60 results about "Gradient boosting decision tree" patented technology

This invention relates to the field of image recognition and detection technology for foodborne pathogens, and discloses a method for identifying Listeria monocytogenes based on image recognition. The identification method includes: acquiring images of chromogenic culture medium plates and converting them to Lab and HSV color spaces; performing adaptive color normalization based on the background region of the culture medium; performing colony instance segmentation on the normalized image and extracting extended regions of interest; extracting saturation distribution sequences along radial rays and detecting halo transition patterns using first-order difference; statistically analyzing halo angle coverage and average transition amplitude, and combining halo quantization feature vectors; inputting the feature vectors into a gradient boosting decision tree classifier to output colony identification results. This invention solves the technical problems of unstable classifier discrimination boundaries caused by color shifts between different batches and the difficulty in detecting halos caused by weak lecithinase reactions.

This application relates to the field of civil aviation optimization technology, and in particular to a dynamic fuel consumption optimization system for civil aircraft based on real-time route data. The system includes modules for data storage, input, multi-source information fusion and feature extraction, intelligent evaluation, adaptive decision support, and output response. The system extracts multi-dimensional features by fusing real-time route and QAR data, constructs a correlation dynamic evaluation model using gradient boosting decision trees, simultaneously calculates flight performance index, fuel efficiency index, and correlation score, and generates a structured report based on a decision rule base, including cost index adjustment suggestions, altitude change schemes, and expected fuel savings predictions. This application enables dynamic and quantitative evaluation of the correlation between route environment and fuel consumption, overcomes the lag of traditional planning, and achieves precise and personalized flight strategy optimization, resulting in significant benefits in reducing costs, improving on-time performance, and reducing emissions.

This invention discloses a carbon emission prediction system and method for papermaking processes based on BO-GBDT. The system collects process parameters and energy consumption data during papermaking production, preprocesses the input data, constructs a feature set containing key influencing factors, and obtains a carbon emission dataset for model training. A Bayesian optimization algorithm is introduced to intelligently search for the optimal hyperparameters of four gradient boosting models, constructing a hyperparameter optimization space and setting an optimization objective function. Model performance is evaluated through cross-validation, and the optimal model is updated and selected. BO-GBDT is selected as the final prediction model. The trained model is then used to accurately predict carbon emissions from the papermaking process. By automatically optimizing the hyperparameters of the gradient boosting decision tree model using Bayesian optimization and combining it with multi-source data feature engineering, high-precision and high-efficiency prediction of carbon emissions from the papermaking process is achieved, providing an effective tool for carbon management in the production process.

This invention relates to the field of medical data-driven dose prediction technology, and discloses a method, system, device, and storage medium for individualized dose prediction of hypothyroidism based on medical data. The method includes: constructing a standardized feature vector based on the child's weight, age in days, corrected age in months, current L-T4 dose, TSH value, FT4 value, previous TSH value, TSH rate of change, feeding method, month of consultation, etiology of hypothyroidism, comorbidity status, previous dose adjustment magnitude, and age at which TSH first reached target levels; extracting TSH dynamic trajectory features from the child's TSH time-series data from previous follow-ups; obtaining a basic recommended dose using a gradient boosting decision tree model constructed with counterfactual filtering training data; and correcting the basic recommended dose to obtain an individualized recommended dose. This method improves the prediction accuracy of the gradient boosting decision tree model and allows the individualized recommended dose to simultaneously take into account multiple clinical confounding factors.

The application discloses an edge-cloud collaborative computing power scheduling architecture and a low-power consumption management method, and relates to the technical field of edge computing.The application collects multi-dimensional resource indexes of distributed edge computing nodes, calculates resource availability scores through standardized processing and weighted comprehensive score calculation; extracts static code features and dynamic running features of tasks, adopts a gradient boosting decision tree algorithm to predict execution time, CPU occupancy, memory requirement and network transmission data volume of the tasks, and performs node performance correction; adopts an improved non-dominated sorting genetic algorithm to solve a multi-objective optimization problem, and generates a task offloading decision; the application solves problems such as difficulty in resource quantification under an edge computing environment, lack of accurate prediction in task scheduling, poor single-objective optimization effect, and unintelligent power consumption control, realizes efficient task scheduling and low-power consumption operation, and has good scalability and adaptability.

