286 results about "Model fitting" patented technology

The invention belongs to the technical field of three-coordinate measurement, and particularly discloses a three-coordinate measurement method based on incomplete curved surface fitting, which comprises the following steps: hierarchically extracting geometric features from incomplete point clouds, and dividing a workpiece to be measured into a plurality of ordered curved surfaces; adding a curved surface label to each point cloud data, and generating a plurality of ordered point cloud sets based on the curved surface labels; generating virtual points based on the geometric features to fill the missing region; reconstructing a three-dimensional sub-model of each ordered curved surface based on the ordered point cloud set, the virtual points and the edge point cloud; and fitting the three-dimensional sub-model to generate a continuous curved surface model, and obtaining workpiece measurement parameters based on the continuous curved surface model. By extracting geometric features, classifying point clouds and generating virtual points, the limitation that a traditional method depends on a prior model is broken through, unknown or non-standard geometry can be processed, global continuous modeling of incomplete point clouds is achieved through ordinal curved surface division, three-dimensional sub-model reconstruction and continuous curved surface fitting, and the accuracy of measurement parameters is ensured.

The invention provides an adaptive welding seam detection and three-dimensional reconstruction method based on deep learning and binocular vision. The adaptive welding seam detection and three-dimensional reconstruction method comprises the steps of S1, collecting samples and making a training data set; s2, the picture of the sample to be welded is processed, a feature region is recognized, the image quality of the region to be welded is analyzed and evaluated through wavelet transform and local variance, and the noise level and the contrast ratio are calculated; s3, dynamically generating edge detection parameters and model fitting parameters according to the image quality; s4, using an edge detection algorithm to extract edge point cloud of the welding seam area; s5, performing RANSAC linear fitting, weighted least square fitting and polynomial curve fitting on the edge point cloud in parallel; s6, selecting an optimal fitting result based on an image quality adaptive dynamic scoring model; and S7, carrying out three-dimensional coordinate conversion in combination with the three-dimensional matching model IGEV-Stereo, and outputting a final welding seam three-dimensional coordinate. According to the invention, automatic detection of the position and size of the welding seam can be efficiently and accurately realized.

The invention discloses a shield segment dislocation detection method and system fusing visual and geometric features, and the method comprises the steps: employing a mobile track three-dimensional laser scanning system, and rapidly obtaining the three-dimensional point cloud data of a tunnel segment; projecting the three-dimensional point cloud data of the tunnel segment to a two-dimensional image according to the scanning parameters and the image preset resolution, and mapping the laser point reflection intensity into a pixel gray value; shield segment inter-ring joints and shield segment in-ring joints are extracted respectively, and segment joint positioning is completed; and according to the seam positioning information, extracting local point clouds at the two sides of the seam, respectively carrying out circular model fitting, calculating the height difference of circular models at the two sides at the seam, and obtaining an in-ring slab staggering value. According to the method, the visual information of the point cloud reflection intensity and the geometric information of the spatial position are fused, rapid and accurate shield segment in-ring slab staggering detection is realized, and the efficiency and the accuracy are high.

A system and method include tuning hyperparameters for an ARIMA model using a derivative free approach by determining a set of initial hyperparameter values, fitting an ARIMA model to the set of initial hyperparameter values, selecting a tuning method for the set of hyperparameters, responsive to selecting a single-objective method, computing a first objective function value from time-series data applied to the ARIMA model based on the set of initial hyperparameter values, or responsive to selecting a multi-objective method, computing at least a second objective function value and a third objective function value from the time-series data applied to the ARIMA model based on the set of initial hyperparameter values, determining whether a stopping criterion for tuning the set of hyperparameters has reached, responsive to determining that the stopping criteria has reached, outputting a set of tuned hyperparameter values.

The present disclosure provides a model training method and device, and a data processing method and device. The method of the present disclosure uses a reference model to screen an existing instruction dataset for an instruction whose model fitting difficulty meets a preset condition, and the method can screen the instruction dataset for a challenging instruction having high model fitting difficulty as a seed instruction. A plurality of similar instruction samples are generated by means of expansion on the basis of the seed instruction, thereby obtaining more challenging instruction samples, a training set comprising the instruction samples and reference responses for the instruction samples is constructed, and knowledge distillation can be achieved by using the reference model on the basis of the existing instruction dataset, thereby obtaining a training set containing higher-quality instruction data. Furthermore, using the training set to train a deep learning model enhances the capability of the deep learning model to handle more complex and challenging tasks, and improves the performance of a trained target model.

