116 results about "Covariate" patented technology

A system and method for dynamic model training of a predictive machine learning model accesses data points of a training dataset including a plurality of model covariates. The predictive machine learning model is configured to generate an output including a risk rank representative of a mortality risk. The method selects one of the covariates and generates a historical data distribution for the selected covariate by applying the model to the training dataset including a plurality of historical application records. The method determines a current data distribution for the selected covariate. When comparison of the current data distribution with the historical data distribution indicates a data distribution shift exceeding a predetermined threshold, the method automatically updates parameters of the predictive machine learning model and retrains the predictive machine learning model using the updated parameters. Comparison of the current data distribution with the historical data distribution may employ covariate shift adaptation.

A state prediction method and apparatus, a computer device, a storage medium, and a computer program product. The method comprises: obtaining data for detection, wherein the data for detection comprises a fundus image and covariate data, and the covariate data is variable data for assisting in identifying a target lesion; on the basis of a preset feature extraction model, performing feature extraction on the fundus image and the covariate data respectively to obtain an image feature vector, a first weight corresponding to the image feature vector, a covariate feature vector, and a second weight corresponding to the covariate feature vector; and processing the image feature vector and the covariate feature vector on the basis of the first weight, the second weight, and a preset hybrid model to obtain a target state prediction result, wherein the preset hybrid model is constructed on the basis of the image feature vector and the covariate feature vector that separately satisfy a maximum likelihood function condition and under the conditions where the data for detection has censored data or does not have censored data.

A method may include: (1) receiving reference data comprising input texts and corresponding labels; (2) training a covariate drift detector comprising a syntactic drift detector and a semantic draft detector with the reference data; (3) training a concept drift detector comprising a plurality of classifiers with the reference data; (4) receiving production data comprising a plurality of instances; (5) determining that the production data has drifted; (6) calculating similarity scores between each instance of the production data and the reference data; (7) detecting concept drift by generating a predictive distribution using the plurality of classifiers and calculating an entropy of the predictive distribution; (8) identifying final drifted instances from the covariate drifted instances and the concept drifted instances; and (9) receiving updated labels for the final drifted instances.

The invention relates to the field of flood prevention water level early warning, and particularly discloses a reservoir flood prevention water level early warning system and method.The reservoir flood prevention water level early warning method comprises the steps that firstly, rainfall data along an upstream river are obtained in real time, and the water level change conditions of a reservoir inlet and a key river reach are monitored; performing data analysis on the collected rainfall data and water level data by adopting an artificial intelligence technology based on deep learning so as to capture space-time correlation characteristics among the rainfall data of each monitoring point along the river and space-time correlation characteristics among the water level data of each monitoring point in a water level monitoring area, and taking the rainfall data as a main variable so as to obtain a time-space correlation characteristic of the rainfall data of each monitoring point in the water level monitoring area; the water level data are used as covariables, and the influence mechanism of rainfall change on water level change is revealed by performing time sequence interaction analysis on the water level data and the covariables, so that the prediction of the reservoir water level change trend is realized. Therefore, the response speed and accuracy of the flood prevention water level early warning of the reservoir can be effectively improved, the dependence on human resources is reduced, and meanwhile, the maintenance cost of a traditional hydrological model is reduced.

Methods for designing a study, e.g., randomized controlled trial (RCT), and methods for evaluating sample size in an uncommenced or ongoing study are provided. Also provided are methods for conducting co-variate adjustment using covariates (e.g., prognostic covariates) obtained by deep learning models in a study.

The invention discloses a method for observing local heavy rainfall in an alpine region, and particularly relates to the technical field of rainfall observation. In order to solve the problem of systematic prediction deviation caused by the fact that a traditional model mistakenly takes the altitude as a positive correlation covariable in a mountain leeside slope or a sinking airflow control area, a local slope direction difference index and a water vapor potential disturbance index are innovatively introduced as alternative covariables, and the actual relation between the altitude and rainfall is dynamically judged through multivariate correlation analysis. Therefore, the covariable setting of the common Kriging model is flexibly adjusted; through residual analysis and systematic deviation value calculation, the method further achieves the recognition and spatial correction of rainfall hot spots and microclimate characteristics, and remarkably improves the accuracy of interpolation prediction and the reliability of regional climate risk recognition.

