41 results about "Gibbs sampling" patented technology

The invention relates to the technical field of automatic control, in particular to a switching positive system identification method and system and a storage medium, and aims to solve the problems that in the prior art, a model violates non-negative physical constraints, hyper-parameter estimation is prone to local optimum, calculation efficiency is low, and switching path identification precision is insufficient. The method comprises the following steps: firstly, determining non-negative priori of a system model and pulse response truncated Gaussian distribution through a preparation module; constructing a Bayesian network, and iteratively optimizing a switching path by adopting Gibbs sampling; and finally, based on regularization optimization and Gibbs sampling in combination with Monte Carlo approximation, accurately estimating the pulse response of the subsystem. According to the method, the non-negative characteristics are embedded into the whole identification process, global parameter optimization is achieved, high-dimensional integral calculation is simplified, identification precision and stability are improved, and the method is suitable for multi-scene engineering application.

Systems, methods and computer readable media relating to neuro-thermodynamic computers configured to implement hierarchical architecture, wherein the hierarchical architecture includes one or more layers of components, and wherein the hierarchical architecture is configured to perform Gibbs sampling and nested Gibbs sampling. For example, a block layer may include an energy based model (EBM) implemented using oscillators and couplings between oscillators. A chip layer may include multiple blocks coupled to each other using relay oscillators. A package layer may include multiple chips coupled to each other using additional relay oscillators.

This invention discloses a multi-level measurement partitioning method for tracking multiple extended targets. Addressing the low accuracy of traditional measurement partitioning when targets are close together or intersecting, this invention first establishes an extended target state representation and observation model, constructing an ET-GP-GMPHD filter. Based on predicted intensity, the measurement set is partitioned in three levels: known target measurements are assigned using k-means clustering guided by Gaussian feature contour points; new targets are identified through SOMST adaptive clustering for the remaining measurements; and multi-partition hypotheses are generated using Gibbs sampling. Finally, the partitioning results are used to update the filter and extract the target state. This invention achieves accurate measurement partitioning for close targets, significantly improving tracking accuracy and robustness.

The application discloses a kind of based on user text generation content's minority preference learning method in the field of information retrieval, comprising the following steps: data preprocessing operation is carried out to the user text generation content obtained;The data obtained by pre-processing establishes a hierarchical Bayesian model, obtains joint distribution model;Model parameters are learned by Gibbs sampling method, and the formula of mass preference distribution and minority preference distribution is obtained;The meaning of the user minority preference based on user text generation content is analyzed using the learned model parameters;The target user under the minority preference is found using the user minority preference distribution.The method of the application distinguishes mass preference and minority preference from the perspective of user preference, identifies the specific meaning of user minority preference using the good interpretability of hierarchical Bayesian method, provides the opportunity for small and medium-sized enterprises to enter suitable niche market, and the minority preference distribution of each user is beneficial to the enterprise to find out the target user of relevant niche market.

The present invention provides a Bayesian tensor completion algorithm based on multi-measurements. The multi-measurement data is represented by multiple tensors, and it is assumed that each measurement value of each tensor element of the tensor follows a Gaussian distribution. Then, CP decomposition is performed on the tensor to obtain the corresponding factor matrices, and it is assumed that the parameters of the factor matrices follow a conjugate prior distribution. Furthermore, the Gibbs sampling method is used to sample the posterior conditional distributions of the respective parameters, and the estimated value of the tensor is output. The missing values in the multi-measurement data are interpolated based on the estimated value of the tensor, thereby realizing data completion. In summary, the completion method of the present invention is aimed at measurement data with low measurement accuracy, high cost, and repeated measurements in some regions. The Gibbs sampling method combined with CP decomposition is used to realize data completion. Compared with the completion methods in the prior art, since the method of the present invention can utilize the information of all measurement data, it can provide a more accurate estimated value, thereby realizing more accurate data completion.