The invention discloses a degraded cultivated land soil organic matter three-dimensional mapping method fusing remote sensing, near-earth sensing and historical data, and relates to the technical field of digital soil mapping, the method is based on an INLA-SPDE three-dimensional model framework, remote sensing, near-earth sensing and historical data are fused, and high-precision three-dimensional mapping is achieved. The method comprises the following steps: collecting organic matter data and near-sensing visible near-infrared reflection spectrum data of different depths of a soil profile at each sampling point in a research area, then screening visible near-infrared reflection spectrum characteristic wavebands significantly related to organic matters, collecting and integrating historical data, and completing standardization processing on remote sensing and near-earth sensing data; dividing a modeling set and a verification set, calculating a range value based on a semi-variable function, determining triangular mesh parameters, and constructing an SPDE model; the near sensing data and the remote sensing data serve as covariables and are fused into the INLA-SPDE three-dimensional model, and a soil organic matter three-dimensional space distribution diagram is generated after model fitting and uncertainty is quantified. According to the method, the problem that the vertical change of the soil attribute cannot be accurately simulated by a traditional method is solved, and high-precision and high-efficiency three-dimensional mapping of the regional scale soil organic matter in the horizontal and vertical dimensions is realized.

The invention relates to the technical field of data processing, and particularly discloses a data analysis method and device fusing a large number rule, equipment and a medium, and the method comprises the steps: determining a minimum convergence amount through hierarchical aggregation; calculating a cumulative sample mean trajectory and carrying out convergence diagnosis; performing noise attenuation weighting based on LLN convergence characteristics; performing distribution and component decomposition under steady moment constraint; performing consistency check and re-extraction robustness of LLN guidance; lLN-constrained model fitting and uncertainty calibration output are carried out; according to the method, based on noise attenuation weighting of LLN convergence characteristics, samples which are close to a steady state obtain greater influence in estimation, and unstable or sparse samples are naturally weakened, so that self-adaptive suppression of heterogeneity and small sample noise is realized, and the robustness of overall estimation is improved; steady moment constraint is introduced into distribution / component decomposition, it can be guaranteed that components obtained through decomposition are consistent with observation convergence characteristics in the aspect of high-order statistics, and component mismatching caused by extreme values or local fluctuation is reduced.

The invention relates to a quadruped robot laser odometer method based on ground point optimization, hardware and application, and the method comprises the steps: obtaining an original point cloud collected by a laser radar, carrying out the preprocessing, dividing a polar coordinate region, jointly extracting ground plane feature points and ground geometric edge feature points based on normal vector and local curvature features, and carrying out the calculation of the ground plane feature points and the ground geometric edge feature points; ground geometric edge feature points are utilized to optimize ground model fitting; optimizing a point set of the ground based on a time sequence reference plane of the ground; the optimized ground points are removed, and non-ground point features are extracted from the remaining point clouds; establishing feature association between the feature points in the current frame and the target point cloud, and screening effective matching pairs; a cascade weight optimization objective function associated with the ground point plane constraint, the non-ground point line feature constraint and the surface feature constraint is constructed, and continuous pose transformation of the quadruped robot is solved; hardware is realized based on the method, and the method is applied to real-time pose estimation and environment mapping of the quadruped robot in outdoor unstructured terrains and complex dynamic environments.

The invention relates to the technical field of computer data processing, and discloses a financial reimbursement data processing method, device and system.The financial reimbursement data processing method comprises the following steps that multi-modal data of a reimbursement voucher is obtained, and the multi-modal data is stored in a block chain; the multi-modal data comprises pictures, voices and videos of reimbursement vouchers; recognizing characters on the picture based on a convolutional neural network, and extracting and analyzing character information of key frames of the voice and the video by using a natural language processing model; and performing feature extraction on the character information to obtain character feature information, judging whether the character feature information falls into a reimbursement directory, and performing local model fitting according to the character feature information. According to the method, the dynamic verification rule is generated based on the historical reimbursement data, the bill anomaly probability is calculated in real time through the anomaly coefficient formula, and the anomaly detection accuracy is improved by combining the error coefficient and keyword matching degree and the historical record relevance index.

