11 results about "Heteroscedasticity" patented technology

A method for automatically abstracting and selecting an optimal set of variance-related functions that are an indicator of an individual outcome in healthcare, wherein the method comprises: generating, by one or more processors, an abstracted set of variance-related candidate-patient functions, wherein the abstracted set of variance-related candidate-patient functions are temporally heteroscedastic functions; optimizing, by one or more processors, each patient function from the abstracted set of variance-related candidate-patient functions by identifying a time period in which the variances and heteroscedasticity of each patient function are maximized, wherein this optimization produces an optimal abstracted set of variance-related patient functions from the time period in which the variances and heteroscedasticity of each patient function are maximized;by one or more processors comparing the optimal abstracted set of variance-related patient functions with a historical dataset for a patient population to create a predictive set of variance-related patient functions, wherein the predictive set of variance-related patient functions predicts a health-related target outcome of the patient population; by one or more processors generating a current optimal patient set of variance-related patient functions for a current patient; by one or more processors comparing the optimal set of variance-related patient functions for the patient population with the current optimal patient set of variance-related patient functions for the current patient;In response to the optimal set of variance-related patient functions for the patient population, which matches the current optimal patient set of variance-related patient functions for the current patient within a predefined limit, one or more processors determine whether the health-related target outcome matches a predefined health-related target outcome for the current patient; and in response to the health-related target outcome matching the predefined health-related outcome for the current patient, one or more processors issue an alert regarding the predefined health-related outcome for the current patient.

This invention discloses a DDoS attack detection method based on heteroscedastic unscented Kalman filtering. Addressing the issues of limited resources in edge networks and low anomaly detection accuracy and high latency in low signal-to-noise ratio environments, this invention utilizes Sketch for full-scale, unsampled traffic feature extraction in the programmable data plane and reports observations to the control plane through differential processing. In the control plane, a third-order state-space model incorporating instantaneous traffic rate, rate of change, and acceleration is innovatively constructed. An additive heteroscedastic noise model is proposed to adaptively handle Sketch hash collisions and traffic shot noise, and unscented Kalman filtering is employed for state estimation. Simultaneously, an intelligent hybrid control mechanism is introduced to overcome filtering lag, and finally, NIS and CUSUM are combined for dual-modal anomaly detection, outputting the system state. This invention enables high-precision real-time detection of DDoS attacks with extremely low resource overhead, effectively solving the trade-off between measurement and detection in existing technologies.

This invention discloses a method, apparatus, medium, and device for obtaining atmospheric boundary layer height. The method includes: accessing multi-source observation data to generate observation records with quality indicators and initial observation uncertainties; performing spatiotemporal mapping to generate a registered profile sequence with an uncertainty field; generating a set of physical candidate heights in parallel based on at least one physical mechanism among thermal gradient, dynamic shear, and material distribution, and recording the variance of the source observations after interpolation for each physical candidate as the candidate uncertainty; constructing feature vectors for the pixels to be estimated; inputting the feature vectors into a first-layer candidate scorer to output a confidence score for each physical candidate, and inputting the feature vectors and confidence scores together into a second-layer heteroscedasticity regressor to output a point estimate and pixel-level uncertainty of the boundary layer height; using the point estimate and pixel-level uncertainty as observation terms, performing Kalman filtering assimilation with the background field, and outputting the atmospheric boundary layer height.

The industrial robot absolute positioning error compensation method solves the problems of weak normal observation and unstable pose estimation under long distance or inclined angle in the existing robot absolute positioning, and belongs to the technical field of industrial robot precision control. The present application comprises: constructing a multi-layer parallel ArUco marker field in the workspace and optimizing the layout; the robot end monocular camera collects the marker field image along the planned path, and the enhanced image is obtained through edge-ROI guided super-resolution reconstruction; corner detection and pose solution are carried out based on the enhanced image, the actual pose is obtained and compared with the theoretical pose to obtain the pose error, and the re-projection error is recorded, and the data set is composed of the robot state characteristics; the data set is used to train the heteroscedastic Gaussian process regression model, wherein the observation noise variance of each sample is proportional to the square of the re-projection error; for the target task path point, the state characteristics are input into the model to predict the pose error and compensate to the theoretical instruction to generate the modified control instruction.

This application discloses an integrated assessment method and device for multivariate seismic vulnerability of tunnels that incorporates physical priors, relating to the technical field of seismic analysis and seismic risk probability assessment of underground engineering structures. The method includes: generating predicted samples based on a logarithmic domain joint distribution description; inputting each predicted sample into a heteroscedastic moment estimation substitution model to obtain predicted values ​​of the conditional mean and conditional variance of the logarithmic domain demand response; reconstructing and dynamically anchoring the conditional marginal distributions of each response based on the predicted values ​​and residual information, and coupling each anchored conditional marginal distribution to obtain a multi-response joint probability model; calculating the point-state failure probability of each projected sample under a preset damage state based on the multi-response joint probability model, constructing discrete sample pairs; and fitting each discrete sample pair to obtain seismic vulnerability curves under each preset damage state. This application improves the accuracy, robustness, and engineering usability of tunnel seismic vulnerability assessment.