This invention discloses a two-dimensional Gibbs sampling method based on a hierarchical Bayesian model. This method constructs a P-function that only requires calculation of two parameters based on a known hierarchical Bayesian model, then uses two-dimensional Gibbs sampling to obtain the target parameters, and finally provides an individualized drug dosage. This significantly improves computational efficiency: since only two parameters, CL and V, need to be calculated, the calculation steps are simplified, resulting in a substantial improvement in computational efficiency. No function calculation is required; the sampling step only needs to select the average values ​​of CL and V in the population as initial values ​​and substitute them into the P-function, making the sample distribution after sampling closer to the target distribution, further improving sampling efficiency.

The invention discloses a financial time series data prediction method and device and electronic equipment, and is applied to the technical field of financial data prediction. According to the financial time series data prediction method, the historical financial time series data are received and stored, the stored historical financial time series data are constructed into the financial time series data tensor, and the neighborhood set of the historical financial time series data is constructed; and finally, financial time series data prediction is carried out based on the financial time series data tensor and the neighborhood set, and a prediction result is obtained. According to the method, the potential dynamics of the financial time series data is effectively represented through the financial time series data tensor, the data driving neighborhood constructed through Gibbs sampling is used as a regularization item, the tensor hidden feature decomposition process is constrained, the hidden feature space is enabled to meet local smoothness while the global structure is kept, and the method is more efficient. Therefore, the prediction precision of the complex financial time series data is remarkably improved, and important help is provided for asset price prediction in the financial field.

This invention discloses a method and system for thyristor reliability assessment. First, based on performance degradation data, the initial estimated values ​​of the parameters to be estimated are calculated using the maximum likelihood estimation method. Then, the prior distribution of the parameters to be estimated is determined. Next, based on all experimental data, a Markov chain is constructed using the Gibbs sampling method to obtain a Monte Carlo sample set of the parameters to be estimated. Finally, the values ​​of the parameters to be estimated are estimated using the Monte Carlo sample set, and the reliability of the thyristor is assessed. This invention solves the problem of difficulty in fusing truncated lifetime data in thyristor reliability assessment. Compared with existing methods, this invention has higher data utilization and higher accuracy.

The invention discloses a user load curve analysis method and system based on Bayesian nonparametric clustering and a time covariance structure, and relates to the technical field of power system data analysis, and the method comprises the steps: collecting intelligent electric meter data, and carrying out the preprocessing of the original intelligent electric meter data; calculating a covariance matrix of the preprocessed data; calculating a mahalanobis distance between the load curves based on the covariance matrix; and constructing a distance dependent Chinese restaurant process model based on mahalanobis distance, performing link allocation and clustering parameter inference in combination with Gibbs sampling, and performing adaptive clustering to obtain a user load curve analysis result. According to the method, the problem of singularity of a covariance matrix under a high-dimensional small sample is solved by adopting Leidoit-Wolf shrinkage estimation, complete Bayesian inference is realized, the clustering number is adaptively determined, and manual intervention is not needed; while high clustering precision is maintained, calculation complexity is significantly reduced, and the method is suitable for large-scale actual data.

The present invention relates to a method for tracking the trajectories of multiple maneuvering targets using particle smoothing estimation with low computational complexity. Aiming at the application scenario of multiple maneuvering target tracking, a hybrid system model with unknown mixed states is established to identify the maneuvering modes and motion states of multiple maneuvering targets. A low-complexity smoothing calculation method is designed when the particle weights are not degraded, and the unknown maneuvering modes and motion states of the targets are estimated by combining Gibbs sampling and Markov chain Monte Carlo methods. Compared with the traditional particle smoothing algorithm, the method of the present invention improves the estimation accuracy of the target maneuvering mode and motion state by introducing a reference trajectory, and improves the computational efficiency by using a particle smoothing algorithm with low computational complexity. Therefore, the method can achieve the same tracking accuracy in a shorter time.