The application discloses a kind of intelligent stirrer multi-mode operation control method and system, it is related to multi-mode operation control technical field, including the following steps, original data is carried out time alignment processing and fusion processing, obtain fusion multidimensional time series data, and carry out time sequence phase verification to obtain phase-corrected fusion multidimensional time series data, and carry out feature extraction to obtain time sequence statistical feature and spectrum analysis feature, calculate the modal confidence coefficient of each original data, the feature enhancement processing is carried out to time sequence statistical feature and spectrum analysis feature by modal confidence coefficient, obtain enhanced feature value, and arrange to obtain feature vector according to fixed order and input to gradient boosting decision tree, output the confidence degree that stirrer current operating state belongs to each preset control mode, based on confidence degree using multilayer decision strategy is judged to obtain target control parameter, and is converted into electric signal and is issued to motor driver, and the stirrer is regulated and controlled by motor driver.

This application provides a marketing expenditure allocation method, apparatus, electronic device, and storage medium. The method includes: firstly, determining a first target dataset containing at least one type of data; then, based on industry marketing characteristics and standards, constructing an indicator system containing multi-dimensional marketing expenditure allocation indicators, and classifying and summarizing the first target dataset to obtain a second target dataset; next, extracting feature factors from the second target dataset, which represent variables that affect marketing expenditure allocation, and determining allocation rules accordingly; finally, combining a gradient boosting decision tree and allocation rules to construct an allocation model to achieve dynamic and accurate allocation of marketing expenditures. This application significantly improves the accuracy and efficiency of marketing expenditure accounting in the oil and gas sales industry and optimizes marketing strategy evaluation and formulation by introducing an automated allocation model based on multi-dimensional data fusion.

The application discloses a shale gas reservoir characteristic prediction method, and belongs to the technical field of shale gas reservoir characteristic prediction. The method comprises the following steps: collecting and preprocessing multi-source data such as well logging, seismic, core and production dynamic; obtaining a fusion characteristic value based on a weighted fusion model; inputting the fusion characteristic into a gradient boosting decision tree model with a regularization term to predict reservoir characteristics; calculating the contribution degree of each input characteristic by using a Shapley value, and quantifying the prediction uncertainty by using a Monte Carlo method; dynamically updating the data source weight according to the prediction quality evaluation index, and forming a self-adaptive multi-source fusion closed loop. The method can realize efficient fusion and dynamic optimization of multi-source heterogeneous data, has the result explainability, credibility quantification and real-time updating capability, is high in prediction precision and stable, and is suitable for shale gas reservoir evaluation and production optimization.

This invention discloses a chip wire bonding inspection method, apparatus, electronic device, and storage medium, relating to the field of wire bonding inspection technology. It includes employing a hardware-triggered synchronization mechanism to connect a high-resolution optical microscope, X-ray computed tomography, and ultrasonic imaging system to acquire multimodal images, and integrating a high-precision vibration sensor to collect environmental vibration data, dynamically correcting the blur of the multimodal images; using a convolutional neural network and attention mechanism to extract multi-scale features from each modality of data, employing a cross-modal Transformer architecture for feature fusion, dynamically weighting the feature contributions of different modalities through a self-attention mechanism to highlight defect-related signals, introducing a graph neural network to model the wire bonding topology, capturing the spatial relationships between wire bondings, and generating a unified defect feature map; constructing an integrated model based on a gradient boosting decision tree and an online learning mechanism, and introducing an incremental learning algorithm.

This invention relates to the field of remote sensing monitoring technology for soil erosion and the ecological environment, and particularly to an inversion method for clearly defining the spatial distribution of biocrusts. The method involves collecting multidimensional environmental factor data influencing biocrust distribution through field surveys combined with UAV and high-resolution remote sensing imagery, and constructing a comprehensive environmental database. Key environmental driving factors are screened through statistical testing, and their effects on biocrust distribution and spatial differences are analyzed. Machine learning methods such as random forest, support vector machine, and gradient boosting decision tree are used to construct a static distribution model of biocrusts. This is further combined with time series decomposition technology to construct a spatiotemporally coupled probabilistic model of biocrust distribution. The model prediction results are visualized using GIS technology, inverting the spatiotemporal distribution characteristics of biocrusts and conducting uncertainty analysis. This achieves a refined and quantitative inversion of the spatial distribution of biocrusts in typical small watersheds in arid and semi-arid regions, clarifying the spatiotemporal evolution law and environmental driving mechanism of biocrust distribution.

