25 results about "Second order statistics" patented technology

The invention provides a non-circular signal sensing method based on a weighted coherence matrix, which belongs to the technical field of wireless communication, and comprises the following steps: acquiring a complex value receiving signal, and calculating a real value augmented sample covariance matrix; based on the real value augmented sample covariance matrix, constructing a real value sample coherence matrix, and calculating a corresponding weight coefficient; constructing test statistics based on the weighted sum of squares of the real value sample coherence matrix and the weight coefficient; and calculating a sensing threshold based on the false alarm probability, comparing the sensing threshold with the test statistics, and determining a spectrum sensing result. According to the method, the second-order statistical property of the non-circular signal is described by using the real-value augmented sample covariance matrix, and weighted square fusion is performed on the real-value sample coherence matrix in combination with the weight coefficient driven by the sample data, so that better sensing performance can be obtained.

A method includes determining estimated features comprising second order statistics based on at least one received signal. The method also includes classifying, using a machine learning network, each channel of the at least one received signal into a channel profile based on the estimated features. The method also includes obtaining multiple minimum mean square error (MMSE) channel estimation weights from a database based on the estimated features, the database storing (i) representative MMSE estimation weights and (ii) channel cluster representatives indexed by the estimated features. The method also includes applying a respective MMSE channel estimation weight for each channel.

The invention relates to the technical field of visual inspection, in particular to an intelligent detection and evaluation system for aero-engine blade repair performance, and the system comprises an aero-engine blade image collection module which is used for obtaining a to-be-detected aero-engine blade repair area image, carrying out the illumination normalization of the image, and generating a repair area subgraph sequence with coordinates. According to the method, the aero-engine blade repair area image is divided into the overlapped sub-areas with the space coordinate indexes, so that the full coverage of detection analysis and the accuracy of defect positioning are ensured, and the contrast ratio, the energy and other second-order statistics are obtained by calculating the gray-level co-occurrence matrix; and in combination with radial and angular energy distribution extracted by two-dimensional fast Fourier transform, a multi-dimensional texture feature set fusing a spatial domain local pixel relationship and a frequency domain periodic structure is constructed, so that the cladding texture state of a repair region can be described more comprehensively, and the identification capability of texture uniformity and directional anomaly is improved.

The application provides a two-stage denoising neural network-based direction of arrival estimation method, device and electronic equipment. The method comprises the following steps: constructing an array receiving signal matrix and extracting an amplitude matrix and a phase matrix according to the receiving signal of a linear uniform array; extracting the median of all elements in the amplitude matrix and performing range compression to obtain an amplitude statistical feature; inputting the amplitude statistical feature into an adaptive threshold subnetwork to generate a compression coefficient; performing amplitude limiting processing on the amplitude matrix by using the compression coefficient, combining the new amplitude matrix and the phase matrix into a limited amplitude signal matrix; constructing a bounded covariance matrix with a second-order statistical form based on the limited amplitude signal matrix; inputting the bounded covariance matrix into a complex residual convolution subnetwork to generate a noise residual matrix; obtaining an equivalent covariance matrix based on the bounded covariance matrix and the noise residual matrix; and performing spatial spectrum search on the equivalent covariance matrix by using a MUSIC method to obtain a direction of arrival estimation result of a signal source.

This invention provides a non-circular signal sensing method based on a weighted coherence matrix, belonging to the field of wireless communication technology. The method includes: acquiring a complex-valued received signal and calculating a real-valued augmented sample covariance matrix; constructing a real-valued sample coherence matrix based on the real-valued augmented sample covariance matrix and calculating corresponding weighting coefficients; constructing a test statistic based on the weighted sum of squares of the real-valued sample coherence matrix and the weighting coefficients; calculating a sensing threshold based on the false alarm probability and comparing the sensing threshold with the test statistic to determine the result of the spectrum sensing. This invention utilizes the real-valued augmented sample covariance matrix to describe the second-order statistical properties of non-circular signals and combines sample data-driven weighting coefficients to perform weighted square fusion of the real-valued sample coherence matrix, achieving superior sensing performance.