The invention discloses an electric power total-factor unified load prediction method and system based on a time sequence large model, and relates to the technical field of machine learning, and the method comprises the steps: triggering a prediction process through a timed task, and obtaining historical load data and external covariable data; constructing a time sequence sample required by training and prediction according to a time window, and performing batch pulling and processing according to a fixed number of days when the data size exceeds a single-batch threshold value; performing data standardization and data cleaning on the data, and generating structured time sequence input; loading a time sequence large model as a unified prediction engine, and inputting a load sequence and an external covariable into a covariable fusion component for collaborative modeling; and outputting fine-grained prediction results of the electric power elements in the target time period at the same time under a single model framework, and post-processing and storing the prediction results. Through the technical scheme of the invention, the model fragmentation and maintenance cost is reduced, the generalization and stability are improved, and the operation stability and the engineering availability are improved.

A method and an apparatus for forecasting a future time target variate, a computer device, and a storage medium are disclosed. Specifically, a method for forecasting a future time target variate is disclosed. The method includes: dividing a history target variate and covariates of target variates into a plurality of patches channel-wise, and performing linear embedding, wherein the covariates of target variates comprise a covariate of the history target variate and a covariate of the future time target variate; performing position embedding on a plurality of tokens and a learnable forecasting token; wherein the plurality of tokens are linear embedded from the plurality of patches; inputting the plurality of tokens and the learnable forecasting token into an encoder; and forecasting and outputting the future time target variate based on the encoder and the learnable forecasting token. According to the foregoing manner, in a case of zero-shot training, the future time target variate can be accurately forecast through limited history target variates and covariate information of the target variates, thereby having a large inspiration effect on the field of basic models in time series forecasting.

The invention mainly relates to the technical field of hydrological disaster assessment, in order to accurately predict the flood risk of a variable environment drainage basin, the invention provides an intelligent prediction method for the flood risk under climate change, and the core idea of the method is that the hydrological process of the drainage basin in the future is simulated and studied based on a global climate mode and a hydrological-deep learning coupling model; feature parameters of a Budyko formula serve as covariables, a time-varying Copula function is adopted to consider hydrological series inconsistency under the influence of climate change and human activities, a joint probability distribution function of flood duration and flood volume is constructed, and the most probable combination of the flood duration and the flood volume is solved; according to the method, future flood risk changes are assessed according to the joint recurrence period difference of the most probable combination of flood duration and flood volume in historical and future periods, the social and economic exposure degree caused by flood risk increase in the future is predicted, the method has high physical significance and statistical basis, and the change characteristics of future flood driven by water circulation variation can be effectively represented; and the flood risk prediction accuracy is improved.

The invention discloses a plateau rainfall fusion method and a plateau rainfall fusion system based on multi-source meteorological collaboration, and relates to the technical field of plateau rainfall fusion methods, and the method comprises the steps: obtaining a multi-source rainfall product, a meteorological covariable and high-resolution digital elevation model data, carrying out the time-space alignment and normalization processing of the multi-source rainfall product and the meteorological covariable, and obtaining the high-resolution digital elevation model data; forming a multi-source meteorological data set; based on physical variables in the multi-source meteorological data set, constructing four physical process links of water vapor transportation, terrain uplift, convection triggering and cloud microphysics, generating attention weight vectors through sub attention branches corresponding to the links, obtaining a causal attention weight matrix after weighted fusion, and performing weighted fusion on multi-source rainfall products to obtain a multi-source rainfall data set; generating a causal fusion feature map; wavelet decomposition is carried out on the causal fusion feature map and meteorological variables, large-scale components and small-scale components are separated out, and meanwhile the terrain uplift rate and the included angle between the wind direction and the slope direction are calculated according to the digital elevation model data and the wind field components.

