37 results about "Covariance function" patented technology

The invention discloses a distributed real-time monitoring and early warning system for a temperature field of a smelting furnace, and relates to the technical field of industrial process intelligent monitoring. The problems of accumulated measurement errors and non-stationary hotspot escape reconstruction hysteresis caused by static emissivity setting in an existing system are solved. Collecting multiband radiation intensity and voltage signals through time domain alignment of the multispectral sensor array and the thermocouple array; iterating emissivity parameters in real time by adopting a dynamic ash body spectrum ratio algorithm in combination with flue gas absorption characteristics; fusing non-contact and contact temperature measurement data based on weighted Kalman filtering and complementary filtering; constructing a space-time variable covariance function to carry out non-stationary Kriging interpolation; dynamically optimizing the local grid resolution by combining an adaptive grid module; the processing flow is accelerated through the parallel computing module; early warning is triggered based on abnormal probability judgment and is fed back to emissivity correction and grid optimization; according to the invention, the monitoring precision and real-time performance of the temperature field are obviously improved, and the risks of false alarm, missing alarm and equipment melting loss are effectively inhibited.

The invention discloses a matrix yaw system of a wind power plant. The matrix yaw system comprises a data acquisition module, a wind plant modeling module, a parameter extraction module and a yaw control module. The data acquisition module acquires a wind field original data set containing three-dimensional space coordinates and timestamps by using a multi-source sensor; the wind field modeling module calculates correlation between points by combining a covariance function through a Gaussian process regression algorithm, and constructs a three-dimensional dynamic wind field model; the parameter extraction module is used for extracting wind regime parameter vectors in the model by adopting a nearest neighbor interpolation algorithm on the basis of actual space coordinates of a fan; and the yaw control module utilizes a depth deterministic strategy gradient reinforcement learning model to generate a yaw angle adjustment instruction in combination with the wind regime parameter vector, the current yaw state of the fan and a preset maximum cumulative reward function. Through multi-module cooperation and intelligent algorithm optimization, accurate matching of wind field dynamic modeling and yaw control is achieved, and the energy efficiency and operation stability of the wind generating set are improved.

The invention relates to a GNSS (Global Navigation Satellite System) multi-path error correction method based on distance correlation modeling, which comprises the following steps of: resolving GNSS original data, and extracting to obtain a satellite position set and a residual error corresponding to the set; generating a uniformly distributed satellite position set on a unit hemispherical surface, calculating a variance-covariance matrix, and constructing a multi-path delay calculation model of the set; obtaining a currently observed to-be-calibrated satellite position set on a unit spherical surface, calculating a variance-covariance matrix, and constructing a multi-path delay calculation model of the set; the observation value of the set is corrected based on multi-path delay obtained through calculation of a multi-path delay calculation model of the set; the invention relates to an error correction method for modeling GNSS multi-path distance correlation characteristics by using least square configuration and a covariance function, which is suitable for multi-path suppression in high-precision GNSS positioning.

The invention discloses a lithium battery system state-of-charge estimation method based on a Hammerstein model, and the method comprises the steps: constructing a second-order RC circuit equation of a lithium battery, describing a dynamic linear module of the Hammerstein model through a noise transfer function model, and constructing a lithium battery system through a static nonlinear module of an adaptive neural fuzzy network; designing a Gaussian signal, inputting the Gaussian signal into the agent model of the lithium battery system to obtain corresponding Gaussian signal output, and decoupling the static nonlinear module and the dynamic linear block by using the covariance function characteristic of the Gaussian signal; identifying parameters of the noise transfer function model by using a least square method based on a covariance function, solving parameters of the adaptive neural fuzzy network by using a crown porcupine optimization algorithm, and updating the weight of the adaptive neural fuzzy network by using a stochastic gradient algorithm with a forgetting factor; and constructing an OCV-SOC curve of the open-circuit voltage and the state of charge by adopting polynomial fitting, and taking output obtained by the Hammerstein model as input of the polynomial fitting to obtain an estimated value of the state of charge SOC.

