26 results about "Information gain ratio" patented technology

The present invention relates to a multi-region collaborative control method and device for a high-precision pressure sensor array. The method: based on a first collaborative sampling parameter, data is collected from multiple sensor units in a pressure sensor array to obtain a pre-processed pressure data set and a sensor unit spatial position matrix; a spatial weighted pressure covariance matrix is ​​constructed; eigenvalue decomposition and information entropy calculation are performed, and the number of target pressure points is determined according to the minimum description length criterion and the information gain ratio; a pressure feature subspace and a local perception domain are constructed; the pre-processed pressure data set is projected onto the pressure feature subspace to generate a sensor unit state data set; a multi-layer attention encoder is input for processing, and the first collaborative sampling parameter of the pressure sensor array is adjusted to obtain a second collaborative sampling parameter. The implementation of the present invention improves the system's response sensitivity to local pressure changes, thereby realizing multi-region collaborative control of pressure sensing.

The invention discloses a liquid cooling adaptive control method and system based on a single-phase immersion liquid cooling data center, and relates to the technical field of liquid cooling control, and the method comprises the steps: reading real-time power consumption data of the data center, and synchronously starting a temperature monitoring sensor to read chip temperature data and environment temperature data; configuring a short-time predictor by using the historical load sequence, and executing information gain ratio and prediction uncertainty analysis of preset candidate granularity; performing matching evaluation of single-phase immersion liquid cooling and the data center by using the calibrated prediction granularity; and if the triggering threshold value is met, self-adaptive optimization under local-global control coordination constraint of single-phase immersion liquid cooling control is executed, and a liquid cooling response scheme is output. The technical problems that in the prior art, the cooling capacity of single-phase immersion liquid cooling is low in matching degree with the load requirement, response lags behind, and energy consumption control is insufficient are solved, and the technical effects of self-adaptive optimization control based on real-time and prediction data, energy consumption reduction and heat dissipation efficiency and temperature control precision improvement are achieved.

The invention discloses an aircraft control agent decision interpretation method and system, relates to the technical field of aircraft control and artificial intelligence crossing, and is used for solving the technical problem that an aircraft fault reason cannot be determined according to a decision result due to the fact that an existing model is poor in agent decision interpretation. The aircraft control agent decision interpretation method comprises the following steps: acquiring real-time working data of an aircraft; synchronizing and storing each kind of working data and then preprocessing; obtaining feature data influencing the decision of the aircraft based on a hypergraph theory; determining the type of a decision made by an intelligent agent, and dividing feature data obtained by a hypergraph theory into a training set and a test set; obtaining optimal division features in the training set according to an information gain rate criterion by using a decision tree algorithm, and determining parameters of a decision tree; selecting a root node and constructing a decision tree model; and performing evaluation and pruning optimization on the decision tree model, and performing visual display on a decision basis corresponding to the decision rule.

The invention discloses a valve-side dry-type bushing end screen diagnosis and evaluation method, system, medium and equipment, and the method comprises the steps: data collection and preprocessing: obtaining multi-source data of a converter transformer valve-side dry-type bushing through real-time monitoring or historical recording of a sensor; dividing the data set, and dividing the multi-source data into a training set and a test set according to a proportion; building a random forest model, generating training subsets of a plurality of decision trees from the training set by adopting replacement random sampling, randomly selecting a feature subset for each decision tree, performing node splitting based on an information gain ratio, and generating the decision trees in a depth-first mode until a preset maximum depth is reached; performing model integration and diagnosis, adopting a voting mechanism to integrate classification results of all decision trees, and outputting defect types and state evaluation grades, the state evaluation grades being grade II and grade I; and performing dynamic tuning and deployment, performing model parameter optimization by taking a test set macro average F1 score greater than or equal to 0.9 as a threshold value, and performing real-time diagnosis on the optimized model.