The invention relates to a covariable time sequence prediction method based on multi-scale decoupling. The method comprises the following steps: acquiring a target variable historical sequence X; carrying out average pooling down-sampling processing to obtain target variable input of multiple sampling scales; performing multi-scale analysis to obtain target variable multi-scale mixed representation; and obtaining a covariable Z, performing time sequence decomposition on the multi-scale mixed representation of the target variable to obtain multi-scale periodic term and trend term representation, modeling the influence of the covariable Z on the historical sequence X of the target variable, and obtaining a prediction result Y of a future sequence. The method has the beneficial effects that a multi-scale analysis and time sequence decomposition technology is utilized, a time sequence multi-level dominant change mode is accurately modeled, time sequence components are decoupled to refine the difference influence of a covariable on different change modes of a target variable, the modeling bottleneck of an existing method on time sequence modeling complexity and covariable influence heterogeneity is broken through, and the time sequence modeling complexity and covariable influence heterogeneity are improved. The defects of an existing covariable time sequence prediction method in target variable and covariable information modeling are overcome.

The invention relates to a rainfall erosivity inversion method integrating crowd-source satellite rainfall data, which comprises the following steps: acquiring data such as a heterogenous remote sensing rainfall product and a DEM on a GEE remote sensing cloud platform, and acquiring characteristic variables such as characteristic multisource rainfall, sea and land positions and terrain after preprocessing such as numerical extraction, projection transformation and grid resampling; the method comprises the following steps: on the basis of meteorological station space distribution vector data, extracting characteristic variable information corresponding to a corresponding point as a covariable, and taking rainfall erosivity obtained by calculating rainfall data actually observed by a meteorological station as a dependent variable, so as to construct sample data; the sample set is randomly divided into a training set and a test set, and the training set is used for constructing a deep forest regression model for inversion of rainfall erosivity and performing spatial inversion mapping; and then verifying the rainfall erosivity inversion result by using the verification set. According to the method, high-precision inversion and mapping can be carried out on rainfall erosivity space distribution of a large-scale region and even a global scale.

Conventional forecast models assume that the underlying data are stationary. In the case of non-stationary data, the conventional forecast model must be increased in complexity, or otherwise, must be frequently retrained. Embodiments are disclosed of a forecast model that accounts for non-stationary data, without increased complexity and without an increase in the frequency of retraining, by recasting the forecasting problem as a matter of tracking differentials in the data. In particular, variables (e.g., covariates) are input into differential determinations and / or intermediate machine-learning models to determine differences in past and forecasted values of a plurality of features. These differences are then input into a machine- learning model to predict a change in the value of the target, which is aggregated with a past value of the target to produce a forecasted value of the target.

The invention discloses a wind power prediction covariable offset adaptive method based on a conditional energy model. According to the method, the wind power generation power prediction model is constructed by utilizing the gated cycle unit network, and offline training of the wind power generation power prediction model is completed by adopting a sample weighting mechanism, so that the robustness of the wind power generation power prediction model to distribution change is enhanced. A conditional de-noising score matching strategy is adopted to learn the distribution difference of data in a training stage and a prediction stage through a conditional energy model, and a sample weight used for measuring the covariable offset degree is obtained based on the model. Data samples flowing in real time are stored in a replay buffer area, incremental learning is carried out on a condition energy model and a wind power generation prediction model through an online updating mechanism, and the prediction performance is kept stable. The method can effectively improve the power prediction precision and operation scheduling capability of the wind power plant under complex meteorological conditions, and has good engineering practical value and deployment flexibility.

The invention belongs to the field of water environment monitoring and water quality prediction, and particularly discloses a causal discovery and deep learning coupled water quality prediction method and system, and the method comprises the steps: carrying out the causal screening of dynamic covariables through employing a causal discovery algorithm based on a neural network, and recognizing causal dynamic covariables; and inputting the causal dynamic covariable, the multi-scale water quality index characteristics and the static covariable data into a trained probability time sequence prediction model, and outputting a probabilistic prediction result of the water quality index concentration of the target water area in a plurality of time steps in the future. According to the method, pseudo-correlation variables are eliminated, the non-stationarity is processed through multi-scale analysis, purer and richer multi-scale information is provided for the probability time sequence prediction model, and the accuracy of point prediction is remarkably improved.

