87 results about "Statistical model" patented technology

The application discloses a kind of LED early fault diagnosis and life prediction method based on spectral power distribution;The present application is based on similarity detection method to carry out fault diagnosis, extracts spectral characteristic value from statistical model, is reduced dimension by principal component analysis, and is clustered using K-means++ method, finally using distance and threshold comparison determines abnormal time.On this basis, long short-term recurrent neural network is established to predict spectral characteristic value, remodel spectrum, and predict remaining useful life.The present application combines spectral power distribution, and carries out fault diagnosis and life prediction to accelerated step aging white light LED based on long short memory recurrent LSTM neural network method, which greatly improves the accuracy of LED early abnormal detection and remaining life prediction.

The application discloses a lower limb muscle fatigue factor analysis method fusing multiple muscle shape features, and comprises the following steps: acquiring muscle shape features of a measured position based on three-dimensional coordinates of marker points of motion capture, constructing a multidimensional feature vector through the muscle shape features, and screening sensitive features sensitive to a fatigue state through variance analysis; obtaining combined features with strong sensitivity to the fatigue state and high interpretability through fatigue correlation analysis and joint feature screening; fusing the combined features into multidimensional fusion features through principal component analysis dimension reduction processing, and obtaining a fatigue factor based on the multidimensional fusion features. The application discloses a lower limb muscle fatigue factor analysis method fusing multiple muscle shape features, a system and a storage medium, synergic shape changes of the vastus lateralis muscle and the vastus medialis muscle are fused through a three-dimensional cone body volume model, fatigue degree quantitative indexes and fatigue cause contribution degrees are output in combination with an interpretable statistical model, and the lower limb muscle fatigue cause is explained.

This application discloses a processing method, apparatus, communication device, and readable storage medium, belonging to the field of communication technology. The processing method of this application includes: the communication device acquiring the reflection multipath parameters of a sensing target on an ISAC channel; clustering the reflection multipath parameters to obtain clustering results under different transmit / receive positions and / or different rotation angles of the sensing target; statistically modeling the multipath clusters of the sensing target based on the clustering results to obtain a statistical model of the multipath clusters of the sensing target; and processing according to the statistical model of the multipath clusters.

A hybrid forecasting system (100) for tiered cloud pricing using ensemble learning, comprising: a data ingestion module configured to continuously ingest and aggregate heterogeneous data from a variety of sources, including historical cloud usage data, real-time resource consumption metrics, customer subscription profiles, service-level agreement parameters, and external demand indicators; a preprocessing engine functionally coupled with the data ingestion module, the preprocessing engine being configured to perform data cleansing, normalization, transformation, feature extraction, and dimensionality reduction to generate structured and model-compatible datasets;a model training unit that is functionally coupled with the preprocessing engine, wherein the model training unit comprises a variety of heterogeneous predictive models, including at least one statistical model, at least one machine learning model, and at least one deep learning model, each configured to process the structured datasets independently to generate predictive results that meet future cloud resource needs, workload variability, and price sensitivity across multiple service tiers;an ensemble aggregation layer that is functionally coupled to the model training unit, wherein the ensemble aggregation layer is configured to receive and combine the forecast results generated by the multitude of forecasting models using ensemble learning techniques, including weighted averaging, stacking or boosting, with the weights assigned to each forecasting model being dynamically adjusted based on predefined performance evaluation metrics to generate a uniform and optimized forecast;a price optimization engine that is functionally connected to the ensemble aggregation layer, wherein the price optimization engine is configured to determine and dynamically adjust tiered price structures based on the unified forecast, taking into account parameters such as forecasted demand, user segmentation, demand elasticity, infrastructure capacity constraints, and predefined optimization goals such as revenue maximization and resource utilization efficiency;and a feedback adjustment module that is functionally coupled with the price optimization engine and the model training unit, wherein the feedback adjustment module is configured to monitor system performance in real time, user response to price adjustments and resource utilization results, and iteratively updates model parameters and pricing strategies using adaptive learning mechanisms, including reinforcement learning, wherein the system (100) is configured to operate in a multi-tenant cloud environment, supports real-time data processing and decision-making, and enables automated, scalable, and adaptive optimization of tiered cloud pricing.