The invention relates to the technical field of image style migration, and provides a diffusion style migration method and system based on latent distribution re-anchoring dynamic injection, and the method comprises the steps: carrying out the second-order statistical alignment of a content hidden variable and a style hidden variable through a potential covariance re-coloring method; automatically positioning an injection starting point of the style according to the edge intensity of the content image, and injecting hidden distribution reanchoring noise into the initialized mixed noise hidden variable to realize hidden distribution reanchoring; the content self-attention features and the style self-attention features are fused through a soft + dynamic style injection module, in the reverse sampling process of the calibrated hidden variables, the fused attention features are gradually injected into an attention layer in the diffusion process at the injection starting point, diffusion denoising is carried out, and a style migration image is generated. According to the method, the image with rich structure details is protected, and the excellent content structure maintaining capability and the accurate style reappearance are realized at the same time.

The invention particularly relates to random response analysis of a wake flow type hybrid energy collector under fluctuating wind excitation, which comprises the following steps: on the basis of a simplified model that a static upstream bluff body is arranged in front of a main bluff body, and periodic vortex shedding wake flow force is utilized to excite vibration, establishing an equivalent electromechanical coupling dynamic model; a random phase is introduced into wake-induced vibration external excitation to represent random fluctuation of wake force under the fluctuating wind; after dimensionless and parameter scale re-calibration are carried out on the model, a multi-scale method is adopted to derive an amplitude-phase slow modulation equation set and first-order asymptotic analysis response expressions of displacement, voltage and current; further linearizing the slow-varying equation under a steady-state condition, solving a second-order statistic of amplitude and phase by combining a moment method and an Ischi differential rule, and determining steady-state moments of the output voltage and the output current and average output power according to the second-order statistic; and the output performance rapid evaluation and parameter design support of the wake flow type hybrid energy collector under random excitation are realized.

The invention relates to the technical field of uplink transmission, and discloses an adaptive adjustment method for a data transmission link of a micro-nano unmanned aerial vehicle in a complex environment, which comprises the following steps: calculating a second-order statistical variance of a downlink to represent environmental fluctuation, and determining the segmentation granularity of an uplink transmission block; on the premise of keeping the total power constant, the data amplitude is reduced and the pilot frequency amplitude is improved along with the increase of the segmentation granularity, and asymmetric power distribution is established; dividing the transmission block into a plurality of independent verification micro-frames for sending; according to the method, a physical layer structure and energy distribution reconstruction are directly driven through the environmental volatility, the problems of link self-adaption failure and channel estimation bottleneck caused by feedback lag in a fast fading environment are solved, and through micro-framing spatial isolation and power zero-sum gaming, the self-adaption performance of a channel is improved. And the uplink stability and the effective throughput in a complex multipath environment are improved.

The application discloses an indoor-oriented three-dimensional Gaussian diffusion model point cloud repairing method, expresses a missing point cloud as a three-dimensional point set, introduces a point cloud centroid as a spatial reference center, constructs a progressive-axis distance component of each point relative to the centroid, and calculates a second-order statistic in each axis direction as a directional scale signal; according to the deviation of the directional scale signal from a reference scale, the noise intensity is re-calibrated in each axis direction to form a diagonal covariance form of a directional adaptive three-dimensional Gaussian forward diffusion model; a denoising network is used to predict noise components in each diffusion step and update according to the progressive-axis diffusion intensity, while an observation consistency constraint is introduced; finally, a diffusion standard loss function is used to train the error between the real noise injected in the forward diffusion model and the predicted noise, and an optimized diffusion model is obtained. The method can be applied to indoor three-dimensional reconstruction, digital twinning, robot perception and indoor point cloud dataset enhancement scenes.