The invention discloses a structure parameter-load input joint identification method based on a Gaussian potential force model, and the method comprises the steps: obtaining a mass matrix, a stiffness matrix and a damping matrix, and constructing a state-space equation; modeling unknown load input into a zero-mean stationary Gaussian process with a specific covariance function to fuse prior information of the covariance function, and converting into an equivalent state-space equation; obtaining sparse dynamic response characteristics, and establishing a state space measurement equation; a structure state and load input are augmented into a state equation, the state equation and a measurement equation set are synthesized into a complete Gaussian process potential force model, unknown structure parameters are regarded as hyper-parameters, kernel function hyper-parameter optimization and structure parameter identification are achieved with the criterion of a maximized negative likelihood function, sequence reasoning is conducted on the Gaussian process potential force model, and the Gaussian process potential force model is obtained. Estimation of load input is obtained. The method has the advantages of being stable in parameter recognition result, high in precision, stable and reliable in load estimation, higher in robustness to model errors and measurement noise and the like.

The invention discloses a multi-period non-stationary multi-hydrological variable spatial valuation method, and relates to the technical field of hydrogeology. Comprising the steps of obtaining a univariate time sequence; combining the univariate time sequences of all observation stations in the drainage basin to obtain a multivariate random time sequence; calculating a long-term average level of each observation station through a space-time random function to obtain a long-term trend; subtracting the multivariable random time sequence of each observation station from the corresponding long-term trend to obtain a random residual error; according to the random residual error, determining a covariance function and a variation function between any two observation stations in the drainage basin; and on the basis, a multi-period non-stationary multivariable space valuation model is constructed by combining a multivariable Kriging model theory, and multi-hydrological variable valuation is performed on the drainage basin to be measured. According to the invention, internal correlation between variables can be revealed, and the prediction precision and reliability can be effectively improved.

The invention discloses a power prediction method for a wind power generation system based on a stacked sparse auto-encoder network Hammerstein model, and aims to solve the problems that only nonlinear mapping is modeled and dynamic characteristics of the system are neglected and parameter coupling of the Hammerstein model leads to complex identification in an existing method, the Hammerstein model is constructed, an ARMAX model is utilized to describe a dynamic linear module, and the dynamic linear module is used to predict the power of the wind power generation system based on the stacked sparse auto-encoder network Hammerstein model. A static nonlinear module is described by stacking the sparse auto-encoder network; designing a zero-mean Gaussian signal input proxy model, realizing series module decoupling based on covariance function characteristics, and eliminating parameter coupling; a self-adaptive multi-strategy grey wolf optimization algorithm is adopted to determine the number of neurons in a network hidden layer, training is performed in combination with a sparse criterion function, and the feature extraction capability is improved. According to the method, synchronous capture of static nonlinear and dynamic linear characteristics is realized, the calculation complexity is reduced, the model identification precision, prediction precision and robustness are improved, and the method is suitable for accurate prediction of the power of a wind power system.

The application discloses a large-scale space random variation characteristic generation method based on grid pseudo-point approximation, and belongs to the field of non-homogeneous material space variation characteristic generation. The method utilizes pseudo-points to reduce the size of a covariance matrix, simultaneously utilizes a linear conjugate gradient method to solve a self-covariance matrix of the grid pseudo-points, reduces the operation amount of self-covariance matrix inversion and the calculation amount of self-covariance matrix decomposition in a simulation process, and can greatly improve the generation efficiency of a Gaussian random field. The large-scale non-homogeneous material space variation characteristic generation model of the Gaussian random field based on grid pseudo-point approximation constructed by the method can realize the generation of a large-scale Gaussian random field based on grid pseudo-points, utilizes an equivalent self-covariance function of a sparse power expectation propagation method to derive a Gaussian random field posterior mean function and a self-covariance function based on grid pseudo-point approximation, adopts Kronecker operation to realize fast decomposition of a posterior self-covariance matrix, and greatly improves the generation efficiency of a multi-dimensional large-scale random field.

The invention discloses a fan icing power loss processing method and device. The fan icing power loss processing method comprises the steps that meteorological environment parameters and icing time are obtained; preprocessing the meteorological environment parameters and the icing time to obtain target meteorological environment parameters and target icing time; inputting the target meteorological environment parameters and the target icing time into a pre-trained multi-parameter dynamic prediction model, and predicting to obtain loss probability distribution of the icing fan; wherein the multi-parameter dynamic prediction model is constructed by Gaussian process regression; gaussian process regression is obtained by determining a mean value function and a covariance function; the multi-parameter dynamic prediction model is obtained by training historical meteorological environment parameters and historical icing time in advance; and determining deicing measures according to the loss probability distribution. Therefore, the timeliness and accuracy of fan loss prediction can be effectively improved through the multi-parameter dynamic prediction model, and early warning can be carried out in time according to loss probability distribution.