This invention discloses a method, system, medium, and product for diagnosing high-resistance faults in low-voltage distribution networks, belonging to the field of distribution network fault diagnosis technology. The method first constructs a comprehensive statistical model integrating amplitude and phase errors, time asynchrony errors, and communication packet loss to obtain measurement data with uncertainty; then, it extracts multi-dimensional node features and incorporates uncertainty to construct feature vectors; next, it constructs and trains a Bayesian graph convolutional neural network based on the power grid topology; finally, it outputs the fault probability and cognitive uncertainty, and combines dual thresholds to complete fault determination. This invention can effectively address the measurement uncertainty problem of smart meters, enhance the ability to identify weak features of high-resistance faults, reduce false alarms and missed alarms, and exhibits excellent robustness and diagnostic accuracy under different fault resistance and noise levels.

This application provides a business data prediction method based on multi-model fusion, applicable to the fields of artificial intelligence, big data, and fintech. The method includes: predicting incremental data for a target year using a Bayesian statistical model based on multi-source business data; obtaining incremental data for a target quarter using a seasonal time-series prediction model based on the multi-source business data; performing long-term decomposition prediction using the seasonal time-series prediction model and a multinomial model based on the incremental data of the target quarter to obtain initial prediction data for the target year and fluctuation data for the remaining quarters; wherein the target quarter and the remaining quarters constitute the target year; and using the incremental data of the target year as trend reference data, and based on the fluctuation data of the remaining quarters, correcting the initial prediction data for the target year to obtain the business data prediction result. This application also provides a business data prediction apparatus, device, storage medium, and program product based on multi-model fusion.

The application relates to a river closure date prediction method based on historical similar year performance driving, which comprises the following steps: using a plurality of feature selection algorithms and leave-one-out cross-validation to screen target predictor sets respectively matched with selected machine learning models and statistical models; based on parameter sensitivity analysis and a Bayesian optimization algorithm, sensitive hyperparameters of the machine learning models are optimized to obtain optimized machine learning models; the statistical models and the optimized machine learning models are configured as candidate river closure date prediction models; a K-neighbor algorithm is used to search a set of similar historical years in a historical observation data set according to current observation data, and a target river closure date prediction model is dynamically optimized according to the comprehensive prediction error of the candidate river closure date prediction models on the set of similar historical years, and a prediction result is output, so that the advantages of multiple models are effectively fused, the generalization limitation of a single model in a complex non-stationary environment is avoided, and the accuracy and robustness of the prediction result are significantly improved.

In some aspects, a method, a system, or a non-transitory computer-readable storage medium are described for training one or more models to predict ulcerative colitis (UC) severity based on human-interpretable image features extracted from a whole-slide image, including acts of accessing a plurality of annotated whole-slide images associated with a plurality of UC patients, wherein each of the plurality of annotated whole-slide images includes at least one annotation describing a cell-type label or a tissue-type segmentation for a portion of the whole-slide image, extracting a plurality of human-interpretable image features based on cell-type labels and tissue-type segmentations associated with the plurality of annotated whole-slide images, training a statistical model based on the plurality of human-interpretable image features to predict the UC severity for a whole-slide image, and storing the trained model on at least one storage device.

This invention discloses a short-window gamma-gamma turbulence parameter prediction method for space-to-ground laser communication, belonging to the technical field of space-to-ground laser communication and atmospheric turbulence channel parameter prediction. This method addresses the problems of traditional methods, such as strong dependence on long observation windows, significant degradation in prediction accuracy under short-window scenarios, and insufficient robustness under low signal-to-noise ratio conditions. It establishes a short-window observation model for the space-to-ground optical link and a gamma-gamma channel statistical model, constructs time-dependent short-window training data, and designs a short-window gamma-gamma network. Temporal features are extracted through a convolutional backbone, and a scintillation exponential physical regularization auxiliary head is used to achieve joint parameter prediction under physical constraints, outputting predicted gamma-gamma distributed parameters. This method can achieve high accuracy and good stability in parameter prediction under short observation windows and low signal-to-noise ratio conditions, and can be used for turbulence channel state characterization at the space-to-ground laser communication receiver.

