical analysis due to tracking a single motion unit are solved.

The invention discloses a fixed-point resampling method for a chain system, belongs to the technical field of signal processing of rotating machinery, and aims to solve the problems that the regularity of a time domain signal of a single chain link is poor, the dynamic characteristics of the whole system are difficult to directly reflect, and frequency domain feature extraction cannot be carried out. The method comprises the following steps: extracting original data of a discrete motion unit from a multi-body dynamics simulation result; searching the nearest discrete motion unit as a monitoring unit in real time by calculating the distance at a preset data monitoring point position of the system; according to the data type, processing the original data of the monitoring unit by adopting one of a direct method, a synthesis method and an average method, and generating characteristic data representing the dynamic state of the fixed position; and finally, writing the feature data into a file according to a time sequence. According to the method, time sequence data of a fixed position is collected through a fixed-point resampling method, and the problems that due to tracking of a single motion unit, data contingency is high, regularity is poor, and frequency domain deepening and statistical analysis are difficult to carry out are solved.

This invention discloses a deep learning-based engine condition monitoring method, comprising the following steps: collecting multi-source sensor data and corresponding speed data during engine operation; preprocessing the original multi-source data to obtain preprocessed multi-source data; performing condition-locked resampling to obtain a set of window sequences; constructing a Krylov subspace and performing orthogonalization to obtain an orthogonal basis for the subspace; performing Krylov subspace change point and state transition detection to obtain the current monitoring state; generating a subspace fingerprint and selecting a deep learning monitoring branch based on the subspace fingerprint routing structure to obtain a health index and anomaly score; writing the health index and anomaly score into a candidate alarm queue, switching the current monitoring state, and outputting alarm results based on the candidate alarm queue. This invention improves the accuracy of engine condition monitoring by combining condition-locked resampling with Krylov subspace change point detection.

Apparatuses, methods, and systems for determining winning arms of electronic testing. One method includes obtaining historical data values related to the A / B test of a user, storing the historical data values, determining a historical weight for the historical data values, receiving new data values from the plurality of computing devices collected based on recipient actions during execution of the A / B, constructing a Dirichlet distribution, inferring corresponding central tendencies of samplings of a metric distribution, wherein each central tendency of the corresponding central tendencies is determined by sampling the Dirichlet distribution, constructing an overall utility distribution for each arms of the A / B test by combining the central tendency of each sampling of the metric distribution with a corresponding sampling of a conversion probability distribution, determining a winning arm of the A / B testing by comparing the overall utility distribution of each arm with each other arm of the A / B test.

The embodiment of the invention provides a transfer prediction method and system based on resampling and three-dimensional attention convolution, and relates to the technical field of medical image artificial intelligence. According to the method, after PET image data is acquired, resampling is carried out on PET images in the PET image data to obtain balanced image data, and then image key features are extracted from the balanced image data through a three-dimensional residual convolutional neural network and based on a three-dimensional convolutional attention mechanism. And training a prediction model by using the image basic features and the image key features to output a transition probability by using the prediction model. According to the method, the distribution of the positive and negative samples can be balanced through resampling, and model deviation caused by height imbalance of the positive and negative samples faced by 3DPET image data is relieved. A three-dimensional attention convolutional network is adopted to deeply mine spatial features, three-dimensional spatial features of 3D PET are fully extracted, and a weighted fusion loss function is combined to optimize a model training process, so that the prediction precision of the lymph node metastasis probability is improved.

The invention discloses a minimum region method flatness error evaluation algorithm based on improved teaching and learning optimization, and belongs to the technical field of geometric quantity measurement. In order to solve the problems that a traditional minimum region method is slow in convergence and prone to falling into local optimum, a teaching and learning optimization algorithm is improved through a Sine chaotic mapping population, a self-adaptive learning factor and local resampling search, and the method is applied to minimum region evaluation of flatness errors. The method comprises the specific steps of point cloud data preprocessing, Sine chaos population initialization, teaching stage adaptive updating, local resampling, convergence judgment and result output. Experiments show that compared with traditional TLBO, particle swarm optimization and other algorithms, the algorithm is higher in convergence speed and evaluation precision, higher in robustness and suitable for flatness detection scenes in high-precision manufacturing.

The present application discloses a method for tracing the source of faults in the operation of power secondary equipment based on supervised learning. The method includes: establishing a data storage unit, storing fault types and constructing a fault propagation map, and using a relational database and data processing and integration tools to update the data in the data storage unit. After processing the stored data, the data set is divided to construct and verify a fault tracing model. By constructing a fault tracing credibility index and a fault propagation perception confidence interval, the accuracy of the fault tracing model and whether the data is unbalanced are judged. If the data is unbalanced, resampling and data enhancement are used for processing. The processed fault tracing model can effectively realize the tracing of the source of faults in the operation of power secondary equipment, improve the ability to handle faults, and provide guarantees for the stable operation of the power system.