The invention provides an old people health analysis system based on a C4.5 decision tree algorithm, and the system comprises a data collection terminal which is used for collecting the physiological health data of a user in real time; the data processing module is used for cleaning, standardizing and storing the data acquired by the data acquisition terminal; the algorithm analysis module is used for analyzing the processed health data by adopting a C4.5 decision tree algorithm, constructing a health data classification model, calculating the information gain ratio of each health data feature based on the information entropy and the information gain ratio, and selecting the optimal feature for splitting based on the information gain ratio so as to predict the health risk of the old people; and the personalized health intervention module is used for generating a personalized health intervention scheme for the user according to the health risk prediction result of the algorithm analysis module. According to the invention, comprehensive analysis and accurate intervention of the health data of the old people can be realized, and the efficiency and life quality of health management of the old people are improved.

The present application relates to power industry safety domain boundary fitting technology, in particular to a kind of high-dimensional static security domain boundary fitting method of power system, considering system generator output constraint, node load value sampling is carried out, through power flow calculation, the sample in the security domain is filtered out, and initial sample set is formed.Boundary sample search algorithm is proposed, for each sample in initial sample set, find a sample in the security domain, a sample outside the security domain, and satisfy the distance between the two is less than the set distance threshold value.The data in the boundary sample set in the original power injection space is converted to new three-dimensional feature space by deep neural network model.Extract the boundary in feature space by the weighted tilt decision tree algorithm based on information gain ratio, and evaluate the boundary performance, select the optimal boundary.The method can realize the fitting of high-dimensional boundary of power system security domain, and reduce the error with actual boundary.

The present invention relates to a carbon metering method for optimizing the allocation of carbon flow in a power system based on a decision tree C4.5, and belongs to the field of carbon metering in a power system. The method is: combining a carbon source layer C, a hub layer S, a branch layer F, and a terminal layer Z, and then optimizing the allocation of carbon flow in a power system based on a decision tree C4.5, to determine the optimization path of the carbon flow; specifically as follows: defining power plants in a specified area as a carbon source layer C, a hub layer S, a branch layer F, and a terminal layer Z; calculating the information entropy H(C) of the carbon source layer C; calculating the information entropy H(S) of the hub layer S; calculating the conditional entropy H(C|S) of the attribute splitting at the substation; calculating the information gain g(C,S) of the hub layer to the carbon source layer; calculating the intermediate information entropy H(C) of the carbon source layer to the hub layer S (C); Calculate the information gain ratio g from the carbon source layer to each hub layer node R (C,S), select the smallest one as the preferred direction of carbon flow from the carbon source layer to the hub layer.

The invention relates to the technical field of natural language processing and information retrieval, and discloses a retrieval enhancement generation method and device based on self-feedback driving, and the method comprises the steps: determining a to-be-queried problem through a pre-obtained query request; retrieving in the knowledge base according to the to-be-queried question, and generating an answer of the round of retrieval; calculating an information quality index of the current round of retrieval according to the answer and the to-be-queried question, and if the current round of retrieval is not the first retrieval, calculating an information gain rate of the current round of retrieval according to an information quality index of the previous round of retrieval and the information quality index of the current round of retrieval; and if the information gain ratio does not meet the preset condition, returning to determine the to-be-queried question in combination with the pre-acquired query request to perform the next round of retrieval, and stopping iteration and outputting the final answer until the information gain ratio meets the preset condition. The problems that an existing retrieval enhancement generation method depends on a fixed retrieval threshold value and lacks dynamic judgment capacity are solved, and the information utilization efficiency and the answer accuracy are improved.

