57 results about "Canonical correlation" patented technology

The invention relates to the technical field of wireless communication, and discloses an information source number detection method and system based on a non-circular signal. The method comprises the following steps: calculating a compensation sample covariance matrix of a received signal, and obtaining a sample canonical correlation coefficient through Takagi decomposition of the compensation sample covariance matrix; constructing a marginal likelihood function of the maternal typical correlation coefficient; taking a sample canonical correlation coefficient as an estimated value of a corresponding matrix, and establishing an estimated statistic by applying a minimum description length criterion; and obtaining the number of the parent typical correlation coefficients when the estimation statistic is minimized, and taking the number as an estimation value of the actual number of the non-circular signals. According to the method, the characteristic that the non-circular signal compensation covariance is not zero is fully utilized, the marginal likelihood function with the minimum redundancy parameters is adopted to construct the statistics, high-precision estimation of the number of the non-circular signals can be achieved, and necessary guarantee is provided for practical application scenes such as direction of arrival estimation and wave velocity formation.

The invention relates to the technical field of marine ecological informatics, and discloses a habitat suitability prediction method and system for marine ecological management.The habitat suitability prediction method for marine ecological management.The habitat suitability prediction method for marine ecological management.The habitat suitability prediction method for marine ecological managementincludes the steps that traditional knowledge data of fishermen is obtained, and audio data is transcribed into a text format through a natural language processing technology; generating a traditional knowledge graph containing the corresponding relationship between the observation characteristics and the fishing results; carrying out canonical correlation analysis on surface observation characteristics and vortex physical parameters in the traditional knowledge graph, and converting traditional knowledge into quantitative expression of a vortex parameter space based on a mapping matrix; and adopting a random forest to integrate multi-source prediction results, taking a traditional knowledge prediction rule and a physical model calculation result as input features, and outputting a middle-layer fish habitat probability distribution diagram. The technical problem that traditional knowledge and a vortex physical model are difficult to effectively integrate for middle-layer fish habitat prediction is solved.

The invention discloses a financial market emotional fluctuation early warning system, and relates to the field of security, according to the scheme, modal features of three texts, voices and social public opinions are input into a multi-layer perceptron to calculate modal weights, and canonical correlation analysis alignment is adopted after weighted fusion, so that high-quality fused emotional features of a unified measurement space are realized. A weighted directed investor relation network is constructed through interaction frequency and Pearson correlation based on a fusion vector, a group emotion evolution mode is captured by applying sequence diagram convolution, a high-correlation emotion community is divided through modularity maximization iteration, community abnormal emotions are jointly detected by means of an auto-encoder and a first-class support vector machine, and an early warning signal is triggered. And finally, soft update adjustment is performed on an early warning threshold value by using a depth deterministic strategy gradient algorithm, so that the system has early response capability and low false alarm rate in a complex and changeable transaction environment, and reliable and accurate decision support is provided for market risk management and control.

The invention discloses an equipment health monitoring method based on multi-modal data fusion, and the method comprises the following steps: carrying out the preprocessing and feature extraction of collected multi-modal monitoring data, and constructing a cross-modal pairing feature sample; a deep canonical correlation analysis model is adopted to model correlativity among different monitoring data, and multi-modal features are mapped to a unified potential health representation space; and further combining with a hidden variable Gaussian process model, carrying out probability modeling and posterior inference on the potential health representation to obtain a continuous estimation result of the equipment health state changing along with time, and generating a health degradation track. The method is suitable for various equipment operation scenes with noise, missing or asynchronization of monitoring data.

The invention discloses a multi-modal data processing method and system based on an attention mechanism, and relates to the technical field of deep learning, and the method comprises the steps: collecting a multi-modal data set, carrying out the multi-scale time sequence calibration through dynamic time warping, and obtaining a time sequence alignment data stream; performing cross-modal semantic association on the time sequence alignment data stream to form a multi-modal feature vector; performing sparse processing on the multi-modal feature vector by using a multi-head self-attention mechanism to generate potential sparse representation; and carrying out coarse graining analysis and fluctuation mode capture on the potential sparse representation, generating a feature sequence length and a variance descriptor, and carrying out spectral entropy calculation to obtain a data complexity score. According to the method, cross-modal semantic association is performed by using canonical correlation analysis, and meanwhile, differential processing is performed on samples with different complexities through the hierarchical adaptive processing model, so that dynamic matching of computing resources is realized, and the resource utilization rate of multi-modal data processing is remarkably improved.

