80 results about "Domain transformation" patented technology

The invention discloses a modeling method based on shield tunneling data feature analysis and parameter relevance, and relates to the field of tunnel engineering data processing. The method comprises the steps that shield tunneling time sequence parameters are obtained, and a non-uniform time sequence is resampled into a space-aligned standardized footage domain sequence through state cleaning and coordinate domain transformation; by means of mixed variable rejection and lagging correlation analysis, environment common cause interference is stripped, physical response delay among parameters is recognized, and a time-delay directed correlation graph model is constructed; and inputting the footage domain sequence and the graph model into a graph neural network, performing feature learning by using a time delay compensation aggregation mechanism, and outputting a key parameter influence degree set with symbols based on a prediction gradient. According to the method, the problem of data space-time dislocation caused by propelling speed fluctuation and the problem of parameter relevance misjudgment caused by physical response lag are solved, and accurate identification and explanation of shield tunneling key parameters are achieved.

The invention relates to the technical field of geotechnical mechanics and engineering, and particularly discloses a soft soil foundation settlement monitoring method and system based on multi-field multi-source information, and the method comprises the steps: collecting multi-source data of a target soft soil area; performing constitutive parameter inversion, data standardization and discrete Fourier transform frequency domain conversion on the data to obtain a standardized frequency domain multi-field multi-source data set; based on the data set, a soft soil constitutive parameter library and a soil mechanics physical equation, constructing an FD-PINN frequency domain physical information neural network, embedding the physical equation as a prior constraint, and training the model by adopting an alternating optimization strategy; inputting the real-time frequency domain data flow into the model, and outputting the current settlement amount, the settlement rate and the multi-physical field frequency domain distribution; and in combination with a pre-established large scale model test result, through IDFT inverse transformation, a time-space domain settlement field is reconstructed, multi-stage early warning is triggered, a targeted reinforcement scheme is recommended, the soft soil foundation settlement monitoring precision and the engineering practicability are remarkably improved, and the method is suitable for construction, operation and maintenance of infrastructures such as high-speed rails and highways.

An assessment apparatus and method for objective pain assessment are provided, wherein the apparatus includes a processor comprising a frequency-domain transformation module, a frequency-band segmentation module, a first assessment submodule, and a second assessment submodule. The frequency-domain transformation module generates a global time-frequency feature matrix, which is segmented by the frequency-band segmentation module in a frequency domain into five frequency bands associated with pain perception. The first assessment submodule extracts last time step features and an adjacency matrix from the time-frequency feature matrix and generates a first feature vector representing global association patterns among electrodes used for acquiring EEG signals. The second assessment submodule generates a second feature vector with local spatiotemporal dynamic features of EEG signals, concatenates it with the first feature vector to form a fused feature vector, computes its class probability distribution, normalizes it, and generates an objective pain quantification indicator corresponding to the EEG signals.

The invention provides an unmanned aerial vehicle full-time perception image reconstruction method based on multi-mode cooperative reinforcement learning and degeneration decoupling. A frequency perception feature modulation model, a dual-mode dual-domain transformation module and a dynamic bidirectional guide mechanism are included. According to the system, firstly, feature information of different frequency bands is adaptively separated and modulated through a frequency sensing feature modulation model, and decoupling and compensation of composite unknown degradation are achieved; realizing cross-domain interaction and information fusion of visible light and infrared characteristics in a spatial domain and a channel domain by using a bimodal dual-domain transformation module; and finally, realizing collaborative enhancement of cross-modal degradation perception through a bidirectional dynamic guide mechanism, and generating an unmanned aerial vehicle visible light reconstruction image and an infrared super-resolution image with higher structural consistency and texture fidelity. According to the method, deep fusion and degeneration decoupling of multi-modal information can be realized in a complex degeneration environment, and the imaging quality and the environmental adaptability of an unmanned aerial vehicle full-time sensing system are remarkably improved.