This invention provides an underdetermined mode identification method based on block term decomposition and adaptive kurtosis harmonic separation, belonging to the field of structural health monitoring and operating mode identification technology. The method acquires multi-channel vibration responses, calculates the covariance matrices under different time delays, and stacks them into a third-order tensor. Block term tensor decomposition is used to extract the time-domain autocovariance function sequence of each potential component. The natural frequencies and damping ratios of each component are initially estimated using local peak finding and logarithmic decay methods. The minimum truncation length is adaptively calculated based on the coupling relationship between period and damping ratio. Kurtosis values ​​are calculated for the truncated autocovariance sequence, and harmonic interference is eliminated based on a kurtosis threshold while retaining the true structural modes. Finally, mode shapes are extracted from the spatial block matrix of the retained components, outputting high-precision natural frequencies, damping ratios, and mode shapes. This invention can achieve accurate identification of dense modes and high-damped modes under complex operating conditions with severe underdeterminacy and harmonic interference, improving the robustness of operating mode parameter identification.

The invention relates to the field of machine learning, in particular to a residual service life prediction method and system based on a deep Gaussian process and meta-learning, a medium and equipment, and the method comprises the steps: obtaining original data to construct a multi-task data set; a multi-layer depth Gaussian process model is constructed based on a multi-task data set, a radial basis function kernel is used as a covariance function, and a multi-task Gaussian likelihood function is used for modeling uncertainty of RUL prediction; meta-training is carried out on a PHM data set, the model is optimized through internal circulation and external circulation, and an Adam optimizer is adopted to learn cross-task generalization weights; transferring the last layer of parameters and likelihood function parameters obtained by meta-training to a fan gearbox data set and an NASA aero-engine data set based on the same meta-learning model framework, and performing fine tuning on a support set of the test data set; and performing RUL prediction on the test sets of the fan gear data set and the NASA aero-engine gear data set by using the weights obtained after fine tuning, and outputting a prediction mean value, a variance, a confidence band and a prediction band.

The invention discloses a renewable energy source prediction scheduling method and system based on improved GPR adaptive generation, and the method comprises the steps: training a renewable energy source power prediction model based on the historical power data of renewable energy sources in combination with a multi-kernel covariance function improved Gaussian process regression algorithm; power prediction intervals of renewable energy sources under different confidence levels are adaptively generated based on the renewable energy source power prediction model, and opportunity constraints are introduced to combine the power prediction intervals with a robust concept to construct a power uncertainty set; and establishing a day-ahead rescheduling optimization model based on the power uncertainty set, and performing joint optimization with the day-ahead rescheduling optimization model, thereby realizing association of power prediction and output scheduling of the renewable energy sources, and improving accuracy of power prediction of the renewable energy sources and reliability of output scheduling. The method can be applied to the technical field of renewable energy prediction and scheduling.

Functions representing sequences of values of a time-series dataset measured within a particular time period are accessed. For a current time window of the time period, a first discretized covariance function is computed that represents a relationship between each value measured within the current time window. Eigenanalysis of the first covariance function is performed to estimate first eigenfunctions. The current time window is incremented to obtain a subsequent time window that overlaps a majority of the current time window at a shared window region. A second discretized covariance function is computed for the subsequent time window and eigenanalysis is performed to estimate second normalized eigenfunctions. An angle change is computed between a portion of the first normalized eigenfunctions and a corresponding portion of the second normalized eigenfunctions located within the shared window region. Based on the angle change, an anomaly detection output is generated.

The application discloses a postoperative CH prediction method and system for hyperhidrosis based on multiple factors, and the method comprises the following steps: acquiring multiple groups of postoperative historical data of patients, including target variables and multiple characteristic variables which have influence on postoperative CH of hyperhidrosis, and pre-processing the historical data; representing the historical data of each patient in the form of a multi-dimensional feature vector, and dividing a training set and a verification set; constructing a Gaussian regression model, and selecting a radial basis kernel and white noise kernel as a covariance function; optimizing hyperparameters of the covariance function on the training set by maximizing a log-likelihood function; and inputting a current patient feature vector into the optimized model, and outputting a prediction result. The method can take into account small sample adaptability, multiple factor interaction analysis and ordered classification prediction, and provides a scientific basis for clinical decision-making.