The invention provides a multi-modal fusion obstructive sleep apnea (OSA) identification method based on deep canonical correlation analysis (DCCA). For multi-modal characteristics, a whole process from data preprocessing, feature extraction and screening to feature fusion and classification is designed. Firstly, AHI indexes, voice data and craniofacial image data of a subject are collected and preprocessed, and DeepSpectrum voice features and geometric morphology image features based on MediaPipe are extracted. Then, feature screening is carried out by adopting a competitive group optimizer (CSO) and a ReliefF algorithm respectively; for a class imbalance problem, an oversampling (AMDO) method based on an adaptive mahalanobis distance is introduced to balance data. Non-linear mapping and deep fusion are carried out on high-dimensional features of the two modals through DCCA, low-dimensional high-correlation features are generated, and information complementarity between the modals is improved. And finally, inputting the fused features into a classifier and evaluating the performance by using five-fold cross validation. According to the invention, effective fusion between modals is realized by using DCCA, and a new method is provided for early screening and auxiliary diagnosis of OSA.

The invention relates to the technical field of mechanical engineering and automatic control, discloses a fault diagnosis method and system based on electro-hydraulic linkage, and aims to solve the problems that diagnosis models are mismatched, early weak faults are difficult to extract and fault root positioning is fuzzy due to electrical and hydraulic data modal isomerism and deep fault feature coupling in the prior art. The method comprises the following steps: synchronously acquiring electro-hydraulic multi-source signals; constructing an electro-hydraulic coupling dynamic state space model based on the health data; generating a multi-dimensional residual sequence through a Kalman filter; performing multi-scale wavelet time-frequency decomposition on the residual error and extracting features; analyzing and fusing cross-domain features by using standard correlation; and finally, realizing accurate fault identification through a support vector machine. The system comprises a synchronous acquisition module, a modeling module, a residual error generation module, a feature fusion module and a fault identification module. Through mechanism modeling and data driving fusion, the early fault sensitivity and the coupling fault distinction degree are remarkably improved.

The application relates to the field of alloy defect detection, and specifically discloses a praseodymium-neodymium alloy nondestructive detection method and system based on acoustic feature analysis, which comprehensively captures defect information contained in an original probe signal from two complementary physical perspectives of instantaneous dynamic characteristics and frequency band energy distribution by simultaneously adopting Hilbert-Huang transform and wavelet packet transform. Further, the scheme discards simple feature splicing, and instead utilizes canonical correlation analysis as an information decoupling tool to online decompose two groups of original feature vectors into a shared part describing defect commonality and unique information parts respectively representing the unique resolution capabilities of HHT and wavelet packet. Finally, the three decoupled components are structurally recombined to form a fusion feature vector which can effectively eliminate redundancy, amplify differences and has higher information density, thereby providing a clear structure and highly refined input for a subsequent classification model.

This invention discloses a fire-fighting pipe fitting leakage risk early warning system based on big data analysis, comprising the following steps: collecting multi-dimensional time-series data such as pressure, flow rate, temperature, and humidity; constructing a data processing and modeling workflow; employing kernel canonical correlation analysis to extract nonlinear correlation features between different monitoring parameters to identify weak correlation changes before leakage; and constructing an anomaly measurement mechanism based on the maximum correlation entropy criterion to quantify the degree of feature shift. By fusing the above correlation features and entropy information, a dynamic risk index is generated and compared with a dynamic threshold to achieve real-time early warning of leakage risk, effectively supporting early fault detection and intelligent assessment of fire-fighting pipe fittings. This invention achieves dynamic perception and intelligent judgment of fire-fighting pipe fitting leakage risk, possessing data-driven early warning capabilities.