The invention provides an image compression artifact removal method based on a frequency domain hybrid expert network, and relates to the field of image processing. The method comprises the following steps: acquiring image data with compression artifacts; extracting shallow image features of the image data through an independent convolutional layer; extracting long-distance dependent image features of the shallow image features through a spatial attention mechanism; based on long-distance dependent image features, inputting the long-distance dependent image features into a frequency domain transformation expert network, and determining an optimal frequency domain transformation expert through parallel processing of multiple frequency domain transformation experts and an expert selection mechanism; processing the long-distance dependent image features through an optimal frequency domain transformation expert to obtain enhanced image features; performing image reconstruction on the enhanced image features to obtain a reconstructed image; the reconstructed image is an image after the compression artifacts are removed. The method is used in an image compression artifact removal process, and solves the technical problem that multiple types of complex compression artifacts are difficult to effectively remove in the prior art.

The invention relates to the field of seismic data reconstruction, in particular to a seismic data low-rank reconstruction method fusing double-domain transformation, and the method comprises the steps: obtaining original incomplete seismic data, and initializing to-be-reconstructed seismic data and other model variables and parameters under an alternating direction multiplier method frame; performing fractional order gradient transformation on seismic data to be reconstructed along different directions, and mapping to obtain fractional order gradient domain data; performing space-time Hankel tensor expansion transformation on each piece of fractional order gradient domain data, and converting the data into a space-time Hankel matrix; performing low-rank constraint on each space-time Hankel matrix by adopting a Schatten norm to obtain a seismic data low-rank reconstruction model fused with double-domain transformation; and carrying out iterative solution on the model by using an ADMM framework until the model is stable, and obtaining a final seismic data reconstruction result. The method provided by the invention can effectively reconstruct the seismic data with the missing trace, and has a reconstruction effect with strong robustness and relatively good precision for incomplete seismic data with different missing degrees.

The invention discloses a multivariate time sequence prediction method based on dynamic complex spectrum filtering, which comprises the following steps: acquiring multivariate time sequence data of a target scene, determining a predicted target variable and a window length, and constructing a training set, a verification set and a test set based on the data; constructing a DCSFNet prediction model, wherein the model sequentially comprises a reversible instance normalization module, a frequency domain conversion module, a dynamic complex spectrum filtering module, a time domain projection module and an inverse reversible instance normalization module; and realizing multivariate time sequence prediction by using the trained DCSFNet model. According to the method, the frequency domain features are adaptively processed through the dynamic complex spectrum filtering module, and reversible normalization and time domain mapping are combined, so that the problems that an existing method is poor in adaptability to diversified time sequence data, frequency domain information is insufficient in utilization, and prediction precision and calculation efficiency are difficult to consider at the same time are effectively solved; and multivariate time sequence prediction with high precision, high efficiency and cross-scene adaptability is realized.

The present disclosure relates to methods, apparatus, systems, and non-transitory computer-readable storage media for training and using a multi-scale machine learning model for the enhancement of compressed video. According to some examples, a computer-implemented method includes receiving a video at a content delivery service; performing an encode on a frame of the video by the content delivery service that converts the frame from a pixel domain to a transform domain and back to the pixel domain to generate first pixel values and a first residual for a block of the frame at a first resolution; generating a first set of features, by a machine learning model of the content delivery service, for an input, at a first resolution, of the first pixel values and the first residual of the block; generating a second set of features, by the machine learning model of the content delivery service, for an input, at a second lower resolution, of second pixel values and a second residual of the block; upsampling the second set of features to the first resolution to generate an upsampled second set of features; generating a modified version of the frame based on the first set of features and the upsampled second set of features; and transmitting the modified version of the frame to a frame buffer or from the content delivery service to a viewer device.

The invention discloses an unsupervised image conversion imaging method based on the Schrodinger bridge theory, and the method comprises the following steps: 1, constructing an image domain-domain conversion frame based on the Schrodinger bridge theory, simulating a smooth evolution path from a source domain image to a target domain image through a time condition generator, and forming antagonism training in combination with a discriminator; 2, integrating a saliency content guide constraint, a global feature consistency constraint and a contrast learning constraint in the conversion framework so as to enhance semantic content retention and detail generation capability; 3, establishing a composite loss function, and carrying out weighted combination on Schrodinger bridge path loss, adversarial loss and each auxiliary constraint loss for guiding model optimization; and 4, training a time condition generator and a discriminator through an optimization algorithm, and carrying out stable and high-fidelity target domain conversion on the source domain image by utilizing the generator after training is completed. According to the method, the stability of model training and the quality and fidelity of the generated image are remarkably improved.