The invention discloses a numerical control machine tool autonomous tool setting method based on 3D visual guidance. The method comprises the following steps: firstly, acquiring three-dimensional point cloud data of a cutter and a workpiece by using a 3D visual sensor and preprocessing; then, segmenting the point clouds through a region growing algorithm, realizing the separation of the tool point clouds and the workpiece point clouds, and extracting the point clouds of each cylindrical section of the workpiece; thirdly, based on a cylinder fitting algorithm, cylinder model fitting is conducted on the segmented tool and workpiece point cloud, and geometric parameters such as the axis direction, the radius and the center coordinate are obtained; calculating a relative position relation between the tool and the workpiece according to the geometric parameters, generating a tool setting path and converting the tool setting path into an NC code; and finally, the NC code is transmitted to a grinding machine control system through a grinding machine communication module, and tool setting operation is completed. The automatic tool setting device has the advantages that the relative position relation between the workpiece and the tool can be automatically measured in the machining process, automatic and rapid tool setting is completed, and the machining quality and efficiency are guaranteed.

The invention relates to the technical field of data processing, and discloses a hydrocephalus correlation analysis method and system based on multi-dimensional data. The method comprises the steps that a feature matrix is generated by obtaining and standardizing hydrocephalus multi-dimensional data, after the matrix is discretized, an association rule mining algorithm is adopted to extract an association mode, a rule set is obtained in combination with knowledge graph verification, data clusters are divided based on mahalanobis distance clustering, mixed effect time sequence model fitting parameters are established for all the clusters, and a mixed effect time sequence model is obtained. And calculating a target sample attribution cluster and predicting a symptom improvement trajectory and a confidence interval. According to the method, automatic integration, credible association rule extraction, precise subtype division and individualized symptom trajectory prediction of the multi-dimensional data of the hydrocephalus patient are realized.

The invention discloses a complex system fault twinborn deduction method based on virtual-real dynamic fusion, and the method comprises the steps: firstly designing a preprocessing scheme of multi-modal data fusion, and carrying out the spatial-temporal feature unification and standardized state vector construction of heterogeneous sensing data; secondly, establishing a real-to-virtual digital mapping model, deducing a multilevel system state based on a dynamic Bayesian network, and introducing a weighted adaptive gradient correction mechanism to improve the fitting precision of the model; and finally, proposing a fault evolution evaluation method of reflecting real from virtual, and realizing hierarchical identification and early warning triggering of the system operation state. By introducing a digital twinning thought, establishing a virtual model synchronously evolved with an entity system, and constructing a whole-process twinning deduction framework of perception, modeling and evaluation, the method can significantly improve the accuracy, response efficiency and robustness of fault prediction of a complex system.

The invention discloses a power distribution network area low voltage prediction method, and relates to the technical field of voltage prediction, and the method comprises the steps: S1, data preprocessing; s2, establishing a GA-BP neural network load prediction model; s3, GA-BP load prediction model simulation is carried out; s4, establishing an LSTM neural network voltage prediction model; s5, performing model simulation and result analysis; and S6, voltage prediction and treatment suggestion. According to the power distribution area low voltage prediction method, firstly, a GA-BP neural network is utilized to predict area loads, influence factors such as temperature, humidity, date types and different moments in one day are fully considered, and predicted load data are utilized as input to construct an LSTM model to predict area voltages; the transformer area low voltage is effectively predicted through the GA-BP-LSTM combined model, the model is high in fitting degree and low in prediction error, the low voltage degree of a user is reflected in real time, and more information support is provided for follow-up transformer area low voltage treatment.

The invention belongs to the field of shale oil exploration evaluation, and discloses an LgR method logging source rock evaluation model fitting parameter prediction method and a shale type shale oil resource quantity calculation method and system. The prediction method comprises the following steps: screening mudstone data in a logging curve; determining a plurality of combinations of possible values of fitting parameters K, a and b, and calculating corresponding mudstone baseline parameters; aiming at different combinations of possible values of fitting parameters K, a and b and corresponding mudstone baseline parameters, according to the screened mudstone data, utilizing an LgR method well logging source rock evaluation model to respectively calculate and obtain organic matter abundance fitting values; and based on the organic matter abundance fitting value and the organic matter abundance measured value, evaluating a fitting effect, and screening out a parameter value combination with the optimal fitting effect as a predicted fitting parameter of the well with the organic matter abundance measured value in the work area. According to the method, all possible parameter value combinations can be comprehensively screened, the influence of subjective factors is eliminated, and undetermined parameters are objectively and accurately predicted.