The present application relates to the technical field of power system simulation, and more particularly to a Thevenin equivalent parameter estimation method and system based on multivariate coefficient of variation, an electronic device and a medium; the method comprises: collecting the measured voltage and the measured current at the equivalent point in the target time window; based on the measured voltage, the measured current and the preset Thevenin equivalent impedance prediction value, an indirect statistical model is constructed; the multivariate coefficient of variation is set as an evaluation index for measuring the dispersion degree of Thevenin equivalent potential; an unconstrained optimization model is established; the unconstrained optimization model is solved to obtain the estimated value of Thevenin equivalent impedance, and the estimated value of Thevenin equivalent potential is determined based on the estimated value of Thevenin equivalent impedance. In this way, the technical problem of insufficient estimation accuracy of the existing Thevenin equivalent parameter estimation method when facing complex and variable load fluctuation conditions is solved, and the accuracy and reliability of parameter estimation are improved.

A kind of small and micro customer credit rating modeling method based on Logistic-AHP-K factor, the method includes: step S1, sample data is obtained after selecting sample processing, and the sample data is preprocessed, and preprocessing data is obtained;Step S2, model design based on preprocessing data;The model includes: statistical model, expert model and fusion model.The present application has the advantages of balance of interpretability and model science.

The application relates to the technical field of medical ultrasonic imaging and digital image processing, in particular to an ultrasonic elasticity image denoising and enhancing method, which comprises the following steps: acquiring original ultrasonic elasticity imaging data to be processed, and constructing a structure tensor matrix reflecting local texture directions; solving the anisotropic coherence degree of each pixel point, obtaining a structure attribute discrimination result, and constructing a structure confidence atlas; collecting the point spread function characteristics of an ultrasonic imaging system, establishing a speckle noise statistical model; obtaining a local smoothing coefficient of the first iteration, and performing anisotropic diffusion correction on an initial elasticity distribution matrix to obtain a first modified elasticity image matrix, and updating the structure confidence atlas to obtain a final denoised and enhanced target elasticity image; the application effectively suppresses multiplicative granular speckles, eliminates the ladder effect or artifacts easily generated by conventional methods, and significantly improves the image signal-to-noise ratio.

The present application belongs to the field of augmented reality, computer vision, computer graphics, and relates to a kind of garment three-dimensional reconstruction method based on geometric prior and generated image auxiliary, comprising: obtaining image, inputting image into trained garment three-dimensional reconstruction model, and obtaining detailed three-dimensional garment grid;Garment three-dimensional reconstruction model includes: multi-modal prior information extraction module, garment generation network and geometry enhancement module;The present application extracts prior information that can reflect geometric structure from synthetic image, i.e.semantic segmentation map and surface normal map, which is jointly trained with real data set, and combined with real data set to construct garment statistical model, and according to garment statistical model, principal component coefficient is restored to garment grid, to make up for the problem of insufficient three-dimensional supervision signal, without relying on additional three-dimensional scanning grid data, improve the representation ability of model to complex garment shape, thereby improve the precision and generalization performance of three-dimensional garment reconstruction.

A method, a system, and a computer program product of real-time estimation of risk in an excavation. The method for a real-time estimation of risk in an excavation, such as in a mine or a tunnel, wherein the method comprises receiving (410), from a plurality of strain measurement devices in an excavation, strain data including data related to a plurality of strain components having different directions at a computing system (1000), and estimating (420) the risk by executing a probabilistic statistical model, such as a Bayesian network, in the computing system, wherein the received strain data is utilized in the probabilistic statistical model for the estimation.

This invention discloses a PET image reconstruction method and system based on manifold prior constraints, belonging to the field of medical image reconstruction and intelligent information processing technology. It acquires historical PET image datasets and PET measurement data from positron emission tomography (PET), constructs a data consistency term based on a Poisson statistical model, and introduces the image manifold prior into the PET image reconstruction optimization model. The optimization model is solved using an alternating iterative approach based on variable splitting, including data consistency updates, manifold projection updates, and dual variable updates. Finally, the reconstructed PET image is output. This invention organically combines the PET imaging physical model with data-driven prior generation, which is beneficial for improving reconstructed image quality, suppressing noise, and preserving structural details in low-dose PET imaging scenarios.