The application provides a kind of all-weather ozone inversion method and system based on Fengyun three microwave data, including data acquisition and preprocessing, ozone inversion sample set establishment, ozone inversion model establishment and training, ozone inversion model verification four steps, through the fusion Fengyun three satellite microwave load multi-band data, ozone column total inversion is carried out based on machine learning method, XGBoost gradient boosting decision tree model is constructed using the training set, and the model training is completed by optimizing the hyperparameter through cross validation method, the precision and all-weather inversion ability of the model are verified using the test set, the inversion result of all-weather ozone column total is output, high-precision, all-weather ozone column total monitoring is realized.The application effectively overcomes the limitations of traditional ultraviolet and infrared remote sensing, which depends on light conditions and is easily disturbed by clouds, fills the technical blank of ozone column total inversion based on satellite microwave load, and realizes truly all-weather, all-time high-precision monitoring.

This invention belongs to the field of resident travel choice prediction technology, and particularly relates to a method and system for predicting resident travel choices in the dynamic evolution of rail transit networks. It includes preprocessing multi-source resident travel data, dividing it into training and test sets; constructing a gradient boosting decision tree model, training the model using the training set, and optimizing the model parameters using a GBDT hyperparameter automatic tuning method based on multi-objective Bayesian optimization; obtaining prediction results on the test set using the trained model, calculating the SHAP value and partial dependency graph of each influencing factor, and obtaining the nonlinear mechanism and dynamic evolution law of each influencing factor. This invention uses multi-source resident travel data from different periods of the dynamic evolution of rail transit networks for analysis and research, and innovatively introduces a multi-objective Bayesian optimization framework for automatic hyperparameter tuning, dynamically capturing the nonlinear laws of resident travel choices during the evolution of rail transit networks.

This invention discloses a landslide crack prediction method integrating LSTM-VAE and gradient boosting decision tree, comprising the following steps: collecting landslide-related monitoring data; preprocessing the monitoring data; constructing a landslide time-series data sequence; constructing a joint time-series data augmentation model based on LSTM and VAE, the LSTM-VAE model; training the LSTM-VAE model using the VAE loss function; generating synthetic data using the LSTM-VAE model and constructing an augmented dataset; dividing the augmented dataset into training, validation, and test sets according to a set ratio; establishing a landslide crack prediction GBDT model and training the GBDT model using the training set; evaluating the predictions of the GBDT model to obtain the optimal landslide crack prediction model. This invention, while ensuring the accuracy of the crack prediction model, solves the problems of traditional machine learning models' difficulty in effectively capturing the temporal characteristics of data and their high requirements for data quality, providing a scientific basis and technical support for landslide risk management at engineering sites.

The application discloses a pressure type anchor rod bearing property intelligent sensing and self-adaptive estimation system and method and a storage medium, and relates to the technical field of geotechnical engineering monitoring.The system comprises a sensing unit composed of strain, displacement and inclination sensors arranged on the anchoring section of the anchor rod, a bearing body and an anchor head; a data collector for collecting signals; a signal processing module for processing signals and internally embedding an estimation model; and a user interaction module for display and early warning.The method synchronously collects data through multiple sensors, extracts characteristic parameters after pretreatment such as wavelet denoising, inputs a self-adaptive estimation model constructed based on a gradient boosting decision tree ensemble learning algorithm, and outputs the estimated bearing capacity of the anchor rod in real time and realizes threshold early warning.The application overcomes the defects of the prior art, such as single monitoring dimension and inability to dynamically and accurately predict bearing capacity, through multi-source information fusion and a machine learning model, realizes the improvement of prediction accuracy, and provides an intelligent solution for anchor rod engineering safety.