The invention discloses an unmanned aerial vehicle autonomous information perception path optimization method fusing sparse Gaussian estimation and RLSAC, and particularly relates to the technical field of unmanned system multi-target tracking, and the method comprises the steps: employing Kalman filtering to carry out the optimization processing of target initial data obtained by a ground laser radar, achieving the filtering of the noise of a target, obtaining the dynamic trajectory of the target, and obtaining the optimal path of the target. Therefore, the output insufficiency of the RLSAC to the dynamic trajectory is made up. The data after Kalman filtering processing is used as original input data of a multi-unmanned aerial vehicle target tracking I PP algorithm based on information path planning, the own unmanned aerial vehicle adopts the I PP algorithm to track a target in real time and transmit target related data to provide input data for RLSAC, the RLSAC is used to process the input data, model fitting is carried out, and the RLSAC is used to carry out target tracking. And the RLSAC outputs rewards of different geometric morphology models adopted by the own unmanned aerial vehicle during mode recognition, and the model which is more consistent with the output of the RLSAC is determined by calculating the confidence coefficient.

The invention provides a composite material bearing structure storage life evaluation method considering an acceleration stress lower limit, and the method comprises the steps: 1, carrying out the initialization modeling: enabling the service life of a product to obey the logarithmic normal distribution, and building a three-parameter inverse power law acceleration model of the service life feature theta and the stress level S; 2, estimating parameters: estimating unknown parameters by applying a maximum likelihood estimation method for the three-parameter inverse power law acceleration model; 3, model selection: comparing the calculated likelihood function values, wherein the larger the likelihood function value is, the more stable and more accurate the model is; meanwhile, the variation coefficients of the acceleration factors are calculated in combination with test data for comparison, and the model with the small variation coefficient is more accurate; and 4, accelerated life evaluation: giving reliability, and evaluating the storage life of the three-parameter inverse power law model. The method is suitable for accelerated test evaluation of a product with a threshold effect; the three-parameter inverse power law model provided by the invention can show a better model fitting effect when the acceleration effect does not meet the linear characteristic.

Methods, systems, and computer storage media for providing iterative data processing optimization using an iterative data processing optimization engine in a data intelligence system are described. Iterative data processing refers to handling data where the processing steps are repeated multiple times, across multiple views or modalities, to train machine learning models, filter and score data or generate output. The iterative data processing optimization engine employs expectation step machine learning models that are simple but with fast language models to efficiently and effectively probe and analyze data, while iteratively refining maximization step machine learning models that are optimized and fast to approximate the probing mechanism of the expectation step machine learning models more efficiently, for example, using metadata, external information, and compressed representation. The iterative data processing optimization engine can operate based on an agentic framework using lightweight artificial intelligence (AI) agents to perform model fitting, featurization, and report generation autonomously.

The invention discloses a multi-modal depth sensing and grabbing system based on a transparent object, which relates to the field of robot operation and comprises a multispectral sensing module, a depth correction module, a grabbing posture generation module and a control module. The visual information and the thermal radiation information of a transparent object are comprehensively obtained by combining two perception modes of an RGB-D image and a thermal imaging (TIR) image, systematic error analysis is performed on a depth map, and error sources of an RGB-D camera and a TIR camera are detected. The system adopts an encoder-decoder model as a depth correction core, the model extracts complementary features of an RGB-D image and a TIR image through a modal exclusive encoder, feature alignment and integration are completed by using a feature fusion module, and the depth estimation precision on the transparent surface is effectively improved. And meanwhile, a Bayesian optimization method is adopted to carry out hyper-parameter optimization on the depth correction model, through hyper-parameter optimization and model fitting processing, the system effectively avoids the problems of over-fitting and under-fitting, and the robustness of the depth correction model and the transparent object grabbing precision are further improved.

The invention discloses an allergic rhinitis diagnosis and allergen traceability system based on dynamic text guidance, and belongs to the technical field of intelligent medical treatment. According to the method, the problems that in the prior art, patient description is inaccurate, allergens are various in variety and have differences, and allergens are difficult to accurately determine and trace are solved, the initial situational sub-graph is verified by introducing periodic features of the patient, the causal contribution degree of the initial situational sub-graph is evaluated through a Bayesian reasoning algorithm, and a mode association result library is formed; according to the method, the crossing of the allergic rhinitis diagnosis and tracing from the traditional static judgment to the dynamic accurate inference is realized, and a personalized and scientific allergen avoidance scheme is provided for patients; through similarity retrieval, environmental information injection verification and calculation of a mode goodness-of-fit score, under the condition that patient symptoms are in multi-factor mixing, a mixed causal graph is created through a graph fusion technology, and the mode goodness-of-fit score is calculated again, so that the accuracy of obtaining an allergen traceability result in practical application is ensured.