This disclosure provides a method and system for detecting communication anomalies in a wind turbine pitch control system. First, the original CAN message stream is processed into a time series, extracting multiple inter-frame arrival time sequences. Then, the wind turbine's operating condition is determined in real-time using SCADA data, generating an operating condition time series. Further, an adaptive time series decomposition is used to combine the inter-frame arrival time sequences and the operating condition time series. Before decomposition, a logarithmic transformation is performed on the data, effectively addressing the inherent shortcomings of traditional additive model time series decomposition in handling heteroscedasticity, thus obtaining multiple variance-stable residual sequences. Finally, a pre-trained isolated forest model is used to score these residual sequences for anomalies, and the cumulative evaluation of anomaly scores combined with state judgment outputs the health status of the wind turbine pitch control system. This approach significantly improves the accuracy and robustness of communication anomaly detection in wind turbine pitch control systems.

The application provides an intelligent water quality prediction and regulation method in a power plant descaling process, and relates to the technical field of water quality prediction, and specifically comprises the following steps: collecting data recorded during chemical cleaning and descaling of a boiler of a power plant and performing data preprocessing to construct a power plant descaling water quality data set; introducing a local fluctuation suppression weight, a water temperature deviation adjustment weight, a reagent mutation suppression factor and a time decay weight to generate an enhanced delay vector; constructing a global state vector through a covariant weight and a direction perception expression; combining the global state vector, a reagent change amount and a temperature deviation to form a prediction input, adopting a heteroscedastic robust task loss based on a Huber loss and an uncertainty factor for optimization, and finally realizing multi-step prediction of a pH value, a Langelier saturation index, a calcium ion concentration, a silicate radical concentration, a conductivity and a turbidity in the next 15 minutes.

This invention discloses a text-image pedestrian retrieval method based on differential alignment and hyperbolic learning, comprising: 1. collecting paired text descriptions and pedestrian images and preprocessing them to obtain a cross-modal pedestrian retrieval dataset; 2. constructing a unified differential alignment framework model, including a two-stream feature extractor, a single-network uncertainty quantization module, a neural differential contrast alignment module, and a hyperbolic similarity matching module; 3. jointly training and optimizing the network model using heteroscedasticity classification loss, normalized differential contrast alignment loss, hyperbolic semantic matching loss, and masked language modeling loss to obtain the optimal re-identification model, which is used to input the text to be detected for image matching and output the target image. This invention suppresses noise by quantizing feature confidence, filters background redundancy by using differential alignment, and introduces hyperbolic space to strictly align the hierarchical structure of natural language, significantly improving the accuracy and robustness of cross-modal re-identification.

The present application relates to a kind of canal water level probability prediction method and system based on MC Dropout and CNN-LSTM, belong to water level prediction technical field.The prediction method includes the following steps:s101.data acquisition;S102.model architecture building;S103.model training and inference.The present application fuses convolutional neural network (CNN) to extract the local space-time characteristics of multi-source hydro-meteorological data, long short-term memory network (LSTM) captures long time series dependency relationship, and integrates Monte Carlo Dropout (MC Dropout) variation inference mechanism and heteroscedastic loss function, realizes the accurate prediction of key water level observation station, uncertainty decomposition (Aleatoric uncertainty and Epistemic uncertainty) and the synchronous output of confidence interval.

This invention discloses a wind turbine power data cleaning method based on dynamic threshold RANSAC, relating to the field of wind turbine operation data processing. The method includes: acquiring historical operation data containing wind speed and power; dividing the data into a pre-cut-in zone, a normal operation zone, and a post-rated zone based on the cut-in wind speed and rated wind speed; for the normal operation zone data, using the Random Sample Consensus (RANSAC) algorithm for robust fitting, and using a dynamic threshold function that monotonically decreases with wind speed to judge the fitting residual point by point to identify power anomaly sample points; using the theoretical power value of the fitted model to repair the anomaly points and applying physical rationality constraints. This invention solves the problem of false deletion in low-wind-speed zones and missed detection in high-wind-speed zones caused by heteroscedasticity in the wind speed-power relationship by adaptively adjusting the anomaly judgment criteria with a dynamic threshold, thus improving the consistency of anomaly identification and the quality of data cleaning.

This invention discloses a GNSS precise orbit determination method, system, and medium for situations involving sudden reduction in ground station networks and satellite rejection. It relates to the field of GNSS orbit determination technology and solves the technical problems of precise orbit determination methods, such as strong dependence on highly redundant ground station networks, observability degradation leading to multi-peak solution spaces under sudden reduction in ground station networks, and the difficulty in simultaneously achieving continuous product output and reliable delivery. This invention includes: acquiring multi-system, multi-frequency pseudorange and carrier phase observations from available ground stations and their quality indices; calculating rejection levels; training neural operator manifold priors to output a low-dimensional manifold distribution of orbit-clock errors; constructing three types of closed invariants as truth-free supervision constraints; establishing a differentiable observable renderer to output observation predictions and heteroscedasticity uncertainties; using generative posterior inference under prior manifold constraints to output multimodal posterior samples of orbits and clock errors; providing integrity bounds and consistency certificates based on closed constraints and residual structure checks; and continuously outputting verifiable ephemeris products under conditions of sudden reduction in ground station networks or local rejection.