The invention provides a dynamic adaptation method and system for a multi-mode power supply compatible charging pile system, and the method comprises the steps: building a multi-protocol physical layer compatible connection between a charging pile and a power supply module through a multi-communication interface layer, and receiving a data frame inputted by the charging pile; analyzing a baud rate, a check bit and an instruction set of the data frame, and identifying a charging pile protocol type and a power module protocol type; querying a matching mapping relationship between the charging pile protocol type and the power supply module protocol type in the dynamic adaptation matrix; if the matching mapping relation exists, data field conversion is executed, and a target protocol frame is generated; and if the matching mapping relation does not exist, starting a machine learning process, creating a temporary mapping rule, and effectively solving the problems of poor compatibility and high manual configuration cost of the charging pile and the power supply module in a traditional protocol mode through the modes of protocol analysis, intelligent matching and dynamic learning.

The invention relates to a frequency domain modeling method, device and equipment for a serial DR-MMC port and a medium, and the method comprises the steps: injecting current disturbance at the serial DR-MMC port, carrying out the measurement equivalence of a response quantity at a grid-connected point according to a preset grid-connected interface equivalent parameter set, and obtaining low-voltage side current small signals of a DR and an MMC; according to the low-voltage side current small signal, performing dual frequency domain transformation on a DR time domain switching function, establishing a DR switching function frequency domain model, and further deriving a DR AC side small signal relationship according to the switching function frequency domain model; constructing a DR frequency domain sub-model, an MMC frequency domain sub-model and a direct current frequency domain sub-model based on the relationship between the low-voltage side current small signal and the alternating current side small signal and in combination with device alternating current and direct current constraints, MMC loop control constraints and direct current network equivalent constraints; and assembling the DR frequency domain sub-model, the MMC frequency domain sub-model and the DC frequency domain sub-model at the grid connection point to obtain a frequency domain model of the AC port. The method has the effect of improving the characterization accuracy of the frequency domain characteristic of the grid-connected point port in the broadband range.

The invention discloses a low-frequency attribute model acquisition method, device and equipment and a readable storage medium, and belongs to the technical field of seismic inversion. The method comprises the following steps: acquiring a three-dimensional geological structure model of a target area, a first attribute value of each sampling point included in an observation well located in the target area and a second attribute value of each seismic node included in a seismic body corresponding to the target area; generating a first sequence small layer model according to the three-dimensional geological structure model, each sampling point and each seismic node; domain transformation is carried out on the first sequence small-layer model to obtain a second sequence small-layer model under the sedimentary domain; according to a first attribute value and a second attribute value of a target node in nodes included in each layer in the second sequence small-layer model, obtaining a layer model corresponding to each layer in the second sequence small-layer model; and generating a low-frequency attribute model according to the second attribute value of each node included in the second layer sequence small-layer model and the layer model corresponding to the layer where each node is located. And the precision of the low-frequency attribute model is improved.

This invention discloses a multivariate time series forecasting method based on prediction domain transformation and dual-path fusion. A time series forecasting model, PDT, is proposed. It utilizes data-adaptive prediction domain transformation to project the time series onto the energy-concentrated optimal latent space for prediction. A dual-path architecture is designed to simultaneously achieve efficient extrapolation of dominant linear trends and capture complex nonlinear dynamics. A masked channel dependency strategy and a lightweight linear encoder are used to adaptively fusion and filter inter-variable dependencies and deeply extract intra-channel features, respectively. The proposed time series forecasting model significantly solves the problem of insufficient nonlinear expressive power of traditional linear models and enhances noise resistance and computational efficiency in high-dimensional multivariate scenarios, comprehensively improving the prediction accuracy and robustness of the model in multivariate time series forecasting tasks.