The invention discloses an automatic boiler dosing method based on response surface modeling-PID coupling control, and relates to the field of thermal power boiler feed water treatment, and the method comprises the steps: collecting historical operation data, and employing a Pearson correlation coefficient method to screen out the correlation between the frequency of a boiler dosing pump and each parameter index; bBD design is carried out through response surface analysis, response values and factors in the dosing process are determined, and three different levels are selected for the factors; establishing a mathematical model between the response value and each factor through model fitting; setting a target value, substituting the target value into the response surface model for calculation, and taking the calculated value as a feedforward input quantity of a PID controller of the boiler dosing system; setting the deviation between the target value and the feedback value to obtain the adjusting frequency of dosing; and obtaining the final frequency of the ammonia adding pump by adopting a weighted average algorithm. According to the method, a mathematical model is constructed, an algorithm model and control logic are fused, and real-time response and control optimization of the boiler dosing control process are achieved.

The invention provides an electric vehicle energy consumption monitoring and abnormal power consumption identification method and system. The method comprises the steps that real-time operation parameters in the running process of an electric vehicle are inquired and obtained; the real-time running parameters of the driving segments are preprocessed; on the basis of the driving fragment preprocessing data, driving fragments are obtained through division, and the energy consumption value of the electric vehicle is calculated through an ampere-hour integral method; constructing a training set according to the driving segment energy consumption values, establishing and training an energy consumption reference model, performing energy consumption prediction on the electric vehicle, performing classification operation according to the driving segment energy consumption values, and marking a threshold range of energy consumption abnormal values; performing model fitting through a time sequence method, and predicting to obtain periodic change information of energy consumption of each driving segment along with seasons and data abnormal points; and according to the driving segment threshold range of the driving segment energy consumption abnormal value and the energy consumption prediction value, carrying out abnormity identification and giving an alarm. According to the invention, the technical problem of inaccurate identification of the running energy consumption of the electric vehicle and the abnormal power consumption of the vehicle is solved.

The invention discloses a dense topology model lightweight method, and belongs to the technical field of three-dimensional model processing. The problems that an existing scheme is low in efficiency, large in structural damage, poor in mapping quality and the like are solved. The method comprises the following steps: importing a dense grid model containing high-precision geometry and texture; selecting an automatic (adaptive lattice clustering algorithm) or manual mode to generate a target simplified topology; constructing a simplified model fitting the original model through a multi-direction projection technology; uV expansion is realized through automatic blocking, LSCM algorithm optimization and manual adjustment, and textures are baked in combination with RendertoTexture and SSAA technologies; and after performance optimization, outputting a lightweight model compatible with a mainstream format and an engine. According to the invention, high efficiency, stability and light weight are realized, key features are accurately reserved, visual consistency is guaranteed, and multi-scene application is adapted.

The invention provides a regional ionosphere modeling method and device, electronic equipment and a storage medium, and belongs to the technical field of satellite navigation positioning, and the method comprises the steps: obtaining the coordinates of a plurality of reference stations in a region, matching the coordinates with a preset threshold value, obtaining the coordinates of reference points, and obtaining the regional ionosphere based on the coordinates of the plurality of reference stations in the region and the coordinates of the reference points. Obtaining a longitude difference value and a latitude difference value between the regional reference station and the reference point, obtaining the coordinate of the target satellite, and obtaining the difference value of the elevation angles of the plurality of reference stations and the reference point observation target satellite based on the coordinate of the target satellite and the coordinates of the plurality of reference stations in the region; and constructing a coefficient matrix based on the difference value of the elevation angle and the longitude difference value and the latitude difference value between the regional reference station and the reference point, and constructing a regional ionosphere model based on the coefficient matrix and the obtained regional ionosphere model coefficient. Due to the fact that the influences of the horizontal gradient and the vertical delay are considered at the same time in the modeling process, the model fitting precision is remarkably improved.

Embodiments create models configured to predict behavior of real-world systems. An example embodiment receives input and output data for a real-world system and, next, subdivides the input and output data received into a plurality of subsets in accordance with a criterion. For each subset of the plurality, a regression model is fit to data of the subset. For each data point in each subset of the plurality of subsets, a respective weight is assigned to the data point for each regression model. In turn, the model configured to predict the behavior of the real-world system is generated by calculating a weighted average of each regression model using the assigned respective weights.