The invention relates to the field of computer vision, artificial intelligence and medical image analysis, in particular to a disease prediction method for supervising multi-omics tensor fusion, and the method comprises the steps: obtaining a tensor covariance among multi-omics data according to the processed multi-omics data, and defining a target function of tensor canonical correlation analysis; according to the tensor covariance and the target function, introducing structured sparse constraint and disease supervision information, and constructing a multi-modal image correlation analysis model based on tensor; solving the multi-modal image correlation analysis model by using an alternating iteration method to obtain a typical weight of each omics data; and predicting the disease according to the typical weight of each piece of omics data. According to the supervised multi-omics data fusion method based on the tensor, high-order related information can be effectively mined, the classification accuracy of chronic diseases is improved, and powerful technical support is provided for clinical diagnosis.

The application relates to a point labeling remote sensing target directional detection method and device, which comprises the following steps: acquiring a point labeling image, inputting the point labeling image into an improved ResNet50 model, and acquiring a class probability graph; the improved model comprises the following steps: connecting a hollow convolution layer, a feature extraction network based on canonical correlation analysis and a mixed channel attention mechanism in sequence at an output layer of the ResNet50 model to acquire the class probability graph; in the process of training the model, pseudo labels of the height and width of a target are acquired according to an original class probability graph, a dynamic radius adjustment mechanism of adjusting a positive label distribution radius is adjusted according to the target pseudo labels, and positive and negative label distribution is combined with point labeling information; the class probability graph is dimensionally reduced, each data point after the dimensional reduction is assigned a weight, a covariance matrix is constructed, eigenvalues of the covariance matrix are decomposed, the width and height directions of the target are determined according to the direction of the decomposition result, the target boundary is acquired by moving outward along the two directions, and a rotating frame is further generated.

This invention discloses a face recognition method based on semi-supervised dual-source face feature fusion, addressing the semi-supervised, multi-view, and cost-sensitive learning problems existing in real-world face recognition applications. The method includes: acquiring multiple face image data under preset dual views; inputting the face image data into a trained semi-supervised cost-sensitive canonical correlation analysis model; performing dual-source feature fusion using the cost-sensitive feature extraction matrix in the semi-supervised cost-sensitive canonical correlation analysis model to obtain the feature representation of the face image data; and classifying the face image data using a classification model based on the feature representation to obtain the face recognition result. This invention can obtain accurate and reliable face recognition results using only a small number of supervised dual-source face images, effectively improving the classification performance of the face recognition model.

The invention provides a personalized comprehensive old-age care service recommendation method and system based on artificial intelligence big data, and relates to the technical field of computer data processing and artificial intelligence. Travel data of a plurality of target users and browsing data of a community service APP are collected, the travel data comprise travel timestamps and in-out directions, and the travel timestamps and the in-out directions of the target users are acquired; the browsing data comprises a plurality of browsing records, browsing frequency and staying duration; constructing a behavior feature vector according to the record quantity of the travel data in the in-out direction in the preset time period, and constructing an interest feature vector according to the browsing data; respectively inputting the behavior feature vector and the interest feature vector into a neural network based on deep canonical correlation analysis to generate a fusion feature vector of each target user; dividing all the target users into a plurality of social groups based on the fused feature vectors; and based on the low-dimensional manifold space, the community activity information is sent to the edge node objects in the same social group, so that precise social recommendation for the solitary old people is realized.

The invention discloses a multi-modal network fusion analysis method based on a multi-layer network. The method comprises the following steps: 1, constructing a single-modal brain network based on canonical correlation analysis; 2, brain network structure-function coupling is extracted; and step 3, constructing and analyzing a high-order multi-mode brain network. The method has the advantages that the constructed high-order multi-mode brain network integrates brain structure and function information and structure-function coupling information, information loss caused by independent analysis of a structure network and a function network is overcome, multi-scale understanding of a brain mechanism and an abnormal mode is achieved, and a neural mechanism can be revealed more comprehensively; and 2, a core-peripheral tissue analysis method is introduced, the degeneration phenomenon of the core brain region of the brain is found from a multi-mode perspective, a new perspective is provided for analyzing the brain information processing process, and the understanding of the key brain region of the brain mechanism is further deepened.

To enable real-time seizure warnings, systems and methods of the present disclosure include a wearable sensor device in communication with processors that are configured to receive from the wearable sensor device data streams associated with a user that include biomarker data parameters. The processors utilize a seizure forecasting machine learning model that combines a deep canonical correlation analysis with a long short-term memory neural network to predict a seizure likelihood in a prediction period.