The present invention discloses a multi-source satellite precipitation product fusion method and device combining sliding quadruple permutation and random forest spatial interpolation. The method includes: obtaining multi-source satellite precipitation products, multi-source environmental covariate data, and measured station daily precipitation data, and unifying the spatio-temporal resolution; obtaining the multi-source precipitation product sequences of each grid point on the basin surface, combining any four sequences to construct a sample combination set, estimating the sequence error variance and error covariance of each sliding window period based on sliding quadruple permutation, constructing an error matrix accordingly, calculating the weights of each product, and obtaining the satellite precipitation data after weighted average; constructing a sample set and dividing it into training and validation samples, and training the random forest spatial interpolation model; predicting the precipitation of grid points according to the trained model, and integrating the predicted precipitation sequences of each grid point to form a set of precipitation product data. The present invention combines the sliding quadruple permutation analysis technology with the random forest spatial interpolation model to improve the fusion accuracy of satellite precipitation products.

The application discloses a data classification prediction method based on covariate and semantic offset and related devices, relates to the technical field of graph data machine learning and data classification prediction, and comprises the following steps: obtaining labeled in-distribution graph data and unlabeled open-world graph data, and uniformly performing standardization processing to obtain standardized graph data; constructing a graph learning model, and outputting a logit based on the graph learning model; calculating an energy score based on the logit, and mapping to obtain a semantic consistency estimation value; constructing a total loss function comprising an in-distribution classification loss, an in-distribution energy upper bound constraint and an open-world energy lower bound constraint, and training a model; obtaining open-world graph data to be measured, inputting standardized graph data of the open-world graph data to be measured into the trained graph learning model, calculating an energy score based on an output logit, combining a preset energy threshold, and performing classification prediction or rejection prediction. The application can accurately distinguish covariate offset and semantic offset, and improves the accuracy of data classification prediction.

The application is a kind of double robust causal dose-response curve estimation method based on high-dimensional independent variables, comprising the following steps: 1) constructing a new target function based on the modified adaptive LASSO method to realize dimension reduction; 2) constructing a double weighted distance correlation coefficient DWDC to select the optimal lambda n ; 3) using DR estimator to estimate the dose-response curve. The method mainly aims at the characteristics of the potential confounding variable set contained in the health medical big data, such as high dimension, nonlinear relationship between health outcome and (or) exposure factor, etc. In the framework of GOAL method, a double robust estimation method of causal dose-response curve is provided, which is called GOALDeR method. A large number of statistical simulations show that the estimation accuracy and precision of GOALDeR method are better than those of existing methods, and the method has double robustness and is less affected by the correlation structure between covariates and the n / p (sample size / covariate dimension) ratio.

The present invention discloses a method, device, and medium for predicting transpiration of medicinal crops, including the following specific steps: collecting transpiration-related environmental data, preprocessing the data, and determining key influencing factors of transpiration; constructing a CNN-W model and a CNN-S model based on the preprocessed data, and determining a feature matrix in combination with the key influencing factors of transpiration, wherein the CNN-W model is used to capture the time dependency of meteorological environmental data, and the CNN-S model is used to capture the time dependency of soil environmental data; constructing a global encoder and a local encoder, extracting time series features based on the feature matrix; fusing the extracted time series features, and predicting transpiration based on the fused features. By fusing and outputting the time series features and subsequently extracting features based on time-dependent covariates, the autocorrelation of the time series data is effectively captured, and the dependency between transpiration and environmental influencing factors is explored, thereby improving the accuracy and stability of transpiration prediction.

The application relates to a multi-source covariate irrigation load short-period prediction method, a device and a medium, and relates to the fields of power system load prediction and intelligent analysis of agricultural irrigation energy. The application is to solve the problems that the existing irrigation load short-period prediction method has limited modeling capability for exogenous factors, cannot effectively utilize user difference information, and is prone to lag or drift in prediction. The application performs correlation evaluation on candidate multi-source covariates and historical global irrigation load, and then selects effective covariates according to the evaluation results; extracts a user feature vector based on the effective covariates; constructs a historical input sequence by combining the historical global irrigation load and the effective covariates, and constructs a future known covariate by combining the known future prior information in the prediction interval; constructs input data by combining the user feature vector, the historical input sequence and the future known covariate; inputs the input data into a load prediction model adopting a TimeXer framework, and outputs an irrigation load prediction result in the prediction interval.

