36 results about "Dimensionality reduction algorithm" patented technology

The invention relates to the technical field of computer vision, in particular to a fabric color fastness analysis method and system based on image processing. Comprising the following steps: acquiring a multispectral image of a to-be-detected fabric, and synchronously acquiring multi-factor data; processing the multispectral image to generate an enhanced image; performing image recognition on the gray sample card in the enhanced image to generate a calibration image; performing spectral data projection on the calibration image through a dimension reduction algorithm, and performing color analysis and quantification on color change to generate color difference features; extracting texture features by using a conditional generative adversarial network, carrying out image recognition and calculation on the calibration image through a decoupling algorithm, and generating a region credibility graph; and inputting the chromatic aberration features, the texture features, the multi-factor data and the regional credibility map into an image feature fusion model for mapping, performing analysis through gradient visualization, and outputting an abnormal feature saliency map. According to the method, a color fastness objective analysis closed loop is created, so that the accuracy and the universality of an analysis result are improved.

The invention discloses a cement-based material phase identification and quantitative analysis method combining artificial intelligence and expert knowledge. The method comprises the following steps: acquiring a BSE image, a qualitative element surface spectrum and a quantitative element surface spectrum of a cement-based cementing material sample; synthesizing a color EDS image based on the qualitative element surface spectrum, and performing superpixel division on the image; based on the quantitative element surface spectrum, extracting an average value of element relative contents of all pixels in each superpixel range as an element feature; performing two-dimensional visualization processing on all the element features by adopting a PHATE dimension reduction algorithm to generate derivative element features; performing manual correction and phase label labeling on a clustering result by utilizing a Glue multi-view interaction platform in combination with expert priori knowledge; and fusing the corrected clustering result with the superpixel division result, and regenerating a new phase classification mask with a phase identifier. According to the method, intelligent identification and high-precision analysis of the cement-based material multiphase system can be realized, and the accuracy, reliability and interpretability of phase classification are improved.

A system, method, and computer-program product includes receiving a plurality of vector embeddings having an initial dimensionality and projecting the plurality of vector embeddings into lower-dimensional spaces using at least two different dimension reduction algorithms to generate corresponding sets of projected vector embeddings. Each set of projected embeddings may be quantized and nearest neighbors for the original embeddings and for each quantized set of projected embeddings may be calculated. Additionally, a neighbor preservation metric may be evaluated for each quantized set by comparing its nearest neighbors to those of the original embeddings. Based on the neighbor preservation metrics and a predefined error tolerance, an optimal compression configuration may be selected.

This invention relates to the field of wind power generation technology and discloses a method, device, equipment, and medium for fault assessment of wind turbine transmission systems. The method utilizes a data dimensionality reduction algorithm to reduce the dimensionality of multidimensional raw data, retaining core distinguishing features and simplifying calculations. Then, a data clustering algorithm is used to intelligently classify operating states, and a preliminary fault mode mapping is constructed by combining historical faults. Subsequently, the rationality of clustering is verified using signal source correlation coefficients, and long-term historical operating data is filtered through historical data matching rates to reduce the risk of misjudgment. Next, based on time series analysis and degradation path analysis, the coupling relationship between vibration trend slope, temperature accumulation offset, and torque decay cycle is obtained. Finally, core features are extracted through convolutional neural networks to accurately output the probability distribution and specific location of fault occurrence, thereby improving the accuracy of fault identification in the transmission system of offshore wind turbines and the ability to predict component performance degradation.

The invention discloses a data analysis method and system based on questionnaire investigation, and particularly relates to the technical field of data analysis, and the method comprises the following steps: S1, collecting and preprocessing questionnaire data, and obtaining original questionnaire data; s2, questionnaire feature engineering: extracting core features from the standardized questionnaire data set based on a joint screening mechanism of semantic similarity and information gain, and obtaining low-dimensional feature vectors through a dimension reduction algorithm; s3, subject mining and user group division are carried out on the low-dimensional feature vectors; and S4, outputting a result based on the analysis model, and generating a targeted questionnaire analysis report which comprises topic distribution, group difference and potential demand association conclusions. According to the data analysis method and system based on questionnaire investigation, through a multi-strategy fusion preprocessing mechanism, a combined screening feature engineering method, a fusion modeling analysis strategy and a self-adaptive model optimization module, the accuracy and efficiency of questionnaire data analysis are improved.