The present invention discloses a method, system, medium and device for quality detection of Fructus Aurantii, which relates to the technical field of quality detection of traditional Chinese medicines, comprising obtaining the original spectral data of Fructus Aurantii samples, extracting the wavelength-absorbance data pairs from the original spectral data, and determining the original spectral matrix; performing polynomial least squares fitting on the original spectral matrix to determine the derivative spectral data for reflecting the changes in the chemical components of the samples; constructing an analysis model for quality detection of Fructus Aurantii based on the PLS-LDA combined model and the LightGBM gradient boosting decision tree, inputting the derivative spectral data into the analysis model, and obtaining the final detection result of the quality of Fructus Aurantii.

This application discloses a power system small—disturbance stability assessment and correction method and system considering the N-l operating mode. It relates to the fields of artificial intelligence, online static security stability assessment, and optimization of power systems. The method includes obtaining data of the power system under the N-l operating mode; inputting the data into a power sensitivity calculation model to output the system’s minimum damping ratio and the damping ratio sensitivity indices of each generator. The model is obtained using random forest and gradient boosting decision tree algorithms. It determines whether the minimum damping ratio is greater than or equal to the threshold value. If it is less than the threshold value, with the objective of minimizing the total active power change of generators, the active power of generators is corrected based on sensitivity indices and constraint conditions. The system’s minimum damping ratio and each generator’s damping ratio sensitivity index are then re-determined until the minimum damping ratio is greater than or equal to the stability threshold, thereby assessing the small-disturbance stability of the system. This application ensures the safe, stable, and reliable operation of the power grid.

This invention discloses a nursing resource allocation and management method and system based on emergency triage information. It introduces a dynamic split weight mechanism, first calculating the global correlation density of each triage feature to quantify its statistical value in the overall population, and simultaneously calculating local mutation significance factors to capture its weak but crucial discriminative information in critically ill samples. Then, the two are combined to generate dynamic split weights, which are used to optimize the split gain of features in the prediction model. This allows the gradient boosting decision tree algorithm to overcome the limitations of traditional global gain bias towards strong features during feature selection, effectively identifying those latent critically ill key features with low global importance but significant local mutations, significantly improving the prediction accuracy for latently critically ill patients. Based on accurate risk prediction results, nursing resources are dynamically allocated, realizing a shift from passive response to proactive intervention, and solving the technical problem of existing technologies failing to intervene in a timely manner due to missed identification of high-risk patients.

The application discloses a method and device for constructing a gradient boosting decision tree (GBDT) model, and relates to the technical field of machine learning, and mainly aims to solve the problem of low accuracy of the existing trained decision tree model. The main technical scheme of the application is as follows: obtaining a sample data set, wherein the sample data set comprises positive sample data with positive labels and unlabeled sample data without labels; when training each regression tree of the GBDT model, a positive sample training subset is constructed based on the positive sample data in the sample data set, a negative sample training subset is constructed by sampling the unlabeled sample data in the sample data set, the positive sample training subset and the multiple negative sample training subsets are combined to obtain a training set of the current regression tree, the current regression tree is trained based on the training set of the current regression tree, and a GBDT model is constructed according to each regression tree. The application is used in the construction process of the GBDT.

This invention relates to the field of aviation big data analysis technology, and particularly to a method, device, electronic device, medium, and product for predicting aircraft fuel consumption. The method includes: acquiring aircraft flight access records and meteorological reanalysis data; processing the data to obtain standardized historical flight data, standardized reference trajectory data, and future meteorological field data; processing the standardized reference trajectory data and future meteorological field data respectively to obtain a reconstructed trajectory for the future flight segment and a four-dimensional meteorological analysis result; combining the two to extract environmental parameters of the trajectory points; generating a physical enhancement feature set based on the standardized historical flight data and trajectory point environmental parameters; and obtaining the aircraft fuel consumption prediction result by using a preset gradient boosting decision tree. This invention solves the problems of poor physical interpretability, inaccurate prediction in complex stages, and weak future prediction ability in related technologies, improving the physical interpretability and prediction accuracy of aircraft fuel consumption prediction, and enhancing the precision and robustness of fuel consumption prediction.

This patent relates to an acute intraperitoneal toxicity prediction method based on MACCS bonds and a machine learning framework. This method collects and processes toxicity data of chemical compounds, calculates molecular descriptors using MACCS bonds, and constructs a gradient boosting decision tree model for toxicity prediction through feature selection and removal of highly correlated features. The model's hyperparameters are optimized using a grid search method, and the interpretability of the model is improved using SHAP value analysis. This achieves high-precision and highly interpretable toxicity prediction. The method achieves a coefficient of determination of 0.914, a mean squared error of 0.047, a root mean square error of 0.218, and a mean absolute error of 0.148 on the test set. This invention significantly improves the accuracy of toxicity prediction and has strong generalization ability, making it widely applicable to toxicity screening in new drug development, reducing reliance on traditional animal experiments, and lowering R&D costs and time.