The invention relates to the technical field of communication, in particular to a communication method for inhibiting an overhigh peak-to-average ratio in an orthogonal time-frequency-space system, which comprises the following steps of: 1, converting a signal from a delay-Doppler domain convenient for channel characterization to a time-frequency domain convenient for modulation implementation; step 2, performing preliminary suppression on the peak-to-average ratio by adopting a T-SLM method, generating a plurality of groups of candidate signals, and selecting one group with the peak-to-average ratio lower than a preset threshold or with the minimum peak-to-average ratio; step 3, carrying out Hisenberg transformation on the selected signal to obtain a time domain signal; carrying out iterative amplitude limiting filtering processing, adding a cyclic prefix, and then sending; step 4, removing the cyclic prefix by a receiving end, and recovering to a time delay-Doppler domain through Wigner transform and Sextile Fourier transform; performing preliminary detection by adopting a message passing algorithm to obtain a hard decision value and a log-likelihood ratio; and selecting a high-reliability observation value based on a log-likelihood ratio, and constructing a reliability selection matrix.

The present disclosure relates to a controller that optimizes read thresholds of a memory device using domain conversion. For decoded data of each read operation, the controller determines an asymmetry ratio (AR) and a number of unsatisfied checks (USC), the AR representing a ratio of a number of first binary values to a number of second binary values in the decoded data. The controller determines a Z-axis such that AR values of a threshold set are arranged in a set order along the Z-axis. The controller determines an optimal read threshold set using coordinate values on the Z-axis that correspond to set AR values and set USC values.

The application discloses a semantic communication method and system based on interleaved frequency division multiplexing, belongs to the field of semantic communication, and is applied to a semantic communication system. The method comprises the following steps: a sending end extracts semantic information through a semantic encoder and transmits the semantic information after modulation through interleaved frequency division multiplexing; a receiving end reconstructs a semantic signal based on a received signal through a cross-domain iterative detector and completes a target task through a semantic decoder. The cross-domain iterative detector performs linear detection in a time domain by utilizing channel sparsity, performs nonlinear detection in a characteristic domain based on a fractional model, and realizes cross-domain transformation through an interleaved frequency division multiplexing modulation matrix with universal characteristics. The application can realize training of an encoder / decoder and decoupling of a channel through interleaved frequency division multiplexing modulation, the channel has strong universality, and the compatibility with an existing digital communication system is good. Since the type of the encoder / decoder is not limited, the whole system can perform multiple tasks, and the task universality is good.

The invention discloses a ship structure crack positioning and feature reconstruction method and system. The method comprises the steps that a sensor array is arranged in a to-be-detected area, guided wave signals are emitted and collected, domain transformation, mode screening and matched frequency window filtering are conducted on original signals, and enhanced signal data are obtained; carrying out multi-mode feature extraction on the enhanced signal, constructing a multi-dimensional feature vector containing mode features and a coupling relation thereof, and realizing initial crack positioning by combining sensor position information; time inversion and wave field back propagation are further carried out on the enhanced signal, an energy field is constructed, accurate crack positioning is realized according to an energy field extreme value, and crack direction and size information is extracted; according to the method, the signal-to-noise ratio, the positioning precision and the stability and quality of time reversal imaging can be remarkably improved.

The invention discloses a large model jailbreak vulnerability test method and device and a computer program product, and the method comprises the steps: firstly, determining a target transfer field and a target attack method corresponding to a target malicious query text from a transfer field library and an attack method library through a field conversion mode, and generating a first prompt instruction in combination with a large model jailbreak attack historical record library, and inputting the first prompt instruction to the generated large model to obtain a target confrontation suffix. Generating a second prompt instruction by using the target malicious query text and the corresponding target confrontation suffix, inputting the second prompt instruction into the target large model to obtain a reply result, performing harmfulness evaluation on the reply result, updating the large model jailbreak attack historical record library by using an evaluation result, and according to the updated large model jailbreak attack historical record library, obtaining a jailbreak attack result of the target malicious query text and the target confrontation suffix of the target malicious query text. And optimizing the target confrontation suffix by using a hybrid sampling strategy to obtain an optimized target confrontation suffix for performing a jailbreak vulnerability test on the target large model to obtain a more accurate test result.

This invention discloses an infrared human pose estimation method and system based on cross-domain feature transfer. A domain transfer module is inserted into each feature extraction layer of the human pose estimation model. This module is specifically designed to learn the transformation mapping relationship from the source domain feature space to the target domain feature space. By embedding the domain transfer module in each feature extraction layer of the network, domain transfer can be performed simultaneously at different abstraction levels of the network, achieving multi-scale and multi-level feature alignment. The domain transfer module is then trained using an infrared image dataset to learn the domain transformation from the source domain to the target domain. This invention solves the technical problems of traditional cross-domain pose estimation methods, such as the need for large amounts of labeled data, low training efficiency, and susceptibility to overfitting, thus improving the accuracy and precision of pose estimation after cross-domain adjustments.