This invention relates to a big data topic analysis method based on an embedding model. First, the Sentence-BERT model is used to perform sentence embedding representation on preprocessed Chinese text data. Then, the UMAP projection dimensionality reduction algorithm is used to reduce the dimensionality of the embedded vectors. Next, the HDBSCAN clustering algorithm is used to cluster the dimensionality-reduced vectors. Based on the assignment of each Chinese text in the target Chinese dataset to a corresponding topic class, the Chinese words with the highest c-TF-IDF scores are selected to represent each topic class. Finally, the DSG model is used to perform word embedding representation on the topic words, calculating the similarity between different topic words and between different topic classes, thereby detecting the volatility of newly emerging topic classes. The entire scheme design has higher topic consistency and topic diversity, and can detect new hot topics in a timely and accurate manner, providing early warnings.

The invention discloses a multi-label smell description prediction method, and relates to the field of compound smell prediction, and the method comprises the steps: obtaining compound identification information, molecular structure descriptors and smell label data, and constructing a multi-label smell data set; generating a molecular structure feature vector through a molecular fingerprint coding technology, and extracting a multi-dimensional descriptor reflecting the physicochemical properties of molecules; compressing the molecular fingerprint features to a low-dimensional space through a dimension reduction algorithm; performing unbalanced data processing on the training set, fusing the dimension-reduced molecular fingerprints with the molecular descriptors to form a joint feature matrix, and configuring a class weight balance mechanism and overfitting suppression parameters by adopting a multi-label classification architecture; independently optimizing a probability threshold for each odor label based on the verification set; and outputting a multi-odor label combination prediction result according to the target molecule identification information. According to the scheme, the multi-odor characteristics of the compound can be accurately depicted, and the combined recognition accuracy of the compound odor is remarkably improved.

A system and method of determining efficacy of treatment by at least one processor may include receiving, from at least one camera, images depicting motion of an animal that may be treated with a predetermined substance of interest. Said processor may extract from the images, a plurality of motion features representing motion of at least one specific body part of the animal, and apply a dimensionality reduction algorithm on the plurality of motion features, to obtain a latent vector representing the plurality of motion features in a latent space. The latent vector may include a plurality of latent features. Said processor may subsequently calculate a value of a behavioral indicator, representing a behavior of the animal, based on the latent features of the latent vector, and determine efficacy of the treatment based on the behavioral indicator value.

A large language model-driven unit combination optimization method, relating to the field of power system technology, includes: acquiring basic economic operation data of the power system; constructing and solving a unit combination model with integer relaxed security constraints based on the basic economic operation data; obtaining and solving the unit combination model; constructing variable dimensionality reduction algorithms, constraint dimensionality reduction algorithms, and infeasibility solution repair algorithms; using a large language model to perform single-algorithm evolution on the variable and constraint dimensionality reduction algorithms; using a large language model to perform single-algorithm evolution on the infeasibility solution repair algorithm; solving and calculating the unit combination model with integer relaxed security constraints; calculating the variable constraint dimensionality reduction security constraint unit combination model and obtaining the optimal solution; and using the optimal infeasibility solution repair algorithm to repair the optimal solution of the variable constraint dimensionality reduction security constraint unit combination model, obtaining the result. This method addresses the shortcomings of existing model dimensionality reduction methods in terms of generality, stability, and interpretability.

The invention belongs to the technical field of oil field logging, and discloses an oil field logging data optimization method based on machine learning and a related device. Original oil field logging data are collected through multi-source logging equipment and preprocessed to generate a preprocessed data set; feature correlation analysis and model importance evaluation are carried out on the data set to extract a key feature set through a dimension reduction algorithm, then the key feature set is adopted to train a pre-constructed machine learning model to obtain a logging data optimization model, and finally the model is applied to optimize to-be-processed logging data and output an optimization result. By adopting the method, the effectiveness and representativeness of logging data characteristics can be remarkably improved, the real condition of an underground reservoir can be accurately reflected, the full-well-section high-resolution logging data can be simply, conveniently and quickly obtained at low cost, a reliable basis is provided for a shale oil and gas development scheme, and the rationality of the development scheme and the overall development efficiency are further enhanced.