The present invention discloses a hyperspectral image denoising method based on Gaussian-Wishart prior, which includes the following steps: 1) Input the noisy hyperspectral image. W and H are the length and width of the spatial dimension of the hyperspectral image respectively, and S is the number of spectral bands; 2) Extract overlapping full-band image patches with a size of dw×dH×S, and use K-means++ to cluster the image patches into groups and input them into the non-parametric Bayesian CP decomposition model; 3) In the Bayesian model, derive the posterior probability formula of the parameters through the relationship between the conjugate prior and the likelihood function, and update the parameters to be estimated sequentially by Gibbs sampling; 4) Reconstruct the image group from the weight coefficients and factor matrices of CP decomposition; 5) Restore the image patches, and perform mean smoothing at the overlapping parts of the image patches to reconstruct the image of this iteration; 6) After balancing the results of this iteration and the original input image through the regularization coefficient, use them as the input image for the next iteration. After multiple iterations of steps 1-6, output the reconstruction result of the last iteration. The present invention does not require the noise variance as input and has good denoising effects and applicability.

The invention discloses a structure load and parameter joint identification method based on Gibbs sampling. The method comprises the following steps: S1, establishing a discrete state space model of a linear time-invariant dynamic system; s2, fitting an unknown external load by adopting an orthogonal polynomial, and representing the external load as a linear combination of an orthogonal polynomial basis function and a fitting coefficient; s3, defining an uncertainty parameter set, wherein the set comprises the fitting coefficient, the measurement noise, the unknown structure parameter and the fitting error; s4, constructing a multilayer Bayesian model based on the Bayesian theory, wherein the model comprises a likelihood function layer, a load prior model layer and hyper-parameters; s5, solving the multilayer Bayesian model by adopting a Gibbs sampling method, and obtaining posterior probability density distribution of each uncertainty parameter through iterative sampling; and S6, based on the posterior probability density distribution, obtaining an identification result of the external load and the unknown structure parameters. According to the method, the parameter uncertainty is considered, and the recognition precision and robustness of the dynamic load and parameters of the complex structure are improved.

The application belongs to the technical field of power systems, and provides a Monte Carlo-based reliability evaluation method for an IES-containing distribution network, comprising: firstly, generating a system fault state sequence covering three scenarios of a comprehensive energy system, a distribution network and simultaneous faults of both by using Markov chain Monte Carlo simulation combined with Gibbs sampling; secondly, constructing a differentiated load reduction model with tie-line power as a coupling variable for different fault types, and iteratively solving an optimal reduction scheme by using a hierarchical distributed optimization strategy and a target cascade analysis method; thirdly, aggregating and calculating expected power supply shortage, average power outage frequency and average power outage duration based on the scheme results to obtain three reliability indexes; and finally, judging the indexes by using a variance coefficient as a convergence criterion, outputting an evaluation result if the accuracy is met, or continuing iteration until convergence. The application significantly improves the accuracy and efficiency of the reliability evaluation of the IES-containing distribution network, and provides direct technical support for system configuration and dispatching strategy optimization.

This invention discloses a method and system for predicting the remaining lifespan of individual sensors based on Bayesian statistics, relating to the field of equipment health status monitoring and lifespan prediction technology. The invention provides a method comprising: establishing a general degradation model and prior distribution using historical degradation data; collecting monitoring data of a specific target sensor under real or accelerated stress in the field; updating the posterior distribution of model parameters based on Bayesian statistical inference and Gibbs sampling to generate a specific degradation model for that individual sensor; and calculating the remaining lifespan based on this specific model and a failure threshold. This invention achieves a breakthrough from "group lifespan assessment" to "accurate prediction of individual lifespan" through data-driven adaptive correction, significantly reducing over-maintenance costs and enhancing equipment operational safety.

The invention discloses a power distribution network net load uncertainty characterization method and system. The method comprises the steps that power grid data are collected, and a Dirichlet model is constructed; the model parameters are sampled from the conditional distribution and updated. And constructing a Gaussian mixture model based on data driving, and predicting conditional probability distribution of errors. And comprehensively evaluating the performance of the model by adopting five evaluation indexes. According to the power distribution network net load uncertainty characterization method and system provided by the invention, the uncertainty of the power distribution network net load can be more accurately characterized by constructing the Dirichlet model and the Gaussian mixture model based on data driving. The Dirichlet model is introduced to enhance the ability of the model to grasp data probability distribution, and the application of the GMM provides flexibility and can adapt to different data characteristics and changes. Model parameters are updated by adopting a Gibbs sampling method, so that the model can dynamically adapt to data changes, and the adaptability to the net load fluctuation of the power distribution network is improved. The five evaluation indexes provide comprehensive and reliable prediction results.