The invention relates to the field of machine learning and pattern recognition, and particularly discloses a variance-covariance subspace distance-based multi-kernel subspace clustering method, which comprises the following steps of: S1, acquiring a high-dimensional data matrix, calculating a variance-covariance matrix and second-order statistical information thereof, defining a preliminary VCSD kernel value and obtaining a VCSD kernel matrix through exponential transformation and normalization, constructing a multi-core pool of r base cores; s2, constructing an optimized objective function based on non-negative matrix factorization, and solving to obtain a local affinity feature map of a block diagonal structure under constraint conditions; s3, capturing high-order feature association through a matrix method, and converting tensor optimization into matrix operation; s4, solving the target function by adopting an alternating optimization strategy, reducing the calculation complexity, and generating a target affinity graph; and S5, clustering the target affinity spectrum, and outputting a result. According to the technical scheme provided by the invention, the problems of missing statistical characteristics, complex calculation and nuclear noise interference of the existing method are solved, and the clustering precision and efficiency are effectively improved.

The application is an ultrasonic signal disturbance suppression method based on covariance whitening method. The application relates to the technical field of medical ultrasonic sensor signal disturbance suppression, and establishes a second-order statistical model of array elements in the channel by using original RF data collected in multiple probe states, and constructs a whitening transformation or a reference domain covariance alignment transformation in the channel dimension, so that statistical changes related to probe disturbance are normalized and suppressed. The application normalizes and aligns the second-order statistical differences caused by the probe disturbance in the original RF channel space, so as to reduce the sensitivity of subsequent signal analysis, feature extraction, classification model or regression model to non-target acquisition state factors. The corrected data still maintains the original two-dimensional RF matrix form, and when used for traditional beam forming or image reconstruction, diagonal whitening, local strip approximation, scale recovery or double branch processing mode can be adopted to give consideration to statistical stability and array element physical consistency.

The application discloses a kind of based on magnetocardiogram's lesion model construction method and system, comprising: acquisition multi-channel magnetocardiogram and preprocessing are obtained preprocessing observation matrix;Based on second-order statistics blind source separation of second-order statistics blind source separation based on multi-delay covariance weighting joint diagonalization, generate interference suppression weight and reconstruction are obtained purification observation matrix;Coupling separation matrix and interference suppression weight generate inversion prior parameter and establish weighted forward model;Under the constraint of weighted forward model, using the improved FOCUSS of connected domain focus to the sparse reconstruction of purification observation matrix is obtained convergent source distribution;Based on convergent source distribution extraction lesion voxel boundary and reconstruction surface grid, combined with energy projection consistency check output three-dimensional lesion model.The application improves lesion positioning accuracy and three-dimensional model construction stability under strong noise and individual difference conditions.

The present application belongs to the technical field of civil engineering structure identification, and particularly relates to a mode shape identification method based on statistical moment theory, comprising the following steps: step one, uniformly arranging measuring points on the surface of a structure along the same direction; step two, obtaining the acceleration response of each measuring point; step three, calculating the second-order statistical moment value of the measuring point by using the acceleration response; step four, calculating the second-order statistical moment ratio of two adjacent measuring points; and step five, constructing the first-order mode shape of the structure by the relationship between the second-order statistical moment and the first-order mode shape of the structure. The mode shape extracted by the method has great advantages in precision, efficiency, convenience and the like, and is not affected by human factors, so that the mode shape of the civil engineering structure can be quickly identified.

This invention discloses a method for tracing the source of generated images based on spatial-frequency cross-domain second-order statistics. This method extracts spatial domain residual anomalous features and frequency domain anomalous features from the generated image, and constructs a cross-domain second-order statistical coupling relationship between them, forming a cross-domain statistical fingerprint for source tracing. The cross-domain statistical fingerprint matrix is ​​obtained by calculating the cross-domain cross-correlation matrix, and then normalized and compressed to obtain a cross-domain second-order statistical feature representation. Based on the similarity matching or distance measurement results between this feature representation and the statistical fingerprint templates of each source category, the source category or confidence score of the generated image is output. This invention can explicitly characterize the coupling relationship between spatial anomalies and frequency anomalies, and still has strong source discrimination ability and good interpretability and generalization performance even when the generation models are highly similar.