The invention relates to the technical field of performance detection, and discloses a metering equipment full-performance detection result automatic determination method, equipment and a medium, and the method comprises the steps: collecting multi-dimensional performance parameters of metering equipment under different test conditions, carrying out the preprocessing and preliminary feature extraction of the multi-dimensional performance parameters, and carrying out the calculation of the full-performance detection result of the metering equipment; performing intelligent comprehensive processing by using a nonlinear high-dimensional dimension reduction algorithm to obtain comprehensive performance parameter data; the comprehensive performance parameter data is intelligently detected through a detection algorithm based on machine learning, a detection result is obtained, a judgment result is automatically generated based on the detection result in combination with self-adaptive threshold adjustment, and the method can solve the technical problems that equipment performance parameters are not comprehensively considered, processing is not accurate, and detection and judgment are not accurate.

This invention discloses a rapeseed quality detection method based on feature wavelength optimization and multi-model fusion. The method involves collecting full-band near-infrared diffuse reflectance spectral data of rapeseed samples and simultaneously measuring the true values ​​of physicochemical indicators to construct an original dataset. Based on the data distribution characteristics of each physicochemical indicator, the original dataset is divided into a training set and a test set. Preprocessing algorithms are selected for each physicochemical indicator to process the full-band near-infrared diffuse reflectance spectral data. Dimensionality reduction algorithms are selected for each physicochemical indicator to extract feature wavelengths from the preprocessed spectral data. Predictive models for each physicochemical indicator are established based on the training set, and the performance of the predictive models is verified using the test set to determine the optimal algorithm combination for each physicochemical indicator. The variable importance projection algorithm is used to calculate the comprehensive contribution score of each wavelength point in the full-band spectrum to the four physicochemical indicators. A multi-indicator comprehensive threshold is set, and the core light source wavelength of the portable device is determined from the high-score region.

The invention discloses an unsupervised dimensionality reduction visualization method for cell image data. The method comprises the following steps: acquiring an unlabeled cell image high-dimensional data set; processing the high-dimensional data set by adopting an unsupervised dimension reduction algorithm to generate low-dimensional embedding representation; generating a first visual chart based on the low-dimensional embedded representation to display the distribution of the data in the low-dimensional space; performing unsupervised clustering analysis on the data points in the low-dimensional embedding representation, and identifying at least one clustering center point; generating a second visual chart based on a clustering analysis result, and marking a clustering center point in an identifiable manner; according to the method, the clustering center point can be accurately identified, and a visual data distribution overview is provided for a user.

The invention discloses an intelligent power distribution system optimization control method based on a knowledge graph, and the method comprises the steps: collecting and preprocessing multi-source power distribution operation data, and constructing a power distribution knowledge graph; performing feature extraction and fusion to generate a power distribution high-dimensional state matrix; constructing a neighborhood graph and executing an Isomap manifold learning algorithm to generate a low-dimensional manifold space; constructing an improved Brown bridge diffusion model, and generating a state evolution path; multi-class risk probabilities are calculated, and a power distribution state risk field is generated; and executing a sequential quadratic programming algorithm, and solving an optimal control strategy. By introducing knowledge graph semantic expression, a curvature correction manifold dimension reduction algorithm, an improved Brownian bridge diffusion model and a sequential quadratic programming algorithm, accurate prediction, risk perception and optimal control of the operation state of the power distribution system are realized.

This invention provides a system and method for identifying the categories of Chinese medicinal materials and detecting chlorogenic acid content based on Vis-NIR hyperspectral imaging technology, belonging to the field of plant detection technology. This invention employs hyperspectral imaging technology and multiple dimensionality reduction algorithms to establish models for identifying the categories of Chinese medicinal materials and detecting chlorogenic acid content. Furthermore, this invention optimizes the feature data during model construction using the BO-BOSS algorithm, further improving the accuracy of the model, ultimately achieving non-destructive and accurate detection of the categories of Chinese medicinal materials and their chlorogenic acid content. The detection method described in this invention features high detection accuracy, strong robustness, and non-destructiveness, without causing irreversible damage to the sample interior. It provides reliable technical support for crop / medicinal material harvesting category diagnosis and effective component detection, and offers valuable reference for hyperspectral imaging technology in the category identification and quality detection of other agricultural products, demonstrating excellent practicality.

