20 results about "Regression tree model" patented technology

The invention discloses an electric power intra-day price prediction method based on dynamic holiday weight and multi-source fusion, and the method comprises the steps: obtaining multi-source historical data, and carrying out the time synchronization processing; holiday and festival time information is acquired, and a dynamic weight is generated based on the influence of holidays and festivals and upstream and downstream dates on the power load and the electricity price; constructing a multi-dimensional predictive factor matrix based on the multi-source historical data after time synchronization processing; and according to the multi-dimensional predictive factor matrix, on the basis of a collaborative optimization multi-model combination comprising a feedforward neural network model and a bagged regression tree model, intra-day joint prediction is executed, the intra-day joint prediction refers to a process of predicting the power load and the electricity price hourly, and an hourly prediction result of the power load and the electricity price is output. A dynamic holiday weight mechanism is introduced, a multi-source fused high-dimensional predictive factor matrix is constructed, and a multi-model combined predictive strategy of collaborative optimization of a feedforward neural network and a bagged regression tree is adopted, so that the precision and stability of intra-day electricity price and load prediction of the electricity market are improved.

The application discloses a kind of central air conditioning system outlet water temperature and cold hot water pump frequency coupling operation method, including S1, collection basic data;S2, based on the basic data collected analysis central air conditioning cold and heat load influencing factor;S3, based on the cold and heat load influencing factor analyzed, constructs decision regression tree model;S4, according to the decision regression tree model constructed, central air conditioning system is carried out cooling and heating condition division;S5, according to the condition category divided to central air conditioning operation data is screened, determines the optimal host outlet water temperature and cold hot water pump frequency under each condition category as corresponding condition optimal setting parameter, realizes coupling operation.(1) the operation control method provided by the application simultaneously to host outlet water temperature and cold hot water pump frequency optimization, improve the energy-saving potential of central air conditioning system;The method of the application starts from actual engineering data, optimizes water temperature and water pump frequency while ensuring indoor comfort requirements, ensure the feasibility of the method.

This application discloses an intelligent orchestration method for Spark tasks based on gradient boosting regression trees, relating to the field of resource scheduling technology. The method includes: acquiring multiple Spark tasks and generating multiple task orchestration schemes; for any given task orchestration scheme, inputting the number of executors for each Spark task into a preset gradient boosting regression tree model, and outputting the predicted runtime of each Spark task; determining the fitness score of each task orchestration scheme based on the number of executors, startup time, and predicted runtime of each Spark task in each orchestration scheme; adjusting each task orchestration scheme and iteratively executing the prediction and scoring steps until a stopping condition is met; and determining the task orchestration scheme with the lowest fitness score as the target orchestration scheme for each Spark task. This application combines the prediction and evaluation stages to achieve a closed-loop decision-making process, improving the overall utilization of cluster resources.

The application discloses a kind of TBM rock breaking efficiency intelligent prediction methods based on rock slag size, which comprises the following steps: install industrial camera on TBM slag belt, and real-time acquisition rock slag image information in TBM tunneling process;The rock slag image information obtained is automatically identified, and the shape and geometric characteristics of the rock slag are obtained;Collect TBM's on-site tunneling parameters, rock slag geometric information characteristics and rock breaking efficiency data, and form sample data set;A gradient boosting regression tree model optimized by particle swarm algorithm is established using the sample data set, and the intelligent prediction of TBM rock breaking efficiency is realized.The application uses particle swarm algorithm to optimize the gradient boosting regression tree model, so as to find the best parameters of the gradient boosting regression tree model, improve the prediction accuracy of the model, and the accurate prediction of rock breaking efficiency can effectively provide reference for TBM tunneling parameter setting and efficient rock breaking.

The invention provides an indoor air conditioning method and system for tumor patients. The indoor air conditioning method comprises the steps that environment parameter values in a room and physiological parameter values of at least one tumor patient in the room are obtained; based on the environmental parameter values and the physiological parameter values, high-order features are determined, and the high-order features are used for representing the influence relation between the different parameter values; the environment parameter values, the physiological parameter values and the high-order features are input into a regression tree model, target environment parameter values output by the regression tree model are obtained, and the regression tree model is obtained through training based on sample environment parameter values in a plurality of sample rooms and sample physiological parameter values of a plurality of sample tumor patients in the sample rooms; the sample environment parameter value is a parameter value of which the comfort level of the sample tumor patient is greater than a preset comfort level; and based on the target environment parameter value, air in the room is adjusted. The air in the room where the tumor patient is located can be adjusted in a targeted and personalized mode.