The invention provides a multi-model multi-resolution self-adaptive image recognition and extraction method based on deep learning, and the method comprises the following steps: an unmanned plane collects an aviation picture, and generates a digital orthoimage through a picture splicing algorithm; judging whether natural language analysis needs to be performed or not according to a processing requirement input by a user; obtaining a target category to be recognized and extracted, and adaptively selecting an optimal deep learning algorithm; according to the overall contour pixel size of the target category, selecting a self-adaptive spatial resolution to carry out reprojection resampling processing; obtaining the recognized and extracted original contour; according to the method, a complex natural language can be analyzed, an unknown target category can be recognized and extracted, a high-precision specific category can also be matched, generalization and expandability are enhanced, and the method has the advantages of being high in robustness, high in robustness and the like. And optimal algorithm parameters can be adaptively selected, and the precision requirement of the result is ensured to the greatest extent.

The application discloses a small sample modeling stability evaluation method and system based on Bootstrap resampling, and particularly relates to the technical field of computer and data intelligence, and the method comprises the following steps: completing data preprocessing and stable stage identification under a unified time base, and forming a segmented set; taking the average block length as the decision quantity to optimize SBB to construct a sample space, and determining the optimal block length in combination with the variance consistency and nominal coverage consistency criteria; performing resampling training around three scales of short, medium and long, and collecting layered indexes such as prediction, parameters and features; completing stability calculation and empirical coverage calibration based on scale-in statistics and scale-weighted mixing, and outputting a pseudo-stationary diagnosis score; finally, engineering judgment and rollback optimization are performed according to the coverage, correlation retention and risk threshold. The system records random seeds, block metadata and model version generation evidence pointers, has traceable and retestable characteristics, and is suitable for scenes such as production lines, network traffic and finance.

The application discloses a kind of synthetic and real data's adaptive resampling method and device, electronic equipment, comprising: obtaining training dataset from multiple data sources;Uniformly pre-process multiple-source training data, and construct data source identification and sample basic feature representation;Based on basic feature representation, calculate the distribution deviation between different data sources and sample bias feature;According to distribution deviation and sample bias feature, the weight of each sample is calculated or resampling probability is calculated;Based on the weight of removing bias or resampling probability, adaptive resampling is executed to multiple-source training data, and the training sample set of removing bias is constructed;Training or updating is carried out to target model using the training sample set of removing bias, and resampling strategy is dynamically adjusted based on model training feedback, to realize multiple rounds of adaptive debiasing and resampling optimization.

The invention provides a three-dimensional medical image segmentation method without resampling, and relates to the field of computer vision, in particular to the three-dimensional medical image segmentation method without resampling. The three-dimensional medical image segmentation framework does not need to be resampled in training and reasoning stages, information of original medical images can be reserved to a greater extent, detail loss caused by resampling is avoided, and therefore segmentation precision is improved. Convolutional low-rank decomposition is introduced into the attention module, so that global attention calculation which originally needs to be subjected to high-dimensional matrix product can be approximated to low-rank matrix operation, and the calculation complexity is effectively reduced. Meanwhile, the corresponding self-adaptive parameterized European matrix is also compressed to a small scale, video memory occupation and computing resource consumption are greatly reduced under the condition that global dependence modeling capability is guaranteed, and efficient operation on large-scale three-dimensional medical image data can be achieved.

This invention discloses an AUV-UFastSLAM algorithm optimized based on the whale algorithm, comprising a series of processes including initialization, prediction, sampling, map updating, and resampling. This method optimizes the particle sampling process using the whale algorithm, enabling the particle swarm to move towards a high-likelihood region, making the AUV pose estimation closer to the true value. An inertia weight factor is introduced to improve the whale algorithm's position update formula, increasing the population convergence speed and accuracy. Simultaneously, Cauchy mutation is used to randomly perturb the optimal neighborhood to increase population diversity and improve the algorithm's global search capability. An improved resampling method is used for particle filtering to ensure particle diversity. Through these adjustments, the accuracy of AUV simultaneous localization and map creation is improved.

The application discloses a kind of MU-MIMO system wireless resource allocation method and system based on condition diffusion strategy enhancement, for MU-MIMO system downlink transmission, method includes: with the total capacity of the MU-MIMO wireless communication system as target, jointly optimize resource block allocation and transmission power, construct optimization problem;Condition diffusion model is trained based on expert dataset;Multiple candidate solutions are generated using the trained model, and the optimal solution of the optimization problem is obtained by further optimizing the multiple candidate solutions through policy enhancement;By constructing a condition diffusion model, imitation learning is performed on the expert dataset;And introduce resampling mechanism, select the optimal solution from multiple candidate solutions, while ensuring to meet system constraints, significantly improve system throughput and reduce computational complexity.

This invention relates to the field of autonomous driving technology, specifically to a method, system, device, and medium for fast trajectory resampling based on autonomous driving motion constraints. This method introduces vehicle kinematics to control a virtual vehicle to move along a desired trajectory, thereby generating a trajectory that satisfies the kinematics, overcoming the shortcomings of filtering methods that cannot take kinematics into account. Simultaneously, to address the problem that control-based methods cannot converge at the final target point of the trajectory, a combination of forward and backward filtering is used, solving the lag problem caused by simple filtering methods while inheriting the advantage of fast computation speed of filtering methods for rapid trajectory resampling.