The invention provides a continuous intervention effect prediction method and device, a training method and device, equipment and a medium, and relates to the technical field of computers, in particular to artificial intelligence, big data and deep learning technologies. Comprising the following steps: performing multi-head self-attention interaction on covariables to obtain covariable embedding; embedding the covariable and inputting the processing variable into a countercurrent network, wherein the countercurrent network is used for estimating conditional distribution of the processing variable under the covariable condition; mapping the processing variables into processing vectors through a smooth basis function, and generating network parameters of each layer in the main network according to different processing variables in the processing vectors; the covariable embedding and processing vector is input into the main network, and the main network is used for calculating fusion features based on the network parameters of each layer according to the covariable embedding and processing vector and outputting an initial prediction result according to the fusion features; and performing weighted calculation on the initial prediction result by using conditional distribution to obtain a target prediction result of the dependent variable under continuous intervention of the covariable and the processing variable.

A computer-implemented method for producing probabilistic forecasts of extreme values. The method comprises obtaining input data comprising a plurality of signals of interest and a plurality of covariates associated therewith, each covariate of the plurality of covariates having an associated data type. The method further comprises performing a first forecast based on the input data. Performing the first forecast comprises: obtaining one or more trained machine learning models, each trained machine learning model of the one or more trained machine learning models having been trained to map one or more covariates of a respective data type to one or more surrogate covariates; mapping, using the one or more trained machine learning models and the input data, the plurality of covariates to one or more surrogate covariates, the one or more surrogate covariates corresponding to a compressed representation of the input data; fitting a statistical model of extremes to the plurality of signals of interest and the one or more surrogate covariates thereby generating a fitted statistical model of extremes, the statistical model of extremes being defined according to a predetermined distribution having a plurality of parameters; and obtaining a probabilistic forecast of future extreme values based on the fitted statistical model of extremes for one or more future time steps. The method further comprises causing control of a controllable system based at least in part on the probabilistic forecast of future extremes.

The invention belongs to the field of intelligent monitoring, and discloses an active and passive fusion clean room environment intelligent monitoring method, which constructs an active and passive fusion monitoring system based on covariable statistics. A two-parameter variation function is established by introducing real-time wind field difference as a key covariable, and the defect that a traditional model ignores flow field dynamics is overcome; a comprehensive blind area guiding index is constructed by using a deviation between a basic information field generated by a fixed sensor and a correction information field formed by robot fusion data and combining an inherent coverage risk and a joint space disparity degree, and an absolute monitoring blind area is accurately identified; therefore, the control mode of fixed route inspection to blind area driving type active detection is converted. According to the method, on the premise that the hardware cost is not increased, the full-domain monitoring coverage rate, precision and sudden pollution response speed of the clean room are remarkably improved.

An information processing apparatus according to an aspect of the present invention includes a processor and a storage. The storage includes a first storage area and a second storage area. The first storage area stores event occurrence data related to the occurrence position of the event to be analyzed. The second storage area stores covariate data observed in the observation region of the event. The processor includes a kernel function designation unit, a calculation method designation unit, and an intensity function estimation unit. The kernel function designation unit receives designation of a kernel function in the Gaussian process. The calculation method designation unit receives designation of a calculation method of an equivalent kernel function. The intensity function estimation unit calculates an equivalent kernel function on the basis of the designated kernel function and calculation method, and estimates the intensity function for the covariate using the calculated equivalent kernel function.

Various embodiments can reduce variance in a target metric (e.g., experiment outcome). Embodiments can use historical pre-experiment outcomes to predict a metric (forecasts) that is expected for a future measurement time. The forecasts can then be used as a covariate to reduce the variance of the target metric. When predicting forecasts, various embodiments can use an automation pipeline that can generate better and quicker forecasts. When there are multiple covariates that may be considered to reduce variance in the target metric, various embodiments can use a closed from solution for determining optimal coefficient of each covariate.