The invention discloses an enterprise financial risk early warning and management and control system based on big data analysis, which comprises a data acquisition module, a database module, a data preprocessing module, a risk assessment module and an early warning management and control module, and is characterized in that enterprise financial data in the Internet is crawled in real time and stored as CSV, so that the real-time updating of the enterprise financial data is realized; according to the method, the enterprise financial data in the database is extracted, cleaning and duplicate removal operation of the enterprise financial data in the database are completed, data processing and conversion are finally carried out on the enterprise financial data, and the accuracy of risk assessment is improved; and constructing a decision tree prediction model by using a C5.0 algorithm to predict a decision path and an information gain ratio of the enterprise risk, drawing an enterprise index trend chart according to a model result, and displaying a corresponding early warning icon.

The invention discloses an oil-immersed transformer fault detection method. The method comprises the following steps: acquiring gas dissolution analysis data of an oil-immersed transformer in an early fault stage and constructing a training data set; constructing a decision tree model by taking the acquired data as input, calculating information gain and an information gain ratio, and selecting nodes; a gradient enhancement model is constructed and initialized; performing hyper-parameter optimization on the gradient enhancement model by adopting a Bayesian optimization scheme; training the gradient enhancement model to obtain an oil-immersed transformer fault detection model; and adopting the oil-immersed transformer fault detection model to carry out actual fault detection on the oil-immersed transformer. The invention also discloses a system for realizing the oil-immersed transformer fault detection method. According to the invention, the fault detection of the oil-immersed transformer can be realized, the reliability is higher, and the accuracy is better.

The present application relates to the field of gas turbine detection, and particularly relates to a gas turbine anomaly detection method based on incremental isolated forest, which comprises the following steps: arranging high-dimensional feature vectors corresponding to all feature windows in time sequence to form a high-dimensional feature vector sequence; pruning the isolated trees with completed weight distribution through information gain ratio; combining all the pruned and optimized isolated trees to form an isolated forest model; and calculating real-time anomaly scores for each high-dimensional feature vector input in real time. The present application introduces a sample weight distribution mechanism based on time decay, so that more recent samples obtain higher weights in model training, can dynamically track the slow drift of the normal operation state of the gas turbine, and calculates the information gain ratio of the leaf nodes of the isolated trees layer by layer upwards, reduces the calculation complexity and storage overhead of the model, screens out high-confidence normal samples in combination with the normal distribution principle, and avoids the huge calculation amount of complete retraining.

The application discloses a liquid cooling adaptive control method and system based on a single-phase immersion liquid cooling data center, relates to the technical field of liquid cooling control, and comprises the following steps: reading real-time power consumption data of the data center, synchronously starting a temperature monitoring sensor to read chip temperature data and environment temperature data; configuring a short-time predictor by using a historical load sequence, performing information gain ratio and prediction uncertainty analysis of a preset candidate granularity; performing matching evaluation of the single-phase immersion liquid cooling and the data center by using a calibrated prediction granularity; if a trigger threshold is met, performing adaptive optimization under local-global control coordination constraints of single-phase immersion liquid cooling control, and outputting a liquid cooling response scheme. The technical problems of low matching degree of cooling capacity of single-phase immersion liquid cooling and load demand, response lag and insufficient energy consumption control in the prior art are solved, adaptive optimization control based on real-time and prediction data is achieved, and the technical effects of reducing energy consumption, improving heat dissipation efficiency and temperature control precision are achieved.

This invention relates to the field of healthcare information technology, and more particularly to a smart healthcare management system and method based on big data. The system includes: collecting and cleaning raw data; using an improved information gain ratio feature selection algorithm to select optimal features from the cleaned data; constructing a dynamic adaptive system; updating the state of the dynamic adaptive system based on the optimal features; utilizing complex network theory to treat the state of the dynamic adaptive system as nodes in a network and synchronizing them; processing the synchronized output results of the network nodes; and monitoring the patient's health status. This invention addresses the problems of low efficiency in medical data processing, inability to dynamically adapt to data changes, insufficient clinical decision support, inadequate data security and privacy protection, limited ability to handle multiple data sources and types, inability to reflect real-time changes in the patient's health status, and inability to effectively assist doctors in formulating treatment plans and health management strategies, thus affecting treatment outcomes.