The invention requests to protect a coupling signal separation method based on symmetric tensor joint decomposition, and provides a new BSS method, namely TenSOFO, for solving instantaneous blind source separation from the perspective of tensor decomposition. According to the method, a novel efficient alternating direction multiplier method framework is provided, and two symmetrical third-order tensors are allowed to be decomposed at the same time in an individual difference scale INDSCAL format. In addition, the basic relation between the BSS based on the second-order statistic-fourth-order statistic SO-FO and the combined INDSCAL decomposition is established, and the provided INDSCAL method can be effectively applied to the instantaneous BSS task. The TenSOFO has the advantages that memory is saved, effective decomposition is achieved, Gaussian noise items disappear when fourth-order FO is used, and source signals can be processed without prior information of other levels. Therefore, the TenSOFO is particularly beneficial to processing long-time sequence signals such as voice and audio sampled at a high rate. Experimental results show that the TenSOFO method provided by the invention is minimum in error measurement and optimal in performance.

A three-dimensional high-precision RL deconvolution beam forming method and device based on a second-order single-vector hydrophone belong to the field of underwater acoustic signal processing and direction of arrival estimation. The method and device are used for solving the problems of the existing single-vector hydrophone beam forming method, such as main lobe diffusion, outstanding sidelobe interference, incomplete three-dimensional modeling, limited multi-target resolution capability, high complexity of spherical convolution operation and poor real-time performance. The method and device comprise the following steps: synchronously collecting sound pressure signals and three-dimensional orthogonal velocity signals by using the second-order single-vector hydrophone; constructing three-dimensional combined second-order statistics and generating three-dimensional space beam output; establishing three-dimensional beam response and spherical convolution model only related to the spherical angle; solving by using the RL deconvolution iterative algorithm after non-negative preprocessing of the beam output; converting the convolution operation into spherical harmonic domain coefficient multiplication by using spherical harmonic expansion and spherical convolution theorem, and realizing fast iterative calculation; and finally extracting the target azimuth and elevation by peak value searching and neighborhood suppression.

The invention relates to the technical field of industrial automation control, and discloses an adaptive collaborative optimization control method for energy consumption and production quality in a weaving process, which comprises the following steps: constructing a weft insertion angle of arrival observation window and calculating first-order and second-order statistical moments in real time; an asymmetric double-layer control loop is operated, and logic response fluctuation is suppressed through variance so as to maintain stability; the method comprises the following steps: establishing a negative correlation function relationship between a second moment and a target first moment by using mean approximation logic, dynamically setting a limit target first moment approaching a physical failure boundary according to a real-time fluctuation degree, and driving an execution mechanism to converge to the target. On the premise of maintaining process convergence, a theoretical minimum energy input point is automatically locked, and dynamic optimal balance of energy consumption and quality is achieved.

The invention discloses a Mongolian multi-modal sentiment analysis method based on cross-modal information enhancement and fusion. In order to solve the problems that emotion expression is dispersed and implicit clues in multi-modal emotion information are difficult to capture due to Mongolian adhesive language characteristics, a three-level innovation scheme is provided: (1) a cross-modal explicit enhancement layer: converting the implicit emotion clues such as rhythm, expression and the like in audios and videos into emotion description texts by using a multi-modal large language model; the modal information is enriched through a path of implicit, explicit and semantic fusion; (2) a semantic alignment layer based on a Gram matrix: extracting a second-order statistical structure of a text modal as a semantic reference, mapping heterogeneous audio and video features to a unified semantic space, and solving cross-modal alignment difficulty caused by Mongolian morphological change; and (3) a gating displacement fusion layer: a self-adaptive displacement mechanism is adopted, accurate injection of non-text information is realized through fine tuning of semantic positions of text features, and the problem of modal submerging in a Mongolian long morpheme sequence is avoided.