This invention relates to a method for radio signal identification based on multidimensional feature extraction and feature fusion, belonging to the fields of signal recognition and deep learning technology. The invention collects radio signal data, segments the collected radio signals, and converts them into two-dimensional data. Four instantaneous features are extracted from the radio signals. Time-frequency transformation is performed on the radio signal data, and Shannon entropy feature values ​​are extracted. The extracted instantaneous features and time-frequency features are fused, and a linear discriminant analysis (LDA) dimensionality reduction algorithm is used to reduce the dimensionality of the fused feature data. The processed signal data is then input into a deep learning classification network model for signal identification to obtain its corresponding signal category. This invention combines the ideas of multidimensional feature extraction and feature fusion to achieve high-accuracy radio signal identification. Furthermore, by leveraging the advantages of deep learning technology, it can improve the speed and accuracy of radio signal identification.

This application provides a data processing method, apparatus, and electronic device for a risk control system. The data processing method first acquires first data about multiple risk control objects from different target data sources. Then, it determines the data type of the first data, quantifies it according to the data type, and determines the second data to obtain the target data set. Finally, it determines the similarity between each target data set and a preset data set using a pre-defined dimensionality reduction algorithm. This allows the risk control system to determine the source data from the target data sources based on the similarity scores. It effectively identifies data redundancy from each target data source based on the similarity scores, thus determining the source data required by the system. This reduces the workload of processing massive amounts of data when implementing risk control strategies, ensures the effectiveness and timeliness of risk control, effectively reduces maintenance costs, and facilitates data sharing mechanisms.

The invention relates to the technical field of wire rod production surface defect detection, in particular to a Litz wire surface defect detection system and method, and the system comprises an image collection module which is used for continuously collecting high-definition images of the surface of a Litz wire; the image processing and analyzing module is used for receiving and processing the image data transmitted by the image acquisition module; and the control and execution module is used for receiving and comparing the data transmitted by the image processing and analysis module and carrying out abnormity alarm, trend early warning and data recording. According to the method, the width, the pitch and the angle of the Litz wire are synthesized into a twisting quality index (TQI) for judgment by adopting a mechanical vision detection matching algorithm, an image is analyzed by utilizing a mode of combining a morphological opening operation and a PCA dimension reduction algorithm, high-robustness and high-precision detection is realized, quantitative detection of the pitch is realized, and the detection precision of the Litz wire is improved. The problems that existing visual detection is poor in stability and low in precision, and the pitch is difficult to quantify are solved.

The invention discloses an apple near infrared spectrum prediction model establishment and grading detection method. The method comprises the following steps: firstly, acquiring a sugar content measured value of an apple sample, and collecting corresponding near infrared spectrum data; next, the collected spectral data is preprocessed, including methods of applying D1, MSC, SNV, Savitzky-Golay smoothing, standardization, maximum and minimum normalization and the like, and an optimal combined preprocessing method is selected from the methods; and carrying out dimension reduction on the preprocessed data through a feature dimension reduction algorithm, such as PCA, ICA and TSVD, so as to screen out an optimal feature dimension reduction method. And finally, predicting the sugar content of the apples by using regression models such as least partial squares regression, support vector regression, ridge regression and kernel ridge regression, and selecting an optimal regression model to establish a final prediction model.

The application provides a kind of underwater sound field prediction method, medium and system based on multi-source data fusion and agent architecture, belongs to underwater sound field prediction technical field, the application is processed through the abnormal value of marine observation data, high-dimensional multi-parameter coupling data is mapped to low-dimensional manifold space by adopting manifold dimension reduction algorithm and is interpolated and expanded, the station environment data is reconstructed using a physical constraint variational encoder, the reconstructed data is constructed as a graph structure to input the marine environment graph reconstruction model to generate a three-dimensional marine environment field by topological interpolation prediction. An underwater sound field prediction agent is constructed, the quantitative features of the three-dimensional marine environment field are extracted, the heterogeneous computing model is adaptively scheduled based on the preset strategy, and finally the original calculation results of each model are integrated and converted into the standardized sound field data unified in the system. The system realizes high-fidelity reconstruction of the marine environment field and adaptive optimization of the sound field prediction model, and completes the full-link automation from data processing to accurate prediction.

