75 results about "Canonical correlation" patented technology

The invention relates to a power construction deviation degree diagnosis method based on multi-modal time series data fusion, and the method comprises the steps: collecting voltage, current and frequency data through a multi-channel synchronous sampling technology, filling missing data through cubic spline interpolation, and constructing an initial data matrix; based on a hierarchical feature extraction technology, mapping the voltage frequency domain features and the current time domain statistical features to a unified feature space through canonical correlation analysis, and generating a multi-modal feature vector with a time sequence tag in combination with a sliding window; analyzing the dynamic trend of the electrical variable under multiple time scales by adopting a long short-term memory network, and capturing a key time point through an attention mechanism; a sudden change point and a stationary section are defined, an isolated forest algorithm is combined to detect an abnormal point location deviating from a trajectory, anomaly is classified as transient disturbance or continuous deviation through a multi-layer perceptron, the evolution trend of regional continuous deviation is predicted, and the key problem of the power deviation degree diagnosis capability is improved.

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 continuous dynamic emotion recognition method, system and device, a medium and a product, and relates to the field of emotion recognizing.The method comprises the steps that electroencephalogram signal data and eye movement signal data of a target subject are obtained; determining electroencephalogram features and eye movement features according to the electroencephalogram signal data and the eye movement signal data; based on a deep learning model, the electroencephalogram features and the eye movement features are fused to obtain multi-modal fusion features, and the continuous dynamic emotion category of the target subject is determined according to the multi-modal fusion features; the deep learning model comprises a cross-modal attention mechanism layer, a deep typicality correlation analysis layer, a convolutional neural network, a Transform network and a full connection layer. According to the invention, the accuracy and real-time performance of continuous dynamic emotion recognition are improved.

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 provides a brain network construction and analysis method based on multivariable analysis. The method is mainly used for multi-view analysis of a brain structure and a functional network. The technical problem to be solved is that information loss is caused by neglecting necessary multivariate relationships among brain region nodes when univariate analysis is carried out on a brain function network and a brain structure network. According to the method, the canonical correlation analysis method based on data driving is used for constructing the single-mode brain network, the problem that a traditional univariate analysis method neglects necessary multivariate relations is avoided, the complex relation between the brain structure and functions can be reflected more accurately, and a more reliable basis is provided for deep research of a brain working mechanism.

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.

The invention relates to a point labeling remote sensing target directional detection method and device, and the method comprises the steps: obtaining a point labeling image, inputting the point labeling image into an improved ResNet50 model, and obtaining a class probability graph; the improved model comprises the following steps: sequentially connecting a cavity convolution layer, a canonical correlation analysis-based feature extraction network and a mixed channel attention mechanism to an output layer of a ResNet50 model to obtain a class probability graph; in the model training process, according to the original class probability graph, obtaining target height and width pseudo labels, adjusting a dynamic radius adjustment mechanism of a positive label distribution radius for the target pseudo labels, and performing positive and negative label distribution in combination with point labeling information; and carrying out dimension reduction on the class probability graph, distributing a weight to each data point after dimension reduction, constructing a covariance matrix, decomposing a characteristic value of the covariance matrix, determining width and height directions of the target according to a direction of a decomposition result, moving outwards along the width and height directions, obtaining a target boundary, and further generating a rotation frame.

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 present invention relates to the technical field of industrial process monitoring. More specifically, it relates to a distributed process monitoring method and device for collaborative modeling within and between blocks. This method includes: The offline modeling stage includes the following steps: decomposing the process data to obtain each sub-block; performing slow feature analysis method modeling within each sub-block; performing canonical correlation analysis modeling between sub-blocks; The online monitoring stage includes the following steps: partitioning the new sampled data; substituting the partitioned sampled data into the slow feature analysis method model within the sub-block and the canonical correlation analysis model between sub-blocks respectively to obtain the corresponding feature components; using Bayesian inference fusion to obtain a comprehensive index as the final monitoring statistic and comparing it with the corresponding control limit to detect the state of the current sub-block. The present invention can detect faults from different characteristic perspectives of the data, provide a preliminary range for fault location, so as to improve the detection performance of the process and the fault detection rate.