This invention discloses a feature selection method for early screening of coronary heart disease based on soft path cost accumulation, belonging to the field of medical data processing technology. The method includes: S1, selecting a candidate early coronary heart disease feature from the candidate feature set and adding it to the selected feature set with the goal of maximizing the soft path cost accumulation function, and then removing the selected candidate early coronary heart disease feature from the candidate feature set; S2, calculating the difference between the information gain ratio of the current selected feature set to the entire dataset and the information gain ratio of the selected feature set before its addition to the entire dataset, using it as the stopping scoring function; S3, repeating S1-S2 until the stopping scoring function obtained k consecutive times is less than 0, where k is a set hyperparameter threshold, or the candidate feature set is empty; S4, taking the current selected feature set corresponding to the maximum stopping scoring function as the optimal early coronary heart disease feature set. This method can improve the accuracy and efficiency of early coronary heart disease screening prediction models.

The invention relates to the technical field of data processing, in particular to an operation and maintenance fault monitoring method based on multi-modal feature extraction. The method comprises the following steps: for each monitoring period of each fault source, classifying multi-modal data in the monitoring period layer by layer according to each attribute of the fault source to obtain a decision tree of the fault source in the monitoring period; the step of determining the target attributes for classification at each node of the decision-making tree comprises the following sub-steps: according to the information gain ratio after classification through various attributes existing in a fault source and the similarity between the classified samples, determining the target attributes of the multi-modal data to be classified at the node, and determining the target attributes of the multi-modal data to be classified according to the similarity between the classified samples, selecting a target attribute from various attributes existing in the fault source; determining the fault occurrence rate of each fault source according to the similarity of the data of each layer of nodes in each decision tree of each fault source in different monitoring periods; and determining a target fault source according to the fault occurrence rate of each fault source. The method improves the accuracy of fault detection.

The invention discloses a display screen production process management system and method based on artificial intelligence, and belongs to the technical field of production management. According to the method, a component type library and a production database are constructed, a process flow decision tree for bearing component productivity parameters is created, trunk / cotyledon nodes are marked, and a production process topological graph is generated; tasks are divided according to production batches, two types of training sample sets with or without incomplete components are constructed, and a node comprehensive sample set is separated after standardization processing; and calculating a feature information gain ratio based on a C4.5 algorithm to screen an optimal feature set, constructing a C4.5 decision tree-based learning device through bootstrap resampling, integrating the C4.5 decision tree-based learning device into a double-branch random forest model by adopting a weighted voting method, and inputting real-time feature data of a current batch to output a productivity prediction result. According to the method, the productivity prediction accuracy and the process suitability of display screen production batches are improved, and the problem of productivity imbalance of multi-component and multi-batch production is effectively solved.

The invention provides an electrical equipment classification rule self-learning method and system, and belongs to the technical field of electrical equipment management. Specifically, a C4.5 decision tree algorithm is adopted to train extracted feature data of the electrical equipment, a feature with the maximum information gain ratio is selected to perform node splitting, a classification rule in a decision tree form is formed, the classification rule is optimized based on feature importance evaluation, a data feedback mechanism is established, and a classification result is obtained. Newly generated equipment data are collected in real time and added into a training data set, the optimized classification rule is retrained and optimized through the training data set containing new data, and related nodes and rules in the decision tree model are updated. Key features are automatically screened based on information gain ratio and feature importance evaluation, low-contribution features are removed, the generalization ability of the model is improved, and overfitting is reduced. Classification rules are continuously and dynamically optimized through data feedback and incremental learning, the method adapts to dynamic factors such as equipment aging and environment change, and high accuracy is kept for a long time.