The embodiment of the invention provides a method for analyzing and predicting the migration ability of a model across data sets and related equipment. The method and the equipment are used for visually analyzing the migration ability of the model among different protein thermal stability data sets by using a dimension reduction algorithm. The method comprises the steps of obtaining a to-be-analyzed thermal stability data set; taking the target thermal stability data subset as a target training data set, and determining a target thermal stability prediction model; inputting the target training data set and the target reasoning data set into a target thermal stability prediction model for feature extraction to obtain training set high-dimensional features and reasoning set high-dimensional features; inputting the training set high-dimensional features and the reasoning set high-dimensional features into a dimension reduction model, and performing dimension reduction processing to obtain training set low-dimensional features and reasoning set low-dimensional features; and mapping the training set low-dimensional features and the reasoning set low-dimensional features to a target low-dimensional space, and determining feature relevancy between the training set low-dimensional features and the reasoning set low-dimensional features.

The invention discloses a wheat soil moisture prediction method based on a mixed PPLSTM model, and the method comprises the following steps: S1, obtaining soil moisture data in a wheat growth period, and carrying out the preliminary screening of data features; s2, performing data preprocessing on the acquired soil moisture data; s3, performing dimension reduction processing on the high-dimensional features by using principal component analysis (PCA); s4, optimizing hyper-parameters of the long short-term memory (LSTM) network by using particle swarm optimization (PSO); s5, inputting the optimized LSTM network into training data for training to obtain a prediction model; s6, testing the trained model by using the verification set, and outputting a prediction result; and S7, optimizing parameters of the LSTM model according to a test result, and performing final training to obtain a model with optimal prediction precision. According to the method, the PSO optimization algorithm, the PCA dimension reduction algorithm and the LSTM network are combined, so that the problems that in a traditional method, high-dimensional input features are redundant, the time dependence relation capturing capacity is insufficient, and hyper-parameter selection depends on experience are solved. Compared with a traditional LSTM model, the method has the advantages that on the basis of keeping the sequence modeling capability, the prediction precision and stability are remarkably improved, and a more reliable decision basis can be provided for intelligent irrigation scheduling, so that the water-saving irrigation practice is effectively promoted, and the sustainable development of precision agriculture is promoted.

The invention provides a multi-objective optimization method for a high-efficiency permanent magnet synchronous motor rotor structure. The multi-objective optimization method comprises the following steps of defining design parameters and an optimization objective function; extraction and weight calculation of clustering working condition points; screening core design parameters; dimensionality reduction of the optimization indexes; and an NSGA-II algorithm is used for optimization. The method has the beneficial effects that parameter optimization and multi-working-condition performance analysis are further carried out in combination with the actual driving working condition, air gap flux density distribution is optimized through rotor topology innovation, higher harmonics are weakened, effective reduction of motor iron loss, torque pulsation and electromagnetic vibration is achieved, and meanwhile the efficient operation interval is widened; according to the method, the dimension reduction of the target and the parameter is realized in combination with a dimension reduction strategy, so that the optimization design efficiency is improved, and the motor can realize the comprehensive balance of the performance in the whole driving cycle range, thereby avoiding the problem of performance mismatch possibly caused by single-working-condition optimization under the multi-working-condition operation condition, and ensuring that good operation characteristics can be kept under the multi-working-condition.

The application provides a recipe construction system, method, readable storage medium and computer program product. A dimension reduction module obtains dimension reduction ingredient information according to ingredient information of each historical recipe information and a dimension reduction algorithm; a neural network module obtains a plurality of trained neural network parameters according to the ingredient information and the dimension reduction ingredient information; the neural network module obtains dimension reduction initial ingredient information according to the plurality of trained neural network parameters and initial ingredient information; a search module searches for a plurality of candidate recipe information with a first number from the plurality of historical recipe information; a judgment module judges whether the property information of each candidate recipe information meets the specification, and outputs a recipe solving information meeting the specification.

The invention relates to an offset printing color separation method for directly converting a source color space and a target color space of an offset printing machine. According to the method, an intermediate standard color space conversion process is abandoned, and a direct color separation path is constructed. The color separation result of target color spaces such as CMYK is determined and parameters are recorded by widely collecting multi-form source color samples in different industries, covering images, graphs and physical color cards, using high-precision equipment to measure numerical values of the samples in multiple color modes and combining professional software and printing experiments. Multi-dimensional characteristic parameters are extracted through data mining and machine learning, a comprehensive and accurate database is established, and support is provided for a direct conversion algorithm. According to the algorithm, color separation values are calculated by means of dimensionality reduction algorithms such as PCA and models such as kd-tree search and linear regression, and self-adaptive adjustment can be achieved. Meanwhile, through a real-time calibration mechanism, a spectrophotometer and a Delta-E color difference formula are utilized, parameters are adjusted in combination with a PID controller, it is ensured that colors are accurately restored, the method adapts to a complex printing environment, and innovation of the offset printing technology is promoted.