The application belongs to the field of social network analysis, and particularly relates to a dynamic social network alignment method based on longitudinal federation and canonical correlation analysis, comprising the following steps: simulating the spatio-temporal relationship of users through a dynamic spatio-temporal graph self-encoding memory model and an attention mechanism to obtain a user relationship matrix; constructing a user attribute matrix and fusing the user relationship matrix to obtain a user matrix; inputting the user feature matrices of platforms X and Y into a model for training through a training model based on federated learning to obtain a prediction result of cross-domain user alignment; and updating and modeling the dynamic relationship representation in combination with the time sequence characteristics of user relationship and fusing other non-time sequence characteristics for cross-platform user alignment prediction. Through the method, the problems of cross-domain data privacy leakage and social network dynamics can be effectively solved, and finally precise cross-platform network user alignment is realized.

The invention belongs to the technical field of medical image processing, provides a medical image-based computer-aided diagnosis method and system, and solves the problem of insufficient computer-aided diagnosis. The method comprises the following steps: collecting a brain diffusion tensor image of a target object and a surface electromyogram signal of an associated muscle group; converting the image into Riemannian manifold data through tensor resolving and symmetric positive definite matrix mapping; extracting a Hurst index of the electromyographic signal based on remarking range analysis, and generating a motion feature vector; using Riemannian logarithm mapping and canonical correlation analysis to project manifold data and motion features to a correlation space, and extracting a maximum correlation component to generate a coupling feature vector; determining a reconstruction site through Riemannian index mapping, and calculating a geodesic line length between the reconstruction site and the reference state point to obtain a deviation value; and quantitatively judging the nerve remodeling degree and the motor function level of the stroke patient according to the deviation value. According to the application, accurate quantitative evaluation of the stroke nerve remodeling and motion recovery state is realized.

The application provides an electroencephalogram adaptive recognition method and system, a storage medium and an electronic device, comprising: preprocessing SSVEP electroencephalogram signals to obtain effective SSVEP electroencephalogram signals; based on a filter bank canonical correlation analysis algorithm, replacing each sub-band corresponding filter with M candidate filters, and based on the candidate filters, extracting a correlation coefficient group of each sub-band of the effective SSVEP electroencephalogram signals for each stimulation target; obtaining a normalized correlation coefficient group; selecting a sub-filter of each sub-band based on the normalized correlation coefficient group; calculating a sub-band correlation coefficient of the SSVEP electroencephalogram signals for each stimulation target, and selecting a stimulation target corresponding to a maximum value of the sub-band correlation coefficient as a recognition result. The electroencephalogram adaptive recognition method and system, the storage medium and the electronic device can better adapt to the recognition of different types of electroencephalogram signals by dynamically adjusting filter bank parameters.

The invention discloses an electric drive system fault diagnosis method based on reversible neural network assisted canonical correlation analysis, and belongs to the technical field of fault diagnosis. Reversible nonlinear mapping among sensor data is realized through a reversible neural network, residual signals are generated in combination with a canonical correlation analysis method, test statistics are designed, and a fault diagnosis task of the electric drive system is realized through threshold comparison. The method breaks through linear limitation of traditional canonical correlation analysis, fault information is reserved, the fault position can be accurately positioned, and the method is suitable for a fault diagnosis task of a nonlinear electric drive system.

The application provides a multi-modal emotion recognition method and system based on discriminative learning. The method comprises the following steps: step 1: collecting multi-modal information, including electroencephalogram signals, facial signals, speech signals and text signals; step 2: inputting the multi-modal information into a feature extraction network respectively to obtain electroencephalogram features, facial features, speech features and text features; step 3: using a canonical correlation analysis method to calculate the correlation between any two modal features; step 4: inputting the modal features into respective corresponding single-modal classifiers respectively to obtain single-modal prediction results; step 5: using the correlation between any two modal features and the single-modal prediction results to design a class loss function corresponding to each modal; step 6: obtaining a target function according to the class loss function corresponding to each modal to guide the training of an emotion recognition model; and step 7: obtaining an emotion recognition result by using the trained emotion recognition model according to multi-modal information of an object to be recognized.