An assessment apparatus and method for objective pain assessment are provided, wherein the apparatus includes a processor comprising a frequency-domain transformation module, a frequency-band segmentation module, a first assessment submodule, and a second assessment submodule. The frequency-domain transformation module generates a global time-frequency feature matrix, which is segmented by the frequency-band segmentation module in a frequency domain into five frequency bands associated with pain perception. The first assessment submodule extracts last time step features and an adjacency matrix from the time-frequency feature matrix and generates a first feature vector representing global association patterns among electrodes used for acquiring EEG signals. The second assessment submodule generates a second feature vector with local spatiotemporal dynamic features of EEG signals, concatenates it with the first feature vector to form a fused feature vector, computes its class probability distribution, normalizes it, and generates an objective pain quantification indicator corresponding to the EEG signals.

The invention relates to the technical field of image noise processing, and provides an image denoising processing method and system fusing a wavelet frame and a sharpening operator, and the method comprises the steps: carrying out the sharpening processing of an obtained to-be-processed image; wavelet domain transformation is carried out on the sharpened image, and a denoising preprocessing mathematical model is constructed with the purpose of minimizing the weighted sum of a deblurring error item, an image sharpening consistency item and a wavelet domain sparse regular item; solving of the denoising preprocessing mathematical model is decomposed into a plurality of sub-problems, an alternating direction multiplier method is adopted for solving, and a restored image after denoising processing is obtained. According to the method, wavelet multi-scale analysis and sharpening operator edge enhancement are fused, an optimization model for minimizing the deblurring error, sharpening consistency and sparse regularization is constructed, and an alternating direction multiplier method and soft threshold processing are adopted, so that the image denoising effect and the detail retention capability are effectively improved; the problems of detail loss, fuzzy aggravation and low calculation efficiency in the image denoising processing process are solved.

The invention relates to the technical field of wireless communication, and provides a spread spectrum sequence generation method and device, equipment, a medium and a product, and the method comprises the steps: generating a basic sequence, and generating a password sequence or a chaos sequence; performing field extension mapping on the basic sequence to form a base sequence, and performing field extension mapping on the password sequence or the chaos sequence to form a field extension sequence; performing extension field addition operation on the base sequence and the extension field sequence to obtain an extension field addition sequence; and carrying out extension domain transformation on the extension domain addition sequence to obtain a spread spectrum sequence. According to the method, the spread spectrum sequence meeting the requirement can be generated, and the method has good correlation, long periodicity, good randomness and high safety.

In one aspect, the inventions include a system for control of a software defined computer network state system. First, an application plane layer is adapted to receive instructions regarding operation of the state system. Preferably, the application plane layer is coupled to an application plane layer interface. Second, a control plane layer includes an adaptive control unit, such as a cognitive computing unit, an artificial intelligence unit or a machine-learning unit. Third, a data plane layer includes an input interface to receive data input from one or more data sources. A title transfer network element is provided to transfer digital assets via a blockchain. The system may use domain transformations and difference engines.

The embodiment of the application discloses a demand matching method and system, the method comprises the following steps: receiving a target demand description corpus input by a user; converting the target demand description corpus into a target technology resource corpus based on a generative adversarial network; calculating the matching degree of the target technology resource corpus and technology resource data in a technology resource database based on a convolutional neural network; determining a target technology resource list according to the matching degree ranking and outputting. Through cross-domain conversion of the text corpus and mixed application of supervised learning, efficient demand matching in the field of technology services is realized, and effective support is provided for the technology service industry.

Devices, systems, methods, and media are disclosed for domain adaptation of a trained machine learning model using hybrid learning. A hybrid approach to domain adaptation is disclosed that combines aspects of discrepancy-based, adversarial, and reconstruction-based approaches to achieve an end-to-end trained model for performing a prediction task (such as semantic segmentation) on a sparsely labeled dataset in a target domain, by leveraging a richly-labeled dataset in the source domain. Some embodiments may also provide a trained domain translation model for generating synthetic data samples in a first domain based on input data samples from a second domain.