This application discloses a parameter optimization method and electronic device for surface treatment processes, belonging to the field of parameter optimization technology. First, based on the parameter characteristics and processing thickness characteristics of a sample set of various process parameters for the surface treatment process, the importance of the process parameters is evaluated, and target process parameters with high importance to the processing thickness are determined from the various process parameters. Then, the target parameter value of each target process parameter is determined from the preset value range corresponding to the target process parameter, thus obtaining the parameter optimization result of the surface treatment process. Since the number of target process parameters is less than the number of various process parameters, and the target process parameters have high importance to the processing thickness, the statistical model and machine learning model only need to predict the processing thickness of a small number of target process parameters in the subsequent parameter optimization process. This avoids model input redundancy, ensures the prediction accuracy of the processing thickness under small samples, and thus improves the accuracy of the parameter optimization result.

This invention relates to the field of computing power scale prediction technology, specifically disclosing a method and system for predicting urban computing power scale based on a sled dog-optimized MLP. This invention constructs a parameter optimization architecture for an MLP driven by a sled dog optimization algorithm, encoding the number of hidden layer neurons, truncation quantiles, and year-specific switch variables as decision vectors. It designs a multi-objective fitness function that integrates training set error, validation set error, generalization gap penalty, model complexity penalty, and stability penalty. This simulates the dynamic selection, movement, obstacle avoidance, disorientation, training, and retirement behaviors of a sled dog population through iterative optimization. This solves the problems of traditional grid search and random search easily getting trapped in local optima, and the reliance on human experience for key MLP parameter configuration. It also overcomes the shortcomings of insufficient fitting of statistical models and overfitting of conventional neural networks in small sample scenarios, achieving improved accuracy in urban computing power scale prediction and enhanced model generalization performance.

The present application relates to nuclear power safety protection technical field, especially a kind of nuclear power plant pump body abnormality detection method and device.The method is: first, obtain pump body characteristic curve, based on the pump body characteristic curve, instrument arrangement and business knowledge determine the influence factor of the pump body;Then obtain the historical working data of pump body, establish training set by data analysis method;Based on training set, complete the training of regression model, reconstruction model and statistical model and obtain early warning threshold based on residual or statistical distribution;Finally, the current relevant data are input into the state reconstruction algorithm and statistical model or regression model, the statistical quantity or predicted value of pump in current state is obtained, whether there is abnormality is judged by comparing with early warning threshold.The present application selectively uses suitable model to judge the abnormality of pump body, simple and convenient.

This invention discloses a RIS-assisted downlink transmission method for UAV air-to-ground network security. The method includes: constructing a large-scale channel gain for the UAV-RIS link; implementing optimal phase configuration and beamforming for legitimate users based on CSI; calculating the received signals and instantaneous signal-to-noise ratio for legitimate users and effective eavesdroppers; introducing a channel statistical model to model the statistical characteristics of channel fading and node locations and derive the link distance PDF; deriving a closed-form expression for the Standard Operating Procedure (SOP) in scenarios with random eavesdropper locations and numbers; and performing precise quantitative analysis of system security performance based on the closed-form expression, dynamically adapting and updating the RIS phase configuration and receiver strategy. This invention effectively corrects the security assessment distortion problem of traditional methods, achieves accurate characterization of the security interruption probability in scenarios with uncertain eavesdropper locations and numbers, reduces the system security interruption probability, and improves transmission security and robustness. It is applicable to UAV air-to-ground secure communication in an integrated air-space-ground architecture.