The application discloses a construction period reservoir bank slope deformation prediction method based on a BVAR model, and is characterized in that the following steps are specifically implemented: step 1, original slope deformation monitoring data are obtained as initial samples, and the original data are subjected to ADF testing; step 2, a BVAR model is constructed; step 3, a Gibbs sampler is used to obtain BVAR model parameters to be estimated and model prediction values; and step 4, final slope deformation prediction values and prediction intervals are obtained. The application considers uncertainty factors in slope deformation monitoring based on prediction intervals, models and predicts analyzes a slope deformation monitoring sequence, has good effects, and solves the problems of less construction period slope deformation monitoring data and no environmental quantity monitoring data.

The invention relates to an attention and conditional probability distribution-based electric vehicle charging data generation method and device, and a storage medium, and the method comprises the following steps: constructing a feature space of an electric vehicle charging behavior, and respectively aiming at a continuous value feature, a time correlation feature and a discrete value feature; performing feature-level deep neural network enhanced conditional probability modeling to obtain a conditional probability neural network model based on feature attention and residual blocks; acquiring electric vehicle charging behavior training data, and training the conditional probability neural network model by adopting a learning rate which is reduced along with the increase of a training round; and based on the trained conditional probability neural network model, Gibbs sampling is carried out under variable constraints, and electric vehicle charging behavior data conforming to physical constraints are screened. Compared with the prior art, the method has the advantages of integrating a multi-type probability distribution model and a degree neural network to dynamically predict probability distribution parameters and the like.

The invention discloses a user abnormal electricity utilization detection method and system based on energy internet big data. The method comprises the steps of performing anomaly detection on energy consumption data based on an isolated forest algorithm, screening abnormal data and marking missing values; sTL decomposition and cubic spline interpolation are adopted to restore the seasonal factor data, and an MICE multiple filling model is combined with a Gibbs sampling method to restore the comprehensive energy consumption data; carrying out dimension reduction processing on the repaired multi-dimensional energy consumption data by utilizing a KPCA (Kernel Principal Component Analysis) algorithm; and constructing a high-dimensional feature space anomaly detection model based on multivariate Gaussian distribution, calculating a probability density value of each sample, and comprehensively judging an abnormal power consumption behavior in combination with a user electric quantity fluctuation coefficient. The system comprises a data acquisition module, an anomaly detection module, a data cleaning module, a dimension reduction analysis module, an anomaly judgment module and a result output module. The method can effectively improve the cleaning precision and abnormity judgment accuracy of the multi-source energy consumption data, and is suitable for energy scheduling optimization and energy consumption abnormity early warning scenes.

The invention discloses a microgrid active power balance optimization method considering wind power and load time sequence correlation. According to the method, historical data of wind power output and load are combined, and probability distribution of wind power output and load in a same time period is simulated by applying a kernel density estimation method based on interval division; then establishing a joint probability distribution model of wind power and load by using a Copula function to quantify correlation between the wind power and the load, and obtaining wind power output and load samples with time sequence correlation based on Gibbs sampling; and finally, establishing a micro-grid linear programming model, and realizing active optimization of active balance of the micro-grid by optimizing an energy storage operation mode of the micro-grid by taking optimization of the overall economy and the wind power consumption level of the micro-grid as an optimization target. The method can provide a theoretical reference for active balance optimization scheduling of the micro-grid.

The application discloses a review usefulness prediction method considering seed information and causality, comprising the following steps: obtaining review texts and corresponding non-text data, thereby constructing a review data set D; obtaining user review preferences, thereby constructing a seed topic word distribution φ s ; constructing a Bayesian seed topic regression model based on the review data set D and the seed topic word distribution φ s ; initializing all parameters in steps S2 and S3 based on the review data set D, and performing parameter inference on a document topic distribution, a topic word distribution and a review usefulness prediction distribution by using an EM algorithm and a Gibbs sampling method. The application allows users to guide the theme discovery process by adding seed information, thereby quickly and accurately mining beneficial themes that are concerned by users, and meanwhile, the prediction accuracy is improved by jointly modeling the review texts and the review related data, so that the application can be widely applied to the fields of causality inference and linguistics.