This invention provides a method and system for day-night radiation imaging fusion and switching based on dual-spectrum imaging, belonging to the field of image processing technology. The method includes extracting visible light brightness features and thermal infrared temperature gradient features, analyzing the spatial consistency of radiation intensity and gradient direction, determining the day / night time period type and the degree of scene dynamic change, performing feature domain transformation, constructing a cross-spectral feature alignment mapping relationship, performing spatial registration and semantic correspondence in the fused feature space, and determining mode switching and output based on a synergy index. This invention achieves efficient fusion and intelligent switching of dual-spectral images, improving imaging quality and stability in complex environments.

The present application relates to the technical field of remote sensing image intelligent processing, and particularly relates to a multi-scale progressive land surface temperature fusion downscaling method and device, wherein the method comprises: preprocessing land surface temperature images in a multi-scale image library; constructing a multi-scale training data set containing land surface temperature and at least one auxiliary parameter; constructing a land surface temperature downscaling network based on multi-parameter fusion, and constructing a domain transformation network based on heterogeneous high-frequency information guidance; training the land surface temperature downscaling network and the domain transformation network based on a progressive double-network joint training strategy; fine-tuning a downscaling model meeting a preset low-to-medium resolution condition; and performing low-to-medium-to-high progressive downscaling on a low-resolution land surface temperature image to be processed, so as to generate a multi-scale progressive land surface temperature meeting a target high-resolution condition. The present application fully considers the downscaling difference problem under different resolutions, realizes the physical property retention of a land surface thermal field, and improves the processing efficiency of large-area remote sensing data.

The invention discloses an infrared target detection method and device for optimizing frequency domain features, equipment and a medium, and belongs to the technical field of infrared image processing, and the method comprises the steps: carrying out the preliminary spatial feature extraction of a to-be-processed infrared image, and obtaining an input feature map; executing a plurality of frequency domain transformations to obtain a plurality of frequency domain feature maps; determining a frequency domain selection loss function according to the frequency domain scale sensitive loss and the frequency domain position sensitive loss; determining a reward function according to the negative value; on the basis, a neural architecture search mechanism is adopted, and corresponding weight matrixes are determined for frequency channels in the multiple frequency domain feature maps; generating a weighted frequency domain graph; performing inverse frequency domain transformation to obtain an enhanced spatial feature map; and generating a target detection result of the to-be-processed infrared image. According to the method, by automatically optimizing frequency domain feature selection, a weak target can be accurately captured and enhanced from a strong noise background, and clutters are effectively suppressed, so that the detection precision and robustness are remarkably improved, and the adaptability of the method to different scenes is improved.

The invention provides a multi-station and multi-device universal photovoltaic power station power prediction method. The method comprises the following steps: S000, constructing a prediction model; s100, performing unified domain transformation on the power data of the multiple power stations; s110, static characteristic embedding and global modulation of the power station are carried out; s120, constructing a multi-power-station universal encoder-multi-head decoder architecture; s130, multi-power-station data missing self-adaptive processing is carried out; s140, carrying out zero power section joint learning; s150, carrying out two-stage training and online calibration; and S160, prediction result optimization and application adaptation are carried out. According to the method, the deployment and operation and maintenance cost can be remarkably reduced, and large-scale operation is facilitated.

The present application belongs to the technical field of engineering structure monitoring data analysis, and proposes a kind of identification method and device for data image migration between different bridges.Bridge monitoring data is converted into image in time domain, and the image is classified according to the contour features of the converted image;The pre-trained model takes the adjusted Resnet 50 network model as the main part, adopts the method of transfer learning, and uses the pre-trained model to train the classified image;To solve the problem of unbalanced target bridge data set, use other bridge data to supplement the data of each category, and improve the recognition accuracy of the training model for the data of each category of the target bridge.The present application can alleviate the problem of data imbalance, and avoid the problem that the recognition accuracy of the model for a certain type of data is low due to the lack of data images of the selected target bridge data set.The recognition accuracy of the detection model for each category of data is significantly improved after the target bridge monitoring data image data set is expanded by the present application.