This invention discloses a customer traffic prediction and dynamic resource allocation system for branch operations, comprising: a data acquisition module for collecting five types of structured data: time, business, customer, external environment, and policy drivers; a feature engineering module for classifying and labeling the collected data to form a high-quality feature set; a model training module that uses a fusion model of gradient boosting decision trees and extreme gradient boosting, dividing the model into training, validation, and test sets for training and optimization, and embedding a feature importance ranking mechanism; a traffic prediction module for inputting real-time data processed by feature engineering and outputting overall and business type-specific traffic prediction values ​​for a preset future time period; an attribution analysis module for locating core driving factors based on feature importance weights and generating an attribution report; and a resource allocation module for generating specific resource allocation plans based on the prediction results and core driving factors. This invention provides excellent support for customer traffic prediction and dynamic resource allocation in branch operations.

This invention provides a method and device for monitoring ground subsidence data in high geothermal extraction. The method includes the following steps: S1: Determining the monitoring area and setting up monitoring points; S2: Installing and debugging corresponding monitoring devices at the monitoring points; S3: Collecting multi-source raw data; S4: Preprocessing the multi-source raw data; S5: Constructing a collaborative fusion model of a long short-term memory network and a gradient boosting decision tree, and outputting the final fused subsidence amount; S6: Performing time series analysis, spatial distribution analysis, and anomaly detection. This invention, through a complete process design of "multi-source data acquisition - intelligent fusion modeling - dynamic analysis and early warning," achieves high-precision and dynamic subsidence monitoring, overcoming the limitations of accuracy and response lag in traditional monitoring methods, and providing key technical support for the safe and sustainable development of high geothermal resources.

This invention discloses a method for identifying and analyzing the driving mechanism of river and lake backflow based on interpretable machine learning, belonging to the fields of hydrological and water resources analysis and artificial intelligence application technology. The method includes: collecting long-sequence hydrological data of the river and lake system; dividing the time series into different characteristic periods using the operational nodes of large-scale water conservancy projects as boundaries; constructing a multi-dimensional input feature set; training a backflow identification model based on a gradient boosting decision tree using a class weight balancing strategy and a Bayesian optimization algorithm; calculating the marginal contribution value of each hydrological driving factor using the SHAP interpretability method; identifying the physical threshold inducing backflow by combining a SHAP dependency graph with a binary box plot; and comparing the analysis results of different periods to reveal the evolution law of the backflow driving mechanism. This invention effectively solves the problems of traditional methods' difficulty in capturing nonlinear hydrological responses and the lack of physical mechanism explanation in black-box models, and can accurately identify backflow events.

The application belongs to the technical field of industrial intelligent manufacturing and quality control, and particularly relates to an online prediction and early warning method for aviation assembly process quality based on data driving and knowledge fusion. In particular, the application relates to a system and method for realizing real-time calculation and closed-loop feedback of aviation assembly process quality risks by constructing a structured factor library, dynamically integrating weights by using an induced ordered weighted average (IOWA) operator, and fusing a gradient boosting decision tree (GBDT) model. The application is particularly suitable for early warning and prediction of the frequency of quality problems in key process of aircraft structure assembly and system installation.

This invention provides an RBAC+ABAC-supported access control method for AI knowledge bases, belonging to the field of AI knowledge base technology. This invention employs a gradient boosting decision tree and a Bloom filter to construct a simplified decision model. An optimization algorithm based on thermodynamic entropy finds the policy configuration with the minimum entropy value through simulated annealing, eliminating rule conflicts and simplifying the logical structure. During vector retrieval, the permission encoding vector and semantic vector are concatenated to form a joint vector to construct a permission-aware index. During answer generation, a permission context fingerprint is attached, and secondary propagation of permissions is verified through a permission re-verification gateway. Operation logs are recorded using a hash chain structure to ensure the immutability of audit traceability. This invention solves the technical problem that AI knowledge bases cannot simultaneously guarantee the efficiency of permission decisions and the maintainability of policy rules when performing fine-grained access control.