The invention discloses a TCR-epitope combined prediction method based on dynamic graph ensemble learning, and relates to the field of TCR-epitope prediction. The invention aims to solve the problem that the existing TCR-epitope combined prediction method is low in prediction accuracy. The method comprises the following steps: forming a data set by using a TCR beta chain CDR3 sequence, an epitope sequence and a tag, and dividing the data set into a training set and a test set; training a DynaTCR model by using the training set to obtain a trained DynaTCR model; the samples predicted wrongly in the training process are stored in the training set of the next round of training, resampling is carried out in the samples predicted correctly according to a preset sampling rate, and the samples obtained through resampling are stored in the training set of the next round of training; and after the current round of training is finished, evaluating the trained DynaTCR model by using the test set. A to-be-predicted TCR beta chain CDR3 sequence and a to-be-predicted epitope sequence are obtained, the to-be-predicted TCR beta chain CDR3 sequence and the to-be-predicted epitope sequence are input into the trained DynaTCR model, and a prediction result is obtained; the method is used for TCR-epitope binding prediction.

The invention belongs to the technical field of artificial intelligence, and relates to an artificial intelligence-based image processing method, which comprises the steps of receiving an input original image; in a processing process of decoding an original image by using a visual language model, performing perception graph construction based on a self-attention mechanism to obtain a corresponding initial perception graph; carrying out iteration refining processing based on the initial perception graph to obtain a first perception graph; performing optimization processing on the first perception graph based on a preset post-processing strategy to obtain a second perception graph; performing nonlinear resampling processing on the original image based on the second perception image to generate a target image; reasoning the target image based on a visual language model to generate text response data; and outputting the text response data. The invention further provides an image processing device based on artificial intelligence, computer equipment and a storage medium. The method can be applied to image processing scenes in the financial science and technology field and the digital medical field, and the accuracy of the generated text response data is effectively improved.

Methods and apparatuses are provided for encoding and decoding video data based on a supplemental enhancement information (SEI) message. An exemplary method includes: generating a reconstructed frame sequence based on a compressed video; decoding a supplemental enhancement information (SEI) message with respect to the reconstructed frame sequence, according to the compressed video; and performing temporal upsampling to the reconstructed frame sequence based on the SEI message by using a neural network.

The invention relates to a method for non-uniform resampling of bearing fault data, which is characterized in that non-uniform resampling is carried out on an original fault signal based on a Generative Adversarial Network (GAN) on the premise of keeping the overall length of the fault signal unchanged. Through fault peak identification and setting of an adjustable up-sampling window, enhanced up-sampling processing is carried out on a fault peak area, and down-sampling compression is carried out on a signal stable area. According to the method, a trainable attention mechanism is introduced, attention weights are adaptively distributed in a generator coding stage, and the model is guided to more effectively reconstruct feature information of a fault peak region. In the training process, similarity matching with a high-sampling-rate reference signal is carried out in a sliding window mode, the alignment position of a peak area is positioned, reconstruction loss in a window is used as an optimization target, and the expression precision of a resampling result is improved. A finally output signal is formed by splicing an up-sampling enhanced peak segment and a down-sampling segment of a stable area, key fault information retention and redundant data compression are both considered, centralized distribution of sampling resources and enhanced reconstruction of fault features are achieved, and the method is suitable for fault data adaptive resampling and subsequent fault diagnosis tasks.

The application relates to the technical field of airplane test data analysis, and discloses an airplane task sensor ground test data alignment method. The method firstly performs nearby alignment on data starting time, then realizes unification of sampling intervals based on resampling, performs upsampling operation on data with large sampling intervals, and realizes data filling based on interpolation. The application can effectively improve the overall quality of data, provide more accurate and reliable basis for subsequent data analysis and modeling, and promote airplane performance analysis and optimization.

The invention discloses an adaptive resampling method and device for synthetic and real data, and electronic equipment. The method comprises the following steps: acquiring a training data set from a plurality of data sources; uniformly preprocessing the multi-source training data, and constructing data source identifiers and sample basic feature representations; calculating distribution deviation and sample bias features among different data sources based on the basic feature representation; according to the distribution deviation and sample bias characteristics, calculating a depolarization weight or a resampling probability of each sample; based on the depolarization weight or the resampling probability, adaptive resampling is carried out on the multi-source training data, and a depolarization training sample set is constructed; and training or updating the target model by using the depolarization training sample set, and dynamically adjusting a resampling strategy based on model training feedback, thereby realizing multi-round adaptive depolarization and resampling optimization.

The present application provides an image processing device, an image processing method and a computer program product capable of reducing the amount of calculation and improving the efficiency of post-processing. The image processing device processes a primary segmentation processing result obtained by performing segmentation processing on an image at a segmentation resolution, and comprises: a boundary point searching unit configured to extract a set of specific boundary points on the image according to a probability map as the primary segmentation processing result; a positioning unit configured to map the extracted specific boundary points back to the probability map to obtain coordinates of the specific boundary points; and a resampling unit configured to perform first resampling processing on the specific boundary points on the probability map, perform second resampling processing different from the first resampling processing on other points on the probability map except the specific boundary points, and obtain a segmentation processing result at a target resolution.