The invention discloses an automobile competitive product and comparative attribute identification method based on large model enhancement, and the method comprises the steps: large model-driven information extraction, multi-view theme modeling and joint preference analysis, the method specifically comprises the following steps: 1) automatically extracting an automobile product and a feature description text from an evaluation copywriting by constructing a cue word guide large model, and carrying out standardized word segmentation; 2) on the basis of the de-duplicated products and the feature words, constructing a coupling LDA model, modeling automobile competitive product themes and product feature related themes, and depicting theme preference distribution of documents; and 3) inferring parameters by adopting collapse-type Gibbs sampling, calculating product and feature distribution under the theme, and mining preferences of competitive product combinations and comparative attributes of the competitive product combinations. According to the method, the problems of dependence on manually defined entities, sparse co-occurrence modes, difficulty in capturing fine-grained comparison dimensions and the like are solved, potential competitive product groups and key comparison attributes can be efficiently and accurately identified, and interpretable decision support is provided for enterprises to formulate differentiated product strategies.

The present invention relates to a method for mining spatiotemporal travel patterns of vehicles based on ST‑LDA, and belongs to the field of intelligent transportation technology. The method comprises the following steps: S1, data preparation: extracting a set of highway trips of a vehicle and converting it into a trip corpus; S2, constructing an ST‑LDA model: the ST‑LDA model comprises two parts: a polynomial distribution between travel patterns and spatiotemporal features, which increases the interpretability of the model from a semantic feature level; and a polynomial distribution between individual vehicles and travel patterns, which well reflects the diversified travel behaviors of individual vehicles; S3, model training: using the obtained trip words as input to train the ST‑LDA model, and using the folded Gibbs sampling method to solve the latent variables in the model to obtain travel pattern recognition results. The technical solution of the present invention reflects the diversity of individual travel behaviors, not only mines the travel patterns of vehicles from the two dimensions of time and space, but also increases the interpretability of the model, and has broad application prospects.

In the invention, a dynamic spectrum access (DSA) method for covert communication, which is inspired by Gibbs sampling, is provided. The method comprises the following steps: firstly, defining a covert communication index as KL divergence between user channel access distribution and uniform distribution; the lower the KL divergence is, the higher the difficulty of detecting or attacking the transmission channel by the attacker is. Secondly, inspired by Gibbs sampling, a rejection mechanism for rejecting access to an overused channel is provided; through the mode, the user is promoted to dynamically access a plurality of channels, and the probability that the user continuously accesses the same channel is reduced. And finally, combining a rejection mechanism with a Q-Learning reinforcement learning algorithm to form a new aperiodic frequency hopping DSA framework for covert communication. And the channel selection is continuously adjusted, so that the covert communication performance is improved. A simulation result shows that compared with a standard Q-Learning algorithm, under different user densities, the provided frequency hopping DSA method has the advantages that the KL divergence is remarkably reduced and the covert communication performance is enhanced while the good channel capacity is maintained.

Systems, methods and computer readable media relating to neuro-thermodynamic computers configured to implement hierarchical architecture, wherein the hierarchical architecture includes one or more layers of components, and wherein the hierarchical architecture is configured to perform Gibbs sampling and nested Gibbs sampling. For example, a block layer may include an energy based model (EBM) implemented using oscillators and couplings between oscillators. A chip layer may include multiple blocks coupled to each other using relay oscillators. A package layer may include multiple chips coupled to each other using additional relay oscillators.

The present invention provides a Bayesian tensor completion algorithm based on complex noise. For target data with missing values and complex noise, the target data is represented as a tensor, which is the sum of a tensor estimated value and noise. The CP decomposition is used to extract the low-rank information of the tensor, and Gibbs sampling is performed in combination with the framework of CP decomposition and Bayesian method. The tensor estimated value is obtained through iteration, and then the target data is simultaneously completed and denoised based on the tensor estimated value. Since the CP decomposition is used to fully exploit the low-rank information of the tensor, and the observed tensor information is fully utilized, and iterative sampling is performed, the completion algorithm can also achieve good completion and denoising for outliers and complex noise. It is a robust and effective tensor completion algorithm. Compared with the existing completion methods in the prior art, the completion algorithm of the present invention can obtain a more accurate tensor estimated value, so as to achieve more accurate completion and denoising of the target data.