The invention relates to the field of agricultural meteorology early warning methods, in particular to an agricultural meteorology early warning method based on regional microclimate data interpolation and correction. An adversarial network model is constructed by introducing a topographic physical constraint loss function and an uncertainty quantization mechanism to generate a high-resolution, physically credible and static meteorological background field, so that the generated meteorological background field is ensured to be rich in space details and strictly follow basic physical rules such as a temperature vertical declining rate and the like; and meanwhile, the uncertainty of each lattice point can be self-evaluated and is used as prior information of a Bayesian layering dynamic correction model, a spatial covariance function fusing a geographic distance and a terrain distance is constructed in the Bayesian layering model, and the purpose that the spatial covariance function of the geographic distance and the terrain distance is fused in a complex terrain area with sparse meteorological stations is achieved. And meanwhile, a meteorological analysis field with high spatial resolution and high timeliness is obtained, so that the early warning accuracy and timeliness of sudden agricultural meteorological disasters in local areas such as frost, dry and hot air and the like are remarkably improved.

The present disclosure provides a method, device, electronic device, and storage medium for constructing a stratum model. The method comprises: estimating random medium statistical characteristic parameters for each unknown spatial point and each known spatial point based on seismic data; determining anisotropic spatial correlation lengths based on the position coordinates and random medium statistical characteristic parameters of each unknown spatial point and each known spatial point; substituting the determined anisotropic spatial correlation lengths into a spatial correlation function to obtain anisotropic spatial covariance function; for each unknown spatial point: determining anisotropic kriging weight coefficients for each known spatial point based on the determined anisotropic spatial covariance function; and determining predicted values ​​for each known spatial point based on the anisotropic kriging weight coefficients and observed values ​​of each known spatial point. This method can establish kriging interpolation results with smaller errors, more consistent with the actual spatial structural characteristics of the underground medium, and less uncertainty.

A method for obtaining a strain field of a key area of a shaft wall comprises the steps that sensing optical fibers are buried in concrete of a key well section of the inner wall of the shaft in the circumferential direction of the shaft; carrying out data acquisition on the sensing optical fiber of the key well section; interference of temperature on strain measurement is eliminated through regional temperature compensation; using a covariance function to represent the correlation of the spatial data; performing interpolation through known data points; and after the predicted values of all interpolation points are calculated, all interpolation results are drawn into a strain thermodynamic diagram of the key horizon. According to the invention, the high-density sensing optical fibers are arranged in the concrete of the inner wall of the 360-degree whole area of the key well section of the shaft, so that the strain field change data can be economically and feasibly obtained in real time, and the high-density space coverage of the shaft strain monitoring sensor at the key part under the condition of low cost is met; therefore, the precision of the well wall strain field of the local well section is improved, and the precise monitoring of the strain evolution of the potential fracture risk area is realized.

The application discloses an RCS full-probability size extrapolation method and system based on an electromagnetic scattering mechanism, and the method is as follows: 1, a backscattering electric field formula under different sizes is derived according to the electromagnetic scattering mechanism, and a target RCS calculation expression of an incident wave vector is obtained according to the definition of a radar cross section (RCS); the target RCS calculation expression is converted into a variant formula used for constructing a covariance function through a coefficient method and an integral mean value theorem; 2, the variant formula is inversely transformed and then is disassembled; 3, a polynomial covariance function is used to represent a polynomial part in the inversely transformed formula, and a spectral mixture covariance function is used to represent a cosine part in the inversely transformed formula; the two kinds of covariance functions are combined into an SPFPE covariance function; 4, the SPFPE covariance function is initialized by using a random number method; 5, hyperparameters of the SPFPE covariance function are optimized with a maximum log-likelihood as an optimization target, and an SPFPE-GPR method is obtained; 6, the target RCS is extrapolated by using the SPFPE-GPR method.

The invention relates to a laser peening inherent strain prediction method based on Gaussian process regression, which comprises the following steps: carrying out a laser peening orthogonal test, and establishing model training data; carrying out normalization processing on the training data by adopting a maximum and minimum normalization method; selecting a mean value function, a covariance function and a hyper-parameter optimization algorithm, and establishing a Gaussian process regression model; training the Gaussian process regression model by using the training data, and optimizing hyper-parameters of the Gaussian process regression model; and utilizing the trained Gaussian process regression model to predict inherent strain distribution under any process parameter combination so as to realize continuous correspondence between the process parameters and the inherent strain. According to the laser peening intrinsic strain prediction method based on Gaussian process regression, intrinsic strain distribution prediction under any technological parameter combination is achieved by establishing the Gaussian process regression model and optimizing hyper-parameters through training data, and the method has the advantages that the number of tests is reduced, and prediction efficiency and accuracy are improved.