A precise target recognition method for short-window SSVEP signals is proposed. This method constructs a signal extension model (DP-MAFD-SEM) using SSVEP signals corresponding to one or more stimulus targets. The short SSVEP signal is extended using this model to increase its length. Then, a canonical correlation analysis (SE-CCA) method based on signal extension is used to identify and classify characteristic frequencies. Extending the short-window SSVEP signal length improves the reliability of covariance matrix estimation methods such as CCA, achieving higher recognition accuracy. This invention provides a novel perspective and approach to improving the recognition accuracy of specific frequencies in short SSVEP signals, achieving higher recognition accuracy with shorter signals. This is beneficial for further improving the information transmission rate of SSVEP-BCIs, promoting the development of high-speed SSVEP-BCIs, and facilitating their practical application.

The invention relates to the technical field of emotion recognition, in particular to an emotion recognition method based on electroencephalogram and eye movement multi-modal signals, which comprises the following steps: constructing an HMSB-CAF model; the extracted electroencephalogram and eye movement features are input into an HMSB-TransNet model, and mapping from high-order features to low-dimensional space is realized through hierarchical multi-scale branch residual transform, so that richer feature representation related to emotion is obtained; using canonical correlation analysis (CCA) to constrain the statistical correlation of the two types of modals in a depth feature space; dynamically calculating weight coefficients of the two types of modals through the learnable parameterized attention vector; self-adaptive fusion is realized according to the weight and the feature contribution, and optimized joint representation is obtained and input into a classifier to complete emotion discrimination. The cross-culture emotion recognition method solves the problems that in an existing cross-culture emotion recognition method, deep mining of modal features is insufficient, and second-order interference influence of modal signals is obvious.

The invention relates to the technical field of fault diagnosis, and discloses an industrial process root cause analysis method and system based on canonical correlation residual difference, and the method comprises the steps: dividing historical operation data into a normal state sample set and an abnormal state sample set based on an operation state; identifying a fault related variable set in the abnormal state sample set based on a fault isolation means, and sequentially setting each variable in the fault related variable set as a candidate root dependent variable; constructing a canonical correlation analysis model based on the candidate root dependent variable and other variables, and obtaining a canonical correlation matrix by using the canonical correlation analysis model; calculating canonical correlation residual errors of the candidate root dependent variables and the non-root dependent variables based on the canonical correlation matrix; calculating a root cause scoring index; and sorting the root cause scoring indexes of all the variables, outputting the root cause scoring index with the highest score according to a sorting result, and taking the variable corresponding to the root cause scoring index with the highest score as the fault variable of the target equipment.

The invention relates to the field of alloy defect detection, and particularly discloses a praseodymium-neodymium alloy nondestructive testing method and system based on acoustic characteristic analysis. Defect information contained in an original probe signal is comprehensively captured from two complementary physical perspectives of instantaneous dynamic characteristics and frequency band energy distribution. Furthermore, according to the scheme, simple feature splicing is abandoned, the canonical correlation analysis is used as an information decoupling tool, and two groups of original feature vectors are decomposed into a shared part for describing defect generality and a unique information part for respectively representing the unique resolution capability of the HHT and the wavelet packet on line. And finally, carrying out structured recombination on the three decoupled components to form a fusion feature vector which can effectively eliminate redundancy, amplify differences and has higher information density, and providing input with a clear structure and high refining for a subsequent classification model.

The invention discloses an intelligent wheelchair control method based on a wearable brain-computer interface, and relates to the technical field of intelligent control. According to the invention, by adopting the visual stimulation design of three rows and three columns of Newton rings and the SSVER-ERP mixed normal form, the significant expansion of a control instruction set and the effective improvement of the discrimination degree are realized, and the instruction content is enriched from simple direction control to compound control containing direction and speed; the problems that a traditional visual stimulation normal form is single in instruction and insufficient in flexibility are solved. According to the method, independent component analysis (ICA) and canonical correlation analysis (CCA) are introduced for signal preprocessing and feature extraction, and a classification model is constructed in combination with a dynamic long short-term memory network (Dynamic LSTM), so that accurate capture and recognition of deep time sequence features in non-stationary and low-signal-to-noise-ratio electroencephalogram signals are realized, and the recognition accuracy and robustness of the system are greatly improved.