This invention provides a method for constructing sensitive APIs for malware detection, comprising: collecting and labeling Android software samples to obtain multiple APK files; reverse-engineering static features from the multiple APK files; constructing a candidate sensitive API list; and constructing a simplified sensitive API set based on the candidate sensitive API list using a logistic regression classification model combined with an information gain ratio statistical method. This invention can solve the technical problem of the large number of sensitive APIs listed in the current Android official documentation, which is inconvenient to use. Experimental data verification shows that although the constructed simplified sensitive API set significantly reduces the number of sensitive APIs compared to the original set, it still retains the effectiveness in identifying malware, with an accuracy rate of over 90%.

A kind of based on deep learning's intelligent adjustment method of maintaining data center room positive pressure, comprising: obtaining training set F;Data cleaning is carried out to F, supplement missing value and handle abnormal value, continuous variable numerical value is discretely handled, and derived feature set F1 is formed;Feature data extraction is carried out to F1, and feature data set S and test data set C are extracted;Entropy and information gain ratio algorithm is used to process S, and decision tree data set TREE is formed;Pruning is carried out to TREE, and branch that contributes less to model generalization ability is deleted, and training set D is formed;The data of D is used to construct decision tree model, and model parameter is adjusted in training process;For the decision result obtained, the accuracy and generalization ability of decision tree model are evaluated using the data in C.The present application can realize the deep learning and intelligent adaptive adjustment of data center indoor positive pressure maintenance and different operating environment, and maintain the positive pressure operation of each functional room of data center.

This invention belongs to the field of mechanical equipment condition monitoring and fault prediction technology, specifically relating to a method for constructing a health index for rolling bearings based on deep reinforcement learning. The method includes: acquiring features to be fused from sensor data of the mechanical equipment and performing normalization processing; utilizing deep reinforcement learning technology to simultaneously perform two stages of tasks: feature selection and feature weight allocation, to construct a comprehensive health index; wherein the action space of deep reinforcement learning includes discrete feature selection actions and continuous feature weight allocation actions, and the reward function is based on the information gain ratio of the health index; by training a deep reinforcement learning agent, it learns to select the most effective subset of features and allocate optimal weights, thereby generating a health index. This invention can automatically and adaptively construct health indices, avoiding the problems of relying on expert knowledge and manual design in traditional methods, and improving the quality and generalization ability of health indices.

This invention discloses a trajectory similarity-based remaining life prediction method based on slow feature information gain ratio. First, multi-dimensional condition monitoring data of the entire lifecycle of decommissioned equipment is acquired. Slow feature analysis is then applied to the condition monitoring data after feature filtering and normalization. Next, the optimal feature vector for data fusion is obtained by combining the generalized eigenvalue of a matrix with the definition of slow feature information gain ratio. The processed multi-dimensional condition monitoring data of the decommissioned unit is multiplied with the optimal feature vector to obtain a health index curve. The same feature filtering, feature normalization, nonlinear expansion, and matrix whitening are then applied to the degradation curve of the multi-dimensional condition monitoring data of in-service machinery to obtain its corresponding health index curve. A specified segment of this curve is matched with the health index curve; the curve segment that meets the similarity filtering requirements provides the remaining life prediction result for the in-service equipment. This invention can be applied to various complex mechanical equipment with full lifecycle condition monitoring data.

The invention relates to the technical field of wireless communication, and discloses a signal sequence recovery method and system, computer equipment and a storage medium, and the signal sequence recovery method comprises the steps: receiving a target signal sequence transmitted by a signal transmitting end in a satellite communication system, constructing an original optimal sampling point set based on the symbol information of the target signal sequence, constructing an optimal sampling point judgment feature set based on a preset feature type; calculating the information gain ratio of each judgment feature in the optimal sampling point judgment feature set based on the original optimal sampling point set, and screening out the optimal sampling point judgment feature; and determining an optimal sampling point based on the optimal sampling point judgment feature, and performing nonlinear interpolation on the target signal sequence according to the optimal sampling point, thereby realizing symbol synchronization and instant clock recovery in the satellite communication process. According to the invention, by calculating the information gain ratio of each judgment feature in different scenes, the judgment feature with the optimal timing recovery precision, the lowest calculation overhead and the highest robustness can be screened out.