This invention provides a UAV remote sensing method for estimating farmland soil salinity by removing vegetation interference. The method separates soil and vegetation using the OTSU automatic thresholding method to extract features from pure soil pixels, reducing the image's spectral characteristics. Then, it constructs an index set including salinity index, vegetation index, and other indices, directly linking salinity estimation to the spectral information of soil properties, reducing the uncertainty caused by mixed pixels. Next, it uses feature reduction algorithms such as recursive feature elimination for variable optimization, then uses the optimized variables as input variables and employs machine learning algorithms such as extreme gradient boosting regression to construct a soil salinity inversion model. Finally, it draws a predicted SSC content map at the plot scale based on the inversion model.

An object of the present invention is to provide a technique for identifying the type of oil.SOLUTION: According to an aspect of the present invention, there is provided a method for generating an estimation model for a type of oil, the method including generating an estimation model using an information processing system including an input unit, an output unit, a processing unit, and a storage unit, the information processing system including an estimation model generation unit configured to generate an estimation model, the estimation model generation unit being configured to take in absorption spectrum obtained by transmitting light having at least a part of wavelengths of 800nm from the wavelengths 2500nm through oil of a known type, and analyze the absorption spectrum using a dimension reduction algorithm to generate the estimation model for the type of oil.SELECTED DRAWING: Figure 9

The application discloses a variable fertilizer machine prescription map efficient storage and retrieval method and device, a latitude and longitude coordinate dimension reduction algorithm is designed, two-dimensional latitude and longitude coordinates are changed into one-dimensional strings, and a multi-way tree data storage format and a retrieval method are designed, the method can solve the problem that the efficiency of traditional prescription map sequential storage and sequential retrieval sharply decreases with the increase of data size, reduces the sensitivity of prescription map retrieval time consumption to data size, and guarantees the high matching of actual fertilization operation and the prescription map under different plot sizes and variable fertilization operation precision.

The present application belongs to the technical field of food safety detection, and particularly relates to a detection method for contaminated vegetable oil by deep learning assisted three-dimensional fluorescence spectrum. The present application firstly predicts the optimal adsorption condition of magnesium silicate on vegetable oil based on a linear regression model and an L-BFGS-B algorithm, realizes the targeted separation of mineral oil in contaminated vegetable oil through the adsorption of magnesium silicate on vegetable oil under the optimal condition. Then, based on the separated mineral oil pollutant sample, a plurality of pre-training network models are applied to extract characteristic fingerprint spectra of different mineral oil categories from the collected three-dimensional fluorescence spectrum, so as to distinguish several common mineral oil pollutant categories. In combination with a parallel factor data dimension reduction algorithm, the fluorescence components of the corresponding pollutants in the mineral oil are decomposed and determined. Finally, based on the corresponding relationship between the fluorescence signals and the concentrations of each pollutant component, a support vector regression model of the corresponding component is built, and then the quantitative detection of various pollution components in the mineral oil is realized.

The embodiment of the invention provides an SWMM model parameter automatic calibration method. The method comprises the following steps: screening parameters in an SWMM model by adopting a Morris screening method to obtain target to-be-calibrated parameters; generating a plurality of groups of parameter samples based on the value range of the target to-be-calibrated parameter, inputting the parameter samples into the SWMM model for simulation calculation, obtaining a simulation node water depth time sequence corresponding to the parameter samples, and forming a training sample data set; performing dimension reduction processing on the simulation node water depth time sequence in the training sample data set by adopting a dimension reduction algorithm to obtain input data after dimension reduction; taking the input data after dimension reduction as input layer data and the parameter samples as output layer data, constructing a back-propagation neural network model, and introducing a sparrow swarm search algorithm to optimize initial parameters of the back-propagation neural network model to obtain a fusion optimized neural network agent model; and carrying out dimension reduction processing on the actually measured output data of the research area by adopting a dimension reduction algorithm, inputting the actually measured data after dimension reduction into the fused and optimized neural network agent model, and outputting the calibrated uncertainty parameters.