This invention discloses a person re-identification method based on scene-independent feature learning. The method trains a scene classifier using source and target datasets. By performing canonical correlation analysis on the features of the person ID classifier and the scene classifier, a correlation factor between the person's identity features and scene features is obtained. Then, through adversarial learning, the effectiveness of the canonical correlation factor is improved while simultaneously reducing the correlation factor, ultimately yielding scene-independent identity features. This method can be combined with almost all known publicly available person re-identification datasets used for supervised learning; it achieves its effectiveness by extracting scene-independent identity features, reducing the negative impact of different scene data; and due to its plug-and-play design, this method is universal for different tasks, scenes, and even domains, such as anime character recognition regardless of art style, or speech recognition regardless of identity.

The application relates to the technical field of wireless communication, and discloses a signal source number detection method and system based on non-circular signals. The method comprises the following steps: calculating a compensated sample covariance matrix of a received signal, and obtaining a sample canonical correlation coefficient through Takagi decomposition of the compensated sample covariance matrix; constructing a marginal likelihood function of a parent canonical correlation coefficient; taking the sample canonical correlation coefficient as an estimated value of the corresponding parent, and establishing an estimated statistic quantity by using a minimum description length criterion; obtaining the number of the parent canonical correlation coefficients when the estimated statistic quantity is minimized, and taking the number as an estimated value of the actual number of non-circular signals. The application fully utilizes the feature that the compensated covariance of the non-circular signal is not 0, and adopts a marginal likelihood function with the least redundant parameters to construct a statistic quantity, so that high-precision estimation of the number of non-circular signals can be realized, and necessary guarantees are provided for practical application scenarios such as direction of arrival estimation and wave velocity formation.

The application discloses a dynamic system data-driven fault detection method based on distributed typical correlation analysis, and comprises the following steps: in an offline process, historical data collected by sensors in each subsystem under normal working conditions is used to construct a centralized CCA residual generator; according to the network topology structure among the subsystems in the dynamic system, the weight coefficients of information transmission among the subsystems are determined based on an average consistency algorithm, an iteration matrix for solving CCA parameters of each subsystem is constructed, and the centralized CCA residual generator is converted into a distributed CCA residual generator; the CCA parameters of each subsystem are solved; in an online process, each subsystem uses the solved CCA parameters to construct a CCA-based residual generator, and the residual signals of each subsystem are distributedly fused based on the average consistency algorithm; finally, a control statistic is designed, a threshold is determined, and distributed optimal fault detection based on data driving in the dynamic system is carried out.

A hyperspectral and laser radar data classification method and system based on KAN, comprising: performing convolution feature extraction on a hyperspectral image and laser radar data respectively to obtain shallow hyperspectral features and shallow laser radar features; performing depth separable convolution and gate adaptive fusion, layer normalization and state space duality modeling, depth convolution enhancement and residual connection on the shallow laser radar features, and then using a KAN network to replace a feedforward network to perform nonlinear mapping to obtain deep laser radar features; performing fuzzy graph convolution processing on the shallow hyperspectral features and the deep laser radar features to obtain hyperspectral branch graph features, laser radar branch graph features and fusion branch graph features of the two; performing multi-view canonical correlation analysis processing on the hyperspectral branch graph features, the laser radar branch graph features and the fusion branch graph features to obtain multi-view enhanced features; and performing gate weighted fusion on the multi-view enhanced features, and outputting a final classification result through a fully connected layer.

The application provides a non-circular source number detection method under colored noise, comprising: constructing a compensated sample covariance matrix based on observation samples; Takagi decomposition is performed on the compensated sample covariance matrix to obtain sample canonical correlation coefficients; an estimated value of parent canonical correlation coefficients is constructed based on the sample canonical correlation coefficients; a log-likelihood function is constructed based on the sample canonical correlation coefficients and the estimated value; a minimum description length statistic is constructed based on the log-likelihood function; and the number of parent canonical correlation coefficients when the minimum description length statistic is minimized is taken as an estimated value of the non-circular source number. The application fully describes the statistical characteristics of non-circular observation samples by constructing a log-likelihood function fusing sample canonical correlation coefficients and estimated parent canonical correlation coefficients, and designs a statistic based on the minimum description length criterion, so that the non-circular source number can be accurately estimated under a colored noise environment, and necessary guarantees are provided for practical application scenarios such as direction of arrival estimation and wave velocity formation.