The invention provides an uncertainty-guided analytic high-resolution range profile class incremental learning method, and mainly solves the problems that catastrophic forgetting is likely to occur in radar high-resolution range profile target recognition, and old class recognition performance is remarkably degraded. According to the method, multi-resolution structured feature representation is constructed, a statistical prototype containing a mean value and a second-order statistical magnitude is taken as a unique carrier of old category knowledge, variance or covariance information is updated through recursion, and old category distribution characteristics are depicted under the condition of no original sample; on the basis of a recursive least square closed-form solution of recursive tracking of a covariance matrix, progressive analytic updating is carried out on the classifier to replace back propagation training; and a self-adaptive prototype distillation and uncertainty guiding mechanism based on a statistical prototype is introduced, and old knowledge is kept in the incremental training process. Experimental results show that under the condition that old class samples are not used at all, high and stable overall recognition accuracy can be kept in a target class continuous expansion scene.

This invention relates to the field of image style transfer technology, providing a diffusion style transfer method and system based on latent distribution re-anchoring dynamic injection. The method includes: performing second-order statistical alignment of content latent variables and style latent variables using latent covariance recoloring; automatically locating the style injection starting point based on the edge intensity of the content image; achieving latent distribution re-anchoring by injecting latent distribution re-anchoring noise into the initial mixed noise latent variables; fusing content self-attention features and style self-attention features through a soft + dynamic style injection module; and progressively injecting the fused attention features into the attention layer of the diffusion process at the injection starting point during backsampling of the calibrated latent variables, performing diffusion denoising to generate a style-transferred image. This invention preserves images rich in structural detail, achieving excellent content structure preservation while realizing accurate style reproduction.

The application provides a kind of detection method and system for the appearance of pastry, including collecting pastry image input U type detection network to do multi-scale feature extraction, the channel of each level feature map of encoder is normalized and used as the initial feature of jump connection, the texture activity index is constructed by the mean of channel variance, the initial feature of Skip connection after channel normalization is processed by discrete wavelet transform in jump connection, and high and low frequency components are separated;Low frequency is processed by depth separable convolution, high frequency adopts channel second-order statistics weighting, and inverse wavelet reconstruction is obtained after scaling by texture activity index, and the fusion feature map is obtained;The offset field is generated by the convolution of decoder level feature and fusion feature map, the maximum single-axis offset of offset is limited according to texture activity, and the feature position correction is completed;According to the comparison between the maximum response of decoding output probability map and correction threshold, it is determined whether the pastry has appearance defect and the detection result is output.

A Mongolian multi-modal sentiment analysis method based on cross-modal information enhancement and fusion. To solve the problems of scattered sentiment expression caused by the agglutinative characteristics of Mongolian and the difficulty of capturing implicit clues in multi-modal sentiment information, a three-level innovative solution is proposed: (1) Cross-modal explicit enhancement layer: Use multi-modal large language models to convert implicit sentiment clues such as prosody and expression in audio and video into text descriptions of sentiment, enriching the information of each modality through the "implicit→explicit→semantic fusion" path; (2) Semantic alignment layer based on Gram matrix: Extract the second-order statistical structure of the text modality as the semantic reference, and map heterogeneous audio and video features to a unified semantic space to solve the cross-modal alignment difficulty caused by the morphological changes of Mongolian; (3) Gating displacement fusion layer: Use an adaptive displacement mechanism to fine-tune the semantic position of text features to achieve precise injection of non-text information, avoiding the modality submersion problem in long morpheme sequences of Mongolian.

A multi-dimensional electric power perception information feature fusion method, which first performs eigenvalue decomposition on the covariance matrix of data samples from different data sources based on principal component analysis (PCA), selects the first k main features with cumulative contribution rate exceeding a threshold value as principal components, and takes the feature vectors corresponding to the k main features as the column vectors of a second-order statistical feature vector matrix, then determines a high-order statistical feature vector matrix through the remaining m - k eigenvalues, performs feature pre-fusion of statistical data of different orders based on the statistical feature vector matrix, and determines a feature data matrix, and finally inputs the feature data matrix into a space-time characteristic fusion convolutional neural network (CNN) model for feature fusion. The present application adopts a unique PCA-ICA joint processing method for feature extraction, which can effectively save storage space and fusion calculation time.