This invention relates to the field of ecological environment assessment and spatial simulation technology, and discloses a method for grassland degradation ecological risk assessment based on a multi-agent model. The method includes a spatial risk assessment module that acquires multi-source basic data and divides it into discrete grid cells, calculating a landscape ecological risk index to generate spatial distribution results; a driving mechanism identification module that extracts driving factors to construct an improved regression tree model and outputs nonlinear response rules; and a multi-agent dynamic simulation module that constructs grassland environmental entities based on grid cells, injects risk indices and response rules, generates herder behavior entities, and inputs management policy parameters. Iterative calculations are performed using these two types of entities to simulate the dynamic process of herder relocation and resource consumption. After the iteration reaches the target year, the grid landscape attributes are reclassified according to the remaining grass cover, and the data is re-input into the assessment module for aggregation calculations, outputting a spatial distribution map to complete the evolution assessment. This invention can intuitively test the intervention effect of management policies on grassland degradation.

The invention provides a non-invasive cardiac expulsion measuring method and system. The method comprises the following steps: inputting preprocessed arterial pressure waveform signals and basic vital sign data into a parameter estimation neural network for feature extraction, and outputting a correction factor cal, a scale factor SF and a waveform correction coefficient; respectively inputting the correction factor cal, the scale factor SF and the waveform correction coefficient into a pulse contour model, a LiDCO power model and a FloTrac standard deviation model for calculation to obtain a cardiac output estimated value CO1, a cardiac output estimated value CO2 and a cardiac output estimated value CO3; and fusing the cardiac output estimated value CO1, the cardiac output estimated value CO2 and the cardiac output estimated value CO3 by adopting a gradient lifting regression tree model, and outputting a final cardiac output value. According to the invention, calibration-free continuous monitoring is realized, and the stability and precision of cardiac output estimation are improved.

The invention relates to an immunoassay automation equipment parameter optimization method based on a gradient boosting regression tree model, and solves the technical problems of how to optimize an inter-plate CV value, an in-plate CV value and a% RE absolute value in a detection process of existing electrochemical luminescence immunoassay equipment and how to improve parameter suitability. According to the method, sample incubation time T, cleaning times N, magnetic bead adsorption time t1 and magnetic bead beating time t2 are predicted through a constructed gradient lifting regression tree model, and equipment executes detection work according to prediction results so as to obtain optimized CV values, S / N and% RE of each hole.

The application belongs to the field of energy and particularly relates to a visual method for energy load prediction, which comprises the following steps: forming an energy load prediction model based on a classification and regression tree model and gradient boosting; inputting energy load historical data parameters and real-time parameters to form the energy load prediction model based on the classification and regression tree model and gradient boosting; and visually processing a prediction path and a prediction result of the energy load prediction model based on the classification and regression tree model and gradient boosting; the application can visually display the process of energy load prediction.

The invention provides an oil and gas recovery control method and device, a storage medium and equipment. The method comprises the steps that working data in the oil and gas recovery process are collected and stored, abnormal value detection and correction are conducted, and a corrected data set is stored; performing normalization processing on the corrected data; performing feature vectorization and tagging processing on the normalized correction data, and dividing a correction data set into a training set and a test set according to feature vectors and tags obtained by processing; establishing an original CART model by using the training set, adjusting by using the test set, and establishing a CART regression tree model; and determining the pumping capacity of the vacuum pump, and controlling the oil and gas recovery system in combination with the established CART regression tree model. According to the method, data collected and stored in the oil and gas recovery process are preprocessed to form feature vectors and labels, the regression model is trained, the trained regression model is predicted, related parameters are adjusted to meet the prediction accuracy requirement, and accurate control over the oil and gas recovery system is achieved.

The application discloses a power intraday price prediction method based on dynamic holiday weight and multi-source fusion, comprising: acquiring multi-source historical data and performing time synchronization processing; acquiring holiday time information, generating dynamic weight based on the influence of holidays and upstream and downstream dates on power load and electricity price; constructing a multi-dimensional prediction factor matrix based on the multi-source historical data after time synchronization processing; performing intraday joint prediction based on the multi-dimensional prediction factor matrix according to a collaborative optimization multi-model combination including a feedforward neural network model and a bagged regression tree model, wherein the intraday joint prediction refers to the process of predicting power load and electricity price by hour, and outputting the hourly prediction results of power load and electricity price. By introducing a dynamic holiday weight mechanism, constructing a multi-source fusion high-dimensional prediction factor matrix, and adopting a multi-model combination prediction strategy of collaborative optimization of a feedforward neural network and a bagged regression tree, the accuracy and stability of the power market intraday electricity price and load prediction are improved.