The invention relates to the technical field of geophysics and geodetic survey data processing, and discloses a GNSS time sequence analysis and modeling method considering variable amplitude, and the method comprises the following steps: S1, obtaining a GNSS coordinate time sequence; s2, modeling the time sequence into a Gaussian process defined by a mean value function and a covariance function; s3, constructing a mean value function for describing a long-term linear trend; s4, constructing a product kernel formed by multiplying a periodic kernel and a non-periodic smooth kernel as a covariance function so as to unify the periodicity and time-varying amplitude of the modeling signal; s5, solving hyper-parameters in the model by adopting a maximum likelihood estimation method; and S6, decomposing the time sequence by using the optimized model to obtain a time-varying amplitude periodic signal. According to the method, modeling can be integrally carried out on the periodic signal and the time-varying amplitude of the periodic signal by constructing the Gaussian process product kernel, so that accurate separation of signal components is realized.

The present application relates to geophysics and geodetic data processing technical field, disclose the GNSS time series analysis and modeling method considering variable amplitude, the method comprises the following steps: S1, obtain the GNSS coordinate time series;S2, time series is modeled as the Gaussian process defined by mean function and covariance function;S3, construct the mean function describing long-term linear trend;S4, construct the product kernel by the periodic kernel and the non-periodic smooth kernel multiplication as the covariance function, to unify the periodicity and time-varying amplitude of the signal modeling;S5, the maximum likelihood estimation method is used to solve the hyperparameter in model;S6, the time series is decomposed by using the optimized model, and the time-varying amplitude periodic signal is obtained.The present application can integrally model the periodic signal and its time-varying amplitude by constructing the Gaussian process product kernel, so as to realize the accurate separation of signal component.

The invention discloses a cutter wear and machining quality multi-task prediction method based on Gaussian process regression, and belongs to the technical field of machining. The method comprises the steps that a multi-task data set is constructed and preprocessed; extracting time domain, frequency domain and time-frequency domain characteristics of the main shaft current data and standardizing the time domain and the frequency domain characteristics; constructing a Gaussian process regression model, and calculating joint probability distribution of the training set and the test set by using a neural network covariance function; a conjugate gradient method is adopted to optimize hyper-parameters, model training is completed, and combined prediction of tool wear and machining quality is achieved. According to the method, double-target relevance is fused through a multi-task learning framework, probability prediction is achieved through Gaussian process regression, and the method has the advantages of being high in prediction precision, high in reliability and good in practicability and is suitable for cutter state monitoring and quality control in intelligent manufacturing.

This invention relates to the field of steel rolling, specifically disclosing a method, system, computer equipment, and medium for predicting rail rolling force. The method includes: collecting on-site data of the target rail production line; selecting multiple reduction parameters from the third pass as model input factors; selecting corresponding rolling force parameters as model output factors; and dividing the data into training and testing sets; constructing a Gaussian process regression model, defined as f(x) ~ GP[m(x), k(x, x')], where m(x) is the mean function, k(x, x') is the covariance function, and the observation equation of the model is y = f(x) + ε, where y is the model output factor, x and x' are the model input factors, ε is Gaussian white noise, and ε ~ N(0, σ n ²), σ n ² represents the noise variance; the Gaussian process regression model is trained and optimized using the training dataset to obtain a trained prediction model; the prediction accuracy of the trained prediction model is verified using the test set; if the prediction accuracy reaches a threshold, the prediction model is used to predict the rail rolling force.

This invention provides a configuration method for RAG systems based on multi-objective Bayesian optimization, belonging to the technical field of RAG systems. This invention obtains an initial observation dataset by randomly sampling initial configurations from a structured search space using a multi-objective evaluation function. For three performance indicators, independent Gaussian process models are established to fit the mean and covariance functions of the objective function. Based on the current Pareto front and the posterior prediction distribution of the Gaussian process model, the expected hypervolume improvement acquisition function is calculated, and the configuration with the largest improvement value is selected for iterative evaluation and updating. Finally, non-dominated solutions are identified to form the Pareto optimal configuration set. This invention solves the technical problem of complex configuration parameter space and conflicts between multiple performance indicators in retrieval-enhanced generation systems, which makes it difficult to automatically obtain the Pareto optimal configuration set.