The application relates to a method for establishing a transistor statistical model based on an artificial neural network system, comprising receiving and generating a nominal model of a standard transistor by using the artificial neural network system based on data in a first data set; screening neurons in the artificial neural network system based on the first data set and the nominal model to obtain final fluctuation neurons; calculating and obtaining the distribution of weights of the final fluctuation neurons and the distribution of threshold voltages in the statistical model based on the change of the weights of the final fluctuation neurons relative to the nominal model, the change of the nominal model relative to threshold voltages, the distribution of drain-source currents and the distribution of gate-source voltages in the first data set; and establishing the statistical model based on the nominal model, the distribution of weights of the final fluctuation neurons and the distribution of threshold voltages.

This invention is a method for scaling prediction of flow battery stack performance and cost based on single-cell data. First, performance data of laboratory single cells is acquired. Then, an area scaling factor is calculated based on target stack parameters to correct system auxiliary power consumption. Finally, a least-squares optimization inversion method is used to obtain the stack integration efficiency reduction factor. An extreme value statistical model of the full-lifecycle decay trajectory is used to determine the lifetime reduction coefficient, achieving accurate prediction of stack-level performance. Finally, the corrected performance parameters are input into a levelized energy storage cost model to achieve system-level economic prediction. This invention solves the problem of insufficient accuracy in predicting performance and cost from laboratory samples to engineering systems, establishing a complete cross-scale prediction system from materials to stack to system, providing reliable decision support for energy storage system planning.

The present application relates to a kind of household water end equipment identity fingerprint library establishment calling identification method and system, belong to the field of Internet of Things data management and smart home.The present application establishment method includes: the flow rate and water pressure time series data of single water use event are collected;Call feature extraction interface to calculate standardized multidimensional feature vector;Based on feature vector, the statistical model of device fingerprint object is constructed;Quality verification and conflict detection are carried out;The fingerprint that passes verification is stored in local fingerprint library in read-only mode by controlled management interface.The calling method includes: the water use event to be identified is converted into query feature vector, and similarity calculation is carried out with fingerprint in library, and the matching result is returned.The advantages of the present application: by standardized feature extraction, statistical model construction, multistage quality verification and controlled management, provide stable and reliable equipment identification infrastructure for intelligent water application, effectively improve identification accuracy and system maintainability.

This invention belongs to the field of intelligent medical technology and discloses a method for detecting gradual change points based on microbial data. The method includes the following steps: acquiring longitudinal microbial data as a user sample set and preprocessing it to obtain time-series observation data; constructing a statistical model for detecting gradual change points in variance based on the time-series observation data, wherein the observation value at each time point in the statistical model includes a smooth mean function term and a random noise term; employing an iterative estimation algorithm to jointly estimate the smooth mean function, the change point time to be detected, and the model parameters controlling the variance change law to determine the critical moment when the noise variance in the time-series observation data begins to change continuously; and outputting the determined critical moment as the disease risk warning time point. This effectively solves the problems in existing technologies where it is impossible to dynamically model microbial data and it is difficult to identify its gradual change critical points.

This invention belongs to the field of ecology, and specifically relates to a method and apparatus for forest litter analysis. It addresses the problem of low efficiency in existing forest litter analysis methods. This invention establishes a mathematical model for predicting litter yield, decomposition rate, and decomposition turnover period using easily measurable variables, and provides statistical methods for model parameters. By using statistical model parameters based on post-fall elevation, thick branch load, and lower layer litter load, and utilizing the upper layer litter load and total litter load, litter yield, decomposition rate, and decomposition turnover period can be quickly estimated. This is a time-saving and labor-saving method for comprehensively estimating litter yield and decomposition rate, thus solving the problem of low efficiency in existing forest litter analysis methods.

This invention relates to a deterministic tooth surface roughness data processing method based on bicubic interpolation, belonging to the field of gear meshing interface friction and wear and surface metrology technology. The method includes: acquiring original tooth surface roughness data through scanning with a high-precision friction and wear testing machine; performing preliminary noise reduction and export using supporting software; reconstructing the data into a two-dimensional matrix in MATLAB; resampling the matrix using a bicubic interpolation algorithm to reduce the data volume while faithfully restoring the morphology details; removing noise introduced by interpolation and measurement processes through median filtering; further adjusting the dimensionless roughness Ra of the morphology through mathematical transformation to generate standardized morphology data of different roughness levels; and finally exporting deterministic morphology data. This invention overcomes the problems of inaccurate characterization of actual morphology and strong parameter dependence of traditional statistical and fractal models, providing a more realistic and reliable roughness data foundation for gear interface tribological simulation.