The invention provides a grillage structure underwater explosion response prediction method and system based on parametric modeling, and relates to the technical field of ship and ocean engineering structure safety assessment, and the method comprises the steps: constructing a test parameter set; inputting the test parameters into finite element simulation software in batches to obtain a response data set, wherein the response data set comprises multiple groups of response data; constructing each group of response data and the corresponding test parameters into a group of training data to obtain a training data set; training the random forest model through test parameters and rupture labels in the training data set to obtain a rupture prediction model; and training the gradient lifting regression tree model through test parameters, the maximum equivalent stress value, the maximum equivalent plastic strain value, the maximum deformation displacement value and the crevasse area in the training data set to obtain a physical response prediction model. The response prediction speed can be greatly increased through parametric modeling and model prediction, and the trained prediction model does not depend on a grid structure and has very high generalization ability.

The invention relates to the technical field of atmospheric environment monitoring, in particular to a water surface atmospheric environment monitoring and tracing system based on multi-source data fusion. According to the system, a monitoring layer adopts a dynamic sampling frequency adaptive algorithm to realize multi-source data synchronous acquisition, and the data precision of a high-pollution area is improved; the data transmission and fusion layer solves the problems of time-space dislocation and standardization of multi-source data through a time attention mechanism and an inverse distance weighting algorithm; the analysis layer improves a forward matrix decomposition model, realizes automatic pollution source identification by introducing a Bayesian optimization factor number and combining with random forest classification, and quantifies secondary pollution contribution by matching with a gradient lifting regression tree model; and the application layer realizes pollution source quantitative traceability and high-value area positioning through a geographically weighted regression model and hotspot analysis, and outputs visual products and prevention and control suggestions. The system effectively solves the problems of low water surface atmosphere monitoring data quality and insufficient traceability precision, and provides technical support for cross-regional joint defense and joint control of the Yangtze river basin.

The invention discloses an intelligent Spark task arrangement method based on a gradient boosting regression tree, and relates to the technical field of resource scheduling, and the method comprises the steps: obtaining a plurality of Spark tasks, and generating a plurality of task arrangement schemes; for any task arrangement scheme, inputting the number of actuators of each Spark task into a preset gradient lifting regression tree model, and outputting the predicted running time of each Spark task; according to the number of actuators, the starting time and the predicted operation duration of each Spark task in each task arrangement scheme, determining a fitness score of each task arrangement scheme; adjusting each task arrangement scheme, and iteratively executing the prediction and scoring steps until a stop condition is met; and determining the task arrangement scheme with the minimum fitness score as a target arrangement scheme of each Spark task. According to the method, the prediction link and the evaluation link are combined, so that a decision closed loop is realized, and the overall utilization rate of cluster resources is improved.

The invention discloses a method for determining evaporation complementary relation parameters based on interpretable machine learning, and relates to the field of ecological hydrology research, and the method comprises the steps: obtaining the evaporation complementary relation parameters of each drainage basin through the inversion of a water balance equation and an evaporation complementary relation; constructing an enhanced regression tree model according to the evaporation complementary relation parameters and the multiple drainage basin features, and determining key driving factors based on feature importance; by taking the key driving factor as an independent variable and the evaporation complementary relationship parameter as a dependent variable, establishing an evaporation complementary relationship parameter determination model corresponding to different partitions; and determining evaporation complementary relation parameters in a global range. According to the method, the relationship between different drainage basin characteristics and the evaporation complementary relationship parameters is explored, the evaporation complementary theory parameter determination model is established based on the interpretable machine learning method, effective acquisition of the evaporation complementary relationship parameters is realized, and the applicability of the evaporation complementary relationship in the global scale is improved.