This application relates to a method for constructing a valve flow conduction model and a method for applying the valve flow conduction model. The method for constructing a valve flow conduction model includes: acquiring multi-dimensional valve data; processing the multi-dimensional valve data through feature engineering to obtain target features; the multi-dimensional valve data includes air pressure and valve opening; the target features include air pressure and the air pressure standard deviation within a preset time period; acquiring a pre-defined mapping relationship between air pressure range, air pressure standard deviation range, and operating conditions; determining the operating condition corresponding to the target features based on the mapping relationship, air pressure, and air pressure standard deviation; training a gradient boosting decision tree algorithm using the target feature data under each operating condition as input data and the predicted valve opening as output data to obtain a valve flow conduction model corresponding to the operating condition, with each valve flow conduction model corresponding to a specific operating condition.

This invention discloses a physical-data fusion-based method for rapid stress spectrum modeling and fatigue life prediction of bridge cranes, belonging to the field of crane structure safety assessment technology. Addressing the problems of low efficiency in traditional finite element stress calculation, the lack of consideration for the influence of variable stress ratios in conventional crack propagation models, and unreasonable handling of multiple alternating loads in a single working cycle, this invention establishes a stress sample library by building a finite element model of the crane's main beam and uses a gradient boosting decision tree model to achieve rapid stress prediction at critical points. Based on measured load spectra, the maximum and minimum stress values ​​of a single cycle are extracted to generate a stress spectrum. The Walker formula is used to correct the crack propagation rate, and the life prediction is completed by combining a periodic sample cycle method. This invention improves the efficiency of stress spectrum acquisition, ensuring that the stress spectrum compilation closely reflects actual service conditions, while correcting the life prediction deviation caused by variable stress ratios. It can be used for fatigue safety assessment and life prediction of in-service bridge crane metal structures, demonstrating high engineering practicality.

This invention belongs to the field of port operation and management technology. It proposes a ship behavior recognition method and system based on the LightGBM multi-classification algorithm. The method involves preprocessing AIS refueling behavior data and limited navigation mark data, performing feature extraction, feature selection, data standardization, and data balancing. This yields specific ship refueling behavior labels corresponding to the AIS refueling behavior data, enabling the model to effectively identify all refueling behaviors of various types of ships during operation and improving the accuracy of ship refueling behavior recognition. The LightGBM algorithm, through an efficient gradient boosting decision tree framework combined with feature extraction, feature selection, and data balancing, can accurately distinguish between different refueling and non-refueling behaviors of ships, improving the recognition accuracy of all ship refueling behaviors.

The grid search optimization gradient boosting decision tree-based protection measurement circuit error evaluation method comprises: standardizing the obtained protection measurement circuit data; implementing data enhancement and expansion through a deep convolutional generative adversarial network to generate a measurement circuit error data set; dividing the error data set into a training set and a test set for model training and model performance evaluation, respectively; training the training set through grid search and K-fold cross-validation to find the optimal parameters of the error severity gradient boosting decision tree classification model and construct a first multi-classification model; inputting the test set into the error severity gradient boosting decision tree optimal parameter model to identify and classify the error severity; and constructing a second multi-classification model to identify and classify the error type. The method applies grid search and K-fold cross-validation to optimize and train the gradient boosting decision tree algorithm, thereby achieving evaluation and classification of the severity and type of possible measurement errors in the protection measurement circuit.

The application discloses a kind of global positioning performance evaluation methods of satellite navigation system based on machine learning, including step 1, construct GBDT model, its input feature includes satellite geometry configuration parameter and satellite signal propagation section parameter;Predictive output is the positioning accuracy value of station position step 2, obtain sample original data set;Step 3, train sample original data preprocessing;Step 4, train GBDT model;Step 5, test sample original data preprocessing;Step 6, test sample prediction;Step 7, evaluate gradient boosting decision tree model;Step 8, evaluate station positioning accuracy.The application uses GBDT model, evaluates satellite navigation system global positioning accuracy;Use the data related to positioning accuracy as input feature, fitting positioning accuracy, does not rely on the observation and transmission of ground station, and positioning accuracy is high.