The invention discloses a deep learning-based intelligent adjustment method for maintaining positive pressure of a data center machine room. The method comprises the steps of obtaining a training set F; performing data cleaning on the F, supplementing missing values and processing abnormal values, and performing discrete processing on continuous variable values to form a derivative feature set F1; performing feature data extraction on the F1, and extracting a feature data set S and a test data set C; processing the S by adopting an entropy and information gain ratio algorithm to form a decision tree data set TREE; performing post pruning on the TREE, deleting branches which contribute little to the generalization ability of the model, and forming a training set D; constructing a decision tree model by using the data of the D, and adjusting model parameters in the training process; and for the obtained decision result, evaluating the accuracy and the flooding ability of the decision tree model by using the data in the C. According to the invention, indoor positive pressure maintenance of the data center and deep learning and intelligent adaptive adjustment of different operation environments can be realized, and each functional room of the data center is maintained to be in positive pressure operation.

The application discloses a display screen production process management system and method based on artificial intelligence, and belongs to the technical field of production management. The method constructs a component type library and a production database, creates a process flow decision tree carrying component capacity parameters, marks main stem / leaflet nodes and generates a production process topology graph; divides tasks according to production batches, constructs two types of training sample sets with or without defective components, separates node comprehensive sample sets after standardization processing; calculates the feature information gain ratio based on the C4.5 algorithm to screen the optimal feature set, constructs a C4.5 decision tree base learner through bootstrap resampling, integrates it into a double-branch random forest model by using a weighted voting method, and inputs current batch real-time feature data to output capacity prediction results. The application improves the capacity prediction accuracy and process adaptability of display screen production batches, and effectively solves the capacity imbalance problem of multi-component and multi-batch production.

This invention provides a method for assessing the situation in 1v1 close-range UAV games based on a multi-criteria random forest. First, it collects state parameters such as position, attitude, and velocity of both friendly and enemy UAVs and labels the situation categories. Then, based on these state parameters, it constructs four types of advantage features: distance advantage, azimuth advantage, velocity advantage, and altitude advantage, and obtains advantage feature vectors through normalization. Next, it uses a bagging ensemble strategy to generate multiple training subsets, randomly assigning one or more splitting criteria from information entropy, information gain ratio, Gini impurity, and chi-square test to each decision tree. Feature selection and node splitting are then performed according to the corresponding criteria, forming a multi-criteria random forest model composed of multiple splitting criteria. Finally, the real-time collected game state data is converted into advantage feature vectors and input into the multi-criteria random forest model. The game situation category and corresponding probability distribution are obtained through the voting results of multiple decision trees, achieving real-time intelligent assessment of the 1v1 close-range UAV game situation. This invention significantly improves situation recognition accuracy, adaptability to unbalanced situation distributions, and reliability in identifying dangerous situations, while maintaining low computational complexity.

The invention relates to the technical field of medical care information, in particular to a smart medical management system and method based on big data. The method comprises the following steps: collecting and cleaning original data, and performing feature selection on the cleaned data by using an improved information gain ratio feature selection algorithm to obtain an optimal feature; a dynamic self-adaptive system is constructed, and the state of the dynamic self-adaptive system is updated based on the optimal features; a complex network theory is utilized, a dynamic self-adaptive system state is regarded as a node in a network, synchronization is carried out, a synchronous output result of the network node is processed, and the health state of a patient is monitored. The problems that medical data processing efficiency is low, data changes cannot be dynamically adapted, clinical decision support is insufficient, data safety and privacy protection are insufficient, the capacity of processing multiple data sources and types is limited, real-time changes of the health state of a patient cannot be reflected, doctors cannot be effectively assisted to make treatment plans and health management strategies, and the medical data processing efficiency is low are solved. The treatment effect is influenced.