A method and a system for generating a 3D hand model are provided. The method includes: receiving heterogeneous hand keypoints collected from a plurality of tracking systems; performing a coarse optimization process to align the heterogeneous hand keypoints into an anatomical reference frame to produce unified hand keypoints; performing a fine optimization process to fit a hand mesh model to the unified hand keypoints; generating a 3D hand mesh using the hand mesh model fit to the unified hand keypoints; obtaining anatomical joint positions from the 3D hand mesh using a trained model; and outputting the 3D hand model including the 3D hand mesh and the anatomical joint positions.

The invention belongs to the field of electroencephalogram signal anomaly detection, and relates to an electroencephalogram anomaly detection method for a multi-feature map convolutional adaptive brain network, which comprises the following steps: acquiring an original electroencephalogram of a user, and performing short-time Fourier transform on the original electroencephalogram to obtain a time-frequency map; using bandwidth integral to apply power spectral density to represent spectrum characteristics of the time-frequency graph; extracting a difference entropy feature and a Shannon entropy feature of the time-frequency graph; respectively inputting the frequency spectrum features, the difference entropy features and the Shannon entropy features into a trained adaptive graph learning GNN model to obtain a detection result; wherein the adaptive graph learning GNN model is composed of an adaptive brain network learning module and a hybrid-jump GNN module; according to the algorithm, function connection corresponding to electroencephalogram signal fragments does not need to be calculated in advance before model learning, corresponding hyper-parameters are dynamically adjusted in the model fitting process, and therefore the brain network structure of each sample is completely learned in a data-driven mode.

The invention provides a lithium ion battery temperature prediction method based on a hybrid model ConvLSTM-NARX, the model is based on a classic convolutional neural network and a long-short-term memory neural network, and a delay mechanism and a feedback cycle mechanism of a nonlinear autoregression network with exogenous input are combined, so that the learning ability of the model for historical data is enhanced, and the prediction accuracy of the temperature of a lithium ion battery is improved. The overall performance of the model is improved. In order to verify the accuracy and generalization of the model, two experiments are performed on the model by using a common data set, and the model is compared with a reference model LSTM and a reference model CNN-LSTM. Experiments show that the error of the hybrid model in a static long-term temperature data set is 0.1 DEG C, and the model fitting degree reaches 94.57%; the error in a temperature data set of dynamic driving is less than 0.13, and the model fitting degree is more than 98%. In conclusion, the hybrid model provided by the invention has good accuracy and generalization.

The invention relates to a numerical control machine tool reliability modeling method and system considering a fault trend. The method comprises the following steps: checking the homogeneity of a numerical control machine tool based on the fault trend; constructing an AMSAA model of the multiple samples subjected to truncation at unequal time; evaluating the precision of the reliability model; aiming at the problem of insufficient reliability model precision of a multi-sample condition of a numerical control machine tool, a multi-sample AMSAA model modeling method of the numerical control machine tool considering a fault trend is provided, sample data classification is carried out through trend inspection and homotype inspection, and fault data of same-type machine tools are preprocessed by adopting a fault total time method; adopting a maximum likelihood method to estimate AMSAA model parameters of the same-type machine tool, and using Cramer-Von Mises to test the goodness of fit of the model; evaluating the precision of the reliability model by taking an average absolute percentage error (MAPE) of an instantaneous MTBF point estimation value and an MTBF observation value as an index; compared with a multi-sample AMSAA model established by a direct maximum likelihood method, the method is higher in prediction precision.

A method for assessing a lens capsule stability condition in an eye of a human patient includes simultaneously directing electromagnetic energy in a predetermined spectrum via an energy source onto a pupil of the eye after movement of the eye results in eye saccades occurring therein. The method further includes acquiring images of the eye indicative of the eye saccades using an image capture device and calculating a motion profile of the lens capsule using the images via an ECU. Additionally, the method includes extracting time-normalized lens capsule oscillation trajectories based on the motion profile via the ECU and then model fitting the lens capsule oscillation trajectories via the ECU, thereby assessing the lens capsule instability condition. Also disclosed herein is an automated system for performing an embodiment of the method, the automated system including an energy source, an image capture device, and an ECU.

A method for determining a model for an unknown function is described comprising training a neural network for selecting inputs at which to evaluate the unknown function. The training includes a plurality of iterations of sampling, from a set of Gaussian processes, at least one initial guess for the unknown function, using the neural network to select inputs and evaluating the selected inputs using the at least one initial guess, determining a value of an objective function from the evaluated selected inputs, adjusting the neural network to improve the value of the objective function and determining the model by evaluating the unknown function at a sequence of inputs given by the trained neural network and fitting the model to the evaluated inputs.