The application discloses a single-photon avalanche diode modeling method based on Verilog-A, which comprises the following steps: model parameter definition and initialization; judging the state of the single-photon avalanche diode, if the avalanche is closed, performing statistical model calculation, judging whether the avalanche state is opened according to the statistical model calculation result, if the avalanche is opened, performing electrical model calculation, updating the avalanche state according to the electrical model calculation result and the quenching threshold current based on Gaussian distribution, and outputting each current; the statistical model calculation comprises calculating the photon detection event time, the dark count event occurrence time and the post-pulse trigger time; the electrical model calculation comprises calculating the leakage current and the segmented avalanche current, and calculating the junction charge of the SPAD cathode-anode, the parasitic capacitance charge of the SPAD cathode-substrate and the parasitic capacitance charge of the SPAD anode-substrate, so as to calculate the corresponding current according to the charge-current relationship. The application can comprehensively reflect the working characteristics of the device.

This invention discloses a few-sample inductor core surface defect detection method based on model interaction, belonging to the fields of machine vision and industrial defect detection technology. The method includes the following steps: S1 Data acquisition and image preprocessing, constructing normal samples, labeled samples, and unlabeled samples; S2 Constructing an unsupervised statistical model based on statistical learning; S3 Constructing a supervised semantic segmentation model; S4 Simultaneously inputting the inductor core image to be detected into both the unsupervised statistical model and the supervised semantic segmentation model for processing, generating segmentation results; S5 Quantifying the differences in detection results; S6 Updating the parameters of the unsupervised statistical model; S7 Generating pseudo-labels based on the unsupervised statistical model; S8 Updating the weights of the supervised semantic segmentation model; S9 Using batches of processed images to be detected, inputting them into the updated unsupervised statistical model and the supervised semantic segmentation model for detection, obtaining detection results, and analyzing and calculating system performance indicators.

The application discloses an intelligent agent driven differentiated report generation method and system and a storage medium. The method comprises the following steps: monitoring key index data flow in real time, and analyzing the characteristics of the key index data flow based on a statistical model to generate a state switching instruction; receiving the instruction and switching among multiple working states such as a normal state, a warning state and an emergency state. In response to the state switching, the report generation processing flow is dynamically adjusted, and the adjustment at least includes changing a data sampling frequency, switching a data preprocessing model and selecting a report generation logic matched with the current state. By introducing the event driven polymorphic working mode, the application realizes the transformation from passive report generation to active and quasi-real-time decision support, significantly improves the response speed of the system to emergencies and the intelligent level of decision support, and balances the system energy efficiency and performance.

Methods for predicting a cutaneous primary site of disease are described. The methods may comprise, for example, receiving, using one or more processors, sequence read data associated with a sample from the individual, selecting, using the one or more processors, a plurality of reads from the sequence read data, determining, using the one or more processors, an ultra-violet (UV) signature metric based on the selected plurality of reads, inputting, using the one or more processors, the UV signature metric into a statistical model, and predicting, using the one or more processors, the primary site of the disease in the individual based on an output of the statistical model.

To provide a statistical model construction device or the like capable of constructing a statistical model capable of accurately estimating a dephosphorization rate constant even when the blowing treatment is stopped midway.SOLUTION: A statistical model construction device includes a data collection part 331 for collecting operation data on the blowing treatment of a converter 11, and a statistical model construction part 333 for constructing a statistical model using operation data as an explanatory variable and a dephosphorization rate constant in the blowing treatment as an objective variable. The dephosphorization rate constant is defined as a proportionality constant assuming that an amount of change in the phosphorus concentration in molten steel of the converter relative to the cumulative per-unit oxygen supply to the converter is proportional to the phosphorus concentration in the molten steel of the converter. The statistical model construction part constructs the statistical model using operation data on the past blowing treatment collected by the data collection part.SELECTED DRAWING: Figure 1