The invention discloses a visibility time sequence prediction method based on a DeepAR model and a weather prediction field, mainly relates to the technical field of visibility time sequence prediction, and is used for solving the problems that in an existing scheme, weather prediction field feature fusion is insufficient, only a single value is output, and weather prediction field features cannot be spliced by an existing DeepAR model. Comprising the steps of generating a comprehensive feature vector according to a feature result, historical visibility time sequence observation data and a preset additional covariable, inputting the comprehensive feature vector into a hidden layer of an initial DeepAR model, and completing construction of a future meteorological field extraction module in the DeepAR model; a DeepAR model with a future meteorological field extraction module is trained and optimized based on historical visibility time sequence observation data, and a trained DeepAR model is obtained; and performing visibility time sequence prediction by using the trained DeepAR model.

The invention provides a dynamic Copula extreme wave energy prediction method based on wind speed covariant full-link driving. The dynamic Copula extreme wave energy prediction method is applied to safety evaluation of ocean engineering and a wave energy power generation system. Firstly, B-spline-logarithmic normal edge distribution with wind speed as a covariable is constructed through data preprocessing, and dynamic changes of wave height and wave period parameters along with the wind speed are described; secondly, selecting an optimal Copula function, coupling a Copula parameter with the wind speed through Logistic mapping, and establishing a dynamic dependency structure model; then, dividing a low wind speed interval, a medium wind speed interval and a high wind speed interval, and verifying the fitting precision of the model in each interval and extreme wave energy over-limit probability prediction performance; and finally, integrating edge distribution and dynamic Copula, and constructing a wind speed driven wave element joint probability prediction model. Compared with a traditional static model, the method can accurately capture the regulation and control effect of the wind speed on the wave height-wave period dependency relationship, remarkably improves the prediction accuracy of an extreme wave energy event, and provides reliable support for ocean engineering safety and wave energy power station operation.

A process for determining direct effect modifiers (DEMs) for an exposure of interest can include determining pre-treatment variables corresponding to characteristics of different subsets of an observed population for the exposure of interest, each individual of the observed population having a respective exposure to the exposure of interest and a corresponding outcome. A predicted conditional average treatment effect (CATE) can be determined for the exposure of interest on the observed population. Each variable in a matrix of covariates selected from the pre-treatment variables can be orthogonalized to the remaining covariates. Regression can be performed on the predicted CATE to determine additional residuals for each pre-treatment variable. Variables with additional residuals significantly associated with CATE are inferred to be DEMs.

An estimation device according to one aspect of the present disclosure comprises: an input unit that inputs observation data including a covariate in a predetermined space and an occurrence position of an event observed in the space, and kernel function data related to a kernel function used in a Gaussian process; and an estimation unit that estimates, on the basis of the observation data and the kernel function data, a posterior prediction distribution followed by an intensity function that outputs an occurrence probability of the event with the covariate as an input. The estimation unit approximates a theoretical lower limit value of a peripheral likelihood for the observation data as a function of a hyperparameter of the Gaussian process and maximizes the theoretical lower limit value using a steepest descent method, to thereby estimate the posterior prediction distribution followed by the intensity function.

The invention provides a mixed data regression model-based pm2.5 influence factor analysis method and system, and the method comprises the steps: building a mixed data regression model of which covariables are component data and numerical data and dependent variables are functional data: the mixed data regression model is a pm2.5 concentration curve of a city, is the functional data, is the proportion of first yield, second yield and third yield of the city, and is called the proportion of third yield for short; the data is component data, logarithm of per capita GDP, average temperature and numerical data, is a to-be-estimated component type coefficient changing along with time, is distributed to a component type covariable at any moment, is a to-be-estimated function type coefficient and is a function type residual error; obtaining robust M-estimation based on equidistant logarithmic ratio transformation, functional basis expansion and an iterative reweighted least square method; and according to the estimated values, analyzing the influence of the three-yield ratio, the per capita GDP and the average temperature of each city on the pm 2.5. The method can be used for analyzing the pm 2.5 influence factors.