Systems, methods and computer readable media relating to neuro-thermodynamic computers configured to implement hierarchical architecture, wherein the hierarchical architecture includes one or more layers of components, and wherein the hierarchical architecture is configured to perform Gibbs sampling and nested Gibbs sampling. For example, a block layer may include an energy based model (EBM) implemented using oscillators and couplings between oscillators. A chip layer may include multiple blocks coupled to each other using relay oscillators. A package layer may include multiple chips coupled to each other using additional relay oscillators.

The application relates to a sky-wave over-the-horizon radar coordinate registration method based on a reference source auxiliary, which comprises the following steps: firstly, acquiring prior information of ionospheric activity parameters in an estimated ionospheric region and reference source data; secondly, constructing a posterior distribution of the ionospheric activity parameters in the estimated ionospheric region under a Bayesian framework based on the prior information of the ionospheric activity parameters in the estimated ionospheric region and the reference source data; thirdly, solving a moment estimation value of the posterior distribution of the ionospheric activity parameters in the estimated ionospheric region based on a Markov chain, Gibbs sampling and importance sampling; fourthly, substituting the moment estimation value of the posterior distribution of the ionospheric activity parameters in the estimated ionospheric region into an international reference ionospheric model to obtain a posterior ionosphere; and finally, calculating an electromagnetic wave propagation path in the posterior ionosphere by using a three-dimensional ray tracing method to obtain a coordinate registration result of a to-be-positioned target. The application can significantly improve the coordinate registration precision and the sky-wave over-the-horizon radar target positioning precision.

The present application relates to the field of data processing, more particularly, the present application relates to a kind of industrial internet platform multi-source heterogeneous data fusion processing method and system, method includes: from multiple heterogeneous data sources collection multi-source text, pre-processing obtains global vocabulary;Based on industry standard classification tree, the shortest path edge number of word to each standard classification node is calculated;The distribution significance of word is calculated, and the path correlation density is obtained by combining structure attenuation factor, and then the guide coefficient of each text belonging to each standard classification node is constructed;Each standard classification node is set as a theme, and the guide coefficient is taken as priori constraint and is integrated into probability calculation in gibbs sampling process, to obtain the probability that text belongs to each theme;Through confidence threshold screening, the fusion label set of each text is output.The present application realizes the automatic alignment of multi-source heterogeneous data and industry standard classification system, improves the automation level and business availability of data fusion.

The present invention belongs to the field of electronic countermeasure technology, and specifically is a Gibbs sampling method for solving the problem of combined measurement. The purpose is to solve the correlation mismatch problem (called the combined measurement problem) caused by the fact that multiple targets may only produce a single measurement in a multi-target tracking application scenario, and to ensure that each target can still be tracked in this case. A traditional solution is to apply the idea of ​​grouping, and treat all targets that may produce combined measurements as a group for processing. The disadvantage of this method is that as the number of targets increases, there may be a computational explosion problem. In response to this, the present invention proposes applying the Gibbs sampling method to a labeled multi-Bernoulli (LMB) filter, and implementing it in a Gaussian mixture (GM) manner to alleviate the computational burden brought by the grouping method.

The application relates to a spatial plume feature clustering method based on a Dirichlet process mixture model, which comprises the following steps: acquiring plume features in a plume diffusion space by using a robot provided with a gas sensor and a positioning device, and constructing a plume feature set; clustering plume features with similar characteristics by using a Dirichlet process mixture model method to obtain a plume spatial distribution type; and designing a Collapsed Gibbs sampling inference parameter to output final spatial plume feature clustering data. The application can consider the complex conditions of plume distribution in a non-structural environment, and can realize rapid, accurate and comprehensive clustering of plume types in the space.