The invention provides a capacity factor prediction method and system for new energy output, terminal equipment and a medium. The method comprises the following steps: acquiring a geographic position identifier, a current time period and meteorological data; retrieving a corresponding pre-trained regression tree model from a preset capacity factor database; inputting the meteorological data into the regression tree model, traversing a tree structure, and determining a target leaf node; reading to obtain a capacity factor prediction value; wherein the regression tree model is obtained through training according to meteorological sample data and sample capacity factors of historical data samples, and prediction output of each leaf node is optimized through Gaussian kernel density estimation. According to the method, the significant nonlinear and time-varying correlation between new energy power generation and meteorological conditions is considered, and compared with a traditional mean value prediction method, the influence of abnormal values can be avoided, so that the accurate prediction of the capacity factor is realized.

This invention discloses a system and method for synergistic regulation of nitrous oxide emission reduction and soil nitrogen leaching in farmland, relating to the field of farmland nitrogen management technology. The method integrates meta-analysis and enhanced regression tree models. Through steps such as collecting relevant research data on biochar application, screening effective sample data, constructing a meta-analysis database, identifying key influencing factors, establishing mathematical quantitative relationships, constructing an enhanced regression tree model, and developing simulation optimization schemes, it achieves accurate prediction and synergistic regulation of N2O emissions and soil nitrogen leaching under different farmland conditions. This invention can quantify the relative importance of each influencing factor, dynamically generate quantitative and operable field management plans adapted to different production scenarios, and ensure the stability of emission reduction effects through long-term monitoring and dynamic feedback mechanisms. It promotes efficient nitrogen utilization and sustainable development in farmland, possesses broad application value, is easy to implement and promote in large-scale farmland, and provides a reliable path for effective greenhouse gas emission reduction.

The invention discloses a black soil degradation real-time monitoring and early warning system and method based on multi-source remote sensing and the Internet of Things, and the system comprises a data sensing layer which is used for receiving the Internet of Things data, satellite image data and unmanned aerial vehicle image data of a research area, constructing a multi-stage land utilization transfer matrix and a geological profile in combination with prior historical data, and carrying out the real-time monitoring and early warning of the black soil degradation. Forming an ecological geological map; the data analysis layer is used for generating an agricultural machinery operation instruction by adopting an enhanced regression tree model fused with a soil science mechanism and a multi-objective optimization algorithm pair according to the ecological geological map so as to realize benefit-ecological balance; and the execution layer is used for receiving and analyzing the agricultural machine operation instruction, downloading and executing the operation parameters, and performing one-way hash on the data for storage after the operation is completed. Through accurate monitoring, optimized operation decision and efficient implementation, sustainable utilization and restoration of the land are supported, black soil resources are protected, the agricultural ecological environment quality is improved, and sustainable development of agriculture is promoted.

The application discloses a kind of unmanned aerial vehicle camera lens production manufacturing online monitoring analysis management method, and the application relates to unmanned aerial vehicle technical field.The method steps include: combining the pearson correlation and feature mutual information quantity between unmanned aerial vehicle lens feature data and unmanned aerial vehicle lens production environment data, obtain the environmental quality importance index and screen unmanned aerial vehicle lens production environment data, obtain unmanned aerial vehicle lens production environment screening data;Multivariate regression tree model is constructed;Unmanned aerial vehicle lens feature data and the feature weight obtained by analytic hierarchy process are combined, obtain lens evaluation index and classify unmanned aerial vehicle lens feature data by kernel density estimation method, obtain unmanned aerial vehicle lens label;When unmanned aerial vehicle lens label is corresponding unmanned aerial vehicle lens production environment screening data that needs to be rechecked, input multivariate regression tree model, obtain prediction error result;Combined with error prediction result and environmental quality importance index, obtain environmental quality correlation index, carry out traceability early warning.

The invention relates to the technical field of ecological environment assessment and space simulation, and discloses a grassland degradation ecological risk assessment method based on a multi-agent model, and the method comprises the steps: obtaining multi-source basic data through a space risk assessment module, dividing the data into discrete grid units, calculating a landscape ecological risk index, and generating a space distribution result; the driving mechanism identification module extracts driving factors to construct a lifting regression tree model, and outputs a nonlinear response rule; the multi-agent dynamic simulation module constructs a grassland environment entity based on a grid unit, injects a risk index and a response rule, generates a pasture behavior entity, inputs a management policy parameter, executes iterative operation by using the two entities, and simulates a pasture addressing transfer and resource consumption dynamic process; after iteration reaches the target year, grid landscape attributes are re-classified according to the residual grass quantity, the grid landscape attributes are re-input into the evaluation module for aggregation operation, and a spatial distribution map is output to complete evolution evaluation. The method can visually test the intervention effect of the management and control policy on the grassland degradation.