The invention discloses a standard cell library file automatic generation method based on a Gaussian process. The method comprises the following steps: extracting Liberty data; classification is carried out according to the size of Liberty training data, and a direct lookup table prediction method or an index-based point-by-point enhancement prediction method is selected to carry out prediction; inputting the training data set into a Gaussian process model for modeling, and selecting a radial basis function kernel as a covariance function; for the PVT of the prediction target, selecting a direct lookup table prediction method or an index-based point-by-point enhancement prediction method to carry out corresponding data format processing; inputting the coded target input features into a trained Gaussian process model for prediction, and obtaining a corresponding target output value and a corresponding prediction variance; related parameters in the lookup table are updated until the prediction tasks of all the arc structures in the standard cell library are completed, and the complete lookup table automatic generation process is achieved.

A computer-implemented method for enabling control or monitoring of a computer-controlled entity operating in an environment by predicting a future state of the computer-controlled entity and / or its environment using sensor data which is indicative of a current state of the computer-controlled entity and / or its environment. The method includes using a first neural network for approximating a drift component of a stochastic differential equation and a second neural network for approximating a diffusion component of the stochastic differential equation, and discretizing the stochastic differential equation into time steps, and obtaining time-evolving mean and covariance functions based on the discretization and determining a probability distribution of a second state of the computer-controlled entity and / or its environment therefrom. The control of the computer-controlled entity may thus be enhanced and made more efficient and reliable using the uncertainty information available from the determined probability distribution.

The invention provides a foundation pit settlement space reasoning method based on an improved space-time Kriging model. The method specifically comprises the following steps: S1, collecting data and establishing a multi-dimensional and staged database structure; s2, performing segmentation processing on a construction period by using the collected data, and establishing a set of corresponding space-time covariance functions for each stage; s3, piecewise splicing the spatio-temporal covariance functions of the multiple stages to establish a spatio-temporal joint covariance structure with the geological disturbance sensing capability; s4, combining the covariance matrix and the covariance vector by using the defined space-time covariance function; and S5, defining settlement space reasoning, and predicting a settlement value. The method can effectively cope with sudden settlement change caused by a construction stage, a geological section and the like, has higher prediction precision and stability, realizes unified modeling of different stages of the whole construction process, and remarkably improves the adaptability of the model to time sequence evolution and physical field response.

The present invention relates to the technical field of sensor layout, and particularly to a multi-sensor layout method and device based on Gaussian process. The method includes: S1. Modeling the monitoring situation of sensors using a univariate sensor spatio-temporal model based on Gaussian process; S2. Transitioning the univariate sensor model to the multi-variable sensor situation to obtain a multi-variable sensor spatio-temporal model; S3. Constructing and simplifying a multi-sensor layout objective function based on the multi-variable sensor spatio-temporal model; S4. Further simplifying the multi-sensor layout objective function using a spatio-temporally separable covariance function; S5. Solving the simplified multi-sensor layout objective function using a greedy algorithm to obtain the optimal sensor layout. The present invention can effectively optimize the multi-sensor layout, has the best prediction effect on unmonitored positions, requires fewer sensors, and significantly reduces the calculation time required to obtain the layout result.

The invention discloses a hand perspiration postoperative CH prediction method and system based on multiple factors, and the method comprises the following steps: obtaining multiple groups of postoperative historical data of a patient, including a target variable and multiple characteristic variables influencing the hand perspiration postoperative CH, and carrying out the preprocessing of the historical data; representing the historical data of each patient in a multi-dimensional feature vector form, and dividing the historical data into a training set and a verification set; constructing a Gaussian regression model, and selecting a radial basis kernel and a white noise kernel as covariance functions; a log-likelihood function is maximized, and hyper-parameters of the covariance function are optimized on the training set; and inputting the feature vector of the current patient into the optimized model, and outputting a prediction result. According to the method, small sample adaptability, multi-factor interaction analysis and ordered classification prediction can be considered, and a scientific basis is provided for clinical decision making.

Computer implemented methods, systems, and computer readable medium are provided for performing causal inference analyses to determine the more effective treatment among alternative treatments in the healthcare setting using real world observational data. Both binary treatment and adaptive treatment strategies are considered in the analysis. The methods comprise generating a Bayesian marginal structural model and performing a single step of Bayesian regression that incorporates matching, weighting, and estimation processes and in which the matching process is performed using a Guassian process (“GP”) prior covariance function.