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 invention relates to the technical field of environment detection, and discloses a soil organic carbon detection hyperspectral band optimization method based on deep learning, which comprises the following steps: filtering and denoising original hyperspectral data by adopting an improved filtering mode; calculating the determination importance of the hyperspectral band to the determined organic carbon content, and dynamically selecting the hyperspectral band with the highest information gain as a candidate hyperspectral band; calculating correlation weights between the candidate hyperspectral data and the soil environment factors by adopting a canonical correlation analysis mode; and performing multi-factor fusion optimal hyperspectral band prediction by using the optimal hyperspectral band prediction model, and detecting the organic carbon content of the soil based on an optimal hyperspectral band prediction result. According to the method, the content of the organic carbon in the soil is efficiently predicted by collecting the hyperspectral data and the measured content of the organic carbon, screening the candidate hyperspectral wave band with high information gain, constructing the hyperspectral wave band prediction model and screening the optimal hyperspectral wave band in combination with environmental factors.

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 a sewage plant fault diagnosis method based on canonical correlation local Fischer discriminant analysis, which comprises the following steps: acquiring normal operation state data and fault data of a sewage plant through a sensor at equal time intervals to obtain a data set, and preprocessing the data set to obtain a data matrix with uniform dimension; performing feature extraction on the data matrix by using canonical correlation analysis, and extracting canonical correlation variables U and V with maximum correlation; splicing the typical correlation variables U and V left and right to obtain a joint feature matrix T = [UV]; performing dimension reduction on the joint feature matrix T by using local Fischer discriminant analysis to obtain a transformation matrix W; projecting the joint feature matrix T to a low-dimensional space through the transformation matrix W to obtain a discrimination score matrix Z = WT; and carrying out normal operation state and fault classification on the discrimination score matrix Z by using a K nearest neighbor algorithm, thereby realizing fault diagnosis of the sewage plant, improving drift variable fault diagnosis accuracy, and effectively identifying faults which are difficult to detect.

The invention discloses a quality-related fault detection method for an attention-enhanced time convolutional network, and belongs to the technical field of industrial process monitoring. Aiming at the problems that a traditional canonical correlation analysis method is insufficient in feature extraction capability when processing nonlinear and time sequence correlation data and an existing deep learning method is not fully combined with a relationship between a quality variable and a process variable, the invention provides a feature extraction method fusing a time convolutional network and an attention mechanism. Firstly, process variables related to quality variables are screened through mutual information; secondly, adaptive feature extraction is carried out on the time series data by utilizing expansion causal convolution and a self-attention mechanism, and the expression ability of key time features is enhanced; then, a correlation model of hidden features and quality variables is constructed in combination with canonical correlation analysis, quality correlation detection statistics are established through singular value decomposition, and a control limit is calculated; and finally, realizing fault detection based on comparison between real-time data statistics and a control limit. The method does not need to monitor quality variables on line, is suitable for real-time quality related fault detection in a complex industrial process, and has high efficiency and robustness.

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.

The invention discloses an intermittent process quality prediction method fusing batch associated information and dynamic data correction. The method comprises the following steps: 1) acquiring and integrating multiple batches of data in the batch process, mining the relevance between batches by adopting canonical correlation analysis, constructing a batch relevance matrix, improving a kernel function by combining Gaussian process regression, and improving the capture capability of a model on the batch data relevance; 2) introducing a dynamic data correction method, dynamically adjusting a prediction error through Bayesian reasoning, optimizing a prediction result in combination with measurement data, and further reducing the influence of noise on the model; and (3) carrying out modeling training and testing by utilizing the improved model, and verifying the effectiveness of the model in the intermittent crystallization process. Through a contrast experiment on a plurality of models, a result shows that the batch process quality prediction method fusing batch association information and dynamic data correction shows higher prediction precision and stability when processing batch process data with high noise and small samples.

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.